تشخیص عیوب یاتاقان مبتنی بر تحلیل تصاویر ارتعاشی به روش توصیفگر آرکم سیفت
محورهای موضوعی : پردازش تصویر و ویدئو
زهره هاشم پور
1
(گروه مهندسی برق، واحد شیراز، دانشگاه آزاد اسلامی، شیراز، ایران)
حامد آگاهی
2
(گروه مهندسی برق، واحد شیراز، دانشگاه آزاد اسلامی، شیراز، ایران)
آذر محمودزاده
3
(گروه مهندسی برق، واحد شیراز، دانشگاه آزاد اسلامی، شیراز، ایران)
کلید واژه: تبدیل سیگنال به تصویر, روش آرکم سیفت, تشخیص عیوب یاتاقان, تجزیه و تحلیل موئلفه اصلی غیر خطی,
چکیده مقاله :
تشخیص عیوب یاتاقان یکی از وظایف اساسی در پایش سلامت ماشین است، زیرا یاتاقان ها اجزای حیاتی ماشین های دوار هستند. این مقاله یک روش جدید را برای تشخیص عیوب در یاتاقان‌ها بر اساس ترکیبی از الگوریتم‌های استخراج ویژگی پیشنهاد می‌کند که در آن از سیگنال دو بعدی استفاده می‌شود. متفاوت از سایر روش‌های کلاسیک پردازش سیگنال یک بعدی، روش پیشنهادی این مقاله، سیگنال‌های ارتعاشی یک بعدی را به سیگنال دو بعدی (تصویر) تبدیل می‌کند، سپس از روش‌های پردازش تصویر برای تجزیه و تحلیل سیگنال تصویر استفاده می‌شود تا به هدف طبقه‌بندی عیوب رخ داده در یاتاقان برسد. تصاویر تبدیل شده از سیگنال های ارتعاشی اغلب ویژگی های بافت خاصی دارند و بافت هر دسته معیوب متفاوت است. علاوه بر این، هر توصیفگر ویژگی های فضایی را استخراج می کند. برخی از ویژگی ها ضعیف و برخی دیگر قوی هستند. در این مقاله روش حذف نقاط کلیدی اضافی سیفت (آرکم سیفت) استفاده شده است. علاوه بر این، برای هر توصیفگر، بهترین ویژگی ها با استفاده از روش تجزیه و تحلیل مؤلفه اصلی غیر خطی انتخاب می شوند. در نهایت، ویژگی‌های انتخاب‌شده با هم ترکیب می‌شوند و برای دستیابی به بهترین عملکرد در طبقه‌بندی چهار روش طبقه بندی اعمال شده و بعد از مقایسه بهترین روش طبقه بندی انتخاب می شود. عملکرد الگوریتم پیشنهادی بر روی مجموعه داده‌های بلبرینگ استاندارد دانشگاه کیس وسترن رزرو ارزیابی شده است. نتایج شبیه سازی نشان می دهد که روش پیشنهادی نسبت به روش های دیگر خطایابی یاتاقان های غلتشی عملکرد بهتری دارد.
Diagnosing bearing defects is one of the basic tasks in machine health monitoring, because bearings are critical components of rotating machines. This paper proposes a new method for detecting defects in bearings based on a combination of feature extraction algorithms in which a two-dimensional signal is used. Different from other classical one-dimensional signal processing methods, the proposed method of this paper converts one-dimensional vibration signals into two-dimensional signal (image), then image processing methods are used to analyze the image signal in order to classify the defects that have occurred. arrive at the bearing. Converted images from vibration signals often have specific texture characteristics, and the texture of each defective category is different. In addition, each descriptor extracts spatial features. Some features are weak and others are strong. In this article, the method of removing additional key points of SIFT (RKEM SIFT) is used. In addition, for each descriptor, the best features are selected using the non-linear principal component analysis method. Finally, the selected features are combined and four classification methods are applied to achieve the best classification performance and after comparison, the best classification method is selected. The performance of the proposed algorithm is evaluated on the standard bearing data set of Case Western Reserve University. The simulation results show that the proposed method performs better than other methods of fault finding of rolling bearings.
