基于顺序集成方法的制冷系统故障检测与诊断研究
|
摘要
鉴于制冷空调系统日益复杂,系统故障难以识别,且会导致能耗增加(多达30%),室内外环境恶化,设备可靠性、安全性及运行经济性下降等诸多问题,有必要对故障检测及诊断进行相关研究,以便及时排除故障,保证系统正常运行。本研究围绕制冷系统故障检测与诊断问题,从故障指示特征智能提取,到制冷系统单发及并发故障(多故障),顺序递进,集成故障诊断、数据挖掘及模式识别领域各种智能方法,实现检测与所有故障确诊一步完成,对轻微故障亦性能良好,诊断正确率高,虚警率及诊断用时少;并基于混淆矩阵建立了故障诊断模型评价指标,探讨了能较好表征典型故障的故障指示特征。
首先,对制冷系统及其典型渐变故障进行理论分析,初步了解征兆与故障(症状与原因)间的理论联系,结合ASHRAE的制冷机组故障模拟实验,探讨制冷系统故障指示特征智能提取方法,以期找到能较好表征故障的参数(集),减轻乃至消除特征间相关度,去除信息冗余,使故障更加清晰地呈现,有利于模型对故障的分离和识别,缩短诊断时间,提高诊断准确率。分别运用基于互信息(MI)的最大冗余最小相关过滤模型(MI-based mRMR filter)、基于遗传算法的封装模型(GA-LDA wrapper、GA-SVM wrapper)进行特征选择,运用主成分分析法(PCA)进行特征提取,得到不同的故障指示特征子集,并在后续章节的分析中逐步筛选出最佳子集。
其次,针对制冷系统中典型的单发故障,运用故障指示特征智能提取与一种基于结构风险最小化的新型机器学习方法——支持向量机(SVM),相结合的顺序集成模型,进行故障检测与诊断,并基于混淆矩阵(Confusion matrix)建立以诊断正确率(CR)、命中率(HR)及虚警率(FAR)为核心的故障诊断模型评价体系,评价模型对于所有样本的总体性能及对包括正常及各类故障的诊断效果(分布性能),命中及虚警情况。结果表明,SVM的故障检测与诊断性能优于故障诊断决策树模型(C4.5),CR达99%以上。GA-SVM封装模型从64个原始特征中所选之8个故障指示特征较其他各种智能提取模型所选特征子集更为突出,在SVM模型及C4.5模型中均表现优良。对特征数的研究表明,不论原始特征抑或经PCA提取的综合特征,特征数越少,故障检测与诊断模型的训练及测试时间越短,但特征数与模型性能之间并非单调关系,特征太少可能造成信息缺失而降低诊断正确率,特征太多增加冗余信息而对故障诊断造成干扰,使模型鲁棒性下降。通常,所选特征数应至少等于包含正常运行及所有故障在内的独立类别数。基于PCA的特征提取只有当所选主元累计方差贡献率超过95%时,效果好于不进行任何智能特征提取的64个原始特征,但亦不及大多特征选择模型。冷凝器结垢、冷凝器水量不足、不凝性气体及蒸发器水量不足四种故障较易被检测与诊断,即使发生程度很轻微,而制冷剂泄漏及过量故障最难被命中,单纯SVM模型对该两类故障尤为难以识别,而GA-SVM模型则极大改善该性能。
第三,就多故障并发时的检测与诊断,提出基于多标识(multi-label)数学解耦技术与SVM顺序集成的模型,并以制冷系统冷凝器水量减少20%、蒸发器水量减少20%的并发故障为例,研究模型性能。发现该模型仅用正常及两类单发故障数据而不用并发故障数据训练,即可对并发故障加以检测及诊断,效果良好,尤其在采用前文述及之8个最佳故障指示特征时。研究亦表明,尽管冷凝器侧水流量及蒸发器水环路阀位两个特征分别可独立表征并发故障中的两类单发故障(子故障),在并发故障的检测与诊断中却无能为力,必须借助其他参数的表征性能。另,提出采用一种较PCA有所改进的多变量统计分析法——指定元分析法(DCA),用于并发故障检测与诊断,但对故障投影方向(指定元)的定义极大地依赖于专业经验及知识。
最后,以一台额定制冷量16.8kW的风冷热泵水机为受试对象,通过能量平衡并引入故障模拟管路及元件,建立了制冷系统故障诊断专用实验台,可以模拟包括制冷剂泄漏、充注过量、液体管路受阻、压缩机吸排气串通、蒸发器水量不足、冷凝器风量不足、冷凝器结垢、膨胀阀预紧力太大或太小等制冷系统典型故障,并进行了部分单发故障及双故障、三故障并发的实验模拟,分析故障发生时,制冷系统关键参数的变化,并探讨其可能的原因。对液体管路受阻、冷凝器结垢、蒸发器水量不足及其并发故障,运用前述智能集成模型,从44个原始特征中筛选出环境相对湿度或温度、冷凝器进出风温差、蒸发器进出水温差及供水温度四个特征,作为最佳故障指示特征,CR达99.58%。
总之,本文所提之智能集成模型,以及讨论之故障指示特征,主要成果已在多个专业国际期刊上发表,在制冷系统故障智能检测与诊断中,具有一定应用价值与意义,值得进一步研究。
Heating, ventilation, air-conditioning and refrigeration (HVAC&R) systems are becoming increasingly complex with various faults happening during operation. If not being fixed in time, system operation parameters will deviate even far from their original design value and accordingly, a series of negative effects will arise --- uncomfortable people indoor, low productivity efficiency, more system energy consumption, shorter equipment lifecycle and even worse atmospheric environment, etc. Fault detection and diagnosis (FDD) may help in timely finding and fixing faults, so as to improve system security, reliability and stability, prevent or avoid faults from happening and spreading. In order to improve accuracy & sensitivity and save computational time for the intelligent detection and diagnosis of typical individual faults and multi-simultaneous faults (MSF) for refrigeration systems, this study put forward a variety of sequentially integrated models, established FDD model evaluation guidelines based on confusion matrix, investigated all kind of possible fault indicative features.
Firstly, refrigeration system and its typical soft faults were first theoretically analyzed with the relationship between symptom and faults, results and cause primarily understood. Intelligent methods for feature selection and extraction were studied for the purpose of finding better fault indicative features set by reducing or removing correlation between features, cutting redundancy, making the faults‘appear’clearly and easy to be identified, shortening FDD time span and improving FDD accuracy simultaneously. Filter models based on mutual information (MI) and minimum- redundancy-maximum-relevance (mRMR), wrappers based on genetic algorithm (GA), linear discriminant analysis (LDA) and support vector machine (SVM), feature extraction model based on principal component analysis (PCA) were widely investigated and carefully applied to the historical normal and faulty data for a 90 tons centrifugal chiller. Fault indicative features sets were obtained and further studied in the later chapters to single out the best one.
Secondly, for the seven typical individual faults in refrigeration systems, intelligent feature selection and extraction methods were sequentially integrated with SVM, a newly concerned machine learning method based on minimizing structural risk, to perform detection and diagnosis. FDD model evaluation system with correct rate (CR), hit rate (HR) and false alarm rate (FAR) as its core was established based on confusion matrix commonly used in pattern recognition field. CR is for the evaluation of the model’s overall FDD performance for all samples; HR and FAR are guidelines for the evaluation of model’s individual performance for each class, normal or each fault. What about the ratio of samples that are hit or correctly reported and what about those falsely alarmed. The results showed that SVM model was better than the famous decision tree (C4.5) in the FDD of refrigeration system, with test CR over 99%. The eight-feature subset selected by the GA-SVM wrapper from the original 64 features behaved much better than other subsets selected by other schemes, even in the FDD by C4.5 model. Investigation on the number of features for fault indication demonstrated that that no matter the selection of the original features or the extraction of the comprehensive features by PCA, the fewer the features, the less training and testing time consumed by the FDD model, but the performance would not be that consistent with the increasing or decreasing of the feature numbers. Excessively fewer features might cause lack of information and undermine the performance accordingly, while too many features would add excessive redundancy, cause interference for FDD and harm model’s robustness. In fact, the features should better be at least equal to or more than the number of individual class including normal and all types of faults concerned. Only when the cumulative variance contribution rate was a little bit more than 95%, did the integrated model with feature extraction by PCA perform better than the SVM model without integration (64 features), but still, it could not surpass those models that integrated with feature selection schemes. Four faults such as condenser fouling, reduced condenser water flowrate, non-condensables and reduced evaporator water flowrate were easy to be detected, isolated and identified, even with the most slight level (level 1), whereas refrigerant leakage/undercharge or overcharge were the most difficult to be hit, especially when the SVM model without integration was employed, but GA-SVM model performed much better for these two faults.
