民航发动机气路参数偏差值挖掘方法及其应用研究
|
摘要
航空发动机是飞机的心脏，其健康状态对飞行安全有很大影响。发动机气路参数偏差值的求解和性能状态评价方法的建立是发动机状态监测的基础，也是国内各航空公司的迫切需要。本文在分析国内外航空发动机性能监控现状的基础上，从国内航空公司的实际需求出发，首先研究航空发动机报文解析技术和气路参数自变量筛选方法。之后分别提出了基于发动机性能基线的气路参数偏差值挖掘方法和参数核心变换支持向量机的偏差值回归求解方法。然后研究了基于偏差值的气路分析技术，主要研究气路分析技术中的偏差值预测、偏差值平滑、基于高维偏差值的发动机性能状态评价以及基于偏差值的气路故障诊断方法，最后将上述理论和技术方法应用到航空发动机性能监控系统的开发中。
航空发动机气路参数偏差值求解之前对相关参数进行筛选处理，为此本文首先对与偏差值相关的自变量参数集合进行了筛选研究。为了消除多重相关性和重复属性对回归分析的影响，采用方差膨胀因子法对自变量参数之间的多重相关性进行诊断分析，采用航空发动机原理知识分析自变量参数之间的非线性关系。针对参数之间复杂的非线性关系，提出基于平均影响值和小波神经网络相结合的发动机自变量参数筛选方法，消除了无关自变量及弱相关自变量对回归效果的影响，为文中的回归分析实现了合理降维。
针对机群发动机数量较大时，提出了基于基线的偏差值挖掘方法。根据气路参数偏差值的含义，将偏差值模型转化为参数标准化模型和性能基线模型的差值，并推导了气路参数标准化模型。考虑到大气环境温度、湿度以及传感器偏置对发动机性能的影响，提出了变指数的气路参数标准化修正模型，并根据性能基线的性质和函数逼近理论采用待定系数的多项式基线模型。根据偏差值定义将上述两个模型做差得到气路参数偏差值待定系数模型，将原厂家解析的历史数据代入偏差值模型进行回归分析，采用改进的高斯牛顿迭代法进行偏差值模型求解，从而准确挖掘出偏差值模型，并使用该模型进行偏差值的精确自主求解。
论文还对机群发动机数量较少的小样本情况下气路参数偏差值求解方法进行了研究。提出一种航空发动机状态参数核心变换后的支持回归向量机的气路参数偏差值求解方法，该方法针对发动机测量参数之间的相似比例关系，通过增加优化参数实现输入集的局部降维，降低模型复杂程度，并提高模型的计算效率。同时该方法采用高维空间点到空间原点欧氏距离排列规则的训练集构造方法，提高支持向量机模型的泛化能力。该方法能够提高气路参数偏差值的求解精度求解速度。
在上述偏差值求解的基础上，还对气路参数偏差值的预测技术进行了研究。针对气路参数偏差值时间序列中存在真实突变的特点，提出一种基于离散沃尔什变换的分式非线性聚合过程神经网络预测模型，由于有理函数具有更好的非线性逼近能力，采用非线性的有理分式空间聚合运算代替线性聚合运算。为避免离散数据在拟合过程中的精度损失，给出基于离散沃尔什变换Levenberg-Marquardt(LM)的网络学习算法，使用测试数据的离散沃尔什变换对内积运算代替过程神经网络中的积分算子，简化了计算过程，提高了计算速度。实际案例测试表明，文中提出的预测模型及网络学习算法能够提高预测精度和突变点处的预测灵敏度，具有更好的非线性逼近能力。
在气路参数平滑处理技术方面，论文提出一种离群点分析与类指数平滑相结合的气路参数偏差值平滑处理方法，并以样本均方误差最小化为目标函数进行模型参数的优化，该方法在对偏差值序列进行合理平滑的同时保留了离群点数据。为了克服使用单维的气路参数偏差值进行发动机性能评估带来的片面性，文中提出基于离散Hopfield网络的发动机性能评估模型，采用能够表征发动机性能的高维参数对发动机性能进行评价，使评价结果更具科学性。为了克服相似故障区分难和使用故障指印图效率低且需要丰富专业知识的不足，文中提出基于故障指印图和自组织竞争网络相结合的气路故障诊断方法，该方法能够提高气路故障诊断的效率和准确性，并在增加新的故障模式时，能重新快速进行故障模式分类，实现准确快速的故障诊断。
最后，以中国国际航空股份有限公司的发动机工程管理为应用背景，研究性能基线与气路参数偏差值在性能监控中应用的关键技术，并从该公司发动机工程管理的实际需求出发，开发了基于Web的航空发动机性能监控系统，实现了气路参数偏差值的自主求解，并为基于Web的航空发动机健康管理与维修决策支持系统其它模块提供数据支持，进而实现了状态参数自动报警、状态参数趋势分析以及发动机健康状态排队等功能。
Aero-engine is the heart of aircraft, its health condition has a great impact onflight security. The gas path parameter deviation solution and performance statusevaluation method established are foundation of engine condition monitoring, andthey are also urgent needs of various airlines. Based on the analysis of domestic andinternational aero-engine performance monitoring research, according to the need ofairline, first the message parsing technology and gas path parameter independentvariables selection method are studied in this paper. Gas path parameter deviationmining method based on engine baseline and deviation regression solution based onparameter core transform SVM are proposed. Then the gas path analysis technologybased on the deviation is studied, mainly the deviation forecasting, deviationsmoothing, engine performance evaluation based on high dimension deviation andgas path fault diagnosis based on deviation are studied. Finally, the theoreticalmethods and calculation results are applied to the development of aero-engineperformance monitoring system.
The relevant parameters must be selected before the aero-engine gas pathparameter deviation solving, so first the selected method of argument parameterssets relevant to deviation is studied in this paper. In order to eliminate the hazards toregression analysis of multiple correlation and repeat property, the variance inflationfactor method is used to diagnose multiple correlations between argumentparameters, the knowledge of aero-engine principle is used to analyze the non-linearrelationship between gas path parameter independent variables. According to thecomplex non-linear relationship between the argument parameters, the engineargument parameters selection method based on the combination of mean impactvalue(MIV) and wavelet neural network is proposed, which can eliminate unrelatedand tiny related independent variable effect to regression, and which reasonablyrealize the dimension reduction purpose for regression theory of this article.
Then the deviation mining method is proposed. The deviation model is dividedinto difference of parameter standardization model and performance baseline modelaccording the meaning of gas path parameter deviation, and the gas path parameterstandardization model is derived. Taking into account the influence of ambienttemperature and humidity, and sensor offset, the corrected uncertain exponentstandardized model based on deviation is proposed. Uncertain coefficientspolynomial baseline model is used according to function approximation theory. Theuncertain coefficients gas path parameter deviation model is obtained using theabove two models to subtract each other, the regression analysis is done by inputting the original manufacturer historical data into the deviation model. The deviationmodel is mined accurately by using the improved Gauss-Newton iterative method tosolve the deviation model, and the deviation is accurately self-solved using thatdeviation model.
The solution method of aero-engine gas path parameter deviation under smallnumber engine in the fleet is studied in this paper. Gas path parameter deviationsolution method based on aero-engine state parameter core transform support vectorregression machine is proposed, the input set local dimensionality reduction isachieved by increasing the optimization parameters according to the similarproportional relationship between the engine measurement parameters, thecomplexity of the model is reduced and calculation efficiency is improved. Thetraining set constructor based on Euclidean distance arrangement rule ofhigh-dimension space point to origin point is proposed in order to improve thegeneralization ability of support vector machines. The algorithm can improve thegas path deviation solution accuracy and solution speed of that model.
Gas path parameter deviation forecasting techniques is studied on the basis ofthe deviation solving. A fractional nonlinear polymerization process neural networkprediction model based on discrete Walsh transform is proposed according to truemutation data exist in gas path parameter deviation time series, since the rationalfunction has better nonlinear approximation ability, nonlinear rational fractionalspace aggregation operations substitute for linear aggregation operations. In order toavoid the loss accuracy of the discrete data in fitting process, the network learningmethod is proposed based on Levenberg-Marquardt(LM) algorithm of discreteWalsh transform, the inner product of measurement data discrete Walsh transform isused to substitute the integral operator in process neural network, that simplify thecalculation process, improve the calculation speed. The conclusion can drawn frominstance that the forecasting model and network learning algorithm proposed in thispaper can improve prediction accuracy and prediction sensitivity on mutations dataand has better nonlinear approximate ability.
In the gas path parameter smoothing technology, the outlier analysis andsimilar exponential smoothing combination of gas path parameter deviation smoothprocessing technique is proposed in the paper, and the parameters are optimizedusing sample mean square error minimum as objective function, the algorithm canreasonably smooth the deviation series and reserve the outlier data. In order toovercome the one-sidedness using one dimension gas path parameter deviation toevaluate engine performance, the engine performance evaluation model based ondiscrete Hopfield network is proposed, the high dimension parameter which cancharacterize engine performance is used to evaluate engine performance, whichmake the evaluation results has better scientific. In order to overcome difficult to distinguish similar fault, low efficiency of fault fingerprints figure used and requiresstrong expertise difficulties, the gas path fault diagnosis based on Self-OrganizingFeature Map(SOFM) under fingerprints figure is proposed in this paper, the methodcan improve the efficiency and accuracy of fault diagnosis, when new fault modelsis adding, it can quickly and easily achieve fault re-classification, to achieveaccurate and fast fault diagnosis.