[1] J. Dybala and R. Zimroz, "Rolling bearing diagnosing method based on Empirical Mode Decomposition of machine vibration signal," Applied Acoustics, vol. 77, pp. 195-203, 2014, doi: 10.1016/j.apacoust.2013.09.001.
[2] L. Jiang, J. Xuan and T. Shi, "Feature extraction based on semi-supervised kernel Marginal Fisher analysis and its application in bearing fault diagnosis," Mechanical Systems and Signal Processing, vol. 41, no. 1-2, pp. 113-126, 2013, doi: 10.1016/j.ymssp.2013.05.017.
[3] M. R. Shahriar, T. Ahsan and U. Chong, "Fault diagnosis of induction motors utilizing local binary pattern-based texture analysis," EURASIP Journal on Image and Video Processing, vol. 2013, Article Number: 29, 2013, doi: 10.1186/1687-5281-2013-29.
[4] P. Wang, H. Yuan, H. Wang, X. Cao and X. Wang, "Rolling Element Bearing Fault Diagnosis Based on Symptom Parameter Wave of Acoustic Emission Signal," Advanced Science Letters, vol. 13, no. 1, pp. 667-670, 2012, doi: 10.1166/asl.2012.3889.
[5] H. Yuan, F. Li and H. Wang, "Using Evaluation and Leading Mechanism to Optimize Fault Diagnosis Based on Ant Algorithm," Energy Proscenia, vol. 1, no. 6, pp. 112-116, 2012, E-ISSN: 2224-2678.2015.
[6] Z. Dong, H. Wang, W. Shuming and W. Hou, "Intelligence diagnosis method based on particle swarm optimized neural network," WSEAS Transactions on Systems, vol. 12, no. 12, pp. 667-677, 2013, E-ISSN: 2224-2678.
[7] B. Li, M. -Y. Chow, Y. Tipsuwan and J. C. Hung, "Neural-network-based motor rolling bearing fault diagnosis," in IEEE Transactions on Industrial Electronics, vol. 47, no. 5, pp. 1060-1069, Oct. 2000, doi: 10.1109/41.873214.
[8] H. Wang, W. Hou, G. Tang and H. Yuan, "Fault Detection Enhancement in Rolling Element Bearings via Peak-Based Multiscale Decomposition and Envelope Demodulation," Mathematical Problems in Engineering, vol. 2014, Article Number: 329458, pp. 1-11, 2014, doi: 10.1155/2014/329458.
[9] X. Li, H. Pan, J. Cheng and J. Cheng, "Non-parallel least squares support matrix machine for rolling bearing fault diagnosis," Mechanism and Machine Theory, vol. 145, pp.1-20, 2020, doi: 10.1016/j.mechmachtheory.2019.103676.
[10] Y. Yang, C. Li , D. Jiang and K. Behdinan, "Nonlinear vibration signatures for localized fault of rolling element bearing in rotor-bearing-casing system," International Journal of Mechanical Sciences, vol. 173, p. 105449, 2020, doi: 10.1016/j.ijmecsci.2020.105449.
[11] Y. Cheng, B. Zhou, Ch. Lu and C. Yang "Fault Diagnosis for Rolling Bearings under Variable Conditions Based on Visual Cognition," Materials, vol. 10, no. 6, p. 582, 2017, doi: 10.3390/ma10060582.
[12] A. Namdar, H. Samet, M. Allahbakhshi, M. Tajdinian and T. Ghanbari, "A robust stator inter-turn fault detection in induction motor utilizing Kalman filter-based algorithm," Measurement, vol. 187, p. 110181, 2022, doi: 10.1016/j.measurement.2021.110181.