Thirdly, for the detection and diagnosis of MSF, put forward a sequentially integrated model that combined multi-label (ML) decoupling technique with SVM. Model performance was investigated for the MSF of the reduced condenser water and evaporator water flowrate simultaneously, both about 20% less than the rated. It was found that the integrated model had an excellent behavior in the FDD of MSF even when it was trained just by the normal and the individual faults instead of the MSF, especially when the eight fault indicative features previously stated were employed. Although the condenser water flowrate (FWC) and the valve position in evaporator water loop (VE) could independently indicate the individual faults (sub-faults) well, they were incapable of indicating MSF and must get assistance from other features to obtain a better performance. Moreover, designated component analysis (DCA), a multivariate statistical analysis method better than PCA in a sense, was adopted for the FDD of MSF in refrigeration systems. The method was effective as long as the prior knowledge and experience for the investigated systems were enough.
At last, a dedicated fault detection and diagnosis test stand has been established by designing energy balance system and introducing fault simulation lines and components for and into an air-source heat pump of 16.8kW rated cooling capacity. Typical faults that could be simulated include refrigerant leakage/undercharge, overcharge, liquid line restriction, compressor valve leakage, reduced evaporator water flowrate, reduced condenser air flowrate, condenser fouling, thermal expansion valve over or less pre-tightened, etc. Experiments have been done for some types of the individual faults and two or three faults happening simultaneously. Variation of the critical parameters while faults happening was analyzed and possible cause or reasons were discussed. To the individual faults of liquid line restriction, condenser fouling, reduced evaporator flowrate and the combinations of two or three of them, the sequentially integrated models previously studied was applied, and four features selected from the original 44 features, including the environment relative humidity or temperature, the temperature difference between the inlet and outlet air of condenser, the temperature difference between the inlet and outlet water of evaporator, and the supply water temperature, were regarded as the best fault indicative features for the faults investigated and the test CR was as high as 99.58%.
In general, the sequentially integrated models put forward in this study and the concept of fault indicative features for the intelligent FDD of refrigeration systems are effective, having a promising perspective and worthy of further investigation.
(This research was supported by the Chinese National Natural Science Foundation under No. 50876059.)
首先,对制冷系统及其典型渐变故障进行理论分析,初步了解征兆与故障(症状与原因)间的理论联系,结合ASHRAE的制冷机组故障模拟实验,探讨制冷系统故障指示特征智能提取方法,以期找到能较好表征故障的参数(集),减轻乃至消除特征间相关度,去除信息冗余,使故障更加清晰地呈现,有利于模型对故障的分离和识别,缩短诊断时间,提高诊断准确率。分别运用基于互信息(MI)的最大冗余最小相关过滤模型(MI-based mRMR filter)、基于遗传算法的封装模型(GA-LDA wrapper、GA-SVM wrapper)进行特征选择,运用主成分分析法(PCA)进行特征提取,得到不同的故障指示特征子集,并在后续章节的分析中逐步筛选出最佳子集。
其次,针对制冷系统中典型的单发故障,运用故障指示特征智能提取与一种基于结构风险最小化的新型机器学习方法——支持向量机(SVM),相结合的顺序集成模型,进行故障检测与诊断,并基于混淆矩阵(Confusion matrix)建立以诊断正确率(CR)、命中率(HR)及虚警率(FAR)为核心的故障诊断模型评价体系,评价模型对于所有样本的总体性能及对包括正常及各类故障的诊断效果(分布性能),命中及虚警情况。结果表明,SVM的故障检测与诊断性能优于故障诊断决策树模型(C4.5),CR达99%以上。GA-SVM封装模型从64个原始特征中所选之8个故障指示特征较其他各种智能提取模型所选特征子集更为突出,在SVM模型及C4.5模型中均表现优良。对特征数的研究表明,不论原始特征抑或经PCA提取的综合特征,特征数越少,故障检测与诊断模型的训练及测试时间越短,但特征数与模型性能之间并非单调关系,特征太少可能造成信息缺失而降低诊断正确率,特征太多增加冗余信息而对故障诊断造成干扰,使模型鲁棒性下降。通常,所选特征数应至少等于包含正常运行及所有故障在内的独立类别数。基于PCA的特征提取只有当所选主元累计方差贡献率超过95%时,效果好于不进行任何智能特征提取的64个原始特征,但亦不及大多特征选择模型。冷凝器结垢、冷凝器水量不足、不凝性气体及蒸发器水量不足四种故障较易被检测与诊断,即使发生程度很轻微,而制冷剂泄漏及过量故障最难被命中,单纯SVM模型对该两类故障尤为难以识别,而GA-SVM模型则极大改善该性能。
第三,就多故障并发时的检测与诊断,提出基于多标识(multi-label)数学解耦技术与SVM顺序集成的模型,并以制冷系统冷凝器水量减少20%、蒸发器水量减少20%的并发故障为例,研究模型性能。发现该模型仅用正常及两类单发故障数据而不用并发故障数据训练,即可对并发故障加以检测及诊断,效果良好,尤其在采用前文述及之8个最佳故障指示特征时。研究亦表明,尽管冷凝器侧水流量及蒸发器水环路阀位两个特征分别可独立表征并发故障中的两类单发故障(子故障),在并发故障的检测与诊断中却无能为力,必须借助其他参数的表征性能。另,提出采用一种较PCA有所改进的多变量统计分析法——指定元分析法(DCA),用于并发故障检测与诊断,但对故障投影方向(指定元)的定义极大地依赖于专业经验及知识。
最后,以一台额定制冷量16.8kW的风冷热泵水机为受试对象,通过能量平衡并引入故障模拟管路及元件,建立了制冷系统故障诊断专用实验台,可以模拟包括制冷剂泄漏、充注过量、液体管路受阻、压缩机吸排气串通、蒸发器水量不足、冷凝器风量不足、冷凝器结垢、膨胀阀预紧力太大或太小等制冷系统典型故障,并进行了部分单发故障及双故障、三故障并发的实验模拟,分析故障发生时,制冷系统关键参数的变化,并探讨其可能的原因。对液体管路受阻、冷凝器结垢、蒸发器水量不足及其并发故障,运用前述智能集成模型,从44个原始特征中筛选出环境相对湿度或温度、冷凝器进出风温差、蒸发器进出水温差及供水温度四个特征,作为最佳故障指示特征,CR达99.58%。
总之,本文所提之智能集成模型,以及讨论之故障指示特征,主要成果已在多个专业国际期刊上发表,在制冷系统故障智能检测与诊断中,具有一定应用价值与意义,值得进一步研究。
Heating, ventilation, air-conditioning and refrigeration (HVAC&R) systems are becoming increasingly complex with various faults happening during operation. If not being fixed in time, system operation parameters will deviate even far from their original design value and accordingly, a series of negative effects will arise --- uncomfortable people indoor, low productivity efficiency, more system energy consumption, shorter equipment lifecycle and even worse atmospheric environment, etc. Fault detection and diagnosis (FDD) may help in timely finding and fixing faults, so as to improve system security, reliability and stability, prevent or avoid faults from happening and spreading. In order to improve accuracy & sensitivity and save computational time for the intelligent detection and diagnosis of typical individual faults and multi-simultaneous faults (MSF) for refrigeration systems, this study put forward a variety of sequentially integrated models, established FDD model evaluation guidelines based on confusion matrix, investigated all kind of possible fault indicative features.
Firstly, refrigeration system and its typical soft faults were first theoretically analyzed with the relationship between symptom and faults, results and cause primarily understood. Intelligent methods for feature selection and extraction were studied for the purpose of finding better fault indicative features set by reducing or removing correlation between features, cutting redundancy, making the faults‘appear’clearly and easy to be identified, shortening FDD time span and improving FDD accuracy simultaneously. Filter models based on mutual information (MI) and minimum- redundancy-maximum-relevance (mRMR), wrappers based on genetic algorithm (GA), linear discriminant analysis (LDA) and support vector machine (SVM), feature extraction model based on principal component analysis (PCA) were widely investigated and carefully applied to the historical normal and faulty data for a 90 tons centrifugal chiller. Fault indicative features sets were obtained and further studied in the later chapters to single out the best one.