Finally, the key technology of performance baseline and gas path parameterdeviation in performance monitoring applications are studied based on engineproject management application of air china, and from the actual needs of thecompany’s engineering department, a Web-based aero-engine performancemonitoring system is developed, which can achieve self-solving techniques of thegas path parameter deviation, and provide data support to other modules ofWeb-based aero-engine management and maintenance decision support system,achieve auto alert and trend analysis of state parameter and engine health statusqueue function.
航空发动机气路参数偏差值求解之前对相关参数进行筛选处理，为此本文首先对与偏差值相关的自变量参数集合进行了筛选研究。为了消除多重相关性和重复属性对回归分析的影响，采用方差膨胀因子法对自变量参数之间的多重相关性进行诊断分析，采用航空发动机原理知识分析自变量参数之间的非线性关系。针对参数之间复杂的非线性关系，提出基于平均影响值和小波神经网络相结合的发动机自变量参数筛选方法，消除了无关自变量及弱相关自变量对回归效果的影响，为文中的回归分析实现了合理降维。
针对机群发动机数量较大时，提出了基于基线的偏差值挖掘方法。根据气路参数偏差值的含义，将偏差值模型转化为参数标准化模型和性能基线模型的差值，并推导了气路参数标准化模型。考虑到大气环境温度、湿度以及传感器偏置对发动机性能的影响，提出了变指数的气路参数标准化修正模型，并根据性能基线的性质和函数逼近理论采用待定系数的多项式基线模型。根据偏差值定义将上述两个模型做差得到气路参数偏差值待定系数模型，将原厂家解析的历史数据代入偏差值模型进行回归分析，采用改进的高斯牛顿迭代法进行偏差值模型求解，从而准确挖掘出偏差值模型，并使用该模型进行偏差值的精确自主求解。
论文还对机群发动机数量较少的小样本情况下气路参数偏差值求解方法进行了研究。提出一种航空发动机状态参数核心变换后的支持回归向量机的气路参数偏差值求解方法，该方法针对发动机测量参数之间的相似比例关系，通过增加优化参数实现输入集的局部降维，降低模型复杂程度，并提高模型的计算效率。同时该方法采用高维空间点到空间原点欧氏距离排列规则的训练集构造方法，提高支持向量机模型的泛化能力。该方法能够提高气路参数偏差值的求解精度求解速度。
在上述偏差值求解的基础上，还对气路参数偏差值的预测技术进行了研究。针对气路参数偏差值时间序列中存在真实突变的特点，提出一种基于离散沃尔什变换的分式非线性聚合过程神经网络预测模型，由于有理函数具有更好的非线性逼近能力，采用非线性的有理分式空间聚合运算代替线性聚合运算。为避免离散数据在拟合过程中的精度损失，给出基于离散沃尔什变换Levenberg-Marquardt(LM)的网络学习算法，使用测试数据的离散沃尔什变换对内积运算代替过程神经网络中的积分算子，简化了计算过程，提高了计算速度。实际案例测试表明，文中提出的预测模型及网络学习算法能够提高预测精度和突变点处的预测灵敏度，具有更好的非线性逼近能力。
在气路参数平滑处理技术方面，论文提出一种离群点分析与类指数平滑相结合的气路参数偏差值平滑处理方法，并以样本均方误差最小化为目标函数进行模型参数的优化，该方法在对偏差值序列进行合理平滑的同时保留了离群点数据。为了克服使用单维的气路参数偏差值进行发动机性能评估带来的片面性，文中提出基于离散Hopfield网络的发动机性能评估模型，采用能够表征发动机性能的高维参数对发动机性能进行评价，使评价结果更具科学性。为了克服相似故障区分难和使用故障指印图效率低且需要丰富专业知识的不足，文中提出基于故障指印图和自组织竞争网络相结合的气路故障诊断方法，该方法能够提高气路故障诊断的效率和准确性，并在增加新的故障模式时，能重新快速进行故障模式分类，实现准确快速的故障诊断。
最后，以中国国际航空股份有限公司的发动机工程管理为应用背景，研究性能基线与气路参数偏差值在性能监控中应用的关键技术，并从该公司发动机工程管理的实际需求出发，开发了基于Web的航空发动机性能监控系统，实现了气路参数偏差值的自主求解，并为基于Web的航空发动机健康管理与维修决策支持系统其它模块提供数据支持，进而实现了状态参数自动报警、状态参数趋势分析以及发动机健康状态排队等功能。
Aero-engine is the heart of aircraft, its health condition has a great impact onflight security. The gas path parameter deviation solution and performance statusevaluation method established are foundation of engine condition monitoring, andthey are also urgent needs of various airlines. Based on the analysis of domestic andinternational aero-engine performance monitoring research, according to the need ofairline, first the message parsing technology and gas path parameter independentvariables selection method are studied in this paper. Gas path parameter deviationmining method based on engine baseline and deviation regression solution based onparameter core transform SVM are proposed. Then the gas path analysis technologybased on the deviation is studied, mainly the deviation forecasting, deviationsmoothing, engine performance evaluation based on high dimension deviation andgas path fault diagnosis based on deviation are studied. Finally, the theoreticalmethods and calculation results are applied to the development of aero-engineperformance monitoring system.
The relevant parameters must be selected before the aero-engine gas pathparameter deviation solving, so first the selected method of argument parameterssets relevant to deviation is studied in this paper. In order to eliminate the hazards toregression analysis of multiple correlation and repeat property, the variance inflationfactor method is used to diagnose multiple correlations between argumentparameters, the knowledge of aero-engine principle is used to analyze the non-linearrelationship between gas path parameter independent variables. According to thecomplex non-linear relationship between the argument parameters, the engineargument parameters selection method based on the combination of mean impactvalue(MIV) and wavelet neural network is proposed, which can eliminate unrelatedand tiny related independent variable effect to regression, and which reasonablyrealize the dimension reduction purpose for regression theory of this article.
Then the deviation mining method is proposed. The deviation model is dividedinto difference of parameter standardization model and performance baseline modelaccording the meaning of gas path parameter deviation, and the gas path parameterstandardization model is derived. Taking into account the influence of ambienttemperature and humidity, and sensor offset, the corrected uncertain exponentstandardized model based on deviation is proposed. Uncertain coefficientspolynomial baseline model is used according to function approximation theory. Theuncertain coefficients gas path parameter deviation model is obtained using theabove two models to subtract each other, the regression analysis is done by inputting the original manufacturer historical data into the deviation model. The deviationmodel is mined accurately by using the improved Gauss-Newton iterative method tosolve the deviation model, and the deviation is accurately self-solved using thatdeviation model.
The solution method of aero-engine gas path parameter deviation under smallnumber engine in the fleet is studied in this paper. Gas path parameter deviationsolution method based on aero-engine state parameter core transform support vectorregression machine is proposed, the input set local dimensionality reduction isachieved by increasing the optimization parameters according to the similarproportional relationship between the engine measurement parameters, thecomplexity of the model is reduced and calculation efficiency is improved. Thetraining set constructor based on Euclidean distance arrangement rule ofhigh-dimension space point to origin point is proposed in order to improve thegeneralization ability of support vector machines. The algorithm can improve thegas path deviation solution accuracy and solution speed of that model.
Gas path parameter deviation forecasting techniques is studied on the basis ofthe deviation solving. A fractional nonlinear polymerization process neural networkprediction model based on discrete Walsh transform is proposed according to truemutation data exist in gas path parameter deviation time series, since the rationalfunction has better nonlinear approximation ability, nonlinear rational fractionalspace aggregation operations substitute for linear aggregation operations. In order toavoid the loss accuracy of the discrete data in fitting process, the network learningmethod is proposed based on Levenberg-Marquardt(LM) algorithm of discreteWalsh transform, the inner product of measurement data discrete Walsh transform isused to substitute the integral operator in process neural network, that simplify thecalculation process, improve the calculation speed. The conclusion can drawn frominstance that the forecasting model and network learning algorithm proposed in thispaper can improve prediction accuracy and prediction sensitivity on mutations dataand has better nonlinear approximate ability.
In the gas path parameter smoothing technology, the outlier analysis andsimilar exponential smoothing combination of gas path parameter deviation smoothprocessing technique is proposed in the paper, and the parameters are optimizedusing sample mean square error minimum as objective function, the algorithm canreasonably smooth the deviation series and reserve the outlier data. In order toovercome the one-sidedness using one dimension gas path parameter deviation toevaluate engine performance, the engine performance evaluation model based ondiscrete Hopfield network is proposed, the high dimension parameter which cancharacterize engine performance is used to evaluate engine performance, whichmake the evaluation results has better scientific. In order to overcome difficult to distinguish similar fault, low efficiency of fault fingerprints figure used and requiresstrong expertise difficulties, the gas path fault diagnosis based on Self-OrganizingFeature Map(SOFM) under fingerprints figure is proposed in this paper, the methodcan improve the efficiency and accuracy of fault diagnosis, when new fault modelsis adding, it can quickly and easily achieve fault re-classification, to achieveaccurate and fast fault diagnosis.
Finally, the key technology of performance baseline and gas path parameterdeviation in performance monitoring applications are studied based on engineproject management application of air china, and from the actual needs of thecompany’s engineering department, a Web-based aero-engine performancemonitoring system is developed, which can achieve self-solving techniques of thegas path parameter deviation, and provide data support to other modules ofWeb-based aero-engine management and maintenance decision support system,achieve auto alert and trend analysis of state parameter and engine health statusqueue function.
引文
[1]王施,王荣桥,陈志英等.航空发动机健康管理综述[J].燃气涡轮试验与研究,2009,22(1):51-58.
