禽蛋品质在线智能化检测关键技术研究
|
摘要
禽蛋品质在线智能化检测关键技术的研究有利于提升我国禽蛋商品化处理及多指标同步检测的能力,突破国外产品的市场垄断,为我国禽蛋商品初加工处理的自动化和规模化提供条件。对声学信号分析、机器视觉与动态称重等技术在禽蛋品质智能化检测中的理论瓶颈和关键技术难题进行了分析,并以此为据开展了禽蛋品质多指标模块化智能检测的研究,实现了对鸡蛋的蛋壳质量、蛋形指数、重量及新鲜度等鸡蛋内外品质在线无损检测；针对禽蛋裂纹在线检测实现相对复杂的问题,检测稳定性受制于多次敲击等问题,进一步开展了表面振动波信号分析技术的研究,分析振动波信号在禽蛋蛋壳表面分布、扩散及衰减情况,以期通过单次敲击即可快速无损检测裂纹禽蛋的方法。主要研究内容如下：
1.鸡蛋蛋壳质量在线检测模块的设计和研究。设计了一套以DSP (TMS320C2812)为核心处理器的鸡蛋蛋壳品质在线检测模块,可实现受检鸡蛋在生产线上滚动前行、到达检测工位时的自动敲击及音频信号的采集与处理,分析了在线检测中生产线速度、敲击力度、敲击点、禽蛋质量等因素对响应信号的影响,并对软硬件进行了优化,为获取稳定性强和信噪比高的响应信号提供基础。通过软件系统实现信号的时频转换,并提取频域信号中的相关特征参数,建立蛋壳品质的定性与定量分析模型。该系统对完好和裂纹鸡蛋检测率分别达97.27%和94.17%；蛋壳强度(蛋壳最大承受应力)的预测值与参考值(准静态压缩法)之间的平均误差为3.01N,相关系数R为0.776。
2.鸡蛋蛋壳质量在线检测模块的集成与优化。对已有的蛋壳质量检测模块在信号采集与处理、自动敲击和上位机三个子模块进行了优化,使其更贴近于自动化与工业化。在信号的采集与处理模块中,以TMS320C5509A为主处理器,简化了音频信号的采集与调理过程,减少了信号干扰环节,提高了信号的精度与处理速度；在自动敲击模块中,通过对信号触发和敲击执行控制环节的优化,实现各敲击工位的紧密排列,缩短了生产线声学模块长度,并具备随生产线速度自适应调整能力；在上下位机通讯与处理模块中,所编制的软件系统可实现对多路DSP的同步通讯及处理,并对结果进行综合判别,且将判别结果存入数据库中,可应用于后续分级执行装置。该模块的集成和优化不仅缩短了生产线声学检测区间长度,还增强了系统抗干扰能力,仅通过对时域信号过零率的分析即可区分完好和裂纹鸡蛋,检测率分别为97.58%和95.76%。
3.鸡蛋外形特征在线检测模块的设计和研究。系统以Visual Studio2008+QT为编程平台,在计算机中即可实现对鸡蛋图像在线采集与实时处理,检测鸡蛋外形特征和表面洁净程度。分析了多个颜色空间下的分量图像和分量融合图像,对R-B色差分量图采用固定阈值法从背景中提取鸡蛋区域。对比了鸡蛋长短轴提取方法,根据研究结果,采用了直角外接矩形法作为检测的长短轴的方法。分析了不同色度(HSI)空间下的鸡蛋表面颜色信息,以表面颜色的不连续性作为判别鸡蛋表面的洁净程度。所建立的线性模型预测独立鸡蛋样本的长、短轴的预测相关系数R分别为0.9477和0.9185,绝对误差平均值分别为0.5393mm和0.3658mm；对鸡蛋蛋形指数的预测精度达到了0.9552；对表面污渍和色斑检测率为94.74%。
4.鸡蛋重量在线检测模块的设计和研究。Y型辊子支撑鸡蛋在生产线上运输前行,当鸡蛋到达称重桥路时,Y型辊子给鸡蛋水平方向推力使其滚动至动态称重传感器检测区域中,采集与分析传感器信号。通过对大量动态信号的分析,运用了5阶巴特沃斯低通滤波器(截至频率为20Hz)保留了信号的低频部分,并提取了能表征鸡蛋重量的信号段(160ms-200ms),建立了鸡蛋重量预测的线性模型,结果表明,动态称重对鸡蛋称重误差范围为-0.75g-0.66g,可满足重量分级的要求。
5.鸡蛋新鲜度在线检测的研究。通过已有研究表明,鸡蛋的新鲜度与其密度呈显著相关关系。将机器视觉模块所获取的鸡蛋长、短轴,与动态称重模块所获取的鸡蛋重量信息相结合,提出了采用物理方法在线检测鸡蛋新鲜度,采用上述三个参数与新鲜度参考值(哈夫单位)构建了多元线性模型,结果表明：对独立鸡蛋样本哈夫单位预测相关性R值为0.8653,绝对误差平均值为2.9874。
6.采用表面振动波分析技术检测鸡蛋蛋壳裂纹。设计一套基于表面振动波的鸡蛋蛋壳裂纹检测基础平台,以Labview编制信号采集分析软件,采集禽蛋受机械激励后产生振动响应信号,分析其在禽蛋(薄壳椭球体结构)蛋壳表面分布、扩散及衰减情况,以期通过单次敲击即可快速无损检测裂纹禽蛋的方法。对试验中完好和裂纹鸡蛋蛋壳敲击振动信号的进行统计性分析,提取了7个特征参数,并用主成分分析方法提取有用信息；将鸡蛋表面8等分,研究裂纹位置对信号的影响。实验结果表明通过分析鸡蛋表面振动波信号的方法检测鸡蛋蛋壳裂纹是可行的,且能有效的减少检测次数。
本课题分析研究了鸡蛋品质在线智能化检测的关键技术,针对不同检测参数采用模块化处理,研究成果对进一步提高禽蛋品质智能化检测的可靠性和精度提供了基础,对促进禽蛋品质检测关键技术的发展和自动化检测与分级装备的研制具有一定的实际意义。同时,研究以鸡蛋为研究对象,但也不失其一般性,研究结果也可为其它农产品的在线检测提供参考和基础支持。
The key technologies of the online intelligent detecting system for egg quality were studied to improve the ability of egg postharvest handling and synchronization detection for multi-index. The research achievement can be used to break the monopolization of foreign products, and make contributions to develop automation system for egg primary processing. In this study, the bottleneck and the key technical problems, which arised with the application of acoustic technique, computer vision and dynamic weighing in egg quality intelligent detection system, was studied to realize the detection of external quality (eggshell strength, cracks, size, weight and cleanliness) and internal quality (freshness) of chicken eggs. Due to the complexity of mechanical device and instability of multi-detection in the existing system, surface wave analysis was studied. In order to achieve the crack detection with one impact, the distribution, spread and attenuation of the wave on eggshell surface were analysed. The main achievements are summarized as follows:
1. Development of on-line measurement module for eggshell quality. An on-line system based on acoustic resonance with digital signal processing (DSP, TMS320C2812) as the core processors was developed for the measurement of eggshell quality. Scroll forward of egg, automatic impact and the acquisition, processing and analysis of the response signal can be achieved based on the on-line module. The effects of excitation point, speed of the conveying system, impact intensity and egg mass on the frequencies response signals were investigated to acquire stable and higher signal-to-noise ratio signals. Fast Fourier transformation was employed to transform the signal from time domain to frequency domain. Spectrum analysis for the sound signal was made for finding out remarkable frequency factors. Qualitative and quantitative analysis were conducted to built the detection modle for eggshell quality. The identification rates of intact eggs and cracked eggs were97.27%and94.17%, respectively. The correlations coefficients (R) between the strength measured by references method (Quasi-static measurement) and acoustic response signal was0.776, and mean square error of prediction was3.01N.