Secondly, for the seven typical individual faults in refrigeration systems, intelligent feature selection and extraction methods were sequentially integrated with SVM, a newly concerned machine learning method based on minimizing structural risk, to perform detection and diagnosis. FDD model evaluation system with correct rate (CR), hit rate (HR) and false alarm rate (FAR) as its core was established based on confusion matrix commonly used in pattern recognition field. CR is for the evaluation of the model’s overall FDD performance for all samples; HR and FAR are guidelines for the evaluation of model’s individual performance for each class, normal or each fault. What about the ratio of samples that are hit or correctly reported and what about those falsely alarmed. The results showed that SVM model was better than the famous decision tree (C4.5) in the FDD of refrigeration system, with test CR over 99%. The eight-feature subset selected by the GA-SVM wrapper from the original 64 features behaved much better than other subsets selected by other schemes, even in the FDD by C4.5 model. Investigation on the number of features for fault indication demonstrated that that no matter the selection of the original features or the extraction of the comprehensive features by PCA, the fewer the features, the less training and testing time consumed by the FDD model, but the performance would not be that consistent with the increasing or decreasing of the feature numbers. Excessively fewer features might cause lack of information and undermine the performance accordingly, while too many features would add excessive redundancy, cause interference for FDD and harm model’s robustness. In fact, the features should better be at least equal to or more than the number of individual class including normal and all types of faults concerned. Only when the cumulative variance contribution rate was a little bit more than 95%, did the integrated model with feature extraction by PCA perform better than the SVM model without integration (64 features), but still, it could not surpass those models that integrated with feature selection schemes. Four faults such as condenser fouling, reduced condenser water flowrate, non-condensables and reduced evaporator water flowrate were easy to be detected, isolated and identified, even with the most slight level (level 1), whereas refrigerant leakage/undercharge or overcharge were the most difficult to be hit, especially when the SVM model without integration was employed, but GA-SVM model performed much better for these two faults.
Thirdly, for the detection and diagnosis of MSF, put forward a sequentially integrated model that combined multi-label (ML) decoupling technique with SVM. Model performance was investigated for the MSF of the reduced condenser water and evaporator water flowrate simultaneously, both about 20% less than the rated. It was found that the integrated model had an excellent behavior in the FDD of MSF even when it was trained just by the normal and the individual faults instead of the MSF, especially when the eight fault indicative features previously stated were employed. Although the condenser water flowrate (FWC) and the valve position in evaporator water loop (VE) could independently indicate the individual faults (sub-faults) well, they were incapable of indicating MSF and must get assistance from other features to obtain a better performance. Moreover, designated component analysis (DCA), a multivariate statistical analysis method better than PCA in a sense, was adopted for the FDD of MSF in refrigeration systems. The method was effective as long as the prior knowledge and experience for the investigated systems were enough.
At last, a dedicated fault detection and diagnosis test stand has been established by designing energy balance system and introducing fault simulation lines and components for and into an air-source heat pump of 16.8kW rated cooling capacity. Typical faults that could be simulated include refrigerant leakage/undercharge, overcharge, liquid line restriction, compressor valve leakage, reduced evaporator water flowrate, reduced condenser air flowrate, condenser fouling, thermal expansion valve over or less pre-tightened, etc. Experiments have been done for some types of the individual faults and two or three faults happening simultaneously. Variation of the critical parameters while faults happening was analyzed and possible cause or reasons were discussed. To the individual faults of liquid line restriction, condenser fouling, reduced evaporator flowrate and the combinations of two or three of them, the sequentially integrated models previously studied was applied, and four features selected from the original 44 features, including the environment relative humidity or temperature, the temperature difference between the inlet and outlet air of condenser, the temperature difference between the inlet and outlet water of evaporator, and the supply water temperature, were regarded as the best fault indicative features for the faults investigated and the test CR was as high as 99.58%.
In general, the sequentially integrated models put forward in this study and the concept of fault indicative features for the intelligent FDD of refrigeration systems are effective, having a promising perspective and worthy of further investigation.
(This research was supported by the Chinese National Natural Science Foundation under No. 50876059.)
引文
[1] Todd MR. Unitary air conditioner field performance. Proceedings of the 10th International Refrigeration and Air Conditioning Conference at Purdue, Paper No. R146, West Lafayette, IN, USA, July 2004.
[2] Proctor J. Residential and Light Commercial Tune-Ups, Presentation at the Public Session. ASHRAE Winter meeting, January 26, Anaheim, CA. , 2004.
[3] Katipamula S, Brambley MR. Methods for fault detection, diagnostics, and prognostics for building systems-A review, Part I[J]. HVAC&R Research, 2005, 11(1):3-25.
[4] Katipamula S, Brambley M. Automated diagnostics improving building system and equipment performance[J]. Energy user news, 1998, 23(4):545-551.
[5] Gordon JM, Kim CN, Hui TC. Centrifugal chillers: thermodynamic modeling and diagnostic case study[J]. International Journal of Refrigerant, 1995, 18(4):253-259.
[6] Roth KW, Westphalen D, et al (TIAX LLC). Energy Consumption Characteristics of Commercial Building HVAC Systems Volume III: Energy Saving Potential. Final report to US DOE Office of Building Technologies, 2002.
[7] Haves P, Salsbury TI, Wright JA. Common monitoring in HVAC subsystems using first principles models. ASHARE Technical Data Bulletin. Volume 12(2): Fault Detection and Diagnosis for HVAC Systems, 1996.
[8] Dexter AL, Benouarets M. Generic approach to identifying faults in HVAC plants. ASHRAE Transactions. 1996, 102(1): 550-556.
[9] Breuker M, Rossi T, Braun J. Smart Maintenance for Rooftop Units[J]. ASHARE Journal, 2000, 42(11):41-46.
[10]吴今培,肖健华.智能故障诊断与专家系统[M].北京:科学出版社, 1997.
[11] Frank PM. New developments using AI in fault diagnosis[J]. Engineering Application of Artificial Intelligence, 1997, 10(1): 3-14.
[12]周东华,王桂增.故障诊断技术综述[J].化工自动化及仪表, 1998, 25(1): 58-62.
[13] Frank PM. Fault diagnosis in dynamic system using analytical and knowledge based redundancy-a survey and some new results[J]. Automatica, 1990, 26(3): 459-474.
[14] Willsky AS. A survey of design methods for failure detection in dynamic system[J]. Automation, 1976, 12: 601-611.
[15] Isermann R. Process fault detection based on modeling and estimation methods--A survey[J]. Automatica, 1984, 20: 387-404.
[16] Ding X, Guo L, Frank PM.. Parameterization of linear observers and its application to observer design[J]. IEEE Trans on Automatic Control, 1994, 39(8): 1648-1652.
[17] Ding X, Frank PM. On-line fault detection in uncertain systems using adaptive observers[J]. European journal of Diagnosis and Safety in Automation, 1993(2): 9-12.
[18]周东华,席裕庚,张钟俊.一类非线性系统参数偏差型故障的实时检测与诊断[J].自动化学报, 1993, 19(2): 184-189.
[19] Garcia AE, Frank PM. Deterministic nonlinear observer based approaches to fault diagnosis: a survey[J]. Control Engineering Practice, 1997, 5(5): 663-670.
[20] Zhang Q, Basseville M. Monitoring nonlinear dynamical systems: a combined observer based and local approach[J]. IEEE CDC, 1998, (1): 1149-1154.
[21] Hibey JL, Charalambous CD. Conditional densities for continuous time nonlinear hybrid systems with applications to fault detection[J]. IEEE Tran on A C, 1998, 44(11): 2146-2169.
[22]王道平,张义忠.故障智能诊断系统的理论与方法[M].北京:冶金工业出版社,2001.
[23] Frank PM. Analytical and qualitative model based fault diagnosis– a survey and some new results[J]. European Journal of Control, 1996, 2(1): 6-28.
[24] Magni JF, Mouyou P. ON residual generation by observer and parity space approaches[J]. IEEE Trans on Automatic Control, 1994, 39(2): 441-447.
[25] Frank PM, Ding X. Survey of robust residual generation and evaluation methods in observer based fault detection systems[J]. Journal of Process Control, 1997, 7(6): 403-424.
[26] Chen J, Patton RJ, Liu GP. Optimal residual design for fault diagnosis using multi-objective optimization and genetic algorithms[J]. International Journal of System Science, 1996, 27(6): 567-576.
[27] Edelmayer A, Bokor J, Szigeti F, et al. Robust detection filter design in the presence of time varying system perturbations[J]. Automatics, 1997, 33(3): 471-475.
[28]周东华,叶银忠.现代故障诊断与容错控制[M].北京:清华大学出版社,2000.
[29]萧德云,李渭华.双通道自适应Lattice滤波器及其在故障检测中的应用[J].控制与决策,1998,13(3):277-280.
[30] Daubechies I. The wavelet transform, time-frequency localization and signal analysis[J]. IEEE Transactions on Information Theory, 1990, 36(5): 961-1005).
[31]叶昊,王桂增,方崇智.小波变换在故障诊断中的应用[J].自动化学报, 1997, 23(6): 736-741.
[32]叶昊,王桂增,方崇智,等.一种基于小波变换的导弹运输车辆故障诊断方法[J].自动化学报, 1998, 24 (3): 301-306.