[2] Mercer C R, Simon D L, Hunter G W, et al. Fundamental TechnologyDevelopment for Gas-turbine Engine Health Management[R].NASA-TM-2007-0022364,2007.
[3] Fu X Y, Ding G, Zhong S S. Aeroengine Turbine Exhaust Gas TemperaturePrediction Using Support Vector Machines[C].//Advances in NeuralNetworks-ISNN2009-6th International Symposium on Neural Networks,ISNN2009, Proceedings. Wuhan, China: Spring Verlag, Tiergartenstrasse17,Heidelberg, D-69121, Germany,2009:235-241.
[4]敖良忠. CFM56-5B发动机性能衰退评估[J].中国民航飞行学院学报,2006,17(2):28-30.
[5] Nott C, Sossamon C, Olcmen S M, et al. Jet-Engine Health Monitoring andOperation Using Fuzzy-Logic Controllers and Bayesian Belief Networks[C].//Collection of Technical Papers-44th AIAA Aerospace Sciences Meeting.Reno, NV, United states: American Institute of Aeronautics and AstronauticsInc.,1801Alexander Bell Drive, Suite500, Reston, VA20191-4344, UnitedStates,2006:17710-17720.
[6]钟诗胜，栾圣罡.面向航空发动机全寿命管理的航线数据处理系统[J].计算机集成制造系,2006,8：1273-1278.
[7] Ogaji S O T, Sampath S, Singh R, et al. Parameter selection for diagnosing agas-turbine’s performance-deterioration[J]. Elsevier Science Ltd.2002,73:25-46.
[8]朱玉斌,方忠祥,侯朝焕等.基于部件参数估计的航空发动机故障预测技术研究[J].测控技术,2012,31(1):128-131.
[9] Ameco, Beijing. Engines scientific management[Z]. The Reliability ResearchProgram Summary of Civil Aviation Engine,2000.121-130.
[10] Ameco, Beijing. The role of analyzing engine test data and exploring its law inestablishing maintenance workscope[Z]. The Reliability Research ProgramSummary of Civil Aviation Engine,2000.135-151.
[11] Li Y G. Performance-and analysis-based gas turbine diagnostics: a review[J].Proc Instn Mech Engrs Vol216Part A: J Power and Energy.2002,216:363-377.
[12] Ameco, Beijing. The present situation and development of state monitoring ofcivil aviation engine[Z]. Beijing：The Reliability Research Program Summaryof Civil Aviation Engine,2000.26-32.
[13]钟诗胜,李洋.基于小波过程神经网络的飞机民用航空发动机状态监视[J].航空学报,2007,22(1):68-71.
[14] Ranjan, Ganguli. Jet Engine Gas-Path Measurement Filtering Using CenterWeighted Idempotent Median Filters[J]. Journal of Propulsion and Power.2003,19(5):930-937.
[15] Li X, Schmidt L C. Transformation of an EGT Grammar: New Grammar, NewDesigns[J]. Journal of Mechanical Design.2004,126:753-756.
[16]贺瑶,王文庆,薛飞.基于云计算的海量数据挖掘研究[J].计算机技术与发展.2013,23(2):69-72.
[17]李华,刘帅,李茂等.数据挖掘理论及其应用研究[J].断块油气田,2010,17(1):88-91.
[18] Katharina M, Kanishka B, Hillol K. Introduction to data mining forsustainability[J]. Fata Mining and Knowledge Discovery,2012,24(2):311-324.
[19] Padhy N, Mishra P, Panigrahi R. The Survey of Data Mining Applications AndFeature Scope[J]. International Journal of Computer Science, Engineering andInformation Technology (IJCSEIT).2012,2(3):43-58.
[20] Cios K J, Pedrycz W, Swiniarski R M. Data Mining Methods for KnowledgeDiscovery[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS.1998,9(6):1533-1534.
[21] Olson D L, Delen D, Meng Y Y. Comparative analysis of data mining methodsfor bankruptcy prediction[J]. Decision Support Systems.2012,52(2):464-473.
[22]郑继刚,王边疆.数据挖掘研究的现状与发展趋势[J].思茅师范高等专科学校,2010,26(3):36-39.
[23] Fauvel M, Chanussot J, Benediktsson J A, et al. Parsimonious Mahalanobiskernel for the classification of high dimensional data[J]. Patten Recognition,3013,46(3):845-854.
[24] Huang H Y, Chang H Y, Liu J F. A novel kernel-based gene selection andclassification scheme for microarray data[C].//6th International Conferenceon Soft Computing and Intelligent Systems, and13th International Symposiumon Advanced Intelligence Systems, SCIS/ISIS2012. Kobe, Japan: IEEEComputer Society,2001L Street N.W., Suite700, Washington, DC20036-4928, United States,2012:1679-1683.
[25]韩利,祁云嵩,王俊.基于粗糙集的支持向量机微阵列数据分类方法[J].科学技术与工程,2009,9(1):152-155.
[26] Wei L W, Wei C S, Wan X Q. Data classification using support vectormachines with mixture kernels[C].//Advanced Materials Research. Guilin,China: Trans Tech Publications, P.O. Box1254, Clausthal-Zellerfeld, D-38670,Germany,2012:936-939.
[27]王宝祥,丁爱萍,张连堂等.一种基于粗糙集的数据分类方法[J].河南大学学报（自然科学版）,2010,40(3):291-294.
[28]马胜祥,马建庆,杨明.基于核函数拟合的非平衡数据分类方法[J].计算机应用与软件,2010,27(4):177-179.
[29] Zhang X N, Song S J, Wu C. Robust Bayesian Classification with IncompleteData[J]. Cognitive Computation,2013,5(2):170-187.
[30]江峰,杜军威,晆跃飞等.基于边界和距离的离群点检测[J].电子学报,2010,(3):700-705.
[31] Jiang F, Sui Y F, Cao C G. Distance metrics and outlier detection in roughsets[J]. Kongzhi yu Juece/Control and Decision,2013,28(2):188-192.
[32] Li H, Zhang S, Wang X. An outlier detection algorithm based on informationentropy and rough set[J]. International Journal of Digital Content Technologyand its Applications,2012,6(20):97-106.
[33] Li X J, Tian S F, Qiu T R, et al. Outlier detection using the information entropyof neighborhood rough sets[J]. Journal of Information and ComputationalScience,2012,9(12):3339-3350.
[34] Jiang F, Du J W, Ge Y, et al. Sequence outlier detection based on rough settheory[J]. Tien Tzu Hsueh Pao/Acta Electronica Sinica,2011,39(2):345-350.
[35] Jeng J T, Chuang C C, Tseng C C, et al. Robust interval competitiveagglomeration clustering algorithm[J]. International Journal of Fuzzy Systems,2010,12(3):227-236.
[36] Lei D J, Zhu Q S, Chen J, et al. Automatic k-means clustering algorithm foroutlier detection[C].//Lecture Notes in Electrical Engineering. Chongqing,China: Springer Verlag, Tiergartenstrasse17, Heidelberg, D-69121, Germany,2012:363-372.
[37] Qin F J. Outlier clustering algorithm for study of outlying patterns[J]. Journalof Computational Information Systems,2012,7(17):7037-7044.
[38]吴晓燕.基于遗传模拟退火算法的高维离群点挖掘[J].计算机信息,2010,26(7-3):139-141.
[39] Jiangtao P, Silong P, Yong H. Partial least squares and random sampleconsensus in outlier detection[J]. Analytica Chimica Acta,2012:24-29.
[40] Tang Z G, Yang J, Yang B R. A new detection algorithm based on manifoldlearning[C].//2010Chinese Control and Decision Conference, CCDC2010.Xuzhou, China: EEE Computer Society,445Hoes Lane-P.O.Box1331,Piscataway, NJ08855-1331, United States,2010:452-457.
[41] Chen M S, Park J S, Yu P S. Efficient Data Mining for Path TraversalPatterns[J]. IEEE TRANSACTIONS ON KNOWLEDGE AND DATAENGINEERING.1998,10(2):209-221.
[42] Fayyad U, Shapiro G P, Smyth P. Knowledge Discovery and Data Mining:Towards a Unifying Framework[J]. American Association for ArtificialIntelligence.1996:82-88.
[43] Bresfelean, Paul V. Data mining and model trees strudy on GDP and itsinfluence factors[C].//11thWSEAS international conference on AIC’11.Florence, Italy: World Scientific and Engineering Academy and Society, P.O.Box4743, Clifton, NJ07015-4743, United States.2011:401~406.
[44]郭茜,朱杰.高维数据挖掘技术在教学质量监控与评价的应用研究[J].高等教育,2010:81-82.
[45]刘城霞.基于MS关联规则数据挖掘模型的应用与探讨[J].计算机技术与发展,2013,23(1):25-30.
[46]要照华,闫宏印.基于粗糙集的海量数据挖掘[J].机械管理开发,2010,25(1):17-18.
[47] Wang W H, Pan W G, He M F, et al. Target values of combustion optimizationin coal fire boiler based on data mining[C].//2nd International Conference onEnergy, Environment and Sustainable Development, EESD2012, Trans TechPublications, P.O. Box1254, Clausthal-Zellerfeld, D-38670, Germany, Jilin,China.2013:1143-1146.
[48]邹媛.基于决策树的数据挖掘算法的应用与研究[J].科学技术与工程,2010,10(18):4510-4515.
[49]肖冬荣,杨磊.基于遗传算法的关联规则数据挖掘[J].通信技术,2010,43(1):205-207.
[50]李兴森,张玲玲,朱正祥.数据挖掘获取的知识的智能评价方法[J].科研管理,2010,31:32-38.
[51]杨启仁.数据挖掘中聚类算法的研究[J].牡丹江大学学报,2010,19(6):107-110.
