可靠度評估在工程領域中扮演著至關重要的角色，不僅有助於預防設備故障，更能有效制定維護策略，確保設備長時間高效運轉。透過可靠度評估，我們能深入了解設備的性能特點，及早發現潛在問題，提前進行維修或更換，降低停機風險，提高生產效益，實現可持續運營管理。
過去需依賴專家手動選擇和提取特徵，耗費大量人力。近年來，深度學習技術的快速發展帶來新方法，如卷積神經網路（CNN）用於特徵提取，但其無法完全處理時間特徵和信號雜訊。而在過往研究中的健康指數標籤方式通常使用基於時長的線性定義方式，然而這樣的標籤與真實的衰退過程不盡符合。
本研究提出了一個新的方法架構實現健康指數的預測和產品壽命的建構，方法模型基於WaveletKernelNet、雙向閘控遞迴神經網路、多頭自注意力機制、簡化群體演算法。WKN-BiGRU-MSA用於提取產品的深層特徵並構建健康指數。簡化群體演算法是用以優化神經網路的架構，並且強化模型的泛化性。而本研究同時提出一種新型的健康指數標籤方式，引入浴缸曲線所定義的兩段健康標籤，旨在使模型預測結果與真實情況更加貼合。
本研究使用了滾動軸承公開資料集進行實驗，證實了所提方法的有效性。總體而言，本方法有助於有效提取震動型資料的深度特徵和可靠度估計。

Reliability assessment is crucial in engineering, aiding in the prevention of equipment failures and formulating maintenance strategies to ensure long-term efficient operation. It allows for a deep understanding of equipment performance, early detection of potential issues, proactive maintenance, reduced downtime, increased production efficiency, and sustainable operations.
Traditionally, feature selection and extraction were manual and labor-intensive. Recent advances in deep learning, such as Convolutional Neural Networks (CNN), have introduced new methods for feature extraction, but these cannot fully address temporal features and signal noise. Previous health index labeling methods, often based on linear definitions of usage duration, did not accurately reflect actual degradation processes.
This study introduces a new framework for health index prediction and product life construction, using WaveletKernelNet, Bidirectional Gated Recurrent Neural Network, Multi-Head Self-Attention mechanism, and Simplified Swarm Optimization algorithm. WKN-BiGRU-MSA extracts deep features and constructs health indices. The Simplified Swarm Optimization algorithm optimizes the neural network architecture, enhancing model generalization. A novel health index labeling method, incorporating a two-stage health label defined by the bathtub curve, aims to align model predictions with real-world conditions.
Experiments using a rolling bearing dataset confirmed the effectiveness of the proposed method, which effectively extracts deep features from vibration data and estimates reliability.

[1] R. K. Mobley, An introduction to predictive maintenance. Elsevier, 2002.
[2] Y. Liu, Q. Liu, C. Xie, and F. Wei, "Reliability assessment for multi-state systems with state transition dependency," Reliability Engineering & System Safety, vol. 188, pp. 276-288, 2019, doi: 10.1016/j.ress.2019.03.013.
[3] X.-Y. Li, H.-Z. Huang, Y.-F. Li, and X. Xiong, "A Markov regenerative process model for phased mission systems under internal degradation and external shocks," Reliability Engineering & System Safety, vol. 215, 2021, doi: 10.1016/j.ress.2021.107796.
[4] R. Khelif, B. Chebel-Morello, S. Malinowski, E. Laajili, F. Fnaiech, and N. Zerhouni, "Direct Remaining Useful Life Estimation Based on Support Vector Regression," IEEE Transactions on Industrial Electronics, vol. 64, no. 3, pp. 2276-2285, 2017, doi: 10.1109/tie.2016.2623260.
[5] N. Gebraeel, M. Lawley, R. Liu, and V. Parmeshwaran, "Residual Life Predictions From Vibration-Based Degradation Signals: A Neural Network Approach," IEEE Transactions on Industrial Electronics, vol. 51, no. 3, pp. 694-700, 2004, doi: 10.1109/tie.2004.824875.
[6] G. Ma, S. Xu, and C. Cheng, "Fault detection of lithium-ion battery packs with a graph-based method," Journal of Energy Storage, vol. 43, 2021, doi: 10.1016/j.est.2021.103209.