[33]郭淑芬.计算机自动绘制发动机故障树技术的研究[J].燃气涡轮试验与研究, 1994 (3): 52-55.
[34]李俭川,胡茑庆,秦国军,等.基于故障树的贝叶斯网络建造方法与故障诊断应用[J].计算机工程与应用, 2003, 39 (24): 225- 228.
[35]宋华,张洪钺,王行仁.TS模糊故障树分析方法[J].控制与决策, 2006, 20 (2): 854-859.
[36] Zadeh LA. Fuzzy sets[J]. Information Control, 1965, 8: 338-353.
[37]蒋慰孙.对专家规则控制的若干看法[J].化工自动化及仪表,1999,26 (5): 14.
[38]黄席樾,熊庆宇,石为人,等.冶金连铸工业过程实时专家控制系统的设计与实现[J].自动化学报, 1998, 24(3): 405-409.
[39]阳春华,沈德耀,吴敏,等.焦炉配煤专家系统的定性定量综合设计方法[J].自动化学报, 2000, 26(2): 226-232.
[40]吴今培.模糊诊断理论及其应用[M].北京,科学出版社, 1995.
[41] Srinivasan D, Cheu RL, Poh YP, et al. Automated fault detection in power distribution networks using a hybrid fuzzy genetic algorithm approach[J]. Engineering Applications of Artificial Intelligence, 2000, 13 (4): 407-418.
[42] Tsang ECC, Wang XZ, Yeung S. Improving learning accuracy of fuzzy decision trees by hybrid neural networks[J]. IEEE Transactions on Fuzzy Systems, 2000, 8 (5): 601- 614.
[43] Benkhedda H, Patton RJ. B-Spline network integrated qualitative and quantitative fault detection[C]. Proceedings of IFAC World Congress, San Francisco, 1996 : 163 168.
[44]赵韩,张彦,方艮海,等.灰色关联分析法在汽车零部件故障分析中的应用[J].农业机械学报, 2005, 36( 8 ): 125-128.
[45]贺晓,刘景宁,李淑霞.基于灰色关联理论的案例推理在故障智能诊断系统中的应用[J].中国机械工程, 2004, 15( 22 ): 2022-2026.
[46]鄂加强,龚金科,王耀南,等.特种车辆柴油发动机故障诊断专家系统实现问题[J].应用基础与工程科学学报, 2005, 13(4): 373-380.
[47] Vapnik V. The nature of statistical learning theory[M]. New York: Springer Verlag, 1995.
[48] Massimo Dentice d'Accadia, Filippo de Rossi. Thermoeconomic analysis and diagnosis of a refrigeration plant[J]. Energy Conversion and Management, 1998, 39(12): 1223-1232.
[49]
[50] McKellar MG. Failure Diagnosis for a Household Refrigerator. Master’s thesis, School of Mechanical Engineering, Purdue University, Purdue, Indiana. 1987.
[51] Stallard, LA. Model Based Expert System for Failure Detection and Identification of Household Refrigerators. Master’s thesis, School of Mechanical Engineering, Purdue University, Purdue, Indiana. 1989.
[52] Rossi, TM. Detection, Diagnosis, and Evaluation of Faults in Vapor Compression Cycle Equipment. Ph.D. thesis, School of Mechanical Engineering, Purdue University, Purdue, Indiana. 1995.
[53] Rossi TM, Braun JE. A Statistical, Rule-Based Fault Detection and Diagnostic Method for Vapor Compression Air Conditioners. International Journal of Heating[J]. Ventilating, and Air Conditioning and Refrigerating Research, 1997, 3(1): 19–37.
[54] Breuker MS, Braun JE. Evaluating the performance of a fault detection and diagnostic method for vapor compression equipment[J]. HVAC&R Research. 1998, 4(4): 401-425.
[55] Li HR, Braun JE. An improved method for fault detection and diagnosis applied to packaged air conditioners[J]. ASHRAE Transactions. 2003, 109(2): 683-692.
[56] Chen B, Braun JE. Simple rule-based methods for fault detection and diagnostics applied to packaged air conditioners[J]. ASHRAE Trans. 2001, 107(1): 847-857.
[57] Yoshimura M, Ito N. Effective Diagnosis Methods for Air-Conditioning Equipment in Telecommunications Buildings. INTELEC 89: The Eleventh International Telecommunications Energy Conference, October 15–18, Centro dei, Firenze, 1989, 21:1–7.
[58] Wagner, J, Shoureshi, R. Failure Detection Diagnostics for Thermofluid Systems. Journal of Dynamic Systems[J]. Measurement, and Control, 1992, 114(4): 699–706.
[59] Ghiaus C. Fault diagnosis of air-conditioning systems based on qualitative bond graph[J]. Energy and Buildings. 1999, 30: 221-232.
[60] Kim M, Payne WV, Domanski PA, et al. Performance of a residential heat pump operating in the cooling mode with single faults imposed. Applied Thermal Engineering, 2009, 29(4): 770-778.
[61] Yoon SH, Payne WV, Domanski PA. Residential heat pump heating performance with single faults imposed. Applied Thermal Engineering, 2011, 31(5): 765-771.
[62] Grimmelius HT, Wound JK, Been G. On-line failure diagnosis for compression refrigeration plants[J]. International Journal of Refrigeration. 1995, 18(1): 31-41.
[63] Gordon JM, Ng KC. Predictive and diagnostic aspects of a universal thermodynamic model for chillers[J]. International Journal of Heat and Mass Transfer. 1995, 38(5): 807-818.
[64] Stylianou M, Nikanpour D. Performance monitoring, fault detection, and diagnosis of reciprocating chillers[J]. ASHRAE Transactions. 1996, 102(1): 615-627.
[65] Sreedharan P, Haves P. Comparison of chiller models for use in model-based fault detection. International Conference for Enhanced Building Operation (ICEBO),organized by Texas A&M University, Austin, TX.
[66] Bourdouxhe JP, Grodent M, Lebrun J. HVAC1 Toolkit: Algorithms and Subroutines for Primary HVAC Systems Energy Calculations. Atlanta: American Society of Heating, Refrigerating and Air-Conditioning Engineers, Inc.
[67] Hydeman M, Webb N, Sreedharan P, Blanc S. Development and testing of a reformulated regression-based electric chiller model[J]. ASHRAE Transactions. 2002, 105(1): 1087-1097.
[68] Tsutsui H, Kamimura K. Chiller condition monitoring using topological case-based modeling[J]. ASHRAE Transactions. 1996, 102(1): 641-648
[69] Peitsman HC, Bakker VE. Application of black-box models of HVAC systems for fault detection[J]. ASHRAE Transactions. 1996, 102(1): 628-640.
[70] Peitsman HC, Soethout LL. 1997. ARX models and real-time model-based diagnosis[J]. ASHRAE Transactions 103(1):657-671.
[71] Stylianou M. Application of classification functions to chiller fault and diagnosis[J]. ASHRAE Transactions. 1997, 103(1): 645-656.
[72] Mclntosh BD, Mitchell WJ, Beckman WA. Fault detection and diagnosis in chillers—Part I: Model development and application[J]. ASHRAE Transactions. 2000, 106(2): 1-15.
[73] Castro NS. Performance evaluation of a reciprocating chiller using experimental data and model predictions for fault detection and diagnosis[J]. ASHRAE Transactions. 2002, 108(1): 1-15.
[74] Navarro-EsbríJ, Torrella E, Cabello R. A vapour compression chiller fault detection technique based on adaptative algorithms. Application to on-line refrigerant leakage detection[J]. International Journal of Refrigeration. 2006, 29(5): 716-723.
[75] Wang SW, Cui JT. Sensor-fault detection, diagnosis and estimation for centrifugal chiller systems using principal-component analysis method[J]. Applied Energy, 2005, 82(3): 197-213
[76] Xu XH, Xiao F, Wang SW. Enhanced chiller sensor fault detection, diagnosis and estimation using wavelet analysis and principal component analysis methods[J]. Applied Thermal Engineering, 2008, 28(2-3): 226-237
[77] Ren N, Liang J, Gu B, Han H. Fault diagnosis strategy for incompletely described samples and its application to refrigeration system[J]. Mechanical Systems and Signal Processing, 2008, 22: 436–450
[78] Cui JT, Wang SW. A model-based online fault detection and diagnosis strategy for centrifugal chiller systems[J]. International Journal of Thermal Sciences, 2005, 44: 986–999
[79] Breuker, MS. Evaluation of a statistical, rule-based detection and diagnosis method for vapor compression air conditioners. Master's thesis, School of Mechanical Engineering,Purdue University, West Lafayette. IN. 1997.
[80] Li HR, Braun JE. A methodology for diagnosing multiple simultaneous faults in vapor compression air conditioners[J]. HVAC&R Research, 13(2) (2007) 369-395.