[52]张立斌.一种用于受训神经网络数据挖掘的遗传算法[J].信息技术,2010,(6):60-65.
[53]林兆福,范作民.发动机基线方程的建立和应用[J].中国民航学院学报,1992,10(4):20-32.
[54]林兆福,范作民,孙春林.航空发动机气动热力参数的趋势分析[J].中国民航学院学报,1989,7(4):1-9.
[55]钟诗胜,周志波,张永等.基于三次回归分析的试车台基线库的建立[J].计算机集成制造系统,2005，11(2):270-274.
[56] Volponi, Allan J. Gas turbine parameter corrections[C].//American Society ofMechanical Engineers. Stockholm, Sweden: ASME, Fairfield, NJ, UnitedStates,1998:613~621.
[57] Mathioudakis K. Gas turbine test parameters corrections including operationwith water injection[C].//ASME Int Gas Turbine Inst Publ IGTI. Amsterdam,Netherlands: American Society of Mechanical Engineers.2002:935~943.
[58] Casoni A, Nuncio, Colitto. Corrected parameter control for two shaft gasturbine[C].//Proc. ASME Turbo Expo. Vienna, Austria: American Society ofMechanical Engineers,2004:741-748.
[59] Kurzke J. Model based gas turbine parameter corrections[C].//ASME Int GasTurbine Inst Publ IGTI. Atlanta, GA, United states: American Society ofMechanical Engineers,2003:91-99.
[60] Kyritsis V E, Pilidis P. An analytical approach for gas turbine parametercorrections[C].//Proc. ASME Turbo Expo. Berlin, Germany: AmericanSociety of Mechanical Engineers,3Park Avenue, New York, NY10016-5990,United States,2008:103:111.
[61] Jones G, Pilidis P, Curnock B. Compressor characteristics in gas turbineperformance modeling[C].//Proc. ASME Turbo Expo. New Orleans, Louisiana,USA: ASME.2001:1-9.
[62] Mathioudakis K, Stamatis A, A Tsalavoutas A, et la. Performance analysis ofindustrial gas turbines for engine condition monitoring[J]. Proc. Inst. Mech.Eng. Part A J.Power Eng.2001,215(2):173-184.
[63]商志根,严洪森.基于概率支持向量回归的产品设计时间预测模型[J].计算机应用研究,2013,30(4):1099-1102.
[64] Luo C S. Research on Grain Moisture Curve Fitting Based on Support VectorMachine Regression[C].//Advances in Intelligent and Soft Computing.Heidelberg, D-69121, Germany: Springer Verlag, Tiergartenstrasse17,Heidelberg, D-69121, Germany,2012:319-326.
[65] Che J X, Wang J Z, Tang Y J. Optimal training subset in a support vectorregression electric load forecasting model[J]. Applied Soft Computing.2012:1523-1531.
[66] Song J N, Tan H, Wang M J. Two-Level Support Vector Regression Approachfor Protein Backbone Torsion Angle Prediction from Primary Sequences[J].Predicting Protein Torsion Angles from Sequences.2012,7:1-16.
[67]李文莉,李郁侠.基于粒子群最小支持向量机的水文预测[J].计算机应用.2012,32(4):1188-1190.
[68] Ding Z X. Application of support vector machine regression in stock priceforecasting[C].//Advances in Intelligent and Soft Computing. Jeju Island,Korea, Republic of: Springer Verlag, Tiergartenstrasse17, Heidelberg,D-69121, Germany,2012:359-365.
[69] Lingras P, Butz C, Bhalchandra P. Financial series forecasting using dualrough support vector regression[J]. Advanced Information and KnowledgeProcessing.2012:115-127.
[70] ALEX J. SMOLA, BERNHARD SCHOLKOPE. A tutorial on support vectorregression[J]. Statistics and Computing.2004:199-222.
[71]李洪双,吕震宙.支持向量回归机在结构可靠性分析中的应用[J].航空学报,2007,28(1):94-99.
[72]黄宴委,吴惕华,赵静.回归型支持向量机的系统辨识及仿真[J].计算机仿真,2004,21(5):41-44.
[73]崔万照,朱长纯,保文星等.混沌时间序列的支持向量机预测[J].物理学报,2004,53(10):3303-3310.
[74] Zeng D L, Liu Y, Liu J W. Short-Term Wind Speed Forecast Based on BestWavelet Tree Decomposition and Support Vector Machine Regression[C].//Advances in Automation and Robotics. Dubai, United arab emirates:Springer Verlag, Tiergartenstrasse17, Heidelberg, D-69121, Germany,2011:373-379.
[75] Chuang C C, Su S F, Jeng J T. Robust support vector regression networks forfunction approximation with outliers[J]. IEEE TRANSACTIONS ONNEURAL NETWORKS.2002,13(6):1322-1330.
[76]张虎,严东超,雷晓犇.基于LS-SVM的飞机部件故障率预测[J].先进制造技术,2004,23(3):21-22.
[77]李元诚,方廷健.基于粗糙集理论的支撑向量机预测方法研究[J].数据采集与处理,2003,18(2):199-203.
[78]张国云,章兢.基于粗糙集理论和支持向量机的动态预测新方法及应用[J].自动化仪表,2005,26(2):18-21.
[79]林耀进,周忠眉,吴顺祥.集成灰色支持向量机预测模型研究与应用[J].计算机应用,2009,29(12):3287-3289.
[80]李庆国,陈守煜.基于模糊模式识别的支持向量机的回归预测方法[J].水科学进展,2005,16(5):741-746.
[81]尉询楷,陆波,汪诚等.支持向量机在航空发动机故障诊断中的应用[J].航空动力学报,2004,19(6):844-848.
[82]钟诗胜,雷达.基于过程支持向量机的航空发动机润滑油消耗率预测[J].润滑与密封,2009,34(10):6-9.
[83]朱明强,侯建军,刘颖等.一种基于卡尔曼数据平滑的分段曲线拟合室内定位算法[J].北京交通大学学报,2012,36(5):95-99.
[84]张学昌,高学军.基于小波包的点云数据平滑处理[J].机械设计,2008,25(12):11-14.
[85]王佰兴.基于小波分析的数据平滑处理算法研究与应用[J].科技创新导报,2009,(31):142-143.
[86]韩波.基于小波数据平滑的计算系统性能衰退规律建模[J].计算机光盘软件与应用,2012,(22):99-100.
[87]刘罗曼.时间序列分析中指数平滑法的应用[J].沈阳师范大学学报（自然科学版）,2009,27(4):416-418.
[88]叶德谦,王毅.一种对二次指数平滑预测中参数和初值的研究[J].燕山大学学报,2008,32(2):173-175.
[89]余有芳.指数平滑系数的优化研究[J].科技通报,2010,26(6):817-820.
[90] Velleman P F. Definition and comparison of robust nonlinear data smoothingalgorithms[J]. Journal of the American statistical association.1980,75(371):609-615.
[91] Nguyen N, Huang H, Oraintara S. Stationary wavelet packet transform anddependent laplacian bivariate shrinkage estimator for array-CGH datasmoothing[J]. Journal of computation biology,2010,17(2):139-152.
[92] Stickel J J. Data smoothing and numerical differentiation by a regularizationmethod[J]. Computers and Chemical Engineering.2010,(34):467-475.
[93] Karim S A A, Pang K V. Data smoothing using Gaussian scale-space anddiscrete wavelet transform[J]. Control and computer engineering.2011:344-348.
[94] Nummi T, Pan J X, Siren T. Testing for cubic smoothing spline underdependent data[J]. The International Biometric Society.2011:871-875.
[95] Ogaji S O T, Singh R. Gas path fault diagnosis framework for a three-shaft gasturbine[J]. Proceedings of the Institution of Mechanical Engineers, Part A:Journal of Power and Energy,2003,217(2):149-158.
[96] Zhu D M, Zhu Z L, Tang Hailong. Design and application of engine test gaspath fault diagnosis system[J]. Hangkong Dongli Xuebao/Journal of AerospacePower,2009,24(12):2768-2772.
[97] Li C Z, Lei Y. Aircraft engine gas path fault diagnosis based on neuralnetwork[C].//2011International Conference on Mechanical Engineering,Materials and Energy, ICMEME2011. Dalian, China: Trans Tech Publications,P.O. Box1254, Clausthal-Zellerfeld, D-38670, Germany,2011:144-148.
[98]廖辉传,刘遵雄.混沌时间序列局域偏最小二乘回归多步预测模型[J].微电子学与计算机,2007,24(4):193-197.
[99]刘新卫.加权几何平均偏最小二乘回归分析预测模型[J].襄樊学院学报,2011,32(2):16-18.
[100]王礼沅,郭基联,张恒喜.递阶偏最小二乘回归在飞机研制费用预测中的应用[J].航空学报,2009,30(8):1380-1384.
[101]李培华,杨海龙,孙伶俐.灰预测与时间序列模型在航天器故障预测中的应用[J].计算机测量与控制,2011,19(1):111-113.
[102]邵小强,马宪民.混沌时间序列预测的建模与仿真研究[J].计算机仿真,2011,28(5):228-231.
[103]韩敏,穆大芸.回声状态网络LM算法及混沌时间序列预测[J].控制与决策,2011,26(10):1469-1473.
[104]吴建生,金龙.基于SSA-MGF的偏最小二乘回归神经网络的预报模型[J].灾害学,2006,21(2):17-22.
[105]陶小创,樊焕贞,吕琛.基于小波神经网络的混沌时间序列预测及应用[J].南京航空航天大学学报,2011,43:174-178.
