Long Short-Term Memory Networks for the Automated Identification of the Stationary Phase in Tribological Experiments
Abstract
:1. Introduction
2. Methodology
2.1. Task Definition and Network Choice
2.2. Long Short-Term Memory Network Structure
2.2.1. LSTM Cell and Cell State
2.2.2. LSTM Network Architecture
2.2.3. Training Data Preparation
2.2.4. Hyperparameters Optimization
2.2.5. LSTM Network Optimization
3. Results and Discussion
3.1. Chosen Hyperparameter from Bayesian Optimization
3.2. LSTM Network Training
4. Conclusions
Author Contributions
Funding
Data Availability Statement
Conflicts of Interest
References
- Jones, S.P.; Jansen, R.; Fusaro, R.L. Preliminary investigation of neural network techniques to predict tribological properties. Tribol. Trans. 1997, 40, 312–320. [Google Scholar] [CrossRef]
- Gyurova, L.A.; Friedrich, K. Artificial neural networks for predicting sliding friction and wear properties of polyphenylene sulfide composites. Tribol. Int. 2011, 44, 603–609. [Google Scholar] [CrossRef]
- Gao, G.; Gong, J.; Qi, Y.; Ren, J.; Wang, H.; Yang, D.; Chen, S. Tribological Behavior of PTFE Composites Filled with PEEK and Nano-ZrO2. Tribol. Trans. 2020, 63, 296–304. [Google Scholar] [CrossRef]
- Zakaulla, M.; Parveen, F.; Amreen; Harish; Ahmad, N. Artificial neural network based prediction on tribological properties of polycarbonate composites reinforced with graphene and boron carbide particle. Mater. Today Proc. 2019, 26, 296–304. [Google Scholar] [CrossRef]
- Velten, K.; Reinicke, R.; Friedrich, K. Wear volume prediction with artificial neural networks. Tribol. Int. 2000, 33, 731–736. [Google Scholar] [CrossRef]
- Genel, K.; Kurnaz, S.C.; Durman, M. Modeling of tribological properties of alumina fiber reinforced zinc-aluminum composites using artificial neural network. Mater. Sci. Eng. A 2003, 363, 203–210. [Google Scholar] [CrossRef]
- LiuJie, X.; Davim, J.P.; Cardoso, R. Prediction on tribological behaviour of composite PEEK-CF30 using artificial neural networks. J. Mater. Process. Technol. 2007, 189, 374–378. [Google Scholar] [CrossRef]
- Zhu, J.; Shi, Y.; Feng, X.; Wang, H.; Lu, X. Prediction on tribological properties of carbon fiber and TiO2 synergistic reinforced polytetrafluoroethylene composites with artificial neural networks. Mater. Des. 2009, 30, 1042–1049. [Google Scholar] [CrossRef]
- Li, S.; Shao, M.; Duan, C.; Yan, Y.; Wang, Q.; Wang, T.; Zhang, X. Tribological behavior prediction of friction materials for ultrasonic motors using Monte Carlo-based artificial neural network. J. Appl. Polym. Sci. 2019, 136, 47157. [Google Scholar] [CrossRef]
- Marian, M.; Tremmel, S. Current trends and applications of machine learning in tribology—A review. Lubricants 2021, 9, 86. [Google Scholar] [CrossRef]
- Rosenkranz, A.; Marian, M.; Profito, F.J.; Aragon, N.; Shah, R. The use of artificial intelligence in tribology—A perspective. Lubricants 2021, 9, 2. [Google Scholar] [CrossRef]
- Jiang, Z.; Gyurova, L.; Zhang, Z.; Friedrich, K.; Schlarb, A.K. Neural network based prediction on mechanical and wear properties of short fibers reinforced polyamide composites. Mater. Des. 2008, 29, 628–637. [Google Scholar] [CrossRef]
- Jiang, Z.; Gyurova, L.A.; Schlarb, A.K.; Friedrich, K.; Zhang, Z. Study on friction and wear behavior of polyphenylene sulfide composites reinforced by short carbon fibers and sub-micro TiO2 particles. Compos. Sci. Technol. 2008, 68, 734–742. [Google Scholar] [CrossRef]
- Gyurova, L.A.; Miniño-Justel, P.; Schlarb, A.K. Modeling the sliding wear and friction properties of polyphenylene sulfide composites using artificial neural networks. Wear 2010, 268, 708–714. [Google Scholar] [CrossRef]
- Gyurova, L.; Jiang, Z.; Schlarb, A.K.; Friedrich, K.; Zhang, Z. Study on the Wear and Friction of Short Carbon Fiber and/or Nano-TiO2 Reinforced Polyphenylene Sulfide Composites using Artificial Neural Networks. In Friction, Wear and Wear Protection; Wiley Online Library: Hoboken, NJ, USA, 2009; pp. 417–422. [Google Scholar] [CrossRef]
