CLASSIFICATION OF FAULT SIGNALS BASED ON DCT AND DEEP LEARNING

Haitham  Al Akabi; Tawfiq  Al-assadi

doi:10.30572/2018/KJE/160413

Authors

Haitham Al Akabi Master’s Degree Student in College of Information Technology, University of Babylon
Tawfiq Al-assadi Assistant Prof. at College of Information Technology, University of Babylon, Iraq

DOI:

https://doi.org/10.30572/2018/KJE/160413

Keywords:

DCT, DL, features extract, gray image, CNN, induction motor

Abstract

Industrial sound analysis plays a key role in machine monitoring systems, as experienced machine operators can hear and detect many rotary machine faults. However, due to factories having complicated noise environments, they are challenging to detect. Detecting rotary motor faults is important to reduce repair costs, avoid unexpected machine downtime, and stop production. One of the primary approaches for fault diagnosis involves deep learning (DL) techniques that classify the fault sound produced by motors. This research proposes a method to detect and classify faults using a Convolution Neural Network (CNN) based on converting sound to a gray image. First, converts the 1-D time domain vibration sound into a 2-D gray image depending on Discrete Cosine Transform (DCT) to extract feature patterns by dividing the 1-D matrix of coefficients resulting from the DCT after normalization into equal parts and storing them in a column followed by a column in a 2-D matrix whose dimensions have been determined. Second, these gray images are utilized as input for CNN, which performs multi-classification in a supervised learning framework. (IDMT-ISA Electric Engine) dataset is used to demonstrate the effectiveness of the suggested approach. The results show high classification Accuracy 99.7%, Precision 99.6%, Recall 99.6%, and F1-Score 100% with effectiveness in diagnosing faults under various noise conditions associated with sound recording. This study could have an impact in the field of sounds analysis

Downloads

Download data is not yet available.

References

Ahmad, Z., Hasan, M.J. and Kim, J.M. (2022) ‘Transfer Learning with 2D Vibration Images for Fault Diagnosis of Bearings Under Variable Speed’, in proceedings of 21st International conference on intelligent systems design and applications (ISDA 2021). Springer Science and Business Media Deutschland GmbH, pp. 154–164. Available at: https://doi.org/10.1007/978-3-030-96308-8_14.

Ahmed, H.O.A. and Nandi, A.K. (2021) ‘Connected Components-based Colour Image Representations of Vibrations for a Two-stage Fault Diagnosis of Roller Bearings Using Convolutional Neural Networks’, Chinese Journal of Mechanical Engineering (English Edition), 34(1), pp. 1–21. Available at: https://doi.org/10.1186/s10033-021-00553-8.

Alaa, R., Hussein, E.A. and Al-Libawy, H. (2024) ‘OBJECT DETECTION ALGORITHMS IMPLEMENTATION ON EMBEDDED DEVICES: CHALLENGES AND SUGGESTED SOLUTIONS’, Kufa Journal of Engineering, 15(3), pp. 148–169. Available at: https://doi.org/10.30572/2018/KJE/150309.

Betta, G. et al. (2002) ‘A DSP-based FFT-analyzer for the fault diagnosis of rotating machine based on vibration analysis’, IEEE Transactions on Instrumentation and Measurement, 51(6), pp. 1316–1322. Available at: https://doi.org/10.1109/TIM.2002.807987.

Di, T., Magistrale, L. and Gaizo, D. Del (2023) Enhancing Drone Spectra Classifi-cation: A Study on Data-Adaptive Pre-processing and Efficient Hard-ware Deployment, IEEE (Institute of Electrical and Electronics Engineers). Politecnico.

Freire Moraes, G.H., Ribeiro Junior, R.F. and Gomes, G.F. (2024) ‘Fault Classification in Diesel Engines Based on Time-Domain Responses through Signal Processing and Convolutional Neural Network’, Vibration, 7(4), pp. 863–893. Available at: https://doi.org/10.3390/vibration7040046.

Grollmisch, S., Abeßer, J. and Liebetrau, J. (2019) ‘Sounding Industry: Challenges and Datasets for Industrial Sound Analysis’, 2019 27th European Signal Processing Conference (EUSIPCO), pp. 1–5. Available at: https://doi.org/978-9-0827-9703-9/19/$31.00.