[106]郭兰平,俞健宁,张建刚等.基于遗传算法的RBF神经网络非线性时间序列预测[J].河北师范大学学报（自然科学版）,2011,35(3):244-247.
[107] Antoniadis A, Paparoditis E, Theofanis Sapatinas. A functional wavelet-kernelapproach for time series prediction[J]. Royal Statistical Society.2006:837-857.
[108] Tay F E H, Cao L J. Application of support vector machines in financial timeseries forecasting[J]. Elsevier Science Ltd.2001:309-317.
[109] Tan G H, Yan J Z, Gao C. Prediction of water quality time series data based onleast squares support vector machine[C].//Procedia Engineering. Kunming,China: Elsevier Ltd, Langford Lane, Kidlington, Oxford, OX51GB, UnitedKingdom,2012,31:1194-1199.
[110] Aussem A, Murtagh F. Combining neural network forecasts onwavelet-transformed time series[J]. Connection Science.1996:1-12.
[111] Gestel T V, Suykens J A K, Baestaens D E. Financial time series predictionusing least squares support vector machines within the evidence framework[J].IEEE Transactions on neural networks.2001,12(4):809-821.
[112] Martinetz T M, Berkovich S G, Schulten K J. Neural-gas network for vectorquantizaion and its application to time series prediction[J]. IEEE Transactionson neural networks.1993,4(4):558-569.
[113] Soltani S. On the use of the wavelet decomposition for time seriesprediction[J]. Elsevier Scence B. V.2002:267-277.
[114] Wang L, Teo K K, Lin Z P. Predicting time series with wavelet packet neuralnetworks[C].//Proc Int Jt Conf Neural Networks. Washington, DC, Unitedstates: Institute of Electrical and Electronics Engineers Inc,2001:1593-1597.
[115] Connor J T, Martin R D, Atlas L E. Recurrent neural networks and robust timeseries prediction[J]. IEEE Transactions on neural networks.1994,5(2):240-254.
[116] Chen Y H, Yang B, Dong J W. Time-series prediction using a local linearwavelet neural network[J]. Elsevier B. V.2005:449-465.
[117] Lee C M, Ko C N. Time series prediction using RBF neural networks with anonlinear time-varying evolution PSO algorithm[J]. Elsevier B. V.2009:449-460.
[118]许少华,何新贵.基于函数正交基展开的过程神经网络学习算法[J].计算机学报,2004,7(5):645-650.
[119]何新贵,梁久祯,许少华.过程神经元网络的训练及其应用[J].中国工程科学,2001,3(4):31-35.
[120]刘志刚,杜鹃,许少华等.基于改进粒子群算法的过程神经网络训练[J].科学技术与工程,2011,11(12):2675-2679.
[121]刘丽杰,李盼池,李欣等.离散过程神经网络在时间序列预测中的应用[J].计算机工程与应用,2011,47(32):224-227.
[122]丁刚,徐敏强,侯立国.基于过程神经网络的航空发动机排气温度预测[J].航空动力学报,2009,24(5):1035-1039.
[123]丁刚，钟诗胜.基于过程神经网络的时间序列预测及其应用研究[J].控制与决策,2006,9:1037-1041.
[124]钟诗胜,栾圣罡,丁刚.基于过程神经网络与气动热力参数的航空发动机状态监控[J].南京理工大学学报,2006,30(5):533-537.
[125]丁刚,付旭云,钟诗胜.基于过程神经网络的航空发动机性能参数预测[J].计算机集成制造系统,2011,17(1):198-207.
[126]钟诗胜,雷达,丁刚.卷积和离散过程神经网络及其在航空发动机排气温度预测中的应用[J].航空学报,2011,32:1-8.
[127]栾圣罡.基于气路参数样本的航空发动机状态监视方法与系统研究[D].哈尔滨工业大学博士论文.2008:62~76.
[128]李永平,陈闽叶,张兴媛.民航发动机的性能参数选择及其排队规则[J].上海工程技术大学学报,2006,20(2):108-111.
[129]于文武,康力平,许春生.航空发动机单元体性能评估方法研究[J].航空计算技术,2007,37(5):18-21.
[130]瞿红春,刘杰,甘晓燕.基于信息熵模糊理论的航空发动机性能评估[J].中国民航大学学报,2009,27(2):23-26.
[131]瞿红春,刘杰,王太勇等.一种基于信息熵的航空发动机性能评估方法[J].机械科学与技术,2009,28(6):701-704.
[132]王梦琦,王端民,杨雪.基于改进模糊综合评判的航空发动机状态评估[J].润滑与密封,2011,36(1):80-84.
[133]崔晓飞,蒋科艺,王永华.基于贝叶斯信息融合的航空发动机状态评估方法研究[J].燃气轮机试验与研究,2009,22(4):39-42.
[134]赵雄飞,刘永葆,贺星等.基于小偏差方法的燃气轮机气路故障判据的建立[J].机械工程与自动化,2011,(4):115-117.
[135] Sun B, Zhang J, Zhang S J. Fault quantitative diagnosis of turbine gas pathcomponent by back-propagation networks(BPN)[J]. Tuijin Jishu/Journal ofPropulsion Technology,1999,20(4):48-52.
[136] Jiang R J, Xie J. Gas turbine gas path fault diagnosis technology based on thefuzzy Petri net[C].//2011International Conference on Transportation,Mechanical, and Electrical Engineering, TMEE2011. Changchun, China:IEEE Computer Society,445Hoes Lane-P.O.Box1331, Piscataway, NJ08855-1331, United States,2011:850-853.
[137] Qu J L, Tang C S, Xiao H X, et al. Integrated diagnosis of aeroengines’ gaspath faults using artificial neural network[J]. Hangkong DongliXuebao/Journal of Aerospace Power,2008,23(11):2124-2127.
[138] Chen T, Sun J G. Aeroengine gas path fault diagnosis using rough sets andneural networks[J]. Hangkong Dongli Xuebao/Journal of Aerospace Power,2006,21(1):207-212.
[139] Torella G, Lombardo G. Nerual networks for the maintance of aero engines[J].AIAA-95-2351.1995:1-12.
[140] Cumming S. Neural Networks for Monitoring of Engine Condition Data[J].Neural Comput&Applic.1993:96-102.
[141] Demirci S, Aykan R. Neural Network Model of Airbus A340Flight Dynamicsfor Reliability Analyses[C].//Collect. Techn. Pap. Model. Simul. Technol.Conf. San Francisco, CA, United States: American Institute of Aeronautics andAstronautics Inc,2005:554-558.
[142] Cristo R, Mathioudakis K. Bayesian network approach for gas path faultdiagnosis[J]. Journal of Engineering for Gas Turbines and Power,2006,128(1):64-72.
[143] Chen T, Sun J G, Hao Y. Neural network and Dempster-Shafter theory basedfault diagnosis for aeroengine gas path[J]. Hangkong Xuebao/ActaAeronautica et Astronautica Sinica,2006,27(6):1014-1017.
[144]莫翔宇,唐庆如,杨晓强.基于灰色关联分析的航空发动机气路故障诊断方法研究[J].航空维修与工程.2009:51-52.
[145] Zhou J B, Lu F, Huang J Q. Gas path component fault diagnosis based on grayrelational analysis for aero-engine[J]. Tuijin Jishu/Journal of PropulsionTechnology,2011,32(1):140-145.
[146]张宗杰,蒋丽英,黄燕.基于多分类器融合的航空发动机气路故障诊断[J].沈阳航空工业学院学报.2010,27(2):42-45.
[147] Zhao S R, Huang X H. Fault diagnosis for aeroengine gas path componentsbased on neural network[J]. Hangkong Dongli Xuebao/Journal of AerospacePower,2008,23(1):163-168.
[148] Luan S G, Zhong S S, Li Y. Hybrid recurrent process neural network for aeroengine condition monitoring[J]. Neural Network World，2008，18(2):133-145.
[149]员世芬,张金梅,田建艳.小波神经网络初始值的选择[J].电脑开发与应用,2005,18(2):37-39.
[150]骆广琦,桑增产,王如根等.航空燃气轮发动机数值仿真[M].北京:国防工业出版社,2007:27-32,97-122.
[151]宋晓峰,陈德钊,胡上序.支持向量机泛化能力估计若干方法[J].计算机科学,2004(31)8:125-127.
[152] Weike Y, Liu B, Xue Y. Fuzzy neural networks and GA based predictivecontrol for active power filter[C].//Proceedings-20135th Conference onMeasuring Technology and Mechatronics Automation, ICMTMA2013. HongKong, China: IEEE Computer Society,2001L Street N.W., Suite700,Washington, DC20036-4928, United States,2013:598-201.
[153] Mohammad M, Hossein N P, Zamin J M, et al. Application of artificial neuralnetworks (ANNS) and linear regressions (LR) to predict the deflection ofconcrete deep beams[J]. Computers and Concrete,2013,11(3):237-252.
[154] Lu Y, Pulasani P R, Reza D, et al. Application of neural networks for theprediction of cartilage stress in a musculoskeletal system[J]. BiomedicalSignal Processing and Control,2013,8(6):475-482.
[155] Leila A, Sid-Ali O, Noureddine D, et al. Lithofacies prediction from well logsdata using different neural network models[C].//ICPRAM2013-Proceedingsof the2nd International Conference on Pattern Recognition Applications andMethods. Barcelona, Spain: SciTePress, Portugal,2013:702-706.
[156]金向阳,林琳,钟诗胜等.航空发动机振动趋势预测的过程神经网络[J].振动、测试与诊断,2011,31(3):331-336.
