A data-driven approach to RUL prediction of tools

doi:10.1007/s40436-023-00464-y

Advances in Manufacturing ›› 2024, Vol. 12 ›› Issue (1): 6-18.doi: 10.1007/s40436-023-00464-y

• • 上一篇

A data-driven approach to RUL prediction of tools

Wei Li^1,5, Liang-Chi Zhang^2,3,4, Chu-Han Wu⁵, Yan Wang⁵, Zhen-Xiang Cui⁶, Chao Niu⁶

1. Department of Mechanical Engineering, University College London, London, WC1E 7JE, UK;
2. Shenzhen Key Laboratory of Cross-Scale Manufacturing Mechanics, Southern University of Science and Technology, Shenzhen, 518055, Guangdong, People's Republic of China;
3. SUSTech Institute for Manufacturing Innovation, Southern University of Science and Technology, Shenzhen, 518055, Guangdong, People's Republic of China;
4. Department of Mechanics and Aerospace Engineering, Southern University of Science and Technology, Shenzhen, 518055, Guangdong, People's Republic of China;
5. School of Mechanical and Manufacturing Engineering, The University of New South Wales, Kensington, NSW, 2052, Australia;
6. Baoshan Iron & Steel Co., Ltd., Shanghai, 200941, People's Republic of China

收稿日期:2023-03-23 修回日期:2023-05-17 发布日期:2024-03-14
通讯作者: Liang-Chi Zhang,E-mail:zhanglc@sustech.edu.cn E-mail:zhanglc@sustech.edu.cn
作者简介:Wei Li is a research fellow in the Department of Mechanical Engineering at University College London. He received his Ph.D. from the University of New South Wales in 2022. His current research felds include deep learning, metal forming, image processing and additive manufacturing;
Liang-Chi Zhang is an academician/chair professor at Southern University of Science and Technology. His research interests include precision manufacturing, bio-manufacturing, nanotechnology, characterisation of advanced materials, tribology, solid mechanics, computational mechanics;
Chu-Han Wu is a research fellow in the school of Mechanical and Manufacturing Engineering at the University of New South Wales Australia. He received his Ph.D. from the University of New South Wales in 2016. His current research felds include contact mechanics, lubrication theory, numerical modelling and metal forming;
Yan Wang is a PhD candidate at the School of Mechanical and Manufacturing Engineering, University of New South Wales, Australia. Her research interests include wear testing, lubricated wear and wear mechanism, with a focus on surface integrity of magnesium alloys subjected to sliding and rolling;
Zhen-Xiang Cui is a researcher at the Research Institute of Baoshan Iron & Steel Co., Ltd. His research interests include the forming of advanced high strength steel, the galling & wear of tools and the galling characteristics of steel plate;
Chao Niu is a researcher of Baoshan Iron and Steel Co., Ltd., engaged in the research of cold stamping forming technology of high strength steels. He has a deep research on mechanical behaviour characterization, formability evaluation and analysis, spring back prediction, etc.
基金资助:
This research was supported by the Baosteel Australia Research and Development Centre (BAJC) Portfolio (Grant No. BA17001), the ARC Hub for Computational Particle Technology (Grant No. IH140100035), the Chinese Guangdong Specific Discipline Project (Grant No. 2020ZDZX2006), and the Shenzhen Key Laboratory Project of Cross-scale Manufacturing Mechanics (Grant No. ZDSYS20200810171201007).

A data-driven approach to RUL prediction of tools

Wei Li^1,5, Liang-Chi Zhang^2,3,4, Chu-Han Wu⁵, Yan Wang⁵, Zhen-Xiang Cui⁶, Chao Niu⁶

1. Department of Mechanical Engineering, University College London, London, WC1E 7JE, UK;
2. Shenzhen Key Laboratory of Cross-Scale Manufacturing Mechanics, Southern University of Science and Technology, Shenzhen, 518055, Guangdong, People's Republic of China;
3. SUSTech Institute for Manufacturing Innovation, Southern University of Science and Technology, Shenzhen, 518055, Guangdong, People's Republic of China;
4. Department of Mechanics and Aerospace Engineering, Southern University of Science and Technology, Shenzhen, 518055, Guangdong, People's Republic of China;
5. School of Mechanical and Manufacturing Engineering, The University of New South Wales, Kensington, NSW, 2052, Australia;
6. Baoshan Iron & Steel Co., Ltd., Shanghai, 200941, People's Republic of China

