پیوندهای مفید
آمار
| تعداد نشریات | 7 |
| تعداد شماره‌ها | 409 |
| تعداد مقالات | 5,454 |
| تعداد مشاهده مقاله | 5,823,802 |
| تعداد دریافت فایل اصل مقاله | 5,201,353 |
بررسی کاهش نویز در تحلیل سیگنال در عیب‌یابی ماشین‌های دوار توسط شبکه عصبی | ||
| نشریه مهندسی مکانیک امیرکبیر | ||
| دوره 55، شماره 12، اسفند 1402، صفحه 1423-1442 اصل مقاله (2.46 M) | ||
| نوع مقاله: مقاله پژوهشی | ||
| شناسه دیجیتال (DOI): 10.22060/mej.2024.22469.7629 | ||
| نویسندگان | ||
| حامد پورهاشم؛ علی جمالی* ؛ نادر نریمان زاده؛ علی چائی بخش | ||
| دانشکده مهندسی مکانیک، دانشگاه گیلان، گیلان، ایران | ||
| چکیده | ||
| عیب‌یابی سیستم‌های مکانیکی برای عملکرد بهتر سیستم و همچنین محافظت از آن، دارای اهمیت ویژه‌ای می‌باشد. در این پژوهش از یک سیستم آزمایشگاهی ماشین دوار برای تولید سیگنال استفاده شده است. داده‌های بدست آمده در فرآیند پیش پردازش قرار می‌گیرند. در این مقاله برای بهبود عملکرد تحلیل سیگنال روش ترکیبی تحلیل توسط ویژگی‌های سیگنال و فیلتر کالمن پیشنهاد می‌شود. ابتدا برای کاهش نویز سیگنال‌ها از فیلتر کالمن استفاده می‌شود. و در ادامه برای پیش پردازش سیگنال ویژگی‌های سیگنال در حوزه زمان و حوزه فرکانس پیشنهاد می‌شود که از آن به عنوان پیش‌پردازش یک بعدی سیگنال استفاده شده است. در ادامه برای تحلیل ویژگی‌های بدست آمده از کلاس‌بندهای ماشین بردار پشتیبان، شبکه عصبی پرسپترون چند لایه و شبکه عصبی پیچشی استفاده شده است. برای بررسی نتایج داده‌ها به دسته داده‌های آموزشی و داده‌های صحت سنجی تقسیم‌بندی می‌شود. نتایج دقت برای داده‌های صحت سنجی در روش‌های مختلف مورد بررسی قرار می‌گیرد. نتایج حاکی از عملکرد بهتر شبکه عصبی پیچشی الکس‌نت در حضور فرآیند کاهش نویز با فیلتر کالمن می‌باشد. این شبکه به طور میانگین به دقت 96/1 درصد برای داده‌های صحت سنجی رسیده است که نسبت به سایر کلاس‌بندها و همچنین نسبت به عیب‌یابی بدون کاهش نویز، دقت آن بهبود یافته است. | ||
| کلیدواژه‌ها | ||
| عیب‌یابی؛ کاهش نویز؛ فیلتر کالمن؛ شبکه عصبی؛ پردازش سیگنال | ||
| عنوان مقاله [English] | ||
| Investigating Noise Reduction in Signal Analysis in Rotary Machines Fault Diagnosing by Neural Network | ||
| نویسندگان [English] | ||
| Hamed Pourhashem؛ Ali Jamali؛ Nader Nariman-zadeh؛ Ali Chaibakhsh | ||
| Faculty of Mechanical Engineering, Guilan University, Rasht, Iran | ||
| چکیده [English] | ||
| Fault diagnosis of mechanical systems is of special importance for better system performance as well as its protection. In this work, a rotary machine laboratory system is used to generate signals. The obtained data are placed in the pre-processing process. In this article, to improve the performance of signal analysis, the combined analysis methods using signal features and Kalman filter are proposed. First, the Kalman filter is used to reduce the signal noise. In the following, for signal pre-processing, the features of the signal in the time domain and frequency domain are suggested, which have been used as one-dimensional signal pre-processing. In the following, several neural networks such as support vector machine, multilayer perceptron, and convolutional neural networks have been used to analyze the obtained features. To check the results, the data is divided into training data and validation data. Accuracy results for validation data are examined in different methods. The results indicate the better performance of the AlexNet convolutional neural network in the presence of the Kalman filter noise reduction. In this case, this network has reached an average of 96.1% accuracy for validation data, which has been improved compared to other classifiers and fault diagnosis without noise reduction. | ||
| کلیدواژه‌ها [English] | ||