[2] Mercer C R, Simon D L, Hunter G W, et al. Fundamental TechnologyDevelopment for Gas-turbine Engine Health Management[R].NASA-TM-2007-0022364,2007.
[3] Fu X Y, Ding G, Zhong S S. Aeroengine Turbine Exhaust Gas TemperaturePrediction Using Support Vector Machines[C].//Advances in NeuralNetworks-ISNN2009-6th International Symposium on Neural Networks,ISNN2009, Proceedings. Wuhan, China: Spring Verlag, Tiergartenstrasse17,Heidelberg, D-69121, Germany,2009:235-241.
[4]敖良忠. CFM56-5B发动机性能衰退评估[J].中国民航飞行学院学报,2006,17(2):28-30.
[5] Nott C, Sossamon C, Olcmen S M, et al. Jet-Engine Health Monitoring andOperation Using Fuzzy-Logic Controllers and Bayesian Belief Networks[C].//Collection of Technical Papers-44th AIAA Aerospace Sciences Meeting.Reno, NV, United states: American Institute of Aeronautics and AstronauticsInc.,1801Alexander Bell Drive, Suite500, Reston, VA20191-4344, UnitedStates,2006:17710-17720.
[6]钟诗胜，栾圣罡.面向航空发动机全寿命管理的航线数据处理系统[J].计算机集成制造系,2006,8：1273-1278.
[7] Ogaji S O T, Sampath S, Singh R, et al. Parameter selection for diagnosing agas-turbine’s performance-deterioration[J]. Elsevier Science Ltd.2002,73:25-46.
[8]朱玉斌,方忠祥,侯朝焕等.基于部件参数估计的航空发动机故障预测技术研究[J].测控技术,2012,31(1):128-131.
[9] Ameco, Beijing. Engines scientific management[Z]. The Reliability ResearchProgram Summary of Civil Aviation Engine,2000.121-130.
[10] Ameco, Beijing. The role of analyzing engine test data and exploring its law inestablishing maintenance workscope[Z]. The Reliability Research ProgramSummary of Civil Aviation Engine,2000.135-151.
[11] Li Y G. Performance-and analysis-based gas turbine diagnostics: a review[J].Proc Instn Mech Engrs Vol216Part A: J Power and Energy.2002,216:363-377.
[12] Ameco, Beijing. The present situation and development of state monitoring ofcivil aviation engine[Z]. Beijing：The Reliability Research Program Summaryof Civil Aviation Engine,2000.26-32.
[13]钟诗胜,李洋.基于小波过程神经网络的飞机民用航空发动机状态监视[J].航空学报,2007,22(1):68-71.
[14] Ranjan, Ganguli. Jet Engine Gas-Path Measurement Filtering Using CenterWeighted Idempotent Median Filters[J]. Journal of Propulsion and Power.2003,19(5):930-937.
[15] Li X, Schmidt L C. Transformation of an EGT Grammar: New Grammar, NewDesigns[J]. Journal of Mechanical Design.2004,126:753-756.
[16]贺瑶,王文庆,薛飞.基于云计算的海量数据挖掘研究[J].计算机技术与发展.2013,23(2):69-72.
[17]李华,刘帅,李茂等.数据挖掘理论及其应用研究[J].断块油气田,2010,17(1):88-91.
[18] Katharina M, Kanishka B, Hillol K. Introduction to data mining forsustainability[J]. Fata Mining and Knowledge Discovery,2012,24(2):311-324.
[19] Padhy N, Mishra P, Panigrahi R. The Survey of Data Mining Applications AndFeature Scope[J]. International Journal of Computer Science, Engineering andInformation Technology (IJCSEIT).2012,2(3):43-58.
[20] Cios K J, Pedrycz W, Swiniarski R M. Data Mining Methods for KnowledgeDiscovery[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS.1998,9(6):1533-1534.
[21] Olson D L, Delen D, Meng Y Y. Comparative analysis of data mining methodsfor bankruptcy prediction[J]. Decision Support Systems.2012,52(2):464-473.
[22]郑继刚,王边疆.数据挖掘研究的现状与发展趋势[J].思茅师范高等专科学校,2010,26(3):36-39.
[23] Fauvel M, Chanussot J, Benediktsson J A, et al. Parsimonious Mahalanobiskernel for the classification of high dimensional data[J]. Patten Recognition,3013,46(3):845-854.
[24] Huang H Y, Chang H Y, Liu J F. A novel kernel-based gene selection andclassification scheme for microarray data[C].//6th International Conferenceon Soft Computing and Intelligent Systems, and13th International Symposiumon Advanced Intelligence Systems, SCIS/ISIS2012. Kobe, Japan: IEEEComputer Society,2001L Street N.W., Suite700, Washington, DC20036-4928, United States,2012:1679-1683.
[25]韩利,祁云嵩,王俊.基于粗糙集的支持向量机微阵列数据分类方法[J].科学技术与工程,2009,9(1):152-155.
[26] Wei L W, Wei C S, Wan X Q. Data classification using support vectormachines with mixture kernels[C].//Advanced Materials Research. Guilin,China: Trans Tech Publications, P.O. Box1254, Clausthal-Zellerfeld, D-38670,Germany,2012:936-939.
[27]王宝祥,丁爱萍,张连堂等.一种基于粗糙集的数据分类方法[J].河南大学学报（自然科学版）,2010,40(3):291-294.
[28]马胜祥,马建庆,杨明.基于核函数拟合的非平衡数据分类方法[J].计算机应用与软件,2010,27(4):177-179.
[29] Zhang X N, Song S J, Wu C. Robust Bayesian Classification with IncompleteData[J]. Cognitive Computation,2013,5(2):170-187.
[30]江峰,杜军威,晆跃飞等.基于边界和距离的离群点检测[J].电子学报,2010,(3):700-705.
[31] Jiang F, Sui Y F, Cao C G. Distance metrics and outlier detection in roughsets[J]. Kongzhi yu Juece/Control and Decision,2013,28(2):188-192.
[32] Li H, Zhang S, Wang X. An outlier detection algorithm based on informationentropy and rough set[J]. International Journal of Digital Content Technologyand its Applications,2012,6(20):97-106.
[33] Li X J, Tian S F, Qiu T R, et al. Outlier detection using the information entropyof neighborhood rough sets[J]. Journal of Information and ComputationalScience,2012,9(12):3339-3350.
[34] Jiang F, Du J W, Ge Y, et al. Sequence outlier detection based on rough settheory[J]. Tien Tzu Hsueh Pao/Acta Electronica Sinica,2011,39(2):345-350.
[35] Jeng J T, Chuang C C, Tseng C C, et al. Robust interval competitiveagglomeration clustering algorithm[J]. International Journal of Fuzzy Systems,2010,12(3):227-236.
[36] Lei D J, Zhu Q S, Chen J, et al. Automatic k-means clustering algorithm foroutlier detection[C].//Lecture Notes in Electrical Engineering. Chongqing,China: Springer Verlag, Tiergartenstrasse17, Heidelberg, D-69121, Germany,2012:363-372.
[37] Qin F J. Outlier clustering algorithm for study of outlying patterns[J]. Journalof Computational Information Systems,2012,7(17):7037-7044.
[38]吴晓燕.基于遗传模拟退火算法的高维离群点挖掘[J].计算机信息,2010,26(7-3):139-141.
[39] Jiangtao P, Silong P, Yong H. Partial least squares and random sampleconsensus in outlier detection[J]. Analytica Chimica Acta,2012:24-29.
[40] Tang Z G, Yang J, Yang B R. A new detection algorithm based on manifoldlearning[C].//2010Chinese Control and Decision Conference, CCDC2010.Xuzhou, China: EEE Computer Society,445Hoes Lane-P.O.Box1331,Piscataway, NJ08855-1331, United States,2010:452-457.
[41] Chen M S, Park J S, Yu P S. Efficient Data Mining for Path TraversalPatterns[J]. IEEE TRANSACTIONS ON KNOWLEDGE AND DATAENGINEERING.1998,10(2):209-221.
[42] Fayyad U, Shapiro G P, Smyth P. Knowledge Discovery and Data Mining:Towards a Unifying Framework[J]. American Association for ArtificialIntelligence.1996:82-88.
[43] Bresfelean, Paul V. Data mining and model trees strudy on GDP and itsinfluence factors[C].//11thWSEAS international conference on AIC’11.Florence, Italy: World Scientific and Engineering Academy and Society, P.O.Box4743, Clifton, NJ07015-4743, United States.2011:401~406.
[44]郭茜,朱杰.高维数据挖掘技术在教学质量监控与评价的应用研究[J].高等教育,2010:81-82.
[45]刘城霞.基于MS关联规则数据挖掘模型的应用与探讨[J].计算机技术与发展,2013,23(1):25-30.
[46]要照华,闫宏印.基于粗糙集的海量数据挖掘[J].机械管理开发,2010,25(1):17-18.
[47] Wang W H, Pan W G, He M F, et al. Target values of combustion optimizationin coal fire boiler based on data mining[C].//2nd International Conference onEnergy, Environment and Sustainable Development, EESD2012, Trans TechPublications, P.O. Box1254, Clausthal-Zellerfeld, D-38670, Germany, Jilin,China.2013:1143-1146.
[48]邹媛.基于决策树的数据挖掘算法的应用与研究[J].科学技术与工程,2010,10(18):4510-4515.
[49]肖冬荣,杨磊.基于遗传算法的关联规则数据挖掘[J].通信技术,2010,43(1):205-207.
[50]李兴森,张玲玲,朱正祥.数据挖掘获取的知识的智能评价方法[J].科研管理,2010,31:32-38.