[7] B. Sun, Y. Li, Z. Wang, Y. Ren, Q. Feng, and D. Yang, "An improved inverse Gaussian process with random effects and measurement errors for RUL prediction of hydraulic piston pump," Measurement, vol. 173, 2021, doi: 10.1016/j.measurement.2020.108604.
[8] L. Wen, X. Li, L. Gao, and Y. Zhang, "A New Convolutional Neural Network-Based Data-Driven Fault Diagnosis Method," IEEE Transactions on Industrial Electronics, vol. 65, no. 7, pp. 5990-5998, 2018, doi: 10.1109/tie.2017.2774777.
[9] L. Ren, J. Dong, X. Wang, Z. Meng, L. Zhao, and M. J. Deen, "A Data-Driven Auto-CNN-LSTM Prediction Model for Lithium-Ion Battery Remaining Useful Life," IEEE Transactions on Industrial Informatics, vol. 17, no. 5, pp. 3478-3487, 2021, doi: 10.1109/tii.2020.3008223.
[10] L. Wan, K. Chen, Y. Li, Y. Wu, Z. Wang, and C. Li, "A Novel Remaining Useful Life Prediction Method Based on CEEMDAN-IFTC-PSR and Ensemble CNN/BiLSTM Model for Cutting Tool," IEEE Access, vol. 10, pp. 2182-2195, 2022, doi: 10.1109/access.2021.3140165.
[11] R. Yan, R. X. Gao, and X. Chen, "Wavelets for fault diagnosis of rotary machines: A review with applications," Signal Processing, vol. 96, pp. 1-15, 2014, doi: 10.1016/j.sigpro.2013.04.015.
[12] T. Li et al., "WaveletKernelNet: An Interpretable Deep Neural Network for Industrial Intelligent Diagnosis," IEEE Transactions on Systems, Man, and Cybernetics: Systems, vol. 52, no. 4, pp. 2302-2312, 2022, doi: 10.1109/tsmc.2020.3048950.
[13] L. Dai, J. Guo, J.-L. Wan, J. Wang, and X. Zan, "A reliability evaluation model of rolling bearings based on WKN-BiGRU and Wiener process," Reliability Engineering & System Safety, vol. 225, 2022, doi: 10.1016/j.ress.2022.108646.
[14] W.-C. Yeh, "A two-stage discrete particle swarm optimization for the problem of multiple multi-level redundancy allocation in series systems," Expert Systems with Applications, vol. 36, no. 5, pp. 9192-9200, 2009, doi: 10.1016/j.eswa.2008.12.024.
[15] W.-C. Yeh, Y.-P. Lin, Y.-C. Liang, and C.-M. Lai, "Convolution neural network hyperparameter optimization using simplified swarm optimization," arXiv preprint arXiv:2103.03995, 2021.
[16] P. W. Kalgren, C. S. Byington, M. J. Roemer, and M. J. Watson, "Defining PHM, a lexical evolution of maintenance and logistics," in 2006 IEEE autotestcon, 2006: IEEE, pp. 353-358.
[17] D. Wang, K.-L. Tsui, and Q. Miao, "Prognostics and health management: A review of vibration based bearing and gear health indicators," Ieee Access, vol. 6, pp. 665-676, 2017.
[18] M. Tahan, E. Tsoutsanis, M. Muhammad, and Z. A. Karim, "Performance-based health monitoring, diagnostics and prognostics for condition-based maintenance of gas turbines: A review," Applied energy, vol. 198, pp. 122-144, 2017.
[19] Y. Lei, N. Li, L. Guo, N. Li, T. Yan, and J. Lin, "Machinery health prognostics: A systematic review from data acquisition to RUL prediction," Mechanical systems and signal processing, vol. 104, pp. 799-834, 2018.
[20] S. T. Kandukuri, A. Klausen, H. R. Karimi, and K. G. Robbersmyr, "A review of diagnostics and prognostics of low-speed machinery towards wind turbine farm-level health management," Renewable and Sustainable Energy Reviews, vol. 53, pp. 697-708, 2016.
[21] N. M. Vichare, P. Rodgers, and M. G. Pecht, "Methods for Binning and Density Estimation of Load Parameters for Prognostic Health Monitoring," International Journal of Performability Engineering, vol. 2, no. 2, p. 149, 2006.
[22] S. Das, R. Hall, S. Herzog, G. Harrison, M. Bodkin, and L. Martin, "Essential steps in prognostic health management," in 2011 IEEE Conference on Prognostics and Health Management, 2011: IEEE, pp. 1-9.
