Deep learning the Hurst parameter of linear fractional processes and assessing its reliability (2401.01789v1)
Abstract: This research explores the reliability of deep learning, specifically Long Short-Term Memory (LSTM) networks, for estimating the Hurst parameter in fractional stochastic processes. The study focuses on three types of processes: fractional Brownian motion (fBm), fractional Ornstein-Uhlenbeck (fOU) process, and linear fractional stable motions (lfsm). The work involves a fast generation of extensive datasets for fBm and fOU to train the LSTM network on a large volume of data in a feasible time. The study analyses the accuracy of the LSTM network's Hurst parameter estimation regarding various performance measures like RMSE, MAE, MRE, and quantiles of the absolute and relative errors. It finds that LSTM outperforms the traditional statistical methods in the case of fBm and fOU processes; however, it has limited accuracy on lfsm processes. The research also delves into the implications of training length and valuation sequence length on the LSTM's performance. The methodology is applied by estimating the Hurst parameter in Li-ion battery degradation data and obtaining confidence bounds for the estimation. The study concludes that while deep learning methods show promise in parameter estimation of fractional processes, their effectiveness is contingent on the process type and the quality of training data.
- Huillet, T. Fractional Lévy motions and related processes Journal of Physics A: Mathematical and General 1999; 32(42). DOI 10.1088/0305-4470/32/42/301
- Dirk P Kroese and Zdravko I Botev. Spatial process generation. arXiv preprint arXiv:1308.0399,2013
- X. Xi, M. Chen, and D. Zhou, “Remaining useful life prediction for degradation processes with memory effects,” IEEE Transactions on Reliability, vol. 66, no. 3, pp. 751–760, Sep. 2017.
- W. Si, Y. Shao, and W. Wei, “Accelerated degradation testing with long-term memory effects,” IEEE Transactions on Reliability, vol. 69, no. 4, pp. 1254–1266, Dec. 2020.
- H. Zhang, D. Zhou, M. Chen, and J. Shang, “FBM-based remaining useful life prediction for degradation processes with long-range dependence and multiple modes,” IEEE Transactions on Reliability, vol. 68, no. 3, pp. 1021–1033, Sep. 2019.
- H. Zhang, Z. Mo, J. Wang, and Q. Miao, “Nonlinear-drifted fractional Brownian motion with multiple hidden state variables for remaining useful life prediction of lithium-ion batteries,” IEEE Transactions on Reliability, vol. 69, no. 2, pp. 768–780, Jun. 2020.
- H. Zhang, D. Zhou, M. Chen, and X. Xi, “Predicting remaining useful life based on a generalized degradation with fractional Brownian motion,” Mechanical Systems and Signal Processing, vol. 115, pp. 736–752, 2019.
- W. Song, X. Chen, C. Cattani, and E. Zio, “Multifractional Brownian motion and quantum-behaved partial swarm optimization for bearing degradation forecasting,” Complexity, vol. 2020, 2020, Art. no. 8543131.
- H. Wang, W. Song, E. Zio, A. Kudreyko, and Y. Zhang, “Remaining useful life prediction for Lithium-ion batteries using fractional Brownian motion and fruit-fly optimization algorithm,” Measurement, vol. 161, 2020, Art. no. 107904.
- Hua Ding, Liangliang Yang, Zeyin Cheng, and Zhaojian Yang, “A remaining useful life prediction method for bearing based on deep neural networks,” Measurement, vol. 172, 2021, Art. no. 108878, ISSN 0263-2241, https://doi.org/10.1016/j.measurement.2020.108878.
- C. Zhang, P. Lim, A. K. Qin, and K. C. Tan, “Multiobjective deep belief networks ensemble for remaining useful life estimation in prognostics,” IEEE Transactions on Neural Networks and Learning Systems, vol. 28, pp. 2306–2318, 2017.
- Haoran Yan, Yi Qin, Sheng Xiang, Yi Wang, and Haizhou Chen, “Long-term gear life prediction based on ordered neurons LSTM neural networks,” Measurement, vol. 165, 2020, Art. no. 108205, ISSN 0263-2241, https://doi.org/10.1016/j.measurement.2020.108205.
- M. Haris, M.N. Hasan, and S. Qin, “Early and robust remaining useful life prediction of supercapacitors using BOHB optimized Deep Belief Network,” Applied Energy, vol. 286, 2021, Art. no. 116541.
- Yi Qin, Dingliang Chen, Sheng Xiang, and Caichao Zhu, “Gated Dual Attention Unit Neural Networks for Remaining Useful Life Prediction of Rolling Bearings,” IEEE Transactions on Industrial Informatics, pp. 1–1, 2020, https://doi.org/10.1109/TII.2020.2999442.
- Yuantao Fan, Sławomir Nowaczyk, and Thorsteinn Rögnvaldsson, “Transfer learning for remaining useful life prediction based on consensus self-organizing models,” Reliability Engineering & System Safety, vol. 203, 2020, Art. no. 107098, ISSN 0951-8320, https://doi.org/10.1016/j.ress.2020.107098.
- Hang Wang, Min-jun Peng, Yong-kuo Liu, Shi-wen Liu, Ren-yi Xu, and Hanan Saeed, “Remaining Useful Life Prediction Techniques of Electric Valves for Nuclear Power Plants with Convolution Kernel and LSTM,” Science and Technology of Nuclear Installations, 2020, pp. 1–13, https://doi.org/10.1155/2020/8349349.