[81]江亿,朱伟峰,周强华.暖通空调系统故障诊断的故障向量空间法[J].清华大学学报, 1999, 39(12): 57～61.
[82]姜益强,姚杨,马最良.基于人工神经网络的空气源热泵冷热水机组的性能模拟[J].流体机械, 2002(5) :59-61.
[83]姜益强,姚杨,马最良.空气源热泵冷水机组的故障诊断[J].制冷学报, 2002 ,23 (3): 58-61.
[84]姚杨.空气源热泵冷水机组中压缩机性能的模拟[J].哈尔滨建筑大学学报, 2002, 33 (6) : 87-91.
[85]姜大勇,黄道.空气处理单元的故障检测与诊断方法[J].建筑热能通风空调, 1999 (2): 25-27.
[86]李玉云.人工神经网络在暖通空调领域的应用研究发展[J].暖通空调, 2001, 31 (1) :77-79.
[87]谢培志,韩厚德.冷藏集装箱制冷机组故障诊断系统的开发[J].制冷与空调. 2006, 4: 48-51.
[88]赵萍,汪正祥.基于神经网络的空调故障诊断技术的研究[J].仪器仪表学报. 2008, 8: 214-216.
[89]李中领,金宁.人工神经网络应用于空调系统故障诊断的研究[J].制冷与空调. 2005, 2: 50-53.
[90]佘锋,程大章.一种基于神经网络的建筑设备故障诊断模型[J].智能建筑与城市信息. 2003, 9(82):40-42.
[91]韩玲.基于人工神经网络模型的螺杆式冷水机组故障诊断研究[D].硕士学位论文.重庆:重庆大学, 2005.
[92]蔡立群.制冷系统故障诊断的专家系统[D].上海:上海交通大学,1993 :24-45
[93]陆紫生,费千.制冷系统数据监测及故障诊断专家系统[J].大连海事大学学报. 2004, 30(1): 101-104.
[94]郭辉.空调器故障诊断专家系统的实现[D].硕士学位论文.武汉:华中科技大学, 2004.
[95]王志毅,谷波,郑钢.模糊数学在制冷故障诊断专家系统中的应用[J].制冷空调与电力机械. 2002, 4: 33~36.
[96]王志毅,谷波,裴通华.应用VB开发制冷系统故障诊断专家系统[J].制冷与空调. 2002, 8: 43-46.
[97]刘宝霞,谭卫娟,吕鸣.空气循环制冷设备故障诊断专家系统研究[J].微计算机信息. 2008, 24(7-1): 209-210.
[98]赵鹏.模糊专家系统在制冷系统在线故障诊断中的实现应用[D].上海:上海交通大学, 1995 : 37-51.
[99]鲍士雄,赵鹏.制冷系统故障诊断中模糊模式识别技术的应用[J].制冷学报, 1998 ,19 (2) : 20-27.
[100]鲍士雄,赵鹏,谷波,陈丽萍,吴勇.制冷系统故障诊断中模糊模式识别技术的应用[J].制冷学报. 1998, 2: 20-27.
[101]王进波.基于Fuzyz理论的空调系统故障诊断及控制的研究[D].硕士学位论文.南京:南京理工大学, 2005.
[102]胡正定,杨晨.基于补偿模糊神经网络的制冷系统故障诊断研究[J].计算机仿真. 2007, 10(24): 148-151.
[103]晋欣桥.冷水机组系统的温度传感器故障诊断[J].上海交通大学学报,2004 ,38 (1) : 976-981.
[104]陈友明,郝小礼.建筑能源管理与控制系统中传感器故障及其检测与诊断[J].暖通空调, 2004 , 34(2) :83-88.
[105]陈友明.自动故障检测与诊断在暖通空调中的研究与应用[J].暖通空调, 2004, 34 (3) : 29-33.
[106]张振军.中央空调系统现场检测方法初探[J].制冷与空调, 2003 (4): 24-26.
[107]李韵. YCAM-H-600热泵故障分析及其对策[J].暖通空调, 2003, 33 (2): 102-103.
[108]姜周曙,胡亚才,屠传经. FTA在溴化锂吸收式制冷机故障诊断中的应用[J].浙江大学学报, 2001, 35(2): 209-213.
[109]王晓明.制冷系统故障先兆分析及故障预报技术的研究[D].硕士学位论文.上海:上海交通大学, 1998:31~39.
[110]王志毅.热泵空调系统故障检测及诊断研究[D].博士学位论文.上海:上海交通大学, 2004.
[111]王俨剀,廖明夫,赵铁.基于小波分析的制冷压缩机气阀故障诊断方法的研究[J].中国机械工程, 2003, 14(12): 1046-1048.
[112]彦启森,申江,石文星.制冷技术及其应用[M].中国建筑工业出版社,2006.
[113] Haves P. Overview of Diagnostic Methods. Proceedings of Diagnostics for Commercial Buildings: From Research to Practice, San Francisco, CA. 1999.
[114] Comstock MC, Braun JE, Groll E.A. A Survey of Common Faults for Chillers[J]. ASHRAE Transactions. 2002, 108(1):1-7.
[115] Comstock MC, Braun JE. Development of analysis tools for the evaluation of fault detection and diagnostics for chillers. HL 99-20, Report # 4036-3. ASHRAE ResearchProject 1043, 1999.
[116] Glass AS, Gruber P, Roos M, Todtli J, Qualitative model based fault detection in air-handling units[J]. IEEE Control Systems Magazine. 1995, 15 (4): 11–22.
[117] Blum A, Langley P. Selection of relevant features and examples in machine learning[J]. Artificial Intelligence. 1997, 97:245-71.
[118] Dash M, Liu H. Feature selection for classifications[J]. Intelligent Data Analysis: An International Journal, 1997, 1:131-156.
[119] Kohavi R, John G. Wrappers for feature subset selection[J]. Artificial Intelligence, 1997, 97:273-324.
[120] Das S. Filters, wrappers and a boosting-based hybrid for feature selection. Proc. 8th Int. Conf. Mach. Learn. 2001:74-81.
[121] Zhu XL. Fundamentals of Applied Information Theory[M].Beijing,China:Tsinghua University Press (in Chinese) , 2000.
[122] Peng HC, Long FH, Ding C. Feature Selection Based on Mutual Information: Criteria of Max-Dependency, Max-Relevance, and Min-Redundancy. IEEE Trans. Pattern Anal[J]. Mach. Intell, 2005.27(8): 1226–1238.
[123] Goldberg DE. Genetic Algorithms in Search, Optimization & Machine Learning, Addison-Wesley, 1989.
[124] Krzanowski WJ. Principles of Multivariate Analysis: A User's Perspective. New York: Oxford University Press, 1988.
[125] Lee JM, Yoo C, Choi SW, et al. Nonlinear process monitoring using kernel principle component analysis[J]. Chemical Engineering Science, 2004, 59(1):223-234.
[126] Valle S, Li W, Qin SJ. Selection of the number of principal components: the variance of the reconstruction error criterion with a comparison to other methods [J]. Industrial and Engineering Chemistry Research, 1999, 38(11): 4389-4401.
[127] Cui JT. A robust fault detection and diagnosis strategy for centrifugal chillers [D]. Hong Kong: Department of Building Services Engineering, Hong Kong Polytechnic University, 2005.
[128] Burges CJC. A tutorial on support vector machines for pattern recognition[J]. Data Mining and Knowledge Discovery, 1998,2 (2):1-47.
[129] Lin HT, Lin CJ. A study on sigmoid kernels for SVM and the training of non-PSD kernels by SMO-type methods [EB/OL]. Technical report, Department of Computer Science, National Taiwan University, 2003. http://www.csie.ntu.edu.tw/~cjlin/papers/tanh.pdf.
[130] Hsu CW, Lin CJ. A comparison of methods for multi-class support vector machines[J]. IEEE Trans. Neural Netw, 2002, 13:415-25.
[131] Chin KK. Support Vector Machines Applied to Speech Pattern Classification, Master’sThesis, Univ. Cambridge, Cambridge, U.K., 1998.
[132] Crammer K, Singer Y. On the learnability and design of output codes for multiclass problems[J]. Comput. Learing Theory, 2000: 35–46,.
[133] Vapnik V. Statistical Learning Theory[M]. New York: Wiley, 1998.
[134] Weston J, Watkins C. Multi-class support vector machines[M]. presented at the Proc. ESANN99, M. Verleysen, Ed., Brussels, Belgium, 1999.
[135] Lin HT, Lin CJ. A practical guide to support vector classification. Technical reports, Department of Computer Science and Information Engineering, National Taiwan University, 2004. Available at http://www.csie.ntu.edu.tw/~cjlin/papers/guide/guide.pdf
[136] Witten IH, Frank E. Data Mining: Practical Machine Learning Tools and Techniques (2nd Edition) [M]. Morgan Kaufmann Publishers, 2005.