2. Improvement and optimization for the eggshell quality automatic detection system. According to the previous research, signal acquisition and processing, automatic impact and upper computer submodule were improved to meet the requirement of automatic and industrialized production. TMS320C5509A was used as the core processor in signal acquisition and processing submodule. In this way, the process of signal acquisition and signal modulating can be simplified. Meanwhile, their resistance to interference and processing speed were improved in the module. By improving the control method of automatic impact, the detection stations can be arranged closely. Therefor, the space of eggshell crack detection module can be shortened. By analysing the features of sound signal from intact and cracked eggs, zero-pass points of the time siganl was computed as the characteristic parameter to discriminat intact and cracked eggs. The identification rates of intact eggs and cracked eggs were97.58%and95.76%, respectively.
3. Development of on-line measurement system for egg's external physical characteristic. The software was developed based on Visual Studio2008+QT on computer. The image of eggs in motion were acquired by CCD camera, and processed in realtime. Long axis, minor axis and cleanliness of eggshell were the three output parameters of the system. Eggs were segmented using global threshold in G-B image. In the reasesrch, after the comparing of different size detection methods, enclosing rectangle mothed was determined to compute the long and minor axis. Meanwhile, the egg images in different color spaces were studied to detecion cleanliness of eggshell. The correlations coefficients (R) between the long and minor axis measured by references method and image process were0.9477and0.9185, and average absolute error of prediction were0.5393mm and0.3658mm. The detection rate of eggshell with blot was94.74%
4. Development of on-line measurement system for egg's weight. Roller with Y type carries the egg forward. When the egg passes by the weighing mechanism, a software program was written based on Labview that allows a fast acquisition and processing of the dynamic signal. A fifth order Butterworth lowpass filter with the cut-off frequency of20Hz was employed to process the time signal. Then, a section of the filted signal (between160ms to200ms)was cut out to compute the egg's weight. Based on the linear model which built for egg's weight prediction, the error between predicted and real ranges from-0.75g to0.66g.
5. The study of egg freshness based on physical method. Researches have showed that freshness of eggs is significantly correlated with the density. Therefore, three parameters of long axis, minor axis and weight, which are computed by machine vision technology and weigh-in-motion technology, were used to build multivariate linear model to compute Haugh Unit. The result showed that, the correlations coefficients (R) between the predicted and reference values was0.8653, and average absolute error was2.9874.
6. Eggshell crack detection based on the surface wave analysis. A system based on surface wave analysis, as the basic experiment, was developed to detect eggshell crack. It was achieved by analysis the distribution, spread and attenuation of the wave on eggshell surface excited by a light mechanical. A software program was written in Labview that allows a fast acquisition and processing of the response signal. Seven features variables were exacted from response frequency signals and the scores vectors were extracted byPrincipal component analysis (PCA). In the reasearch, the eggshell was divided into eight equal parts to explore the influence caused by the different locations of crack. The result showed that, surface wave analysis was a feasible approach to detect the crack on the eggshell, and can reduce the detecion time.
In this work, some key technologies for the online intelligent detecting system of egg quality was studied, and some different detection modules were designed to detect different indexs of egg quality. The research achievement can further improve the reliability and detection precision of egg quality detection system. It was of actual practical significance in improving automatic detection system and grading equipment. It also can set the stage and guides to online detection system for other agricultural products.
1.鸡蛋蛋壳质量在线检测模块的设计和研究。设计了一套以DSP (TMS320C2812)为核心处理器的鸡蛋蛋壳品质在线检测模块,可实现受检鸡蛋在生产线上滚动前行、到达检测工位时的自动敲击及音频信号的采集与处理,分析了在线检测中生产线速度、敲击力度、敲击点、禽蛋质量等因素对响应信号的影响,并对软硬件进行了优化,为获取稳定性强和信噪比高的响应信号提供基础。通过软件系统实现信号的时频转换,并提取频域信号中的相关特征参数,建立蛋壳品质的定性与定量分析模型。该系统对完好和裂纹鸡蛋检测率分别达97.27%和94.17%；蛋壳强度(蛋壳最大承受应力)的预测值与参考值(准静态压缩法)之间的平均误差为3.01N,相关系数R为0.776。
2.鸡蛋蛋壳质量在线检测模块的集成与优化。对已有的蛋壳质量检测模块在信号采集与处理、自动敲击和上位机三个子模块进行了优化,使其更贴近于自动化与工业化。在信号的采集与处理模块中,以TMS320C5509A为主处理器,简化了音频信号的采集与调理过程,减少了信号干扰环节,提高了信号的精度与处理速度；在自动敲击模块中,通过对信号触发和敲击执行控制环节的优化,实现各敲击工位的紧密排列,缩短了生产线声学模块长度,并具备随生产线速度自适应调整能力；在上下位机通讯与处理模块中,所编制的软件系统可实现对多路DSP的同步通讯及处理,并对结果进行综合判别,且将判别结果存入数据库中,可应用于后续分级执行装置。该模块的集成和优化不仅缩短了生产线声学检测区间长度,还增强了系统抗干扰能力,仅通过对时域信号过零率的分析即可区分完好和裂纹鸡蛋,检测率分别为97.58%和95.76%。
3.鸡蛋外形特征在线检测模块的设计和研究。系统以Visual Studio2008+QT为编程平台,在计算机中即可实现对鸡蛋图像在线采集与实时处理,检测鸡蛋外形特征和表面洁净程度。分析了多个颜色空间下的分量图像和分量融合图像,对R-B色差分量图采用固定阈值法从背景中提取鸡蛋区域。对比了鸡蛋长短轴提取方法,根据研究结果,采用了直角外接矩形法作为检测的长短轴的方法。分析了不同色度(HSI)空间下的鸡蛋表面颜色信息,以表面颜色的不连续性作为判别鸡蛋表面的洁净程度。所建立的线性模型预测独立鸡蛋样本的长、短轴的预测相关系数R分别为0.9477和0.9185,绝对误差平均值分别为0.5393mm和0.3658mm；对鸡蛋蛋形指数的预测精度达到了0.9552；对表面污渍和色斑检测率为94.74%。
4.鸡蛋重量在线检测模块的设计和研究。Y型辊子支撑鸡蛋在生产线上运输前行,当鸡蛋到达称重桥路时,Y型辊子给鸡蛋水平方向推力使其滚动至动态称重传感器检测区域中,采集与分析传感器信号。通过对大量动态信号的分析,运用了5阶巴特沃斯低通滤波器(截至频率为20Hz)保留了信号的低频部分,并提取了能表征鸡蛋重量的信号段(160ms-200ms),建立了鸡蛋重量预测的线性模型,结果表明,动态称重对鸡蛋称重误差范围为-0.75g-0.66g,可满足重量分级的要求。
5.鸡蛋新鲜度在线检测的研究。通过已有研究表明,鸡蛋的新鲜度与其密度呈显著相关关系。将机器视觉模块所获取的鸡蛋长、短轴,与动态称重模块所获取的鸡蛋重量信息相结合,提出了采用物理方法在线检测鸡蛋新鲜度,采用上述三个参数与新鲜度参考值(哈夫单位)构建了多元线性模型,结果表明：对独立鸡蛋样本哈夫单位预测相关性R值为0.8653,绝对误差平均值为2.9874。
6.采用表面振动波分析技术检测鸡蛋蛋壳裂纹。设计一套基于表面振动波的鸡蛋蛋壳裂纹检测基础平台,以Labview编制信号采集分析软件,采集禽蛋受机械激励后产生振动响应信号,分析其在禽蛋(薄壳椭球体结构)蛋壳表面分布、扩散及衰减情况,以期通过单次敲击即可快速无损检测裂纹禽蛋的方法。对试验中完好和裂纹鸡蛋蛋壳敲击振动信号的进行统计性分析,提取了7个特征参数,并用主成分分析方法提取有用信息；将鸡蛋表面8等分,研究裂纹位置对信号的影响。实验结果表明通过分析鸡蛋表面振动波信号的方法检测鸡蛋蛋壳裂纹是可行的,且能有效的减少检测次数。
本课题分析研究了鸡蛋品质在线智能化检测的关键技术,针对不同检测参数采用模块化处理,研究成果对进一步提高禽蛋品质智能化检测的可靠性和精度提供了基础,对促进禽蛋品质检测关键技术的发展和自动化检测与分级装备的研制具有一定的实际意义。同时,研究以鸡蛋为研究对象,但也不失其一般性,研究结果也可为其它农产品的在线检测提供参考和基础支持。
The key technologies of the online intelligent detecting system for egg quality were studied to improve the ability of egg postharvest handling and synchronization detection for multi-index. The research achievement can be used to break the monopolization of foreign products, and make contributions to develop automation system for egg primary processing. In this study, the bottleneck and the key technical problems, which arised with the application of acoustic technique, computer vision and dynamic weighing in egg quality intelligent detection system, was studied to realize the detection of external quality (eggshell strength, cracks, size, weight and cleanliness) and internal quality (freshness) of chicken eggs. Due to the complexity of mechanical device and instability of multi-detection in the existing system, surface wave analysis was studied. In order to achieve the crack detection with one impact, the distribution, spread and attenuation of the wave on eggshell surface were analysed. The main achievements are summarized as follows:
1. Development of on-line measurement module for eggshell quality. An on-line system based on acoustic resonance with digital signal processing (DSP, TMS320C2812) as the core processors was developed for the measurement of eggshell quality. Scroll forward of egg, automatic impact and the acquisition, processing and analysis of the response signal can be achieved based on the on-line module. The effects of excitation point, speed of the conveying system, impact intensity and egg mass on the frequencies response signals were investigated to acquire stable and higher signal-to-noise ratio signals. Fast Fourier transformation was employed to transform the signal from time domain to frequency domain. Spectrum analysis for the sound signal was made for finding out remarkable frequency factors. Qualitative and quantitative analysis were conducted to built the detection modle for eggshell quality. The identification rates of intact eggs and cracked eggs were97.27%and94.17%, respectively. The correlations coefficients (R) between the strength measured by references method (Quasi-static measurement) and acoustic response signal was0.776, and mean square error of prediction was3.01N.
2. Improvement and optimization for the eggshell quality automatic detection system. According to the previous research, signal acquisition and processing, automatic impact and upper computer submodule were improved to meet the requirement of automatic and industrialized production. TMS320C5509A was used as the core processor in signal acquisition and processing submodule. In this way, the process of signal acquisition and signal modulating can be simplified. Meanwhile, their resistance to interference and processing speed were improved in the module. By improving the control method of automatic impact, the detection stations can be arranged closely. Therefor, the space of eggshell crack detection module can be shortened. By analysing the features of sound signal from intact and cracked eggs, zero-pass points of the time siganl was computed as the characteristic parameter to discriminat intact and cracked eggs. The identification rates of intact eggs and cracked eggs were97.58%and95.76%, respectively.
3. Development of on-line measurement system for egg's external physical characteristic. The software was developed based on Visual Studio2008+QT on computer. The image of eggs in motion were acquired by CCD camera, and processed in realtime. Long axis, minor axis and cleanliness of eggshell were the three output parameters of the system. Eggs were segmented using global threshold in G-B image. In the reasesrch, after the comparing of different size detection methods, enclosing rectangle mothed was determined to compute the long and minor axis. Meanwhile, the egg images in different color spaces were studied to detecion cleanliness of eggshell. The correlations coefficients (R) between the long and minor axis measured by references method and image process were0.9477and0.9185, and average absolute error of prediction were0.5393mm and0.3658mm. The detection rate of eggshell with blot was94.74%
4. Development of on-line measurement system for egg's weight. Roller with Y type carries the egg forward. When the egg passes by the weighing mechanism, a software program was written based on Labview that allows a fast acquisition and processing of the dynamic signal. A fifth order Butterworth lowpass filter with the cut-off frequency of20Hz was employed to process the time signal. Then, a section of the filted signal (between160ms to200ms)was cut out to compute the egg's weight. Based on the linear model which built for egg's weight prediction, the error between predicted and real ranges from-0.75g to0.66g.
5. The study of egg freshness based on physical method. Researches have showed that freshness of eggs is significantly correlated with the density. Therefore, three parameters of long axis, minor axis and weight, which are computed by machine vision technology and weigh-in-motion technology, were used to build multivariate linear model to compute Haugh Unit. The result showed that, the correlations coefficients (R) between the predicted and reference values was0.8653, and average absolute error was2.9874.
6. Eggshell crack detection based on the surface wave analysis. A system based on surface wave analysis, as the basic experiment, was developed to detect eggshell crack. It was achieved by analysis the distribution, spread and attenuation of the wave on eggshell surface excited by a light mechanical. A software program was written in Labview that allows a fast acquisition and processing of the response signal. Seven features variables were exacted from response frequency signals and the scores vectors were extracted byPrincipal component analysis (PCA). In the reasearch, the eggshell was divided into eight equal parts to explore the influence caused by the different locations of crack. The result showed that, surface wave analysis was a feasible approach to detect the crack on the eggshell, and can reduce the detecion time.
In this work, some key technologies for the online intelligent detecting system of egg quality was studied, and some different detection modules were designed to detect different indexs of egg quality. The research achievement can further improve the reliability and detection precision of egg quality detection system. It was of actual practical significance in improving automatic detection system and grading equipment. It also can set the stage and guides to online detection system for other agricultural products.
引文
[1]V. Leemans, M.-F. Destain. A real-time grading method of apples based on features extracted from defects[J]. Journal of Food Engineering,2004,61(1):83-89.
[2]B. Jarimopas, N. Jaisin. An experimental machine vision system for sorting sweet tamarind[J]. Journal of Food Engineering,2008,89(3):291-297.
[3]N. Razmjooy, B. S. MousaviF. Soleymani. A real-time mathematical computer method for potato inspection using machine vision[J]. Computers & Mathematics with Applications, 2012,63(1):268-279.
[4]A. Al-Mallahi, T. Kataoka, H. Okamoto, et al. Detection of potato tubers using an ultraviolet imaging-based machine vision system[J]. Biosystems engineering, 2010,105(2):257-265.
[5]姚富光,钟先信.X射线果品品质在线检测系统研究[J].激光杂志,2010,(002)：44-45.
[6]李光梅,魏新华,李法德等.水果综合分选机称重模块的设计与实现[J].农业工程学报,2009,25(2)：96-100.
[7]J. Frances, J. Calpe, M. Martinez, et al., Application of ARMA modeling to the improvement of weight estimations in fruit sorting and grading machinery [C], in Acoustics, Speech, and Signal Processing,2000. ICASSPOO. Proceedings.2000 IEEE International Conference on,2000, pp.3666-3669.
[8]K. Choi, Development of apple sorter by soluble solid content using photodiodes [C], in Proceeding of Winter Conference of KSAM,1998, pp.362-367.
[9]何东健.水果内部品质在线近红外分光检测装置及试验[J].农业工程学报,2001,17(1)：146-148.
[10]V. A. McGlone, P. J. Martinsen, C. J. Clark, et al. On-line detection of Brownheart in Braeburn apples using near infrared transmission measurements[J]. Postharvest biology and technology,2005,37(2):142-151.