[13] L. Martinez-Herrera, R. Ferrucho-Alvarez, M. Ledesma-Carrillo, I. Mata-Chavez and M. Lopez-Ramirez, "Multiple Fault Detection in Induction Motors through Homogeneity and Kurtosis Computation," Energies, vol. 15, no. 4, p. 1541, 2022, doi: 10.3390/en15041541.
[14] L. Qian, Q. Pan, Y. Lv and X. ZhaO, "Fault Detection of Bearing by Resnet Classifier with Model-Based Data Augmentation," Machines, vol. 10, no. 7, p. 521, 2022, doi: 10.3390/machines10070521.
[15] C. Lu, Z.-Y. Wang, W.-L. Qin, and J. Ma, "Fault diagnosis of rotary machinery components using a stacked denoising autoencoder-based health state identification," Signal Process, vol. 130, pp. 377–388, Jan. 2017, doi: 10.1016/j.sigpro.2016.07.028.
[16] S. Haidong, J. Hongkai, L. Xingqiu, and W. Shuaipeng, "Intelligent fault diagnosis of rolling bearing using deep wavelet auto-encoder with extreme learning machine," Knowl.-Based Syst., vol. 140, pp. 1–14, 2018, doi: 10.1016/j.knosys.2017.10.024.
[17] R. M. Haralick, K. Shanmugam and I. Dinstein, "Textural Features for Image Classification," in IEEE Transactions on Systems, Man, and Cybernetics, vol. SMC-3, no. 6, pp. 610-621, Nov. 1973, doi: 10.1109/TSMC.1973.4309314.
[18] T.Ojala, M. Pietikainen and D. Harwood, "Performance evaluation of texture measures with classification based on Kullback discrimination of distributions," in IAPR international conference on pattern recognition, Conference A: Computer Vision & Image Processing, Israel, 9–13 October 1994, pp. 582– 585, doi: 10.1109/ICPR.1994.576366.
[19] D.G. Lowe, "Distinctive image features from scale-invariant keypoints," Int. J. Comput. Vision , vol. 60, pp. 91-110, 2004, doi: 10.1023/B:VISI.0000029664.99615.94.
[20] Z. Hossein-Nejad and M. Nasri, "RKEM: Redundant Key-point Elimination Method in Image Registration," IET Image Processing, vol. 11, pp. 273-284, 2017, doi: 10.1049/iet-ipr.2016.0440.
[21] D. Hoang and H. Kang, "Rolling element bearing fault diagnosis using convolutional neural network and vibration image," Cognitive System Research, vol. 53, pp. 42-50, 2019, doi: 10.1016/j.cogsys.2018.03.002.
[22] A. Tharwat, "principal component analysis- a tutorial," International Journal of Applied Pattern Recognition, vol. 3, no. 3, pp. 197-240, 2016, doi: 10.1504/IJAPR.2016.079733.
[23] J. Ye, "Least squares linear discriminant analysis," Machine Learning, Proceedings of the Twenty-Fourth International, vol. 227, pp. 1087-1093, June 2007, doi: 10.1145/1273496.1273633.
[24] M. Zhou and W. Yao, "Kernel Density-Based Linear Regression Estimate," Communications in Statistics Theory and Methods, vol. 42, no. 24, 2013, doi:10.1080/03610926.2011.650269.
[25] A. Widodo and S. Handoyo, "The classification performance using logistic regression and support vector machine," Journal of Theoretical and Applied Information Technology, vol. 95, no. 19, 2017.
[26] B. T. Jijo and A. M. Abdulazeez, "Classification Based on Decision Tree Algorithm for Machine Learning," Journal of Applied Science and Technology Trends, vol. 2, no. 01, 2021, doi: 10.38094/jastt20165.
[27] K. Rezaei, H. Agahi and A. Mahmoodzadeh, "A Weighted Voting Classifiers Ensemble for the Brain Tumors Classification in MR Images," IETE Journal of Research, vol. 68, no. 5, 2022, doi: 10.1080/03772063.2020.1780487.