Han, S., Oh, S. and Jeong, J. (2021) ‘Bearing Fault Diagnosis Based on Multiscale Convolutional Neural Network Using Data Augmentation’, Journal of Sensors, 2021. Available at: https://doi.org/10.1155/2021/6699637.

Hao Yijia et al. (2020) ‘Multi-Scale CNN based on Attention Mechanism for Rolling Bearing Fault Diagnosis’, in the 9th Asia-Pacific International Symposium on Advanced Reliability and Maintenance Modeling (APARM). IEEE, pp. 1–5. Available at: https://doi.org/978-1-7281-7102-9/20/$31.00©2020IEEE.

He, J., Lv, Z. and Chen, X. (2023) ‘Rolling bearing fault diagnosis method based on 2D grayscale images and Wasserstein Generative Adversarial Nets under unbalanced sample condition’, Complex Engineering Systems, 3(3), pp. 1–15. Available at: https://doi.org/10.20517/ces.2023.20.

Hinton, G.E. et al. (2012) ‘Improving neural networks by preventing co-adaptation of feature detectors’, Neural Information Processing Systems (NeurIPS), pp. 1–5. Available at: http://www.utstat.toronto.edu/.

Hoang, D.T. and Kang, H.J. (2019) ‘Rolling element bearing fault diagnosis using convolutional neural network and vibration image’, Cognitive Systems Research, 53, pp. 1–9. Available at: https://doi.org/10.1016/j.cogsys.2018.03.002.

Ioffe, S. (2017) ‘Batch Renormalization: Towards Reducing Minibatch Dependence in Batch-Normalized Models’, in 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA, pp. 1–9.

Islam, R., Uddin, J. and Kim, J.-M. (2018) ‘Texture analysis based feature extraction using Gabor filter and SVD for reliable fault diagnosis of an induction motor Texture analysis based feature extraction using Gabor filter and SVD 21’, Int. J. Information Technology and Management, 17(2), pp. 20–32.

Jaber, A. (2011) ‘‫LOW COMPLEXITY EMBEDDED IMAGE COMPRESSION ALGORITHM USING SUBBAND CODING OF THE DCT COEFFICIENTS‬’, Kufa Journal of Engineering, 3(2), pp. 1–16.‬‬‬

Jiang, H., Lan, B. and Li, H. (2020) ‘ABNORMAL SOUND DETECTION SYSTEM BASED ON AUTOENCODER Technical Report’, Detection and Classification of Acoustic Scenes and Events, pp. 1–4.

Kang, M. and Kim, J.M. (2013) ‘Singular value decomposition based feature extraction approaches for classifying faults of induction motors’, Mechanical Systems and Signal Processing, 41(1–2), pp. 348–356. Available at: https://doi.org/10.1016/j.ymssp.2013.08.002.

Lam, E.Y. and Goodman, J.W. (2000) ‘A mathematical analysis of the DCT coefficient distributions for images’, IEEE Transactions on Image Processing, 9(10), pp. 1661–1666. Available at: https://doi.org/10.1109/83.869177.

Lei, Y. et al. (2016) ‘An Intelligent Fault Diagnosis Method Using Unsupervised Feature Learning Towards Mechanical Big Data’, IEEE Transactions on Industrial Electronics, 63(5), pp. 3137–3147. Available at: https://doi.org/10.1109/TIE.2016.2519325.

Li, X., Zhang, W. and Ding, Q. (2019) ‘Understanding and improving deep learning-based rolling bearing fault diagnosis with attention mechanism’, Signal Processing, 161, pp. 136–154. Available at: https://doi.org/10.1016/j.sigpro.2019.03.019.

Liu, H., Li, L. and Ma, J. (2016) ‘Rolling Bearing Fault Diagnosis Based on STFT-Deep Learning and Sound Signals’, Shock and Vibration, 2016, pp. 1–13. Available at: https://doi.org/10.1155/2016/6127479.

Ma, P. et al. (2019) ‘A novel bearing fault diagnosis method based on 2D image representation and transfer learning-convolutional neural network’, Measurement Science and Technology, 30(5), pp. 1–23. Available at: https://doi.org/10.1088/1361-6501/ab0793.

Manhertz, G. and Bereczky, A. (2021) ‘STFT spectrogram based hybrid evaluation method for rotating machine transient vibration analysis’, Mechanical Systems and Signal Processing, 154, pp. 1–16. Available at: https://doi.org/10.1016/j.ymssp.2020.107583.