[11]G. Y. Kim, K. J. Lee, K. H. Choi, et al. Defect and ripeness inspection of citrus using NIR transmission spectrum[J]. Key engineering materials,2004,270:1008-1013.
[12]杨海锋,吕小文,秦玉蝇等.近红外光谱分析技术在豆粕质量监控中的应用研究[J].饲料工业,2006,27(19)：31-34.
[13]任奕林,伍冬生李旭荣.我国禽蛋业的现状及发展对策[J].中国家禽,2005,27(2)：5-6.
[14]国家统计局.中国统计年鉴2012[M].北京：中国统计出版社,2012
[15]A. Gulich, J. FITZGARALD. USDA Egg Grading Manual, No.75[J]. Agric. Marketing Service, Washington, DC,1964,
[16]袁宝君,蔡延平,顾振华,GB 2748——-2003鲜蛋卫生标准[M],北京：中国标准出版社,2003.
[17]V. Patel, R. McClendonJ. Goodrum. Detection of blood spots and dirt stains in eggs using computer vision and neural networks[J]. Applied Engineering in agriculture, 1996,12(2):253-258.
[18]V. Patel, R. McClendonJ. Goodrum. Color computer vision and artificial neural networks for the detection of defects in poultry eggs[J]. Artificial Intelligence Review, 1998,12(1):163-176.
[19]M. C. Garcia-Alegre, A. Ribeiro, D. Guinea, et al. Eggshell defects detection based on color processing[J]. Machine Vision Applications in Industrial Inspection VIII, 2000,3966:280-287.
[20]文友先,王巧华,陈小伟等鸭蛋大小及蛋心颜色自动分级系统软件研制[J].华中农业大学学报,2001,20(4)：395-399.
[21]邓海霞,刘友明,文友先等.基于机器视觉群体鸡蛋尺寸的检测方法[J].华中农业大学学报,2006,25(4)：452-454.
[22]饶秀勤,岑益科,应义斌.基于外形几何特征的鸡蛋重量检测模型[J].中国家禽,2008,(5)：18-20.
[23]冯俊青,基于SVM的鸡蛋外观品质检测方法研究[D],内蒙古农业大学,2008.
[24]M. Dehrouyeh, M. Omid, H. Ahmadi, et al. Grading and Quality Inspection of Defected Eggs Using Machine Vision[J]. International Journal of Advanced Science and Technology, 2010,17:23-31.
[25]J. Lin, V. PuriR. Anantheswaran. Measurement of eggshell thermal-mechanical properties[J]. Transactions of the ASAE,1995,38(6):1769-1776.
[26]J. Goodrum, R. Elster. Machine vision for crack detection in rotating eggs[J]. Transactions of the ASAE,1992,35
[27]H. Cho, Y. Kwon. Crack detection in eggs by machine vision[J]. Transactions of the ASAE, 1996,39(3):777-784.
[28]L. Jenshin, Y. LinM. Hsieh. An automatic system for eggshell quality monitoring[J]. Transactions of the ASAE,2001,44(3):1028-1034.
[29]K. C. Lawrence, S. C. Yoon, D. R. Jones, et al. Modified pressure system for imaging egg cracks[J]. Trans. ASABE,2009,52:983-990.
[30]潘磊庆,屠康,苏子鹏等.基于计算机视觉和神经网络检测鸡蛋裂纹的研究[J].农业工程学报,2007,23(5)：154-158.
[31]H. R. Pourreza, R. Pourreza, S. Fazeli, et al. Automatic detection of eggshell defects based on machine vision[J]. Journal of Animal and Veterinary Advances,2008,7(10):1200-1203.
[32]刘鹏,屠康,潘磊庆等.基于多传感器融合的鸡蛋裂纹系统性识别[J].农业机械学报,2010,41(10)：185-189
[33]D. Sinha, R. Johnston, W. Grace, et al. Acoustic Resonances in Chicken Eggs[J]. Biotechnology Progress,1992,8(3):240-243.
[34]公茂法,汤元信李其才.禽蛋质量自动检测方法与实现[J].自动化与仪器仪表,1995,5：35-38.
[35]P. Coucke. Assessment of some physical quality parameters of eggs based on vibration analysis[J]. Dissertationes de Agricultura,1998,
[36]H.-K. Cho, W.-K. ChoiJ.-H. Paek. Detection of surface cracks in shell eggs by acoustic impulse method[J]. Transactions of the ASAE,2000,43(6):1921-1926.
[37]文友先,余佑生.鸭蛋破损检测的试验研究[J].华中农业大学学报,2002,21(003)：285-287.
[38]V. Jindal, E. Sritham. Detecting eggshell cracks by acoustic impulse response and artificial neural networks[J]. American Society of Agricultural Engineers, St. Joseph, MI, ASAE paper,2003,(036170)
[39]J. Wang, R. JiangY. Yu. Relationship between dynamic resonance frequency and egg physical properties[J]. Food research international,2004,37(1):45-50.
[40]姜瑞涉,王俊,陆秋君等.鸡蛋敲击响应特性与蛋壳裂纹检测[J].农业机械学报,2005,36(3)：75-78.
[41]王巧华,邓小炎文友先.鸡蛋敲击响应的奇异性特征与蛋壳裂纹多层检测[J].农业机械学报,2008,39(12)：127-131.
[42]H. LIN, J.-W. ZHAO, Q.-S. CHEN, et al. Eggshell crack detection based on acoustic impulse response and supervised pattern recognition [J]. Czech J. Food Sci. 2009,27(6):393-402.
[43]H. Lin, J.-w. Zhao, Q.-s. Chen, et al. Eggshell crack detection based on acoustic response and support vector data description algorithm[J]. European Food Research and Technology, 2009,230(1):95-100.
[44]Y. Zhao, J. Wang, Q. Lu, et al. Pattern recognition of eggshell crack using PCA and LDA[J]. Innovative Food Science & Emerging Technologies,2010,11(3):520-525.
[45]孙力,蔡健荣,林颢等.基于声学特性的禽蛋裂纹实时在线检测系统[J].农业机械学报,2011,42(5)：183-186.
[46]L. Sun, S. Q. Zhang, J. R. Cai, et al. The Application of DSP in Eggshell Quality Online Detection System[J]. Applied Mechanics and Materials,2011,43:68-71.
[47]B. De Ketelaere, H. VanhoutteJ. De Baerdemaeker. Parameter estimation and multivariable model building for the non-destructive, on-line determination of eggshell strength[J]. Journal of sound and vibration,2003,266(3):699-709.
[48]E. Altuntas, A. Sekeroglu. Effect of egg shape index on mechanical properties of chicken eggs[J]. Journal of Food Engineering,2008,85(4):606-612.
[49]周平,蔡健荣,林颢.基于声学特性的鸡蛋蛋壳强度检测的研究[J].食品科技,2010,(002)：237-240.
[50]H. Lin, J.-w. Zhao, L. Sun, et al. Stiffness measurement of eggshell by acoustic resonance and PLS models[J]. Journal of Food Engineering,2011,103(4):351-356.
[51]C. K. Yong, Intact egg freshness quality inspection using neural networks [C], in Neural Networks,1995. Proceedings., IEEE International Conference on,1995, pp.1080-1085.
[52]K. Ku(?)hda, M. Fukaya, S. Miyoshi, et al. Nondestructive prediction method for yolk: albumen ratio in chicken eggs by computer image analysis [J]. Poultry Science, 1999,78(6):909-913.
[53]刘俭英,余佑生.鸭蛋新鲜度模型的试验研究[J].华中农业大学学报,2002,21(6)：567-569.