| Fault diagnosis, Noise Reduction, Kalman Filter, Neural Network, Signal Processing | ||
| مراجع | ||
|
[1] R.F. Ribeiro Junior, I.A. dos Santos Areias, M.M. Campos, C.E. Teixeira, L.E.B. da Silva, G.F. Gomes, Fault detection and diagnosis in electric motors using convolution neural network and short-time fourier transform, Journal of Vibration Engineering & Technologies, (2022) 1-12. [2] M. Zakizadeh, A. Jamali, M. Rafeeyan, A. Chaibakhsh, Monitoring and Troubleshooting Alstom Locomotive Blowers using Vibration Analysis and Support Vector Machine, Amirkabir Journal of Science & Research (Mechanical Engineering), 54(8) (2022) 1833-1850 (in Persian). [3] V.H. Farahani, Applying the envelope curve of vibration signals in condition monitoring and rolling bearings fault detection, Journal of Vibration & Sound, 2(3) (2013) 11-20 (in Persian). [4] M. Shekarzadeh, M. Sadegh Alayy, Centrifugal pump bearings Fault diagnosis using the combination of independent component analysis methods and particle swarm optimization, Journal of New Applied and Computational Findings in Mechanical Systems, 3(1) (2023) 53-61 (in Persian). [5] M. Kamari, G. Payeganeh, K.N. Khajavi, Implementation of Neuro– Fuzzy and Multi-Layer Perceptron System Intelligent Techniques for Main Fault Diagnosis of Rotating Machinery, Amirkabir Journal of Science & Research (Mechanical Engineering), 45(2) (2013) 105-118 (in Persian). [6] M.A. Sattari, G.H. Roshani, R. Hanus, E. Nazemi, Applicability of time-domain feature extraction methods and artificial intelligence in two-phase flow meters based on gamma-ray absorption technique, Measurement, 168 (2021) 108474. [7] X. Wang, D. Mao, X. Li, Bearing fault diagnosis based on vibro-acoustic data fusion and 1D-CNN network, Measurement, 173 (2021) 108518. [8] R.-P. Nikula, K. Karioja, M. Pylvänäinen, K. Leiviskä, Automation of low-speed bearing fault diagnosis based on autocorrelation of time domain features, Mechanical Systems and Signal Processing, 138 (2020) 106572. [9] A. Kafeel, S. Aziz, M. Awais, M.A. Khan, K. Afaq, S.A. Idris, H. Alshazly, S.M. Mostafa, An Expert System for Rotating Machine Fault Detection Using Vibration Signal Analysis, Sensors, 21(22) (2021) 7587. [10] S. Nezamivand Chegini, Z. Karimi Rastehkenari, A. Bagheri, B. Ahmadi, Denoising vibration signals of rotating machines using probability density function, similarity measure and improved thresholding function, Amirkabir Journal of Science & Research (Mechanical Engineering), 53(Number 4 (Special Issue)) (2021) 2493-2512 (in Persian). [11] S. Nezamivand Chegini, F. Zarif, A. Bagheri, A. Tavoli, Vibration signals denoise of rotating machines using experimental wavelet transform and common thresholding methods, Journal of Solid and Fluid Mechanics, 9(1) (2019) 111-124 (in Persian). [12] V. Gupta, M. Mittal, Arrhythmia detection in ECG signal using fractional wavelet transform with principal component analysis, Journal of The Institution of Engineers (India): Series B, 101(5) (2020) 451-461. [13] H. Ehya, A. Nysveen, T.N. Skreien, Performance evaluation of signal processing tools used for fault detection of hydrogenerators operating in noisy environments, IEEE Transactions on Industry Applications, 57(4) (2021) 3654-3665. [14] Y. Gao, Y. Gao, B. Liu, Y. Jiang, Enhanced fault detection and exclusion based on Kalman filter with colored measurement noise and application to RTK, GPS Solutions, 25 (2021) 1-13. [15] S. Mokhtari, K.K. Yen, A novel bilateral fuzzy adaptive unscented kalman filter and its implementation to nonlinear systems with additive noise, in: 2020 IEEE