Misra, S. et al. (2022) ‘Fault Detection in Induction Motor Using Time Domain and Spectral Imaging-Based Transfer Learning Approach on Vibration Data’, Sensors, 22(21), pp. 1–16. Available at: https://doi.org/10.3390/s22218210.

Mohammed, H.A., Kareem, S.W. and Mohammed, A.S. (2022) ‘A COMPARATIVE EVALUATION OF DEEP LEARNING METHODS IN DIGITAL IMAGE CLASSIFICATION’, Kufa Journal of Engineering, 13(4), pp. 53–69. Available at: https://doi.org/10.30572/2018/KJE/130405.

Mukherjee, I. and Tallur, S. (2021) ‘Light-Weight CNN Enabled Edge-Based Framework for Machine Health Diagnosis’, IEEE Access, 9, pp. 84375–84386. Available at: https://doi.org/10.1109/ACCESS.2021.3088237.

Nguyen, D. et al. (2013) ‘Highly reliable state monitoring system for induction motors using dominant features in a two-dimension vibration signal’, New Review of Hypermedia and Multimedia, 19(3–4), pp. 248–258. Available at: https://doi.org/10.1080/13614568.2013.832407.

Ribaric, S. and Fratric, I. (2011) ‘Experimental Evaluation of Matching-Score Normalization Techniques on Different Multimodal Biometric Systems’, IEEE International Conference on Biometrics: Theory, Applications and Systems (BTAS), pp. 1–4.

Saranya, C. and Manikandan, G. (2013) ‘A Study on Normalization Techniques for Privacy Preserving Data Mining’, International Journal of Engineering and Technology (IJET), 5, pp. 2701–2704.

Sivalingan, H. (2024) ‘CLOUD-SMART SURVEILLANCE: ENHANCING ANOMALY DETECTION IN VIDEO STREAMS WITH DF-CONVLSTM-BASED VAE-GAN’, Kufa Journal of Engineering, 15(4), pp. 125–140. Available at: https://doi.org/10.30572/2018/KJE/150409.

Strantzalis, K. et al. (2022) ‘Operational State Recognition of a DC Motor Using Edge Artificial Intelligence’, Sensors, 22(24). Available at: https://doi.org/10.3390/s22249658.

Tang, H. et al. (2021) ‘A novel intelligent fault diagnosis method for rolling bearings based on wasserstein generative adversarial network and convolutional neural network under unbalanced dataset’, Sensors, 21(20), pp. 1–24. Available at: https://doi.org/10.3390/s21206754.

Tran, V.T. et al. (2013) ‘An application to transient current signal based induction motor fault diagnosis of Fourier-Bessel expansion and simplified fuzzy ARTMAP’, Expert Systems with Applications, 40(13), pp. 5372–5384. Available at: https://doi.org/10.1016/j.eswa.2013.03.040.

Uddin, J. et al. (2014) ‘Reliable fault classification of induction motors using texture feature extraction and a multiclass support vector machine’, Mathematical Problems in Engineering, 2014, pp. 1–10. Available at: https://doi.org/10.1155/2014/814593.

Wang, X., Mao, D. and Li, X. (2021) ‘Bearing fault diagnosis based on vibro-acoustic data fusion and 1D-CNN network’, Measurement, 173, pp. 1–13. Available at: https://doi.org/10.1016/j.measurement.2020.108518.

Xu, M. et al. (2022) ‘Bearing-Fault Diagnosis with Signal-to-RGB Image Mapping and Multichannel Multiscale Convolutional Neural Network’, Entropy, 24(11), pp. 1–20. Available at: https://doi.org/10.3390/e24111569.

Zhang, Z., Wang, Y. and Wang, K. (2012) ‘Fault diagnosis and prognosis using wavelet packet decomposition, Fourier transform and artificial neural network’, Journal of Intelligent Manufacturing, 24(6), pp. 1–15. Available at: https://doi.org/10.1007/s10845-012-0657-2.

Zhao, H., Sun, S. and Jin, B. (2018) ‘Sequential Fault Diagnosis Based on LSTM Neural Network’, IEEE Access, 6, pp. 12929–12939. Available at: https://doi.org/10.1109/ACCESS.2018.2794765.

Zhou, F. et al. (2021) ‘A sparse denoising deep neural network for improving fault diagnosis performance’, Signal, Image and Video Processing, 15(8), pp. 1889–1898. Available at: https://doi.org/10.1007/s11760-021-01939-w.