[28] https://csegroups.case.edu/bearingdatacenter/pages/welcomecase-western-reserve-university-bearing-data center.
_||_[1] J. Dybala and R. Zimroz, "Rolling bearing diagnosing method based on Empirical Mode Decomposition of machine vibration signal," Applied Acoustics, vol. 77, pp. 195-203, 2014, doi: 10.1016/j.apacoust.2013.09.001.
[2] L. Jiang, J. Xuan and T. Shi, "Feature extraction based on semi-supervised kernel Marginal Fisher analysis and its application in bearing fault diagnosis," Mechanical Systems and Signal Processing, vol. 41, no. 1-2, pp. 113-126, 2013, doi: 10.1016/j.ymssp.2013.05.017.
[3] M. R. Shahriar, T. Ahsan and U. Chong, "Fault diagnosis of induction motors utilizing local binary pattern-based texture analysis," EURASIP Journal on Image and Video Processing, vol. 2013, Article Number: 29, 2013, doi: 10.1186/1687-5281-2013-29.
[4] P. Wang, H. Yuan, H. Wang, X. Cao and X. Wang, "Rolling Element Bearing Fault Diagnosis Based on Symptom Parameter Wave of Acoustic Emission Signal," Advanced Science Letters, vol. 13, no. 1, pp. 667-670, 2012, doi: 10.1166/asl.2012.3889.
[5] H. Yuan, F. Li and H. Wang, "Using Evaluation and Leading Mechanism to Optimize Fault Diagnosis Based on Ant Algorithm," Energy Proscenia, vol. 1, no. 6, pp. 112-116, 2012, E-ISSN: 2224-2678.2015.
[6] Z. Dong, H. Wang, W. Shuming and W. Hou, "Intelligence diagnosis method based on particle swarm optimized neural network," WSEAS Transactions on Systems, vol. 12, no. 12, pp. 667-677, 2013, E-ISSN: 2224-2678.
[7] B. Li, M. -Y. Chow, Y. Tipsuwan and J. C. Hung, "Neural-network-based motor rolling bearing fault diagnosis," in IEEE Transactions on Industrial Electronics, vol. 47, no. 5, pp. 1060-1069, Oct. 2000, doi: 10.1109/41.873214.
[8] H. Wang, W. Hou, G. Tang and H. Yuan, "Fault Detection Enhancement in Rolling Element Bearings via Peak-Based Multiscale Decomposition and Envelope Demodulation," Mathematical Problems in Engineering, vol. 2014, Article Number: 329458, pp. 1-11, 2014, doi: 10.1155/2014/329458.
[9] X. Li, H. Pan, J. Cheng and J. Cheng, "Non-parallel least squares support matrix machine for rolling bearing fault diagnosis," Mechanism and Machine Theory, vol. 145, pp.1-20, 2020, doi: 10.1016/j.mechmachtheory.2019.103676.
[10] Y. Yang, C. Li , D. Jiang and K. Behdinan, "Nonlinear vibration signatures for localized fault of rolling element bearing in rotor-bearing-casing system," International Journal of Mechanical Sciences, vol. 173, p. 105449, 2020, doi: 10.1016/j.ijmecsci.2020.105449.
[11] Y. Cheng, B. Zhou, Ch. Lu and C. Yang "Fault Diagnosis for Rolling Bearings under Variable Conditions Based on Visual Cognition," Materials, vol. 10, no. 6, p. 582, 2017, doi: 10.3390/ma10060582.
[12] A. Namdar, H. Samet, M. Allahbakhshi, M. Tajdinian and T. Ghanbari, "A robust stator inter-turn fault detection in induction motor utilizing Kalman filter-based algorithm," Measurement, vol. 187, p. 110181, 2022, doi: 10.1016/j.measurement.2021.110181.
[13] L. Martinez-Herrera, R. Ferrucho-Alvarez, M. Ledesma-Carrillo, I. Mata-Chavez and M. Lopez-Ramirez, "Multiple Fault Detection in Induction Motors through Homogeneity and Kurtosis Computation," Energies, vol. 15, no. 4, p. 1541, 2022, doi: 10.3390/en15041541.