Received:2023-03-23 Revised:2023-05-17 Published:2024-03-14
Contact: Liang-Chi Zhang,E-mail:zhanglc@sustech.edu.cn E-mail:zhanglc@sustech.edu.cn
Supported by:
This research was supported by the Baosteel Australia Research and Development Centre (BAJC) Portfolio (Grant No. BA17001), the ARC Hub for Computational Particle Technology (Grant No. IH140100035), the Chinese Guangdong Specific Discipline Project (Grant No. 2020ZDZX2006), and the Shenzhen Key Laboratory Project of Cross-scale Manufacturing Mechanics (Grant No. ZDSYS20200810171201007).

摘要/Abstract

摘要： An effective and reliable prediction of the remaining useful life (RUL) of a tool is important to a metal forming process because it can significantly reduce unexpected maintenance, avoid machine shutdowns and increase system stability. This study proposes a new data-driven approach to the RUL prediction for metal forming processes under multiple contact sliding conditions. The data-driven approach took advantage of bidirectional long short-term memory (BLSTM) and convolutional neural networks (CNN). A pre-trained lightweight CNN-based network, WearNet, was re-trained to classify the wear states of workpiece surfaces with a high accuracy, then the classification results were passed into a BLSTM-based regression model as inputs for RUL estimation. The experimental results demonstrated that this approach was able to predict the RUL values with a small error (below 5%) and a low root mean square error (RMSE) (around 1.5), which was more superior and robust than the other state-of-the-art methods.

The full text can be downloaded at https://link.springer.com/article/10.1007/s40436-023-00464-y

关键词: Remaining useful life (RUL), Bidirectional long short-term memory (BLSTM), Data-driven approach, Metal forming

Abstract: An effective and reliable prediction of the remaining useful life (RUL) of a tool is important to a metal forming process because it can significantly reduce unexpected maintenance, avoid machine shutdowns and increase system stability. This study proposes a new data-driven approach to the RUL prediction for metal forming processes under multiple contact sliding conditions. The data-driven approach took advantage of bidirectional long short-term memory (BLSTM) and convolutional neural networks (CNN). A pre-trained lightweight CNN-based network, WearNet, was re-trained to classify the wear states of workpiece surfaces with a high accuracy, then the classification results were passed into a BLSTM-based regression model as inputs for RUL estimation. The experimental results demonstrated that this approach was able to predict the RUL values with a small error (below 5%) and a low root mean square error (RMSE) (around 1.5), which was more superior and robust than the other state-of-the-art methods.

The full text can be downloaded at https://link.springer.com/article/10.1007/s40436-023-00464-y

Key words: Remaining useful life (RUL), Bidirectional long short-term memory (BLSTM), Data-driven approach, Metal forming

Wei Li, Liang-Chi Zhang, Chu-Han Wu, Yan Wang, Zhen-Xiang Cui, Chao Niu. A data-driven approach to RUL prediction of tools[J]. Advances in Manufacturing, 2024, 12(1): 6-18.