- Busse, M.; Schlarb, A.K. A novel neural network approach for modeling tribological properties of polyphenylene sulfide reinforced on different scales. In Tribology of Polymeric Nanocomposites: Friction and Wear of Bulk Materials and Coatings, 2nd ed.; Elsevier: Amsterdam, The Netherlands, 2013; pp. 779–793. [Google Scholar] [CrossRef]
- Zhao, Y.; Lin, L.; Schlarb, A.K. Artificial neural network accomplished prediction on tribology—A promising procedure to facilitate the tribological characterization of polymer composites. Wear 2023, 532–533, 205106. [Google Scholar] [CrossRef]
- Frangu, L.; Ripa, M.; Multi, I.I.; Perceptron, L. Artificial Neural Networks Applications in Tribology—A Survey. In Proceedings of the NATO Advanced Study Institute on Neural Networks for Instrumentation, Measurement, and Related Industrial Applications: Study Cases, Crema, Italy, 9–20 October 2001. [Google Scholar]
- Sose, A.T.; Joshi, S.Y.; Kunche, L.K.; Wang, F.; Deshmukh, S.A. A review of recent advances and applications of machine learning in tribology. Phys. Chem. Chem. Phys. 2023, 25, 4408–4443. [Google Scholar] [CrossRef]
- Paturi, U.M.R.; Palakurthy, S.T.; Reddy, N.S. The Role of Machine Learning in Tribology: A Systematic Review; Springer: Dordrecht, The Netherlands, 2023. [Google Scholar] [CrossRef]
- Aiordachioaie, D.; Ceanga, E.; Roman, N.; Mihalcea, R. Pre-processing of acoustic signals by neural networks for fault detection and diagnosis of rolling mill. In Proceedings of the Fifth International Conference on Artificial Neural Networks (Conf. Publ. No. 440), Cambridge, UK, 7–9 July 1997; IEEE Conference Publication: New York, NY, USA, 1997; pp. 251–256. [Google Scholar]
- Yin, F.; He, Z.; Nie, S.; Ji, H.; Ma, Z. Tribological properties and wear prediction of various ceramic friction pairs under seawater lubrication condition of different medium characteristics using CNN-LSTM method. Tribol. Int. 2023, 189, 108935. [Google Scholar] [CrossRef]
- Yin, F.; Luo, H.; Nie, S.; Ji, H.; Ma, Z. Physics-Informed machine learning for tribological properties prediction of S32750/CFRPEEK tribopair under seawater lubrication via PISSA-CNN-LSTM. Tribol. Int. 2024, 199, 109965. [Google Scholar] [CrossRef]
- Motamedi, N. Towards the Prediction and Understanding of Tribological Effects on System Performance Through Artificial Intelligence. Ph.D. Thesis, Université de Lille, Lille, France, 2023. [Google Scholar]
- DIN ISO 7148-2:2014-07; Gleitlager—Prüfung des Tribologischen Verhaltens von Gleitlagerwerkstoffen—Teil 2: Prüfung von Polymeren Gleitlagerwerkstoffen (ISO 7148-2:2012). DIN Standards: Berlin, Germnay, 2014.
- LeCun, Y.; Boser, B.; Denker, J.S.; Henderson, D.; Howard, R.E.; Hubbard, W.; Jackel, L.D. Backpropagation Applied to Handwritten Zip Code Recognition. Neural Comput. 1989, 1, 541–551. [Google Scholar] [CrossRef]
- LeCun, Y.; Bottou, L.; Bengio, Y.; Haffner, P. Gradient-Based Learning Applied to Document Recognition. Proc. IEEE 1998, 86, 2278–2324. [Google Scholar] [CrossRef]
- Platt, J.C.; Nowlan, S.J. A convolutional neural network hand tracker. Proc. Adv. Neural Inf. Process. Syst. 1995, 901–908. [Google Scholar]
- Lawrence, S.; Giles, C.L.; Tsoi, A.C.; Back, A.D. Face Recognition: A Convolutional Neural-Network Approach. IEEE Trans. Neural Netw. 1997, 8, 98–113. [Google Scholar] [CrossRef]
- Hochreiter, S.; Schmidhuber, J. Long Short-Term Memory. Neural Comput. 1997, 9, 1735–1780. [Google Scholar] [CrossRef] [PubMed]
- Karim, F.; Majumdar, S.; Darabi, H.; Chen, S. LSTM Fully Convolutional Networks for Time Series Classification. IEEE Access 2017, 6, 1662–1669. [Google Scholar] [CrossRef]
- Karim, F.; Majumdar, S.; Darabi, H. Insights into lstm fully convolutional networks for time series classification. IEEE Access 2019, 7, 67718–67725. [Google Scholar] [CrossRef]
- Sadouk, L. CNN Approaches for Time Series Classification. In Time Series Analysis-Data, Methods, and Applications; Books on Demand: Norderstedt, Germany, 2019; pp. 1–23. [Google Scholar] [CrossRef]