[23] L. I. Rudin, S. Osher, and E. Fatemi, "Nonlinear total variation based noise removal algorithms," Physica D: nonlinear phenomena, vol. 60, no. 1-4, pp. 259-268, 1992.
[24] G. Chen, W. Xie, and Y. Zhao, "Wavelet-based denoising: A brief review," in 2013 fourth international conference on intelligent control and information processing (ICICIP), 2013: IEEE, pp. 570-574.
[25] S. García, J. Luengo, and F. Herrera, Data preprocessing in data mining. Springer, 2015.
[26] Y. Si, Y. Wang, and D. Zhou, "Key-performance-indicator-related process monitoring based on improved kernel partial least squares," IEEE Transactions on Industrial Electronics, vol. 68, no. 3, pp. 2626-2636, 2020.
[27] X. Ma, Y. Si, Z. Yuan, Y. Qin, and Y. Wang, "Multistep dynamic slow feature analysis for industrial process monitoring," IEEE Transactions on Instrumentation and Measurement, vol. 69, no. 12, pp. 9535-9548, 2020.
[28] M. Hamadache, J. H. Jung, J. Park, and B. D. Youn, "A comprehensive review of artificial intelligence-based approaches for rolling element bearing PHM: Shallow and deep learning," JMST Advances, vol. 1, pp. 125-151, 2019.
[29] L. Jing, M. Zhao, P. Li, and X. Xu, "A convolutional neural network based feature learning and fault diagnosis method for the condition monitoring of gearbox," Measurement, vol. 111, pp. 1-10, 2017.
[30] L. Bellani, M. Compare, P. Baraldi, and E. Zio, "Towards developing a novel framework for practical phm: A sequential decision problem solved by reinforcement learning and artificial neural networks," International Journal of Prognostics and Health Management, vol. 10, no. 4, 2019.
[31] J. K. Kimotho, C. Sondermann-Woelke, T. Meyer, and W. Sextro, "Application of event based decision tree and ensemble of data driven methods for maintenance action recommendation," International Journal of Prognostics and Health Management, vol. 4, no. 2, 2013.
[32] H. T. Pham, B.-S. Yang, and T. T. Nguyen, "Machine performance degradation assessment and remaining useful life prediction using proportional hazard model and support vector machine," Mechanical Systems and Signal Processing, vol. 32, pp. 320-330, 2012.
[33] X. Dong, Z. Yu, W. Cao, Y. Shi, and Q. Ma, "A survey on ensemble learning," Frontiers of Computer Science, vol. 14, pp. 241-258, 2020.
[34] L. Yang and A. Shami, "On hyperparameter optimization of machine learning algorithms: Theory and practice," Neurocomputing, vol. 415, pp. 295-316, 2020.
[35] M. W. Browne, "Cross-validation methods," Journal of mathematical psychology, vol. 44, no. 1, pp. 108-132, 2000.
[36] Z. Zhao et al., "Deep learning algorithms for rotating machinery intelligent diagnosis: An open source benchmark study," ISA Trans, vol. 107, pp. 224-255, Dec 2020, doi: 10.1016/j.isatra.2020.08.010.
[37] Y. LeCun et al., "Backpropagation Applied to Handwritten Zip Code Recognition," Neural Computation, vol. 1, no. 4, pp. 541-551, 1989, doi: 10.1162/neco.1989.1.4.541.
[38] T. M. T. Md Zahangir Alom1, "The History Began from AlexNet: A Comprehensive Survey on Deep Learning Approaches."
[39] X. Z. Kaiming He, Shaoqing Ren, "Deep Residual Learning for Image Recognition."
[40] "MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications," Andrew G, Menglong Zhu, Bo Chen.
[41] T. Ince, S. Kiranyaz, L. Eren, M. Askar, and M. Gabbouj, "Real-Time Motor Fault Detection by 1-D Convolutional Neural Networks," IEEE Transactions on Industrial Electronics, vol. 63, no. 11, pp. 7067-7075, 2016, doi: 10.1109/tie.2016.2582729.
[42] B. Yang, R. Liu, and E. Zio, "Remaining Useful Life Prediction Based on a Double-Convolutional Neural Network Architecture," IEEE Transactions on Industrial Electronics, vol. 66, no. 12, pp. 9521-9530, 2019, doi: 10.1109/tie.2019.2924605.