[54]王巧华,任奕林,文友先.基于BP神经网络的鸡蛋新鲜度无损检测方法[J].农业机械学报,2006,37(1)：104-106.
[55]岑益科,基于机器视觉的鸡蛋品质检测方法研究[D],杭州：浙江大学,2006.
[56]王巧华,文友先,林雪冬等.鸡蛋透射光图像形态特征与其新鲜度的相关关系[J][J].农业工程学报,2008,24(3)：179-183.
[57]L. Yande, Y. Yibin. Study on optical nondestructive inspection of chicken-egg freshness[J]. Proceeding of JICAST,2002,
[58]A. Berardinelli, A. Giunchi, A. Guarnieri, et al. Shell egg albumen height assessment by FT-NIR spectroscopy[J]. Transactions of the ASAE,2005,48(4):1423-1428.
[59]B. J. Kemps, F. R. Bamelis, B. De Ketelaere, et al. Visible transmission spectroscopy for the assessment of egg freshness[J]. Journal of the Science of Food and Agriculture, 2006,86(9):1399-1406.
[60]N. Abdel-Nour, M. Ngadi, S. Prasher, et al. Prediction of Egg Freshness and Albumen Quality Using Visible/Near Infrared Spectroscopy[J]. Food and Bioprocess Technology, 2011,4(5):731-736.
[61]侯卓成,杨宁,李俊英等.傅里叶变换近红外反射用于鸡蛋蛋品质的研究[J].光谱学与光谱分析,2009,(008)：2063-2066.
[62]H. Lin, J. Zhao, L. Sun, et al. Freshness measurement of eggs using near infrared (NIR) spectroscopy and multivariate data analysis[J]. Innovative Food Science & Emerging Technologies,2011,12(2):182-186.
[63]A. Brant, K. NorrisG. Chin. A spectrophotometric method for detecting blood in white-shell eggs[J]. Poultry Science,1953,32(2):357-363.
[64]Y. Usui, K. NakanoY. Motonaga, A Study of The Development Of Non-Destructive Detection System for Abnormal Eggs [C], in EFFTA 2003 Conference, Hungary,2003, pp. 5-9.
[65]臼井善彦,中野和弘(?)藤麻奈.異常鶏の非破壞検出法に関する研究(第3報)：可视分光分析にする褐色卵の血.卵検出[J].農業施設,2006,36(4)：209-214.
[1]B. Diezma-Iglesias, M. Ruiz-AltisentP. Barreiro. Detection of internal quality in seedless watermelon by acoustic impulse response[J]. Biosystems engineering,2004,88(2):221-230.
[2]C. Primo-Martin, N. Sozer, R. Hamer, et al. Effect of water activity on fracture and acoustic characteristics of a crust model[J]. Journal of Food Engineering, 2009,90(2):277-284.
[3]M. Taniwaki, T. HanadaN. Sakurai. Postharvest quality evaluation of "Fuyu" and "Taishuu" persimmons using a nondestructive vibrational method and an acoustic vibration technique[J]. Postharvest biology and technology,2009,51(1):80-85.
[4]L. Piazza, J. GigliS. Benedetti. Study of structure and flavour release relationships in low moisture bakery products by means of the acoustic-mechanical combined technique and the electronic nose[J]. Journal of Cereal Science,2008,48(2):413-419.
[5]I. Elbatawi. An acoustic impact method to detect hollow heart of potato tubers[J]. Biosystems engineering,2008,100(2):206-213.
[6]A. Baltazar, J. I. ArandaG. Gonzalez-Aguilar. Bayesian classification of ripening stages of tomato fruit using acoustic impact and colorimeter sensor data[J]. Computers and electronics in agriculture,2008,60(2):113-121.
[7]赵杰文,孙永海.现代食品检测技术[M].中国轻工业出版社,2008.
[8]http://www.vishay.com/.
[9]http://www.ti.com.cn/cn/lit/ds/symlink/ina217.pdf.
[10]顾卫钢,手把手教你学DSP[M],北京：北京航空航天大学出版社.
[11]彭启琮,张诗雅,常冉TI DSP集成化开发环境(CCS)使用手册[M].清华大学出版社有限公司,2005.
[1]Y. Cai, J. Yuan, X. Ma, et al., Low Power Embedded Speech Enhancement System Based on a Fixed-Point DSP [C], in Dependable, Autonomic and Secure Computing,2009. DASC'09. Eighth IEEE International Conference on,2009, pp.132-136.
[2]Z. Xiaochuan, L. QingshengH. Baoling, Signal processing of biologically inspired hexapod robot's navigation system based on GPS/INS [C], in Industrial Electronics and Applications,2009. ICIEA2009.4th IEEE Conference on,2009, pp.1139-1144.
[3]W. Li, J.-L. YanH.-L. Zhao. Implementation of Time Delay Estimation Algorithm of Ultrasonic Flowmeter in Coal Mine Based on Fixed Point DSP[J]. Meitan Jishu/Coal Technology,2012,31(1):175-176.
[4]J. Gao, L. WangJ. M. Ma. A Multi-Channel Audio Signal Processing Platform Based on DSP[J]. Applied Mechanics and Materials,2012,121:1858-1862.
[5]陈泰红,任胜杰,魏宇.手把手教你学DSP：基于TMS320C55x[M1.北京航空航天大学出版社,2011.
[6]Texas Instruments corporation, TLV320AIC23B Data Manual[EB/OL]. www.ti.com2004.2
[7]蔡志明,卢传富,李立夏.精通Qt4编程[M].电子工业出版社,2008.
[1]艾海舟,武勃,图像处理,分析与机器视觉[M],北京：人民邮电出版社,2003.
[2]姜松,漆虹,五国江等.禽蛋基本特性参数分析与试验[J].农业机械学报,2012,43(004)：137-142.
[3]F. Ayupov. On the egg mathematical model[J]. Advanced Scieiztific-Industrial Experience in Poultry Breeding. Express Information,1976,9:14-16.
[4]C. Steger, M. UlrichC. Wiedemann,机器视觉算法与应用[M],北京：清华大学出版社,2008.
[5]V. Narushin. Egg geometry calculation using the measurements of length and breadth[J]. Poultry Science,2005,84(3):482-484.
[6]R. C. Gonzalez, R. E. Woods数字图像处理.阮秋琦,阮宇智,等译[J].数字图像处理[M](第二版),2003：500-505.
[1]孙廷耀.关于如何选用称重传感器的几点建议[J].计是不是技术,2001,(001)：53-54.
[2]刘迎春,叶湘滨.传感器原理,设计与应用[D].国防科技大学出版社,2006.
[3]王化祥,张淑英.传感器原理及应用[D].天津大学出版社,1999.
[4]张国雄,电子科技金篆芷.测控电路[D].机械工业出版社,2001.
[5]B. BIRD. VEHICLE APPLICATION GUIDE[J]. URO(?),2003:8.
[6]张桐,陈国顺王正林.精通LabVIEW程序设计[D].电子工业出版社,2008.
[7]A. Hidalgo, M. Rossi, F. Clerici, et al. A market study on the quality characteristics of eggs from different housing systems[J]. Food Chemistry,2008,106(3):1031-1038.
[8]R. Dutta, E. L. Hines, J. W. Gardner, et al. Non-destructive egg freshness determination:an electronic nose based approach[J]. Measurement Science and Technology,2003,14(2):190.
[1]纪少波,程勇,唐娟等.缸盖表面振动速度预处理方法及应用研究[J].内燃机工程,2012,33(003)：40-44.
[2]虞海强,基于振动分析法的变压器状态检测研究[D],西华大学,2012.
[3]周建平,林爱弟,吴劲晖等.电力变压器振动监测的测点位置选择[J].电子测量与仪器学报,2012,26(12)：1100-1107.