参考文献

1 Wu JY, Wu M, Chen Z et al (2021) A joint classification-regression method for multi-stage remaining useful life prediction. J Manuf Syst 58:109–119
2 Huang C, Huang H, Li Y et al (2021) A novel deep convolutional neural network-bootstrap integrated method for RUL prediction of rolling bearing. J Manuf Syst 61:757–772
3 Ferreira C, Gonçalves G (2022) Remaining useful life prediction and challenges: a literature review on the use of machine learning methods. J Manuf Syst 63:550–562
4 Ding H, Yang L, Cheng Z et al (2021) A remaining useful life prediction method for bearing based on deep neural networks. Meas 172:108878. https://doi.org/10.1016/j.measurement.2020.108878
5 Arena M, Di Pasquale V, Iannone R et al (2022) A maintenance driven scheduling cockpit for integrated production and maintenance operation schedule. Adv Manuf 10:205–219
6 Li Y, Xiang Y, Pan B et al (2022) A hybrid remaining useful life prediction method for cutting tool considering the wear state. Int J Adv Manuf Technol 121:3583–3596
7 Cubillo A, Perinpanayagam S, Esperon-Miguez M (2016) A review of physics-based models in prognostics: application to gears and bearings of rotating machinery. Adv Mech Eng 8:1–21
8 Si X, Wang W, Hu C et al (2011) Remaining useful life estimation—a review on the statistical data driven approaches. Eur J Oper Res 213:1–14
9 Wang Y, Deng C, Wu J et al (2015) Failure time prediction for mechanical device based on the degradation sequence. J Intell Manuf 26:1181–1199
10 Carr MJ, Wang W (2010) Modeling failure modes for residual life prediction using stochastic filtering theory. IEEE Trans Reliab 59:346–355
11 Peng C, Tseng S (2013) Statistical lifetime inference with skew-Wiener linear degradation models. IEEE Trans Reliab 62:338–350
12 Bian L, Gebraeel N (2014) Stochastic modeling and real-time prognostics for multi-component systems with degradation rate interactions. IIE Trans 46:470–482
13 Liu Y, Zuo MJ, Li Y et al (2015) Dynamic reliability assessment for multi-state systems utilizing system-level inspection data. IEEE Trans Reliab 64:1287–1299
14 Tobon-Mejia DA, Medjaher K, Zerhouni N et al (2012) A data-driven failure prognostics method based on mixture of Gaussians hidden Markov models. IEEE Trans Reliab 61:491–503
15 Pham H, Yang B, Nguyen T (2012) Machine performance degradation assessment and remaining useful life prediction using proportional hazard model and support vector machine. Mech Syst Signal Process 32:320–330
16 Ren L, Sun Y, Cui J et al (2021) Bearing remaining useful life prediction based on deep autoencoder and deep neural networks. J Manuf Syst 48:71–77
17 Liu J, Wang W, Ma F et al (2012) A data-model-fusion prognostic framework for dynamic system state forecasting. Eng Appl Artif Intell 25:814–823
18 Mikołajczyk T, Nowicki K, Bustillo A et al (2018) Predicting tool life in turning operations using neural networks and image processing. Mech Syst Signal Process 104:503–513
19 Guo L, Li N, Jia F et al (2017) A recurrent neural network based health indicator for remaining useful life prediction of bearings. Neurocomputing 240:98–109
20 Saon S, Hiyama T (2010) Predicting remaining useful life of rotating machinery based artificial neural network. Comput Math with Appl 60:1078–1087
21 Wang W, Vrbanek J Jr (2008) An evolving fuzzy predictor for industrial applications. IEEE Trans Fuzzy Syst 16:1439–1449
22 Li W, Zhang L, Chen X et al (2021) Predicting the evolution of sheet metal surface scratching by the technique of artificial intelligence. Int J Adv Manuf Technol 112:853–865
23 Vapnik V, Golowich SE, Smola A (1997) Support vector method for function approximation, regression estimation, and signal processing. Adv Neural Inf Process Syst 9:281–287
24 Benkedjouh T, Medjaher K, Zerhouni N et al (2015) Health assessment and life prediction of cutting tools based on support vector regression. J Intell Manuf 26:213–223
25 Benkedjouh T, Medjaher K, Zerhouni N et al (2013) Remaining useful life estimation based on nonlinear feature reduction and support vector regression. Eng Appl Artif Intell 26:1751–1760