[137] Fawcett T. ROC Graphs: Notes and Practical Considerations for Researchers[M]. Kluwer Academic Publishers. Printed in the Netherlands, 2004.
[138] Ye′lamos I, Graells M, Puigjaner L, Simultaneous Fault Diagnosis in Chemical Plants Using a MultiLabel Approach[J]. AIChE Journal, 200753(11): 2871-2884.
[139] Chang CC, Lin CJ. LIBSVM : a library for support vector machines. Software available at http://www.csie.ntu.edu.tw/~cjlin/libsvm/2001.
[140] Ross Q. C4.5: Programs for Machine Learning[M]. Morgan Kaufmann Publishers, San Mateo, CA. 1993.
[141] Witten IH, Frank E, Data Mining: Practical Machine Learning Tools and Techniques with Java Implementations, 2005, China Machine Press. Software available at www.cs.waikato.ac.nz/ml/weka
[142]沈倩.刘育明.梁军.基于DCA方法的故障检测与诊断分析[J].制造业自动化, 2005, 27(6): 51-54.
[143]张杰.阳宪惠.多变量统计过程控制[M].北京:化学工业出版社, 2000.
[144] Liu YG. Statistical control of multivariate processes with applications to automobile body assembly[D]. Michigan: University of Michigan, 2002.
[145] Liu YG, Hu SJ. Assembly fixture fault diagnosis using designated component analysis[J]. Transaction of the ASME, 2005, 127(2): 358-368.
[146] Camelia JA, Hu SJ. Multiple fault diagnosis for sheet metal fixtures using designated component analysis[J]. Journal of Manufacturing Science and Engineering, 2004, 126(1): 91-97.
[2] Proctor J. Residential and Light Commercial Tune-Ups, Presentation at the Public Session. ASHRAE Winter meeting, January 26, Anaheim, CA. , 2004.
[3] Katipamula S, Brambley MR. Methods for fault detection, diagnostics, and prognostics for building systems-A review, Part I[J]. HVAC&R Research, 2005, 11(1):3-25.
[4] Katipamula S, Brambley M. Automated diagnostics improving building system and equipment performance[J]. Energy user news, 1998, 23(4):545-551.
[5] Gordon JM, Kim CN, Hui TC. Centrifugal chillers: thermodynamic modeling and diagnostic case study[J]. International Journal of Refrigerant, 1995, 18(4):253-259.
[6] Roth KW, Westphalen D, et al (TIAX LLC). Energy Consumption Characteristics of Commercial Building HVAC Systems Volume III: Energy Saving Potential. Final report to US DOE Office of Building Technologies, 2002.
[7] Haves P, Salsbury TI, Wright JA. Common monitoring in HVAC subsystems using first principles models. ASHARE Technical Data Bulletin. Volume 12(2): Fault Detection and Diagnosis for HVAC Systems, 1996.
[8] Dexter AL, Benouarets M. Generic approach to identifying faults in HVAC plants. ASHRAE Transactions. 1996, 102(1): 550-556.
[9] Breuker M, Rossi T, Braun J. Smart Maintenance for Rooftop Units[J]. ASHARE Journal, 2000, 42(11):41-46.
[10]吴今培,肖健华.智能故障诊断与专家系统[M].北京:科学出版社, 1997.
[11] Frank PM. New developments using AI in fault diagnosis[J]. Engineering Application of Artificial Intelligence, 1997, 10(1): 3-14.
[12]周东华,王桂增.故障诊断技术综述[J].化工自动化及仪表, 1998, 25(1): 58-62.
[13] Frank PM. Fault diagnosis in dynamic system using analytical and knowledge based redundancy-a survey and some new results[J]. Automatica, 1990, 26(3): 459-474.
[14] Willsky AS. A survey of design methods for failure detection in dynamic system[J]. Automation, 1976, 12: 601-611.
[15] Isermann R. Process fault detection based on modeling and estimation methods--A survey[J]. Automatica, 1984, 20: 387-404.
[16] Ding X, Guo L, Frank PM.. Parameterization of linear observers and its application to observer design[J]. IEEE Trans on Automatic Control, 1994, 39(8): 1648-1652.
[17] Ding X, Frank PM. On-line fault detection in uncertain systems using adaptive observers[J]. European journal of Diagnosis and Safety in Automation, 1993(2): 9-12.
[18]周东华,席裕庚,张钟俊.一类非线性系统参数偏差型故障的实时检测与诊断[J].自动化学报, 1993, 19(2): 184-189.
[19] Garcia AE, Frank PM. Deterministic nonlinear observer based approaches to fault diagnosis: a survey[J]. Control Engineering Practice, 1997, 5(5): 663-670.
[20] Zhang Q, Basseville M. Monitoring nonlinear dynamical systems: a combined observer based and local approach[J]. IEEE CDC, 1998, (1): 1149-1154.
[21] Hibey JL, Charalambous CD. Conditional densities for continuous time nonlinear hybrid systems with applications to fault detection[J]. IEEE Tran on A C, 1998, 44(11): 2146-2169.
[22]王道平,张义忠.故障智能诊断系统的理论与方法[M].北京:冶金工业出版社,2001.
[23] Frank PM. Analytical and qualitative model based fault diagnosis– a survey and some new results[J]. European Journal of Control, 1996, 2(1): 6-28.
[24] Magni JF, Mouyou P. ON residual generation by observer and parity space approaches[J]. IEEE Trans on Automatic Control, 1994, 39(2): 441-447.
[25] Frank PM, Ding X. Survey of robust residual generation and evaluation methods in observer based fault detection systems[J]. Journal of Process Control, 1997, 7(6): 403-424.
[26] Chen J, Patton RJ, Liu GP. Optimal residual design for fault diagnosis using multi-objective optimization and genetic algorithms[J]. International Journal of System Science, 1996, 27(6): 567-576.
[27] Edelmayer A, Bokor J, Szigeti F, et al. Robust detection filter design in the presence of time varying system perturbations[J]. Automatics, 1997, 33(3): 471-475.
[28]周东华,叶银忠.现代故障诊断与容错控制[M].北京:清华大学出版社,2000.
[29]萧德云,李渭华.双通道自适应Lattice滤波器及其在故障检测中的应用[J].控制与决策,1998,13(3):277-280.
[30] Daubechies I. The wavelet transform, time-frequency localization and signal analysis[J]. IEEE Transactions on Information Theory, 1990, 36(5): 961-1005).
[31]叶昊,王桂增,方崇智.小波变换在故障诊断中的应用[J].自动化学报, 1997, 23(6): 736-741.
[32]叶昊,王桂增,方崇智,等.一种基于小波变换的导弹运输车辆故障诊断方法[J].自动化学报, 1998, 24 (3): 301-306.
[33]郭淑芬.计算机自动绘制发动机故障树技术的研究[J].燃气涡轮试验与研究, 1994 (3): 52-55.
[34]李俭川,胡茑庆,秦国军,等.基于故障树的贝叶斯网络建造方法与故障诊断应用[J].计算机工程与应用, 2003, 39 (24): 225- 228.
[35]宋华,张洪钺,王行仁.TS模糊故障树分析方法[J].控制与决策, 2006, 20 (2): 854-859.
[36] Zadeh LA. Fuzzy sets[J]. Information Control, 1965, 8: 338-353.
[37]蒋慰孙.对专家规则控制的若干看法[J].化工自动化及仪表,1999,26 (5): 14.
[38]黄席樾,熊庆宇,石为人,等.冶金连铸工业过程实时专家控制系统的设计与实现[J].自动化学报, 1998, 24(3): 405-409.
[39]阳春华,沈德耀,吴敏,等.焦炉配煤专家系统的定性定量综合设计方法[J].自动化学报, 2000, 26(2): 226-232.
[40]吴今培.模糊诊断理论及其应用[M].北京,科学出版社, 1995.
[41] Srinivasan D, Cheu RL, Poh YP, et al. Automated fault detection in power distribution networks using a hybrid fuzzy genetic algorithm approach[J]. Engineering Applications of Artificial Intelligence, 2000, 13 (4): 407-418.
[42] Tsang ECC, Wang XZ, Yeung S. Improving learning accuracy of fuzzy decision trees by hybrid neural networks[J]. IEEE Transactions on Fuzzy Systems, 2000, 8 (5): 601- 614.
[43] Benkhedda H, Patton RJ. B-Spline network integrated qualitative and quantitative fault detection[C]. Proceedings of IFAC World Congress, San Francisco, 1996 : 163 168.