[4]胡波,振动与噪声分析在变速箱在线质量检测中的应用与研究[D],合肥工业大学,2012.
[5]H. Abdi, L. J. Williams. Principal component analysis[J]. Wiley Interdisciplinary Reviews: Computational Statistics,2010,2(4):433-459.
[6]P. J. Shaw. Multivariate statistics for the environmental sciences[D]. Arnold London,2003.
[7]边肇祺,张学工.模式识别[M].清华大学出版社,2000.
[8]H. Yu, J. Yang. A direct LDA algorithm for high-dimensional data-with application to face recognition[J]. Pattern recognition,2001,34(10):2067.
[9]J.-H. Chen. KNN based knowledge-sharing model for severe change order disputes in construction[J]. Automation in Construction,2008,17(6):773-779.
[10]N. Caglar, M. Elmas, Z. D. Yaman, et al. Neural networks in 3-dimensional dynamic analysis of reinforced concrete buildings[J]. Construction and Building Materials, 2008,22(5):788-800.
[11]王碧泉,陈祖荫.模式识别：理论,方法和应用[M].地震出版社,1989.
[12]H. Kim, B. L. DrakeH. Park. Multiclass classifiers based on dimension reduction with generalized LDA[J]. Pattern recognition,2007,40(11):2939-2945.
[13]A. Doudou. Estimation of turbulence spectra in flows of hard conditions sensed with LDA[J]. Measurement,2007,40(1):75-92.
[14]W. Wu, D. Massart. Regularised nearest neighbour classification method for pattern recognition of near infrared spectra[J]. Analytica chimica acta,1997,349(1):253-261.
[15]T. Koukal, F. SuppanW. Schneider. The impact of relative radiometric calibration on the accuracy of kNN-predictions of forest attributes[J]. Remote Sensing of Environment, 2007,110(4):431-437.
[16]C.-M. Liu, S.-Y. Fu. Effective protocols for kNN search on broadcast multi-dimensional index trees[J]. Information Systems,2008,33(1):18-35.
[17]罗一帆,郭振飞,朱振宇等.近红外光谱测定茶叶中茶多酚和茶多糖的人工神经网络模型研究[J].光谱学与光谱分析,2005,25(008)：1230-1233.
[18]任瑞雪,苟玉彗.人工神经网络—近红外光谱法用于粉末药品扑热息痛的非破坏定量分析[J].光谱学与光谱分析,2001,21(004)：521-523.
[19]K. Yetilmezsoy, S. Demirel. Artificial neural network (ANN) approach for modeling of Pb (Ⅱ) adsorption from aqueous solution by Antep pistachio (Pistacia Vera L.) shells[J]. Journal of Hazardous Materials,2008,153(3):1288-1300.
[20]M. O'farrell, E. Lewis, C. Flanagan, et al. Combining principal component analysis with an artificial neural network to perform online quality assessment of food as it cooks in a large-scale industrial oven[J]. Sensors and Actuators B:Chemical,2005,107(1):104-112.
[21]戴葵,神经网络设计[M],北京：机械工业出版社,2002.
[2]B. Jarimopas, N. Jaisin. An experimental machine vision system for sorting sweet tamarind[J]. Journal of Food Engineering,2008,89(3):291-297.
[3]N. Razmjooy, B. S. MousaviF. Soleymani. A real-time mathematical computer method for potato inspection using machine vision[J]. Computers & Mathematics with Applications, 2012,63(1):268-279.
[4]A. Al-Mallahi, T. Kataoka, H. Okamoto, et al. Detection of potato tubers using an ultraviolet imaging-based machine vision system[J]. Biosystems engineering, 2010,105(2):257-265.
[5]姚富光,钟先信.X射线果品品质在线检测系统研究[J].激光杂志,2010,(002)：44-45.
[6]李光梅,魏新华,李法德等.水果综合分选机称重模块的设计与实现[J].农业工程学报,2009,25(2)：96-100.
[7]J. Frances, J. Calpe, M. Martinez, et al., Application of ARMA modeling to the improvement of weight estimations in fruit sorting and grading machinery [C], in Acoustics, Speech, and Signal Processing,2000. ICASSPOO. Proceedings.2000 IEEE International Conference on,2000, pp.3666-3669.
[8]K. Choi, Development of apple sorter by soluble solid content using photodiodes [C], in Proceeding of Winter Conference of KSAM,1998, pp.362-367.
[9]何东健.水果内部品质在线近红外分光检测装置及试验[J].农业工程学报,2001,17(1)：146-148.
[10]V. A. McGlone, P. J. Martinsen, C. J. Clark, et al. On-line detection of Brownheart in Braeburn apples using near infrared transmission measurements[J]. Postharvest biology and technology,2005,37(2):142-151.
[11]G. Y. Kim, K. J. Lee, K. H. Choi, et al. Defect and ripeness inspection of citrus using NIR transmission spectrum[J]. Key engineering materials,2004,270:1008-1013.
[12]杨海锋,吕小文,秦玉蝇等.近红外光谱分析技术在豆粕质量监控中的应用研究[J].饲料工业,2006,27(19)：31-34.
[13]任奕林,伍冬生李旭荣.我国禽蛋业的现状及发展对策[J].中国家禽,2005,27(2)：5-6.
[14]国家统计局.中国统计年鉴2012[M].北京：中国统计出版社,2012
[15]A. Gulich, J. FITZGARALD. USDA Egg Grading Manual, No.75[J]. Agric. Marketing Service, Washington, DC,1964,
[16]袁宝君,蔡延平,顾振华,GB 2748——-2003鲜蛋卫生标准[M],北京：中国标准出版社,2003.
[17]V. Patel, R. McClendonJ. Goodrum. Detection of blood spots and dirt stains in eggs using computer vision and neural networks[J]. Applied Engineering in agriculture, 1996,12(2):253-258.
[18]V. Patel, R. McClendonJ. Goodrum. Color computer vision and artificial neural networks for the detection of defects in poultry eggs[J]. Artificial Intelligence Review, 1998,12(1):163-176.
[19]M. C. Garcia-Alegre, A. Ribeiro, D. Guinea, et al. Eggshell defects detection based on color processing[J]. Machine Vision Applications in Industrial Inspection VIII, 2000,3966:280-287.
[20]文友先,王巧华,陈小伟等鸭蛋大小及蛋心颜色自动分级系统软件研制[J].华中农业大学学报,2001,20(4)：395-399.
[21]邓海霞,刘友明,文友先等.基于机器视觉群体鸡蛋尺寸的检测方法[J].华中农业大学学报,2006,25(4)：452-454.
[22]饶秀勤,岑益科,应义斌.基于外形几何特征的鸡蛋重量检测模型[J].中国家禽,2008,(5)：18-20.
[23]冯俊青,基于SVM的鸡蛋外观品质检测方法研究[D],内蒙古农业大学,2008.
[24]M. Dehrouyeh, M. Omid, H. Ahmadi, et al. Grading and Quality Inspection of Defected Eggs Using Machine Vision[J]. International Journal of Advanced Science and Technology, 2010,17:23-31.
[25]J. Lin, V. PuriR. Anantheswaran. Measurement of eggshell thermal-mechanical properties[J]. Transactions of the ASAE,1995,38(6):1769-1776.
[26]J. Goodrum, R. Elster. Machine vision for crack detection in rotating eggs[J]. Transactions of the ASAE,1992,35
[27]H. Cho, Y. Kwon. Crack detection in eggs by machine vision[J]. Transactions of the ASAE, 1996,39(3):777-784.
[28]L. Jenshin, Y. LinM. Hsieh. An automatic system for eggshell quality monitoring[J]. Transactions of the ASAE,2001,44(3):1028-1034.