[43] D. Yao, B. Li, H. Liu, J. Yang, and L. Jia, "Remaining useful life prediction of roller bearings based on improved 1D-CNN and simple recurrent unit," Measurement, vol. 175, 2021, doi: 10.1016/j.measurement.2021.109166.
[44] Y.-T. Hsu, "A Lightweight Classification Model for Breast Cancer Mass Abnormality based on Simplified Swarm Optimization Algorithm and Knowledge Distillation," 2023.
[45] L. Rabiner and R. Schafer, Theory and applications of digital speech processing. Prentice Hall Press, 2010.
[46] L. Debnath and F. A. Shah, Wavelet transforms and their applications. Springer, 2002.
[47] O. Rioul and M. Vetterli, "Wavelets and signal processing. IEEE Signal Process Mag 8: 14–38," ed, 1991.
[48] S. Hochreiter and J. Schmidhuber, "Long short-term memory," Neural computation, vol. 9, no. 8, pp. 1735-1780, 1997.
[49] A. Graves and J. Schmidhuber, "Framewise phoneme classification with bidirectional LSTM and other neural network architectures," Neural networks, vol. 18, no. 5-6, pp. 602-610, 2005.
[50] H. Fan, M. Jiang, L. Xu, H. Zhu, J. Cheng, and J. Jiang, "Comparison of long short term memory networks and the hydrological model in runoff simulation," Water, vol. 12, no. 1, p. 175, 2020.
[51] K. Cho et al., "Learning phrase representations using RNN encoder-decoder for statistical machine translation," arXiv preprint arXiv:1406.1078, 2014.
[52] J. Zhang, Y. Jiang, S. Wu, X. Li, H. Luo, and S. Yin, "Prediction of remaining useful life based on bidirectional gated recurrent unit with temporal self-attention mechanism," Reliability Engineering & System Safety, vol. 221, p. 108297, 2022.
[53] J. Zhang, Y. Jiang, S. Wu, X. Li, H. Luo, and S. Yin, "Prediction of remaining useful life based on bidirectional gated recurrent unit with temporal self-attention mechanism," Reliability Engineering & System Safety, vol. 221, 2022, doi: 10.1016/j.ress.2021.108297.
[54] J. Chen, H. Jing, Y. Chang, and Q. Liu, "Gated recurrent unit based recurrent neural network for remaining useful life prediction of nonlinear deterioration process," Reliability Engineering & System Safety, vol. 185, pp. 372-382, 2019, doi: 10.1016/j.ress.2019.01.006.
[55] A. Vaswani et al., "Attention is all you need," Advances in neural information processing systems, vol. 30, 2017.
[56] Y. Bengio, P. Simard, and P. Frasconi, "Learning long-term dependencies with gradient descent is difficult," IEEE transactions on neural networks, vol. 5, no. 2, pp. 157-166, 1994.
[57] D. Bahdanau, K. Cho, and Y. Bengio, "Neural machine translation by jointly learning to align and translate," arXiv preprint arXiv:1409.0473, 2014.
[58] G. Jiang, Z. Duan, Q. Zhao, D. Li, and Y. Luan, "Remaining useful life prediction of rolling bearings based on TCN-MSA," Measurement Science and Technology, vol. 35, no. 2, p. 025125, 2023.
[59] Z. Lin et al., "A structured self-attentive sentence embedding," arXiv preprint arXiv:1703.03130, 2017.
[60] J. Wang, J. Guo, L. Wang, Y. Yang, Z. Wang, and R. Wang, "A hybrid intelligent rolling bearing fault diagnosis method combining WKN-BiLSTM and attention mechanism," Measurement Science and Technology, vol. 34, no. 8, p. 085106, 2023.
[61] J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, "Bert: Pre-training of deep bidirectional transformers for language understanding," arXiv preprint arXiv:1810.04805, 2018.
[62] K. Clark, U. Khandelwal, O. Levy, and C. D. Manning, "What does bert look at? an analysis of bert's attention," arXiv preprint arXiv:1906.04341, 2019.
[63] T. Elsken, J. H. Metzen, and F. Hutter, "Neural architecture search: A survey," The Journal of Machine Learning Research, vol. 20, no. 1, pp. 1997-2017, 2019.
[64] E. Tuba, N. Bačanin, I. Strumberger, and M. Tuba, "Convolutional neural networks hyperparameters tuning," in Artificial intelligence: theory and applications: Springer, 2021, pp. 65-84.