[14] L. Qian, Q. Pan, Y. Lv and X. ZhaO, "Fault Detection of Bearing by Resnet Classifier with Model-Based Data Augmentation," Machines, vol. 10, no. 7, p. 521, 2022, doi: 10.3390/machines10070521.
[15] C. Lu, Z.-Y. Wang, W.-L. Qin, and J. Ma, "Fault diagnosis of rotary machinery components using a stacked denoising autoencoder-based health state identification," Signal Process, vol. 130, pp. 377–388, Jan. 2017, doi: 10.1016/j.sigpro.2016.07.028.
[16] S. Haidong, J. Hongkai, L. Xingqiu, and W. Shuaipeng, "Intelligent fault diagnosis of rolling bearing using deep wavelet auto-encoder with extreme learning machine," Knowl.-Based Syst., vol. 140, pp. 1–14, 2018, doi: 10.1016/j.knosys.2017.10.024.
[17] R. M. Haralick, K. Shanmugam and I. Dinstein, "Textural Features for Image Classification," in IEEE Transactions on Systems, Man, and Cybernetics, vol. SMC-3, no. 6, pp. 610-621, Nov. 1973, doi: 10.1109/TSMC.1973.4309314.
[18] T.Ojala, M. Pietikainen and D. Harwood, "Performance evaluation of texture measures with classification based on Kullback discrimination of distributions," in IAPR international conference on pattern recognition, Conference A: Computer Vision & Image Processing, Israel, 9–13 October 1994, pp. 582– 585, doi: 10.1109/ICPR.1994.576366.
[19] D.G. Lowe, "Distinctive image features from scale-invariant keypoints," Int. J. Comput. Vision , vol. 60, pp. 91-110, 2004, doi: 10.1023/B:VISI.0000029664.99615.94.
[20] Z. Hossein-Nejad and M. Nasri, "RKEM: Redundant Key-point Elimination Method in Image Registration," IET Image Processing, vol. 11, pp. 273-284, 2017, doi: 10.1049/iet-ipr.2016.0440.
[21] D. Hoang and H. Kang, "Rolling element bearing fault diagnosis using convolutional neural network and vibration image," Cognitive System Research, vol. 53, pp. 42-50, 2019, doi: 10.1016/j.cogsys.2018.03.002.
[22] A. Tharwat, "principal component analysis- a tutorial," International Journal of Applied Pattern Recognition, vol. 3, no. 3, pp. 197-240, 2016, doi: 10.1504/IJAPR.2016.079733.
[23] J. Ye, "Least squares linear discriminant analysis," Machine Learning, Proceedings of the Twenty-Fourth International, vol. 227, pp. 1087-1093, June 2007, doi: 10.1145/1273496.1273633.
[24] M. Zhou and W. Yao, "Kernel Density-Based Linear Regression Estimate," Communications in Statistics Theory and Methods, vol. 42, no. 24, 2013, doi:10.1080/03610926.2011.650269.
[25] A. Widodo and S. Handoyo, "The classification performance using logistic regression and support vector machine," Journal of Theoretical and Applied Information Technology, vol. 95, no. 19, 2017.
[26] B. T. Jijo and A. M. Abdulazeez, "Classification Based on Decision Tree Algorithm for Machine Learning," Journal of Applied Science and Technology Trends, vol. 2, no. 01, 2021, doi: 10.38094/jastt20165.
[27] K. Rezaei, H. Agahi and A. Mahmoodzadeh, "A Weighted Voting Classifiers Ensemble for the Brain Tumors Classification in MR Images," IETE Journal of Research, vol. 68, no. 5, 2022, doi: 10.1080/03772063.2020.1780487.
[28] https://csegroups.case.edu/bearingdatacenter/pages/welcomecase-western-reserve-university-bearing-data center.