Abstract
The purpose is to improve the accuracy of common fault diagnosis in mechanical engineering. With deep learning technology, this exploration first analyzes the current situation of the most common rolling bearing fault diagnosis in mechanical engineering. It introduces the application of convolutional neural networks and long short-term memory (LSTM) in fault diagnosis. Next, a rolling bearing fault diagnosis method is constructed based on a hyperparameter optimization algorithm and LSTM; after inputting the initial vibration acceleration data into the LSTM, the hyperparameter optimization algorithm is adopted to optimize the network structure model globally. After the algorithm optimization, the accuracy reaches 95.91%, 98.93%, and 99.89%, respectively, which are improved to varying degrees. Moreover, the results based on the hyperparameter optimization algorithm and LSTM are the best, with an increase of 4.35%. The average accuracy rates of LSTM Particle Swarm Optimization—LSTM, Random Search—LSTM, and hyperparameter optimization—LSTM are 95.89%, 96.77%, 93.56%, and 99.81%, respectively. The results show that the fault diagnosis ability of the hyperparameter optimization—LSTM algorithm is superior to the other three diagnosis models. Applying the deep learning network to the fault diagnosis of practical bearings provides a new idea for studying mechanical faults.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Data availability
No datasets were generated or analyzed during the current study.
Code availability
Not applicable.
References
Aruna R, Kushwah VS, Praveen SP, Pradhan R, Chinchawade AJ, Asaad RR, Kumar RL (2024) Coalescing novel QoS routing with fault tolerance for improving QoS parameters in wireless Ad-Hoc network using craft protocol. Wirel Netw 30:711–735
Bai R, Xu Q, Meng Z et al (2021) Rolling bearing fault diagnosis based on multi-channel convolution neural network and multi-scale clipping fusion data augmentation. Measurement 184:109885
Che C, Wang H, Ni X et al (2021) Hybrid multimodal fusion with deep learning for rolling bearing fault diagnosis. Measurement 173:108655
Chen Z, Deng S, Chen X et al (2017) Deep neural networks-based rolling bearing fault diagnosis. Microelectron Reliab 75:327–333
Cheng J, Yang Y, Li X et al (2021) Adaptive periodic mode decomposition and its application in rolling bearing fault diagnosis. Mech Syst Signal Process 161:107943
Guo B, Hu J, Wu W et al (2019) The Tabu_Genetic algorithm: a novel method for hyper-parameter optimization of learning algorithms. Electronics 8(5):579
Han T, Zhang L, Yin Z et al (2021) Rolling bearing fault diagnosis with combined convolutional neural networks and support vector machine. Measurement 177:109022
He Y, Nie B, Zhang J, Kumar PM, Muthu B (2022) Fault detection and diagnosis of cyber-physical system using the computer vision and image processing. Wirel Pers Commun 127:2141–2160
Hoang DT, Kang HJ (2019) A survey on deep learning based bearing fault diagnosis. Neurocomputing 335:327–335
Jha RK, Swami PD (2020) Intelligent fault diagnosis of rolling bearing and gear system under fluctuating load conditions using image processing technique. J Mech Sci Technol 34(10):4107–4115
Jiang S, Xuan J, Duan J et al (2021) Dual attention dense convolutional network for intelligent fault diagnosis of spindle-rolling bearings. J Vib Control 27(21–22):2403–2419
Kattenborn T, Leitloff J, Schiefer F et al (2021) Review on convolutional neural networks (CNN) in vegetation remote sensing. ISPRS J Photogramm Remote Sens 173:24–49
Li X, Peng L, Yao X et al (2017) Long short-term memory neural network for air pollutant concentration predictions: method development and evaluation. Environ Pollut 231:997–1004
Li Y, Yang Y, Wang X et al (2018) Early fault diagnosis of rolling bearings based on hierarchical symbol dynamic entropy and binary tree support vector machine. J Sound Vib 428:72–86
Li X, Jiang H, Niu M et al (2020) An enhanced selective ensemble deep learning method for rolling bearing fault diagnosis with beetle antennae search algorithm. Mech Syst Signal Process 142:106752
Liang M, Cao P, Tang J (2021) Rolling bearing fault diagnosis based on feature fusion with parallel convolutional neural network. Int J Adv Manuf Technol 112(3):819–831
Liu Y, Cao B, Li H (2021) Improving ant colony optimization algorithm with epsilon greedy and Levy flight. Complex Intell Syst 7(4):1711–1722
Papyan V, Romano Y, Sulam J et al (2018) Theoretical foundations of deep learning via sparse representations: a multilayer sparse model and its connection to convolutional neural networks. IEEE Signal Process Mag 35(4):72–89
Sherstinsky A (2020) Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network. Physica D 404:132306
Wan L, Li H, Chen Y et al (2020) Rolling bearing fault prediction method based on QPSO-BP neural network and dempster–shafer evidence theory. Energies 13(5):1094
Wang Y, Tang B, Qin Y et al (2020a) Rolling bearing fault detection of civil aircraft engine based on adaptive estimation ofinstantaneous angular speed. IEEE Trans Ind Inform 16:4938–4948
Wang X, Zhao Y, Pourpanah F (2020b) Recent advances in deep learning. Int J Mach Learn Cybern 11(4):747–750
Xu Y, Li Z, Wang S et al (2021) A hybrid deep-learning model for fault diagnosis of rolling bearings. Measurement 169:108502
Zhang K, Xu Y, Liao Z et al (2021) A novel fast entrogram and its applications in rolling bearing fault diagnosis. Mech Syst Signal Process 154:107582
Funding
This work was supported by Jiaxing Key Laboratory of Aero-Engine Manufacturing Technology for Key Components (Project No. 2021004).
Author information
Authors and Affiliations
Contributions
Weifeng Meng and Pengpei Zhao are responsible for designing the framework, analyzing performance, validating the results, and writing the article. Yongjie Shi, Liantao Li, and Zhenyao Meng are responsible for collecting the information required for the framework, providing software, conducting critical reviews, and administering the process.
Corresponding author
Ethics declarations
Conflict of interest
Authors do not have any conflicts.
Ethical approval
This article contains no studies with human participants performed by authors.
Informed consent
Not Applicable.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Meng, W., Zhao, P., Shi, Y. et al. Intelligent fault diagnosis of mechanical engineering using NLF-LSTM optimized deep learning model. Optim Eng (2024). https://doi.org/10.1007/s11081-024-09904-5
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s11081-024-09904-5