- Chong, S.Y.; Tiňo, P.; Yao, X. Relationship between generalization and diversity in coevolutionary learning. IEEE Trans. Comput. Intell. AI Games 2009, 1, 214–232. [Google Scholar] [CrossRef]
- Yang, J.; Zeng, X.; Zhong, S.; Wu, S. Effective neural network ensemble approach for improving generalization performance. IEEE Trans. Neural Networks Learn. Syst. 2013, 24, 878–887. [Google Scholar] [CrossRef]
- Ortega, L.A.; Cabañas, R.; Masegosa, A.R. Diversity and Generalization in Neural Network Ensembles. Proc. Mach. Learn. Res. 2022, 151, 11720–11743. [Google Scholar]
- Hutter, F.; Kotthoff, L.; Vanschoren, J. Automated Machine Learning: Methods, Systems, Challenges; Springer Nature: Berlin/Heidelberg, Germany, 2019. [Google Scholar] [CrossRef]
- Diaz, G.I.; Fokoue-Nkoutche, A.; Nannicini, G.; Samulowitz, H. An effective algorithm for hyperparameter optimization of neural networks. IBM J. Res. Dev. 2017, 61, 9:1–9:11. [Google Scholar] [CrossRef]
- Smithson, S.C.; Yang, G.; Gross, W.J.; Meyer, B.H. Neural networks designing neural networks: Multi-objective hyper-parameter optimization. In Proceedings of the 2016 IEEE/ACM International Conference on Computer-Aided Design (ICCAD), Austin, TX, USA, 7–10 November 2016. [Google Scholar] [CrossRef]
- Bergstra, J.; Bardenet, R.; Bengio, Y.; Kégl, B. Algorithms for hyper-parameter optimization. Adv. Neural Inf. Process. Syst. 2011, 24, 1–9. [Google Scholar]
- Mockus, J. The Bayesian Approach to Global Optimization; Springer Science and Business Media: Berlin/Heidelberg, Germany, 1981. [Google Scholar]
- Pelikan, M.; Goldberg, D.E.; Cantú-Paz, E. Hierarchical problem solving by the Bayesian optimization algorithm. In Proceedings of the 2nd Annual Conference on Genetic and Evolutionary Computation, Las Vegas, NV, USA, 10–12 July 2000. [Google Scholar]
- Pelikan, M.; Goldberg, D.E. Research on the Bayesian Optimization Algorithm; IlliGAL Report (2000010); Illinois Genetic Algorithms Laboratory, University of Illinois at Urbana at Champaign: Champaign, IL, USA, 2000. [Google Scholar]
Hyperparameter | Lower Limit | Upper Limit | Parameter Specification |
---|---|---|---|
Number of layers | 1 | 2 | integer |
Number of neurons per layer | 50 | 150 | integer |
Dropout Rate | 0.1 | 0.5 | - |
Initial Learning Rate | 1 × 10−4 | 1 × 10−2 | logarithmic |
Learning Rate Drop Factor | 0.1 | 0.9 | - |
Learning Rate Drop Period | 5 | 20 | integer |
MiniBatch Size | 16 | 64 | integer, discrete values * |
Hyperparameter | Parameter Value |
---|---|
Number of layers | 1 |
Number of neurons per layer | 59 |
Dropout Rate | 0.102 |
Initial Learning Rate | 0.0097 |
Learning Rate Drop Factor | 0.6007 |
Learning Rate Drop Period | 18 |
MiniBatch Size | 16 |
No. Data | 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 | 10 | 11 | 12 | 13 | 14 |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
MSE | 0.088 | 0.033 | 0.144 | 0.127 | 0.241 | 0.169 | 0.152 | 0.200 | 0.182 | 0.071 | 0.013 | 0.050 | 0.304 | 0.071 |
RMSE | 0.296 | 0.182 | 0.380 | 0.356 | 0.490 | 0.411 | 0.389 | 0.447 | 0.426 | 0.266 | 0.115 | 0.225 | 0.551 | 0.266 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Zhao, Y.; Lin, L.; Schlarb, A.K. Long Short-Term Memory Networks for the Automated Identification of the Stationary Phase in Tribological Experiments. Lubricants 2024, 12, 423. https://doi.org/10.3390/lubricants12120423
Zhao Y, Lin L, Schlarb AK. Long Short-Term Memory Networks for the Automated Identification of the Stationary Phase in Tribological Experiments. Lubricants. 2024; 12(12):423. https://doi.org/10.3390/lubricants12120423
Chicago/Turabian StyleZhao, Yuxiao, Leyu Lin, and Alois K. Schlarb. 2024. "Long Short-Term Memory Networks for the Automated Identification of the Stationary Phase in Tribological Experiments" Lubricants 12, no. 12: 423. https://doi.org/10.3390/lubricants12120423
APA StyleZhao, Y., Lin, L., & Schlarb, A. K. (2024). Long Short-Term Memory Networks for the Automated Identification of the Stationary Phase in Tribological Experiments. Lubricants, 12(12), 423. https://doi.org/10.3390/lubricants12120423