[51]杨启仁.数据挖掘中聚类算法的研究[J].牡丹江大学学报,2010,19(6):107-110.
[52]张立斌.一种用于受训神经网络数据挖掘的遗传算法[J].信息技术,2010,(6):60-65.
[53]林兆福,范作民.发动机基线方程的建立和应用[J].中国民航学院学报,1992,10(4):20-32.
[54]林兆福,范作民,孙春林.航空发动机气动热力参数的趋势分析[J].中国民航学院学报,1989,7(4):1-9.
[55]钟诗胜,周志波,张永等.基于三次回归分析的试车台基线库的建立[J].计算机集成制造系统,2005，11(2):270-274.
[56] Volponi, Allan J. Gas turbine parameter corrections[C].//American Society ofMechanical Engineers. Stockholm, Sweden: ASME, Fairfield, NJ, UnitedStates,1998:613~621.
[57] Mathioudakis K. Gas turbine test parameters corrections including operationwith water injection[C].//ASME Int Gas Turbine Inst Publ IGTI. Amsterdam,Netherlands: American Society of Mechanical Engineers.2002:935~943.
[58] Casoni A, Nuncio, Colitto. Corrected parameter control for two shaft gasturbine[C].//Proc. ASME Turbo Expo. Vienna, Austria: American Society ofMechanical Engineers,2004:741-748.
[59] Kurzke J. Model based gas turbine parameter corrections[C].//ASME Int GasTurbine Inst Publ IGTI. Atlanta, GA, United states: American Society ofMechanical Engineers,2003:91-99.
[60] Kyritsis V E, Pilidis P. An analytical approach for gas turbine parametercorrections[C].//Proc. ASME Turbo Expo. Berlin, Germany: AmericanSociety of Mechanical Engineers,3Park Avenue, New York, NY10016-5990,United States,2008:103:111.
[61] Jones G, Pilidis P, Curnock B. Compressor characteristics in gas turbineperformance modeling[C].//Proc. ASME Turbo Expo. New Orleans, Louisiana,USA: ASME.2001:1-9.
[62] Mathioudakis K, Stamatis A, A Tsalavoutas A, et la. Performance analysis ofindustrial gas turbines for engine condition monitoring[J]. Proc. Inst. Mech.Eng. Part A J.Power Eng.2001,215(2):173-184.
[63]商志根,严洪森.基于概率支持向量回归的产品设计时间预测模型[J].计算机应用研究,2013,30(4):1099-1102.
[64] Luo C S. Research on Grain Moisture Curve Fitting Based on Support VectorMachine Regression[C].//Advances in Intelligent and Soft Computing.Heidelberg, D-69121, Germany: Springer Verlag, Tiergartenstrasse17,Heidelberg, D-69121, Germany,2012:319-326.
[65] Che J X, Wang J Z, Tang Y J. Optimal training subset in a support vectorregression electric load forecasting model[J]. Applied Soft Computing.2012:1523-1531.
[66] Song J N, Tan H, Wang M J. Two-Level Support Vector Regression Approachfor Protein Backbone Torsion Angle Prediction from Primary Sequences[J].Predicting Protein Torsion Angles from Sequences.2012,7:1-16.
[67]李文莉,李郁侠.基于粒子群最小支持向量机的水文预测[J].计算机应用.2012,32(4):1188-1190.
[68] Ding Z X. Application of support vector machine regression in stock priceforecasting[C].//Advances in Intelligent and Soft Computing. Jeju Island,Korea, Republic of: Springer Verlag, Tiergartenstrasse17, Heidelberg,D-69121, Germany,2012:359-365.
[69] Lingras P, Butz C, Bhalchandra P. Financial series forecasting using dualrough support vector regression[J]. Advanced Information and KnowledgeProcessing.2012:115-127.
[70] ALEX J. SMOLA, BERNHARD SCHOLKOPE. A tutorial on support vectorregression[J]. Statistics and Computing.2004:199-222.
[71]李洪双,吕震宙.支持向量回归机在结构可靠性分析中的应用[J].航空学报,2007,28(1):94-99.
[72]黄宴委,吴惕华,赵静.回归型支持向量机的系统辨识及仿真[J].计算机仿真,2004,21(5):41-44.
[73]崔万照,朱长纯,保文星等.混沌时间序列的支持向量机预测[J].物理学报,2004,53(10):3303-3310.
[74] Zeng D L, Liu Y, Liu J W. Short-Term Wind Speed Forecast Based on BestWavelet Tree Decomposition and Support Vector Machine Regression[C].//Advances in Automation and Robotics. Dubai, United arab emirates:Springer Verlag, Tiergartenstrasse17, Heidelberg, D-69121, Germany,2011:373-379.
[75] Chuang C C, Su S F, Jeng J T. Robust support vector regression networks forfunction approximation with outliers[J]. IEEE TRANSACTIONS ONNEURAL NETWORKS.2002,13(6):1322-1330.
[76]张虎,严东超,雷晓犇.基于LS-SVM的飞机部件故障率预测[J].先进制造技术,2004,23(3):21-22.
[77]李元诚,方廷健.基于粗糙集理论的支撑向量机预测方法研究[J].数据采集与处理,2003,18(2):199-203.
[78]张国云,章兢.基于粗糙集理论和支持向量机的动态预测新方法及应用[J].自动化仪表,2005,26(2):18-21.
[79]林耀进,周忠眉,吴顺祥.集成灰色支持向量机预测模型研究与应用[J].计算机应用,2009,29(12):3287-3289.
[80]李庆国,陈守煜.基于模糊模式识别的支持向量机的回归预测方法[J].水科学进展,2005,16(5):741-746.
[81]尉询楷,陆波,汪诚等.支持向量机在航空发动机故障诊断中的应用[J].航空动力学报,2004,19(6):844-848.
[82]钟诗胜,雷达.基于过程支持向量机的航空发动机润滑油消耗率预测[J].润滑与密封,2009,34(10):6-9.
[83]朱明强,侯建军,刘颖等.一种基于卡尔曼数据平滑的分段曲线拟合室内定位算法[J].北京交通大学学报,2012,36(5):95-99.
[84]张学昌,高学军.基于小波包的点云数据平滑处理[J].机械设计,2008,25(12):11-14.
[85]王佰兴.基于小波分析的数据平滑处理算法研究与应用[J].科技创新导报,2009,(31):142-143.
[86]韩波.基于小波数据平滑的计算系统性能衰退规律建模[J].计算机光盘软件与应用,2012,(22):99-100.
[87]刘罗曼.时间序列分析中指数平滑法的应用[J].沈阳师范大学学报（自然科学版）,2009,27(4):416-418.
[88]叶德谦,王毅.一种对二次指数平滑预测中参数和初值的研究[J].燕山大学学报,2008,32(2):173-175.
[89]余有芳.指数平滑系数的优化研究[J].科技通报,2010,26(6):817-820.
[90] Velleman P F. Definition and comparison of robust nonlinear data smoothingalgorithms[J]. Journal of the American statistical association.1980,75(371):609-615.
[91] Nguyen N, Huang H, Oraintara S. Stationary wavelet packet transform anddependent laplacian bivariate shrinkage estimator for array-CGH datasmoothing[J]. Journal of computation biology,2010,17(2):139-152.
[92] Stickel J J. Data smoothing and numerical differentiation by a regularizationmethod[J]. Computers and Chemical Engineering.2010,(34):467-475.
[93] Karim S A A, Pang K V. Data smoothing using Gaussian scale-space anddiscrete wavelet transform[J]. Control and computer engineering.2011:344-348.
[94] Nummi T, Pan J X, Siren T. Testing for cubic smoothing spline underdependent data[J]. The International Biometric Society.2011:871-875.
[95] Ogaji S O T, Singh R. Gas path fault diagnosis framework for a three-shaft gasturbine[J]. Proceedings of the Institution of Mechanical Engineers, Part A:Journal of Power and Energy,2003,217(2):149-158.
[96] Zhu D M, Zhu Z L, Tang Hailong. Design and application of engine test gaspath fault diagnosis system[J]. Hangkong Dongli Xuebao/Journal of AerospacePower,2009,24(12):2768-2772.
[97] Li C Z, Lei Y. Aircraft engine gas path fault diagnosis based on neuralnetwork[C].//2011International Conference on Mechanical Engineering,Materials and Energy, ICMEME2011. Dalian, China: Trans Tech Publications,P.O. Box1254, Clausthal-Zellerfeld, D-38670, Germany,2011:144-148.
[98]廖辉传,刘遵雄.混沌时间序列局域偏最小二乘回归多步预测模型[J].微电子学与计算机,2007,24(4):193-197.
[99]刘新卫.加权几何平均偏最小二乘回归分析预测模型[J].襄樊学院学报,2011,32(2):16-18.
[100]王礼沅,郭基联,张恒喜.递阶偏最小二乘回归在飞机研制费用预测中的应用[J].航空学报,2009,30(8):1380-1384.
[101]李培华,杨海龙,孙伶俐.灰预测与时间序列模型在航天器故障预测中的应用[J].计算机测量与控制,2011,19(1):111-113.
[102]邵小强,马宪民.混沌时间序列预测的建模与仿真研究[J].计算机仿真,2011,28(5):228-231.
[103]韩敏,穆大芸.回声状态网络LM算法及混沌时间序列预测[J].控制与决策,2011,26(10):1469-1473.
[104]吴建生,金龙.基于SSA-MGF的偏最小二乘回归神经网络的预报模型[J].灾害学,2006,21(2):17-22.
[105]陶小创,樊焕贞,吕琛.基于小波神经网络的混沌时间序列预测及应用[J].南京航空航天大学学报,2011,43:174-178.