Industry Applications Society Annual Meeting, IEEE, 2020, pp. 1-6. [16] P. Talwar, K. Cecil, Adaptive Filter and EMD Based De-Noising Method of ECG Signals: A Review, American Journal of Multidisciplinary Research & Development (AJMRD), 5(03) (2023) 09-14. [17] F. Honarmand-Shazilehei, N. Pariz, M.B.N. Sistani, Sensor fault detection in a class of nonlinear systems using modal Kalman filter, ISA transactions, 107 (2020) 214-223. [18] S. Cho, M. Choi, Z. Gao, T. Moan, Fault detection and diagnosis of a blade pitch system in a floating wind turbine based on Kalman filters and artificial neural networks, Renewable Energy, 169 (2021) 1-13. [19] Y. Yao, J. Wang, M. Xie, Adaptive residual CNN-based fault detection and diagnosis system of small modular reactors, Applied Soft Computing, 114 (2022) 108064. [20] M. Yakoubi, R. Hamdi, M.B. Salah, EEG enhancement using extended Kalman filter to train multi-layer perceptron, Biomedical Engineering: Applications, Basis and Communications, 31(01) (2019) 1950005. [21] M. Singh, A.G. Shaik, Incipient fault detection in stator windings of an induction motor using stockwell transform and SVM, IEEE Transactions on Instrumentation and Measurement, 69(12) (2020) 9496-9504. [22] S. Chatterjee, R.K. Gatla, P. Sinha, C. Jena, S. Kundu, B. Panda, L. Nanda, A. Pradhan, Fault detection of a Li-ion battery using SVM based machine learning and unscented Kalman filter, Materials Today: Proceedings, 74 (2023) 703-707. [23] Z. Zemali, L. Cherroun, N. Hadroug, A. Hafaifa, A. Iratni, O.S. Alshammari, I. Colak, Robust intelligent fault diagnosis strategy using Kalman observers and neuro-fuzzy systems for a wind turbine benchmark, Renewable Energy, 205 (2023) 873-898. [24] M. Khodarahmi, V. Maihami, A review on Kalman filter models, Archives of Computational Methods in Engineering, 30(1) (2023) 727-747. [25] R.I. Alfian, A. Ma'arif, S. Sunardi, Noise reduction in the accelerometer and gyroscope sensor with the Kalman filter algorithm, Journal of Robotics and Control (JRC), 2(3) (2021) 180-189. [26] F. Li, Z. Luo, K. Bai, M. Yin, D. Zou, W. Wang, X. Wang, W. Tan, Q. Sui, Z. Li, Noise shaping enhanced DMT signal transmission utilizing low-resolution DAC, IEEE Photonics Journal, 13(6) (2021) 1-7. [27] S.K. Mishra, M. Gupta, D.K. Upadhyay, Active realization of fractional order Butterworth lowpass filter using DVCC, Journal of King Saud University-Engineering Sciences, 32(2) (2020) 158-165. [28] I.M. Khairuddin, S.N. Sidek, A.P.A. Majeed, M.A.M. Razman, A.A. Puzi, H.M. Yusof, The classification of movement intention through machine learning models: the identification of significant time-domain EMG features, PeerJ Computer Science, 7 (2021) e379. [29] K. Zhang, J. Chen, T. Zhang, Z. Zhou, A compact convolutional neural network augmented with multiscale feature extraction of acquired monitoring data for mechanical intelligent fault diagnosis, Journal of Manufacturing Systems, 55 (2020) 273-284. [30] J.J. Saucedo-Dorantes, A.Y. Jaen-Cuellar, M. Delgado-Prieto, R. de Jesus Romero-Troncoso, R.A. Osornio-Rios, Condition monitoring strategy based on an optimized selection of high-dimensional set of hybrid features to diagnose and detect multiple and combined faults in an induction motor, Measurement, 178 (2021) 109404. [31] A.F. Khalil, S. Rostam, Machine Learning-based Predictive Maintenance for Fault Detection in Rotating Machinery: A Case Study, Engineering, Technology & Applied Science Research, 14(2) (2024) 13181-13189. | ||
|
آمار تعداد مشاهده مقاله: 445 تعداد دریافت فایل اصل مقاله: 511 |
||