[44]赵韩,张彦,方艮海,等.灰色关联分析法在汽车零部件故障分析中的应用[J].农业机械学报, 2005, 36( 8 ): 125-128.
[45]贺晓,刘景宁,李淑霞.基于灰色关联理论的案例推理在故障智能诊断系统中的应用[J].中国机械工程, 2004, 15( 22 ): 2022-2026.
[46]鄂加强,龚金科,王耀南,等.特种车辆柴油发动机故障诊断专家系统实现问题[J].应用基础与工程科学学报, 2005, 13(4): 373-380.
[47] Vapnik V. The nature of statistical learning theory[M]. New York: Springer Verlag, 1995.
[48] Massimo Dentice d'Accadia, Filippo de Rossi. Thermoeconomic analysis and diagnosis of a refrigeration plant[J]. Energy Conversion and Management, 1998, 39(12): 1223-1232.
[49]
[50] McKellar MG. Failure Diagnosis for a Household Refrigerator. Master’s thesis, School of Mechanical Engineering, Purdue University, Purdue, Indiana. 1987.
[51] Stallard, LA. Model Based Expert System for Failure Detection and Identification of Household Refrigerators. Master’s thesis, School of Mechanical Engineering, Purdue University, Purdue, Indiana. 1989.
[52] Rossi, TM. Detection, Diagnosis, and Evaluation of Faults in Vapor Compression Cycle Equipment. Ph.D. thesis, School of Mechanical Engineering, Purdue University, Purdue, Indiana. 1995.
[53] Rossi TM, Braun JE. A Statistical, Rule-Based Fault Detection and Diagnostic Method for Vapor Compression Air Conditioners. International Journal of Heating[J]. Ventilating, and Air Conditioning and Refrigerating Research, 1997, 3(1): 19–37.
[54] Breuker MS, Braun JE. Evaluating the performance of a fault detection and diagnostic method for vapor compression equipment[J]. HVAC&R Research. 1998, 4(4): 401-425.
[55] Li HR, Braun JE. An improved method for fault detection and diagnosis applied to packaged air conditioners[J]. ASHRAE Transactions. 2003, 109(2): 683-692.
[56] Chen B, Braun JE. Simple rule-based methods for fault detection and diagnostics applied to packaged air conditioners[J]. ASHRAE Trans. 2001, 107(1): 847-857.
[57] Yoshimura M, Ito N. Effective Diagnosis Methods for Air-Conditioning Equipment in Telecommunications Buildings. INTELEC 89: The Eleventh International Telecommunications Energy Conference, October 15–18, Centro dei, Firenze, 1989, 21:1–7.
[58] Wagner, J, Shoureshi, R. Failure Detection Diagnostics for Thermofluid Systems. Journal of Dynamic Systems[J]. Measurement, and Control, 1992, 114(4): 699–706.
[59] Ghiaus C. Fault diagnosis of air-conditioning systems based on qualitative bond graph[J]. Energy and Buildings. 1999, 30: 221-232.
[60] Kim M, Payne WV, Domanski PA, et al. Performance of a residential heat pump operating in the cooling mode with single faults imposed. Applied Thermal Engineering, 2009, 29(4): 770-778.
[61] Yoon SH, Payne WV, Domanski PA. Residential heat pump heating performance with single faults imposed. Applied Thermal Engineering, 2011, 31(5): 765-771.
[62] Grimmelius HT, Wound JK, Been G. On-line failure diagnosis for compression refrigeration plants[J]. International Journal of Refrigeration. 1995, 18(1): 31-41.
[63] Gordon JM, Ng KC. Predictive and diagnostic aspects of a universal thermodynamic model for chillers[J]. International Journal of Heat and Mass Transfer. 1995, 38(5): 807-818.
[64] Stylianou M, Nikanpour D. Performance monitoring, fault detection, and diagnosis of reciprocating chillers[J]. ASHRAE Transactions. 1996, 102(1): 615-627.
[65] Sreedharan P, Haves P. Comparison of chiller models for use in model-based fault detection. International Conference for Enhanced Building Operation (ICEBO),organized by Texas A&M University, Austin, TX.
[66] Bourdouxhe JP, Grodent M, Lebrun J. HVAC1 Toolkit: Algorithms and Subroutines for Primary HVAC Systems Energy Calculations. Atlanta: American Society of Heating, Refrigerating and Air-Conditioning Engineers, Inc.
[67] Hydeman M, Webb N, Sreedharan P, Blanc S. Development and testing of a reformulated regression-based electric chiller model[J]. ASHRAE Transactions. 2002, 105(1): 1087-1097.
[68] Tsutsui H, Kamimura K. Chiller condition monitoring using topological case-based modeling[J]. ASHRAE Transactions. 1996, 102(1): 641-648
[69] Peitsman HC, Bakker VE. Application of black-box models of HVAC systems for fault detection[J]. ASHRAE Transactions. 1996, 102(1): 628-640.
[70] Peitsman HC, Soethout LL. 1997. ARX models and real-time model-based diagnosis[J]. ASHRAE Transactions 103(1):657-671.
[71] Stylianou M. Application of classification functions to chiller fault and diagnosis[J]. ASHRAE Transactions. 1997, 103(1): 645-656.
[72] Mclntosh BD, Mitchell WJ, Beckman WA. Fault detection and diagnosis in chillers—Part I: Model development and application[J]. ASHRAE Transactions. 2000, 106(2): 1-15.
[73] Castro NS. Performance evaluation of a reciprocating chiller using experimental data and model predictions for fault detection and diagnosis[J]. ASHRAE Transactions. 2002, 108(1): 1-15.
[74] Navarro-EsbríJ, Torrella E, Cabello R. A vapour compression chiller fault detection technique based on adaptative algorithms. Application to on-line refrigerant leakage detection[J]. International Journal of Refrigeration. 2006, 29(5): 716-723.
[75] Wang SW, Cui JT. Sensor-fault detection, diagnosis and estimation for centrifugal chiller systems using principal-component analysis method[J]. Applied Energy, 2005, 82(3): 197-213
[76] Xu XH, Xiao F, Wang SW. Enhanced chiller sensor fault detection, diagnosis and estimation using wavelet analysis and principal component analysis methods[J]. Applied Thermal Engineering, 2008, 28(2-3): 226-237
[77] Ren N, Liang J, Gu B, Han H. Fault diagnosis strategy for incompletely described samples and its application to refrigeration system[J]. Mechanical Systems and Signal Processing, 2008, 22: 436–450
[78] Cui JT, Wang SW. A model-based online fault detection and diagnosis strategy for centrifugal chiller systems[J]. International Journal of Thermal Sciences, 2005, 44: 986–999
[79] Breuker, MS. Evaluation of a statistical, rule-based detection and diagnosis method for vapor compression air conditioners. Master's thesis, School of Mechanical Engineering,Purdue University, West Lafayette. IN. 1997.
[80] Li HR, Braun JE. A methodology for diagnosing multiple simultaneous faults in vapor compression air conditioners[J]. HVAC&R Research, 13(2) (2007) 369-395.
[81]江亿,朱伟峰,周强华.暖通空调系统故障诊断的故障向量空间法[J].清华大学学报, 1999, 39(12): 57～61.
[82]姜益强,姚杨,马最良.基于人工神经网络的空气源热泵冷热水机组的性能模拟[J].流体机械, 2002(5) :59-61.
[83]姜益强,姚杨,马最良.空气源热泵冷水机组的故障诊断[J].制冷学报, 2002 ,23 (3): 58-61.
[84]姚杨.空气源热泵冷水机组中压缩机性能的模拟[J].哈尔滨建筑大学学报, 2002, 33 (6) : 87-91.
[85]姜大勇,黄道.空气处理单元的故障检测与诊断方法[J].建筑热能通风空调, 1999 (2): 25-27.
[86]李玉云.人工神经网络在暖通空调领域的应用研究发展[J].暖通空调, 2001, 31 (1) :77-79.
[87]谢培志,韩厚德.冷藏集装箱制冷机组故障诊断系统的开发[J].制冷与空调. 2006, 4: 48-51.
[88]赵萍,汪正祥.基于神经网络的空调故障诊断技术的研究[J].仪器仪表学报. 2008, 8: 214-216.
[89]李中领,金宁.人工神经网络应用于空调系统故障诊断的研究[J].制冷与空调. 2005, 2: 50-53.
[90]佘锋,程大章.一种基于神经网络的建筑设备故障诊断模型[J].智能建筑与城市信息. 2003, 9(82):40-42.
[91]韩玲.基于人工神经网络模型的螺杆式冷水机组故障诊断研究[D].硕士学位论文.重庆:重庆大学, 2005.
[92]蔡立群.制冷系统故障诊断的专家系统[D].上海:上海交通大学,1993 :24-45
[93]陆紫生,费千.制冷系统数据监测及故障诊断专家系统[J].大连海事大学学报. 2004, 30(1): 101-104.