[29]K. C. Lawrence, S. C. Yoon, D. R. Jones, et al. Modified pressure system for imaging egg cracks[J]. Trans. ASABE,2009,52:983-990.
[30]潘磊庆,屠康,苏子鹏等.基于计算机视觉和神经网络检测鸡蛋裂纹的研究[J].农业工程学报,2007,23(5)：154-158.
[31]H. R. Pourreza, R. Pourreza, S. Fazeli, et al. Automatic detection of eggshell defects based on machine vision[J]. Journal of Animal and Veterinary Advances,2008,7(10):1200-1203.
[32]刘鹏,屠康,潘磊庆等.基于多传感器融合的鸡蛋裂纹系统性识别[J].农业机械学报,2010,41(10)：185-189
[33]D. Sinha, R. Johnston, W. Grace, et al. Acoustic Resonances in Chicken Eggs[J]. Biotechnology Progress,1992,8(3):240-243.
[34]公茂法,汤元信李其才.禽蛋质量自动检测方法与实现[J].自动化与仪器仪表,1995,5：35-38.
[35]P. Coucke. Assessment of some physical quality parameters of eggs based on vibration analysis[J]. Dissertationes de Agricultura,1998,
[36]H.-K. Cho, W.-K. ChoiJ.-H. Paek. Detection of surface cracks in shell eggs by acoustic impulse method[J]. Transactions of the ASAE,2000,43(6):1921-1926.
[37]文友先,余佑生.鸭蛋破损检测的试验研究[J].华中农业大学学报,2002,21(003)：285-287.
[38]V. Jindal, E. Sritham. Detecting eggshell cracks by acoustic impulse response and artificial neural networks[J]. American Society of Agricultural Engineers, St. Joseph, MI, ASAE paper,2003,(036170)
[39]J. Wang, R. JiangY. Yu. Relationship between dynamic resonance frequency and egg physical properties[J]. Food research international,2004,37(1):45-50.
[40]姜瑞涉,王俊,陆秋君等.鸡蛋敲击响应特性与蛋壳裂纹检测[J].农业机械学报,2005,36(3)：75-78.
[41]王巧华,邓小炎文友先.鸡蛋敲击响应的奇异性特征与蛋壳裂纹多层检测[J].农业机械学报,2008,39(12)：127-131.
[42]H. LIN, J.-W. ZHAO, Q.-S. CHEN, et al. Eggshell crack detection based on acoustic impulse response and supervised pattern recognition [J]. Czech J. Food Sci. 2009,27(6):393-402.
[43]H. Lin, J.-w. Zhao, Q.-s. Chen, et al. Eggshell crack detection based on acoustic response and support vector data description algorithm[J]. European Food Research and Technology, 2009,230(1):95-100.
[44]Y. Zhao, J. Wang, Q. Lu, et al. Pattern recognition of eggshell crack using PCA and LDA[J]. Innovative Food Science & Emerging Technologies,2010,11(3):520-525.
[45]孙力,蔡健荣,林颢等.基于声学特性的禽蛋裂纹实时在线检测系统[J].农业机械学报,2011,42(5)：183-186.
[46]L. Sun, S. Q. Zhang, J. R. Cai, et al. The Application of DSP in Eggshell Quality Online Detection System[J]. Applied Mechanics and Materials,2011,43:68-71.
[47]B. De Ketelaere, H. VanhoutteJ. De Baerdemaeker. Parameter estimation and multivariable model building for the non-destructive, on-line determination of eggshell strength[J]. Journal of sound and vibration,2003,266(3):699-709.
[48]E. Altuntas, A. Sekeroglu. Effect of egg shape index on mechanical properties of chicken eggs[J]. Journal of Food Engineering,2008,85(4):606-612.
[49]周平,蔡健荣,林颢.基于声学特性的鸡蛋蛋壳强度检测的研究[J].食品科技,2010,(002)：237-240.
[50]H. Lin, J.-w. Zhao, L. Sun, et al. Stiffness measurement of eggshell by acoustic resonance and PLS models[J]. Journal of Food Engineering,2011,103(4):351-356.
[51]C. K. Yong, Intact egg freshness quality inspection using neural networks [C], in Neural Networks,1995. Proceedings., IEEE International Conference on,1995, pp.1080-1085.
[52]K. Ku(?)hda, M. Fukaya, S. Miyoshi, et al. Nondestructive prediction method for yolk: albumen ratio in chicken eggs by computer image analysis [J]. Poultry Science, 1999,78(6):909-913.
[53]刘俭英,余佑生.鸭蛋新鲜度模型的试验研究[J].华中农业大学学报,2002,21(6)：567-569.
[54]王巧华,任奕林,文友先.基于BP神经网络的鸡蛋新鲜度无损检测方法[J].农业机械学报,2006,37(1)：104-106.
[55]岑益科,基于机器视觉的鸡蛋品质检测方法研究[D],杭州：浙江大学,2006.
[56]王巧华,文友先,林雪冬等.鸡蛋透射光图像形态特征与其新鲜度的相关关系[J][J].农业工程学报,2008,24(3)：179-183.
[57]L. Yande, Y. Yibin. Study on optical nondestructive inspection of chicken-egg freshness[J]. Proceeding of JICAST,2002,
[58]A. Berardinelli, A. Giunchi, A. Guarnieri, et al. Shell egg albumen height assessment by FT-NIR spectroscopy[J]. Transactions of the ASAE,2005,48(4):1423-1428.
[59]B. J. Kemps, F. R. Bamelis, B. De Ketelaere, et al. Visible transmission spectroscopy for the assessment of egg freshness[J]. Journal of the Science of Food and Agriculture, 2006,86(9):1399-1406.
[60]N. Abdel-Nour, M. Ngadi, S. Prasher, et al. Prediction of Egg Freshness and Albumen Quality Using Visible/Near Infrared Spectroscopy[J]. Food and Bioprocess Technology, 2011,4(5):731-736.
[61]侯卓成,杨宁,李俊英等.傅里叶变换近红外反射用于鸡蛋蛋品质的研究[J].光谱学与光谱分析,2009,(008)：2063-2066.
[62]H. Lin, J. Zhao, L. Sun, et al. Freshness measurement of eggs using near infrared (NIR) spectroscopy and multivariate data analysis[J]. Innovative Food Science & Emerging Technologies,2011,12(2):182-186.
[63]A. Brant, K. NorrisG. Chin. A spectrophotometric method for detecting blood in white-shell eggs[J]. Poultry Science,1953,32(2):357-363.
[64]Y. Usui, K. NakanoY. Motonaga, A Study of The Development Of Non-Destructive Detection System for Abnormal Eggs [C], in EFFTA 2003 Conference, Hungary,2003, pp. 5-9.
[65]臼井善彦,中野和弘(?)藤麻奈.異常鶏の非破壞検出法に関する研究(第3報)：可视分光分析にする褐色卵の血.卵検出[J].農業施設,2006,36(4)：209-214.
[1]B. Diezma-Iglesias, M. Ruiz-AltisentP. Barreiro. Detection of internal quality in seedless watermelon by acoustic impulse response[J]. Biosystems engineering,2004,88(2):221-230.
[2]C. Primo-Martin, N. Sozer, R. Hamer, et al. Effect of water activity on fracture and acoustic characteristics of a crust model[J]. Journal of Food Engineering, 2009,90(2):277-284.
[3]M. Taniwaki, T. HanadaN. Sakurai. Postharvest quality evaluation of "Fuyu" and "Taishuu" persimmons using a nondestructive vibrational method and an acoustic vibration technique[J]. Postharvest biology and technology,2009,51(1):80-85.