[65] W.-C. Yeh, Y.-P. Lin, Y.-C. Liang, C.-M. Lai, and C.-L. Huang, "Simplified swarm optimization for hyperparameters of convolutional neural networks," Computers & Industrial Engineering, vol. 177, p. 109076, 2023.
[66] Z. Lu et al., "Nsga-net: neural architecture search using multi-objective genetic algorithm," in Proceedings of the genetic and evolutionary computation conference, 2019, pp. 419-427.
[67] B. Zoph and Q. V. Le, "Neural architecture search with reinforcement learning," arXiv preprint arXiv:1611.01578, 2016.
[68] S. Santra, J.-W. Hsieh, and C.-F. Lin, "Gradient descent effects on differential neural architecture search: A survey," IEEE Access, vol. 9, pp. 89602-89618, 2021.
[69] S. Wang, Z. Yu, G. Xu, and F. Zhao, "Research on tool remaining life prediction method based on CNN-LSTM-PSO," Ieee Access, vol. 11, pp. 80448-80464, 2023.
[70] Y. Zhu, B. Xu, Z. Luo, Z. Liu, H. Wang, and C. Du, "Prediction method of turbine engine RUL based on GA-SVR," in 2022 International Conference on Artificial Intelligence and Computer Information Technology (AICIT), 2022: IEEE, pp. 1-6.
[71] R. Poli, J. Kennedy, and T. Blackwell, "Particle swarm optimization," Swarm Intelligence, vol. 1, no. 1, pp. 33-57, 2007/06/01 2007, doi: 10.1007/s11721-007-0002-0.
[72] W.-C. Yeh, "New parameter-free simplified swarm optimization for artificial neural network training and its application in the prediction of time series," IEEE Transactions on Neural Networks and Learning Systems, vol. 24, no. 4, pp. 661-665, 2013.
[73] J.-H. Lee, W.-C. Yeh, and M.-C. Chuang, "Web page classification based on a simplified swarm optimization," Applied Mathematics and Computation, vol. 270, pp. 13-24, 2015.
[74] C.-L. Huang, "A particle-based simplified swarm optimization algorithm for reliability redundancy allocation problems," Reliability Engineering & System Safety, vol. 142, pp. 221-230, 2015.
[75] N. R. Mann, R. E. Schafer, and N. D. Singpurwalla, "Methods for statistical analysis of reliability and life data(Book)," Research supported by the U. S. Air Force and Rockwell International Corp. New York, John Wiley and Sons, Inc., 1974. 573 p, 1974.
[76] G.-A. Klutke, P. C. Kiessler, and M. A. Wortman, "A critical look at the bathtub curve," IEEE Transactions on reliability, vol. 52, no. 1, pp. 125-129, 2003.
[77] N. M. Aszemi and P. Dominic, "Hyperparameter optimization in convolutional neural network using genetic algorithms," International Journal of Advanced Computer Science and Applications, vol. 10, no. 6, 2019.
[78] J. Chen, J. Jiang, X. Guo, and L. Tan, "A self-Adaptive CNN with PSO for bearing fault diagnosis," Systems Science & Control Engineering, vol. 9, no. 1, pp. 11-22, 2021.
[79] S. Wang, Z. Yu, G. Xu, and F. Zhao, "Research on tool remaining life prediction method based on CNN-LSTM-PSO," Ieee Access, 2023.
[80] P. Singh, S. Chaudhury, and B. K. Panigrahi, "Hybrid MPSO-CNN: Multi-level particle swarm optimized hyperparameters of convolutional neural network," Swarm and Evolutionary Computation, vol. 63, p. 100863, 2021.
[81] Z. Zhao et al., "Deep learning algorithms for rotating machinery intelligent diagnosis: An open source benchmark study," ISA transactions, vol. 107, pp. 224-255, 2020.
[82] P. Nectoux et al., "PRONOSTIA: An experimental platform for bearings accelerated degradation tests," in IEEE International Conference on Prognostics and Health Management, PHM'12., 2012: IEEE Catalog Number: CPF12PHM-CDR, pp. 1-8.
[83] A. Soualhi, K. Medjaher, and N. Zerhouni, "Bearing health monitoring based on Hilbert–Huang transform, support vector machine, and regression," IEEE Transactions on instrumentation and measurement, vol. 64, no. 1, pp. 52-62, 2014.
[84] S. Mallat, A wavelet tour of signal processing. Elsevier, 1999.