[106]郭兰平,俞健宁,张建刚等.基于遗传算法的RBF神经网络非线性时间序列预测[J].河北师范大学学报（自然科学版）,2011,35(3):244-247.
[107] Antoniadis A, Paparoditis E, Theofanis Sapatinas. A functional wavelet-kernelapproach for time series prediction[J]. Royal Statistical Society.2006:837-857.
[108] Tay F E H, Cao L J. Application of support vector machines in financial timeseries forecasting[J]. Elsevier Science Ltd.2001:309-317.
[109] Tan G H, Yan J Z, Gao C. Prediction of water quality time series data based onleast squares support vector machine[C].//Procedia Engineering. Kunming,China: Elsevier Ltd, Langford Lane, Kidlington, Oxford, OX51GB, UnitedKingdom,2012,31:1194-1199.
[110] Aussem A, Murtagh F. Combining neural network forecasts onwavelet-transformed time series[J]. Connection Science.1996:1-12.
[111] Gestel T V, Suykens J A K, Baestaens D E. Financial time series predictionusing least squares support vector machines within the evidence framework[J].IEEE Transactions on neural networks.2001,12(4):809-821.
[112] Martinetz T M, Berkovich S G, Schulten K J. Neural-gas network for vectorquantizaion and its application to time series prediction[J]. IEEE Transactionson neural networks.1993,4(4):558-569.
[113] Soltani S. On the use of the wavelet decomposition for time seriesprediction[J]. Elsevier Scence B. V.2002:267-277.
[114] Wang L, Teo K K, Lin Z P. Predicting time series with wavelet packet neuralnetworks[C].//Proc Int Jt Conf Neural Networks. Washington, DC, Unitedstates: Institute of Electrical and Electronics Engineers Inc,2001:1593-1597.
[115] Connor J T, Martin R D, Atlas L E. Recurrent neural networks and robust timeseries prediction[J]. IEEE Transactions on neural networks.1994,5(2):240-254.
[116] Chen Y H, Yang B, Dong J W. Time-series prediction using a local linearwavelet neural network[J]. Elsevier B. V.2005:449-465.
[117] Lee C M, Ko C N. Time series prediction using RBF neural networks with anonlinear time-varying evolution PSO algorithm[J]. Elsevier B. V.2009:449-460.
[118]许少华,何新贵.基于函数正交基展开的过程神经网络学习算法[J].计算机学报,2004,7(5):645-650.
[119]何新贵,梁久祯,许少华.过程神经元网络的训练及其应用[J].中国工程科学,2001,3(4):31-35.
[120]刘志刚,杜鹃,许少华等.基于改进粒子群算法的过程神经网络训练[J].科学技术与工程,2011,11(12):2675-2679.
[121]刘丽杰,李盼池,李欣等.离散过程神经网络在时间序列预测中的应用[J].计算机工程与应用,2011,47(32):224-227.
[122]丁刚,徐敏强,侯立国.基于过程神经网络的航空发动机排气温度预测[J].航空动力学报,2009,24(5):1035-1039.
[123]丁刚，钟诗胜.基于过程神经网络的时间序列预测及其应用研究[J].控制与决策,2006,9:1037-1041.
[124]钟诗胜,栾圣罡,丁刚.基于过程神经网络与气动热力参数的航空发动机状态监控[J].南京理工大学学报,2006,30(5):533-537.
[125]丁刚,付旭云,钟诗胜.基于过程神经网络的航空发动机性能参数预测[J].计算机集成制造系统,2011,17(1):198-207.
[126]钟诗胜,雷达,丁刚.卷积和离散过程神经网络及其在航空发动机排气温度预测中的应用[J].航空学报,2011,32:1-8.
[127]栾圣罡.基于气路参数样本的航空发动机状态监视方法与系统研究[D].哈尔滨工业大学博士论文.2008:62~76.
[128]李永平,陈闽叶,张兴媛.民航发动机的性能参数选择及其排队规则[J].上海工程技术大学学报,2006,20(2):108-111.
[129]于文武,康力平,许春生.航空发动机单元体性能评估方法研究[J].航空计算技术,2007,37(5):18-21.
[130]瞿红春,刘杰,甘晓燕.基于信息熵模糊理论的航空发动机性能评估[J].中国民航大学学报,2009,27(2):23-26.
[131]瞿红春,刘杰,王太勇等.一种基于信息熵的航空发动机性能评估方法[J].机械科学与技术,2009,28(6):701-704.
[132]王梦琦,王端民,杨雪.基于改进模糊综合评判的航空发动机状态评估[J].润滑与密封,2011,36(1):80-84.
[133]崔晓飞,蒋科艺,王永华.基于贝叶斯信息融合的航空发动机状态评估方法研究[J].燃气轮机试验与研究,2009,22(4):39-42.
[134]赵雄飞,刘永葆,贺星等.基于小偏差方法的燃气轮机气路故障判据的建立[J].机械工程与自动化,2011,(4):115-117.
[135] Sun B, Zhang J, Zhang S J. Fault quantitative diagnosis of turbine gas pathcomponent by back-propagation networks(BPN)[J]. Tuijin Jishu/Journal ofPropulsion Technology,1999,20(4):48-52.
[136] Jiang R J, Xie J. Gas turbine gas path fault diagnosis technology based on thefuzzy Petri net[C].//2011International Conference on Transportation,Mechanical, and Electrical Engineering, TMEE2011. Changchun, China:IEEE Computer Society,445Hoes Lane-P.O.Box1331, Piscataway, NJ08855-1331, United States,2011:850-853.
[137] Qu J L, Tang C S, Xiao H X, et al. Integrated diagnosis of aeroengines’ gaspath faults using artificial neural network[J]. Hangkong DongliXuebao/Journal of Aerospace Power,2008,23(11):2124-2127.
[138] Chen T, Sun J G. Aeroengine gas path fault diagnosis using rough sets andneural networks[J]. Hangkong Dongli Xuebao/Journal of Aerospace Power,2006,21(1):207-212.
[139] Torella G, Lombardo G. Nerual networks for the maintance of aero engines[J].AIAA-95-2351.1995:1-12.
[140] Cumming S. Neural Networks for Monitoring of Engine Condition Data[J].Neural Comput&Applic.1993:96-102.
[141] Demirci S, Aykan R. Neural Network Model of Airbus A340Flight Dynamicsfor Reliability Analyses[C].//Collect. Techn. Pap. Model. Simul. Technol.Conf. San Francisco, CA, United States: American Institute of Aeronautics andAstronautics Inc,2005:554-558.
[142] Cristo R, Mathioudakis K. Bayesian network approach for gas path faultdiagnosis[J]. Journal of Engineering for Gas Turbines and Power,2006,128(1):64-72.
[143] Chen T, Sun J G, Hao Y. Neural network and Dempster-Shafter theory basedfault diagnosis for aeroengine gas path[J]. Hangkong Xuebao/ActaAeronautica et Astronautica Sinica,2006,27(6):1014-1017.
[144]莫翔宇,唐庆如,杨晓强.基于灰色关联分析的航空发动机气路故障诊断方法研究[J].航空维修与工程.2009:51-52.
[145] Zhou J B, Lu F, Huang J Q. Gas path component fault diagnosis based on grayrelational analysis for aero-engine[J]. Tuijin Jishu/Journal of PropulsionTechnology,2011,32(1):140-145.
[146]张宗杰,蒋丽英,黄燕.基于多分类器融合的航空发动机气路故障诊断[J].沈阳航空工业学院学报.2010,27(2):42-45.
[147] Zhao S R, Huang X H. Fault diagnosis for aeroengine gas path componentsbased on neural network[J]. Hangkong Dongli Xuebao/Journal of AerospacePower,2008,23(1):163-168.
[148] Luan S G, Zhong S S, Li Y. Hybrid recurrent process neural network for aeroengine condition monitoring[J]. Neural Network World，2008，18(2):133-145.
[149]员世芬,张金梅,田建艳.小波神经网络初始值的选择[J].电脑开发与应用,2005,18(2):37-39.
[150]骆广琦,桑增产,王如根等.航空燃气轮发动机数值仿真[M].北京:国防工业出版社,2007:27-32,97-122.
[151]宋晓峰,陈德钊,胡上序.支持向量机泛化能力估计若干方法[J].计算机科学,2004(31)8:125-127.
[152] Weike Y, Liu B, Xue Y. Fuzzy neural networks and GA based predictivecontrol for active power filter[C].//Proceedings-20135th Conference onMeasuring Technology and Mechatronics Automation, ICMTMA2013. HongKong, China: IEEE Computer Society,2001L Street N.W., Suite700,Washington, DC20036-4928, United States,2013:598-201.
[153] Mohammad M, Hossein N P, Zamin J M, et al. Application of artificial neuralnetworks (ANNS) and linear regressions (LR) to predict the deflection ofconcrete deep beams[J]. Computers and Concrete,2013,11(3):237-252.
[154] Lu Y, Pulasani P R, Reza D, et al. Application of neural networks for theprediction of cartilage stress in a musculoskeletal system[J]. BiomedicalSignal Processing and Control,2013,8(6):475-482.
[155] Leila A, Sid-Ali O, Noureddine D, et al. Lithofacies prediction from well logsdata using different neural network models[C].//ICPRAM2013-Proceedingsof the2nd International Conference on Pattern Recognition Applications andMethods. Barcelona, Spain: SciTePress, Portugal,2013:702-706.
[156]金向阳,林琳,钟诗胜等.航空发动机振动趋势预测的过程神经网络[J].振动、测试与诊断,2011,31(3):331-336.