[4]L. Piazza, J. GigliS. Benedetti. Study of structure and flavour release relationships in low moisture bakery products by means of the acoustic-mechanical combined technique and the electronic nose[J]. Journal of Cereal Science,2008,48(2):413-419.
[5]I. Elbatawi. An acoustic impact method to detect hollow heart of potato tubers[J]. Biosystems engineering,2008,100(2):206-213.
[6]A. Baltazar, J. I. ArandaG. Gonzalez-Aguilar. Bayesian classification of ripening stages of tomato fruit using acoustic impact and colorimeter sensor data[J]. Computers and electronics in agriculture,2008,60(2):113-121.
[7]赵杰文,孙永海.现代食品检测技术[M].中国轻工业出版社,2008.
[8]http://www.vishay.com/.
[9]http://www.ti.com.cn/cn/lit/ds/symlink/ina217.pdf.
[10]顾卫钢,手把手教你学DSP[M],北京：北京航空航天大学出版社.
[11]彭启琮,张诗雅,常冉TI DSP集成化开发环境(CCS)使用手册[M].清华大学出版社有限公司,2005.
[1]Y. Cai, J. Yuan, X. Ma, et al., Low Power Embedded Speech Enhancement System Based on a Fixed-Point DSP [C], in Dependable, Autonomic and Secure Computing,2009. DASC'09. Eighth IEEE International Conference on,2009, pp.132-136.
[2]Z. Xiaochuan, L. QingshengH. Baoling, Signal processing of biologically inspired hexapod robot's navigation system based on GPS/INS [C], in Industrial Electronics and Applications,2009. ICIEA2009.4th IEEE Conference on,2009, pp.1139-1144.
[3]W. Li, J.-L. YanH.-L. Zhao. Implementation of Time Delay Estimation Algorithm of Ultrasonic Flowmeter in Coal Mine Based on Fixed Point DSP[J]. Meitan Jishu/Coal Technology,2012,31(1):175-176.
[4]J. Gao, L. WangJ. M. Ma. A Multi-Channel Audio Signal Processing Platform Based on DSP[J]. Applied Mechanics and Materials,2012,121:1858-1862.
[5]陈泰红,任胜杰,魏宇.手把手教你学DSP：基于TMS320C55x[M1.北京航空航天大学出版社,2011.
[6]Texas Instruments corporation, TLV320AIC23B Data Manual[EB/OL]. www.ti.com2004.2
[7]蔡志明,卢传富,李立夏.精通Qt4编程[M].电子工业出版社,2008.
[1]艾海舟,武勃,图像处理,分析与机器视觉[M],北京：人民邮电出版社,2003.
[2]姜松,漆虹,五国江等.禽蛋基本特性参数分析与试验[J].农业机械学报,2012,43(004)：137-142.
[3]F. Ayupov. On the egg mathematical model[J]. Advanced Scieiztific-Industrial Experience in Poultry Breeding. Express Information,1976,9:14-16.
[4]C. Steger, M. UlrichC. Wiedemann,机器视觉算法与应用[M],北京：清华大学出版社,2008.
[5]V. Narushin. Egg geometry calculation using the measurements of length and breadth[J]. Poultry Science,2005,84(3):482-484.
[6]R. C. Gonzalez, R. E. Woods数字图像处理.阮秋琦,阮宇智,等译[J].数字图像处理[M](第二版),2003：500-505.
[1]孙廷耀.关于如何选用称重传感器的几点建议[J].计是不是技术,2001,(001)：53-54.
[2]刘迎春,叶湘滨.传感器原理,设计与应用[D].国防科技大学出版社,2006.
[3]王化祥,张淑英.传感器原理及应用[D].天津大学出版社,1999.
[4]张国雄,电子科技金篆芷.测控电路[D].机械工业出版社,2001.
[5]B. BIRD. VEHICLE APPLICATION GUIDE[J]. URO(?),2003:8.
[6]张桐,陈国顺王正林.精通LabVIEW程序设计[D].电子工业出版社,2008.
[7]A. Hidalgo, M. Rossi, F. Clerici, et al. A market study on the quality characteristics of eggs from different housing systems[J]. Food Chemistry,2008,106(3):1031-1038.
[8]R. Dutta, E. L. Hines, J. W. Gardner, et al. Non-destructive egg freshness determination:an electronic nose based approach[J]. Measurement Science and Technology,2003,14(2):190.
[1]纪少波,程勇,唐娟等.缸盖表面振动速度预处理方法及应用研究[J].内燃机工程,2012,33(003)：40-44.
[2]虞海强,基于振动分析法的变压器状态检测研究[D],西华大学,2012.
[3]周建平,林爱弟,吴劲晖等.电力变压器振动监测的测点位置选择[J].电子测量与仪器学报,2012,26(12)：1100-1107.
[4]胡波,振动与噪声分析在变速箱在线质量检测中的应用与研究[D],合肥工业大学,2012.
[5]H. Abdi, L. J. Williams. Principal component analysis[J]. Wiley Interdisciplinary Reviews: Computational Statistics,2010,2(4):433-459.
[6]P. J. Shaw. Multivariate statistics for the environmental sciences[D]. Arnold London,2003.
[7]边肇祺,张学工.模式识别[M].清华大学出版社,2000.
[8]H. Yu, J. Yang. A direct LDA algorithm for high-dimensional data-with application to face recognition[J]. Pattern recognition,2001,34(10):2067.
[9]J.-H. Chen. KNN based knowledge-sharing model for severe change order disputes in construction[J]. Automation in Construction,2008,17(6):773-779.
[10]N. Caglar, M. Elmas, Z. D. Yaman, et al. Neural networks in 3-dimensional dynamic analysis of reinforced concrete buildings[J]. Construction and Building Materials, 2008,22(5):788-800.
[11]王碧泉,陈祖荫.模式识别：理论,方法和应用[M].地震出版社,1989.
[12]H. Kim, B. L. DrakeH. Park. Multiclass classifiers based on dimension reduction with generalized LDA[J]. Pattern recognition,2007,40(11):2939-2945.
[13]A. Doudou. Estimation of turbulence spectra in flows of hard conditions sensed with LDA[J]. Measurement,2007,40(1):75-92.
[14]W. Wu, D. Massart. Regularised nearest neighbour classification method for pattern recognition of near infrared spectra[J]. Analytica chimica acta,1997,349(1):253-261.
[15]T. Koukal, F. SuppanW. Schneider. The impact of relative radiometric calibration on the accuracy of kNN-predictions of forest attributes[J]. Remote Sensing of Environment, 2007,110(4):431-437.
[16]C.-M. Liu, S.-Y. Fu. Effective protocols for kNN search on broadcast multi-dimensional index trees[J]. Information Systems,2008,33(1):18-35.
[17]罗一帆,郭振飞,朱振宇等.近红外光谱测定茶叶中茶多酚和茶多糖的人工神经网络模型研究[J].光谱学与光谱分析,2005,25(008)：1230-1233.
[18]任瑞雪,苟玉彗.人工神经网络—近红外光谱法用于粉末药品扑热息痛的非破坏定量分析[J].光谱学与光谱分析,2001,21(004)：521-523.
[19]K. Yetilmezsoy, S. Demirel. Artificial neural network (ANN) approach for modeling of Pb (Ⅱ) adsorption from aqueous solution by Antep pistachio (Pistacia Vera L.) shells[J]. Journal of Hazardous Materials,2008,153(3):1288-1300.
[20]M. O'farrell, E. Lewis, C. Flanagan, et al. Combining principal component analysis with an artificial neural network to perform online quality assessment of food as it cooks in a large-scale industrial oven[J]. Sensors and Actuators B:Chemical,2005,107(1):104-112.
[21]戴葵,神经网络设计[M],北京：机械工业出版社,2002.