[94]郭辉.空调器故障诊断专家系统的实现[D].硕士学位论文.武汉:华中科技大学, 2004.
[95]王志毅,谷波,郑钢.模糊数学在制冷故障诊断专家系统中的应用[J].制冷空调与电力机械. 2002, 4: 33~36.
[96]王志毅,谷波,裴通华.应用VB开发制冷系统故障诊断专家系统[J].制冷与空调. 2002, 8: 43-46.
[97]刘宝霞,谭卫娟,吕鸣.空气循环制冷设备故障诊断专家系统研究[J].微计算机信息. 2008, 24(7-1): 209-210.
[98]赵鹏.模糊专家系统在制冷系统在线故障诊断中的实现应用[D].上海:上海交通大学, 1995 : 37-51.
[99]鲍士雄,赵鹏.制冷系统故障诊断中模糊模式识别技术的应用[J].制冷学报, 1998 ,19 (2) : 20-27.
[100]鲍士雄,赵鹏,谷波,陈丽萍,吴勇.制冷系统故障诊断中模糊模式识别技术的应用[J].制冷学报. 1998, 2: 20-27.
[101]王进波.基于Fuzyz理论的空调系统故障诊断及控制的研究[D].硕士学位论文.南京:南京理工大学, 2005.
[102]胡正定,杨晨.基于补偿模糊神经网络的制冷系统故障诊断研究[J].计算机仿真. 2007, 10(24): 148-151.
[103]晋欣桥.冷水机组系统的温度传感器故障诊断[J].上海交通大学学报,2004 ,38 (1) : 976-981.
[104]陈友明,郝小礼.建筑能源管理与控制系统中传感器故障及其检测与诊断[J].暖通空调, 2004 , 34(2) :83-88.
[105]陈友明.自动故障检测与诊断在暖通空调中的研究与应用[J].暖通空调, 2004, 34 (3) : 29-33.
[106]张振军.中央空调系统现场检测方法初探[J].制冷与空调, 2003 (4): 24-26.
[107]李韵. YCAM-H-600热泵故障分析及其对策[J].暖通空调, 2003, 33 (2): 102-103.
[108]姜周曙,胡亚才,屠传经. FTA在溴化锂吸收式制冷机故障诊断中的应用[J].浙江大学学报, 2001, 35(2): 209-213.
[109]王晓明.制冷系统故障先兆分析及故障预报技术的研究[D].硕士学位论文.上海:上海交通大学, 1998:31~39.
[110]王志毅.热泵空调系统故障检测及诊断研究[D].博士学位论文.上海:上海交通大学, 2004.
[111]王俨剀,廖明夫,赵铁.基于小波分析的制冷压缩机气阀故障诊断方法的研究[J].中国机械工程, 2003, 14(12): 1046-1048.
[112]彦启森,申江,石文星.制冷技术及其应用[M].中国建筑工业出版社,2006.
[113] Haves P. Overview of Diagnostic Methods. Proceedings of Diagnostics for Commercial Buildings: From Research to Practice, San Francisco, CA. 1999.
[114] Comstock MC, Braun JE, Groll E.A. A Survey of Common Faults for Chillers[J]. ASHRAE Transactions. 2002, 108(1):1-7.
[115] Comstock MC, Braun JE. Development of analysis tools for the evaluation of fault detection and diagnostics for chillers. HL 99-20, Report # 4036-3. ASHRAE ResearchProject 1043, 1999.
[116] Glass AS, Gruber P, Roos M, Todtli J, Qualitative model based fault detection in air-handling units[J]. IEEE Control Systems Magazine. 1995, 15 (4): 11–22.
[117] Blum A, Langley P. Selection of relevant features and examples in machine learning[J]. Artificial Intelligence. 1997, 97:245-71.
[118] Dash M, Liu H. Feature selection for classifications[J]. Intelligent Data Analysis: An International Journal, 1997, 1:131-156.
[119] Kohavi R, John G. Wrappers for feature subset selection[J]. Artificial Intelligence, 1997, 97:273-324.
[120] Das S. Filters, wrappers and a boosting-based hybrid for feature selection. Proc. 8th Int. Conf. Mach. Learn. 2001:74-81.
[121] Zhu XL. Fundamentals of Applied Information Theory[M].Beijing,China:Tsinghua University Press (in Chinese) , 2000.
[122] Peng HC, Long FH, Ding C. Feature Selection Based on Mutual Information: Criteria of Max-Dependency, Max-Relevance, and Min-Redundancy. IEEE Trans. Pattern Anal[J]. Mach. Intell, 2005.27(8): 1226–1238.
[123] Goldberg DE. Genetic Algorithms in Search, Optimization & Machine Learning, Addison-Wesley, 1989.
[124] Krzanowski WJ. Principles of Multivariate Analysis: A User's Perspective. New York: Oxford University Press, 1988.
[125] Lee JM, Yoo C, Choi SW, et al. Nonlinear process monitoring using kernel principle component analysis[J]. Chemical Engineering Science, 2004, 59(1):223-234.
[126] Valle S, Li W, Qin SJ. Selection of the number of principal components: the variance of the reconstruction error criterion with a comparison to other methods [J]. Industrial and Engineering Chemistry Research, 1999, 38(11): 4389-4401.
[127] Cui JT. A robust fault detection and diagnosis strategy for centrifugal chillers [D]. Hong Kong: Department of Building Services Engineering, Hong Kong Polytechnic University, 2005.
[128] Burges CJC. A tutorial on support vector machines for pattern recognition[J]. Data Mining and Knowledge Discovery, 1998,2 (2):1-47.
[129] Lin HT, Lin CJ. A study on sigmoid kernels for SVM and the training of non-PSD kernels by SMO-type methods [EB/OL]. Technical report, Department of Computer Science, National Taiwan University, 2003. http://www.csie.ntu.edu.tw/~cjlin/papers/tanh.pdf.
[130] Hsu CW, Lin CJ. A comparison of methods for multi-class support vector machines[J]. IEEE Trans. Neural Netw, 2002, 13:415-25.
[131] Chin KK. Support Vector Machines Applied to Speech Pattern Classification, Master’sThesis, Univ. Cambridge, Cambridge, U.K., 1998.
[132] Crammer K, Singer Y. On the learnability and design of output codes for multiclass problems[J]. Comput. Learing Theory, 2000: 35–46,.
[133] Vapnik V. Statistical Learning Theory[M]. New York: Wiley, 1998.
[134] Weston J, Watkins C. Multi-class support vector machines[M]. presented at the Proc. ESANN99, M. Verleysen, Ed., Brussels, Belgium, 1999.
[135] Lin HT, Lin CJ. A practical guide to support vector classification. Technical reports, Department of Computer Science and Information Engineering, National Taiwan University, 2004. Available at http://www.csie.ntu.edu.tw/~cjlin/papers/guide/guide.pdf
[136] Witten IH, Frank E. Data Mining: Practical Machine Learning Tools and Techniques (2nd Edition) [M]. Morgan Kaufmann Publishers, 2005.
[137] Fawcett T. ROC Graphs: Notes and Practical Considerations for Researchers[M]. Kluwer Academic Publishers. Printed in the Netherlands, 2004.
[138] Ye′lamos I, Graells M, Puigjaner L, Simultaneous Fault Diagnosis in Chemical Plants Using a MultiLabel Approach[J]. AIChE Journal, 200753(11): 2871-2884.
[139] Chang CC, Lin CJ. LIBSVM : a library for support vector machines. Software available at http://www.csie.ntu.edu.tw/~cjlin/libsvm/2001.
[140] Ross Q. C4.5: Programs for Machine Learning[M]. Morgan Kaufmann Publishers, San Mateo, CA. 1993.
[141] Witten IH, Frank E, Data Mining: Practical Machine Learning Tools and Techniques with Java Implementations, 2005, China Machine Press. Software available at www.cs.waikato.ac.nz/ml/weka
[142]沈倩.刘育明.梁军.基于DCA方法的故障检测与诊断分析[J].制造业自动化, 2005, 27(6): 51-54.
[143]张杰.阳宪惠.多变量统计过程控制[M].北京:化学工业出版社, 2000.
[144] Liu YG. Statistical control of multivariate processes with applications to automobile body assembly[D]. Michigan: University of Michigan, 2002.
[145] Liu YG, Hu SJ. Assembly fixture fault diagnosis using designated component analysis[J]. Transaction of the ASME, 2005, 127(2): 358-368.
[146] Camelia JA, Hu SJ. Multiple fault diagnosis for sheet metal fixtures using designated component analysis[J]. Journal of Manufacturing Science and Engineering, 2004, 126(1): 91-97.