26 Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9:1735–1780
27 Gers FA, Schmidhuber J, Cummins F (2000) Learning to forget: continual prediction with LSTM. Neural Comput 12:2451–2471
28 Shen F, Yan R (2022) A new intermediate-domain SVM-based transfer model for rolling bearing RUL prediction. IEEE ASME Trans Mechatron 27:1357–1369
29 Qin Y, Xiang S, Chai Y et al (2019) Macroscopic-microscopic attention in LSTM networks based on fusion features for gear remaining life prediction. IEEE Trans Ind Electron 67:10865–10875
30 Li W, Zhang L, Wu C et al (2022) A new lightweight deep neural network for surface scratch detection. Int J Adv Manuf Technol 123:1999–2015
31 Yang B, Lei Y, Jia F et al (2019) An intelligent fault diagnosis approach based on transfer learning from laboratory bearings to locomotive bearings. Mech Syst Signal Process 122:692–706
32 Zhu J, Chen N, Shen C (2019) A new deep transfer learning method for bearing fault diagnosis under different working conditions. IEEE Sens J 20:8394–8402
33 Liu L, Song X, Chen K et al (2021) An enhanced encoder-decoder framework for bearing remaining useful life prediction. Meas 170:108753. https://doi.org/10.1016/j.measurement.2020.108753
34 Xiang S, Qin Y, Zhu C et al (2020) Long short-term memory neural network with weight amplification and its application into gear remaining useful life prediction. Eng Appl Artif Intell 91:103587. https://doi.org/10.1016/j.engappai.2020.103587
35 Zhou J, Zhao X, Gao J (2019) Tool remaining useful life prediction method based on LSTM under variable working conditions. Int J Adv Manuf Technol 104:4715–4726
36 Ma M, Mao Z (2020) Deep-convolution-based LSTM network for remaining useful life prediction. IEEE Trans Industr Inform 17:1658–1667
37 Habbouche H, Benkedjouh T, Zerhouni N (2021) Intelligent prognostics of bearings based on bidirectional long short-term memory and wavelet packet decomposition. Int J Adv Manuf Technol 114:145–157
38 Liu C, Zhu L (2020) A two-stage approach for predicting the remaining useful life of tools using bidirectional long short-term memory. Meas 164:108029. https://doi.org/10.1016/j.measurement.2020.108029
39 Liu PL, Du ZC, Li HM (2021) Thermal error modeling based on BiLSTM deep learning for CNC machine tool. Adv Manuf 9:235–249
40 Hou M, Pi D, Li B (2020) Similarity-based deep learning approach for remaining useful life prediction. Meas 159:107788. https://doi.org/10.1016/j.measurement.2020.107788
41 Srivastava N, Hinton G, Krizhevsky A et al (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15:1929–1958
42 Zhang K, Chen J, Zhang T et al (2020) A compact convolutional neural network augmented with multiscale feature extraction of acquired monitoring data for mechanical intelligent fault diagnosis. J Manuf Syst 55:273–284
43 Zeng F, Li Y, Jiang Y et al (2021) An online transfer learning-based remaining useful life prediction method of ball bearings. Meas 176:109201. https://doi.org/10.1016/j.measurement.2021.109201
44 Finkeldey F, Saadallah A, Wiederkehr P et al (2020) Real-time prediction of process forces in milling operations using synchronized data fusion of simulation and sensor data. Eng Appl Artif Intell 94:103753. https://doi.org/10.1016/j.engappai.2020.103753

[1]	Wei Li, Liang-Chi Zhang, Chu-Han Wu, Zhen-Xiang Cui, Chao Niu, Yan Wang. Debris effect on the surface wear and damage evolution of counterpart materials subjected to contact sliding[J]. Advances in Manufacturing, 2022, 10(1): 72-86.
[2]	Xiao-Long Sun, Xin-Cun Zhuang, Feng-Chun Yang, Zhen Zhao. Reduction of die roll height in duplex gears through a sheet-bulk metal forming method[J]. Advances in Manufacturing, 2019, 7(1): 42-51.
[3]	Ke-Sheng Wang Vishal S. Sharma Zhen-You Zhang. SCADA data based condition monitoring of wind turbines[J]. Advances in Manufacturing, 2014, 2(1): 61-69.

A data-driven approach to RUL prediction of tools

A data-driven approach to RUL prediction of tools

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 3

编辑推荐

Metrics

本文评价