Robust Mechanical Fault Diagnosis Using Time-Frequency Feature Fusion and Deep Convolutional Neural Networks
Abstract
We study fault feature extraction and diagnosis for rotating machinery using a compact 1D CNN. The dataset comprises 322,800 labeled windows (2,048 points at 12–20 kHz) collected from laboratory benches and an industrial pumping station, covering normal operation and faults in bearings (inner/outer race, rolling-element spalling), gears (pitting, cracks), and motors (imbalance). The model stacks 5–8 convolutional layers with small kernels (3–5), Batch Normalization, ReLU, max-pooling, and two fully connected layers with dropout, followed by a softmax classifier. On a held-out test set, the method attains 96.8% overall accuracy and 95.0% macro-F1, outperforming support vector machines and a deep feed-forward network by +8.3 and +5.6 percentage points in accuracy, respectively. Robustness tests under additive noise maintain 92.8% accuracy at 5 dB. In a three-month on-site validation at a pumping station, the system detected incipient bearing cracks early and issued timely warnings with 96.5% online accuracy, reducing unplanned shutdown risk. These results indicate that the proposed CNN delivers accurate, robust, and field-ready diagnosis for predictive maintenance.References
Jardine AK, Lin D, Banjevic D. A review on machinery diagnostics and prognostics implementing condition-based maintenance. Mech Syst Signal Process. 2006; 20(7):1483-510.
China Machinery Industry Federation. China Machinery Industry Development Report 2022. Beijing: China Machine Press; 2022.
LeCun Y, Bengio Y, Hinton G. Deep learning. Nature. 2015; 521(7553):436-44.
U.S. Department of Energy. Operations and Maintenance Best Practices: A Guide to Achieving Operational Efficiency. Washington, DC: U.S. Department of Energy; 2021.
Ministry of Industry and Information Technology of the People’s Republic of China. Technology Roadmap for Key Areas of Made in China 2025. Beijing: Ministry of Industry and Information Technology; 2015.
Tang XY, Liu JC, Ying ZL. A path signature perspective of process data feature extraction. Br J Math Stat Psychol. 2025 May 26; doi:10.1111/bmsp.12390.
Zhou J, Shuang K, Wang QW, Qian B, Guo JY. Bi-directional feature learning-based approach for zero-shot event argument extraction. Inf Process Manag. 2025 Sep; 62(5):104199. doi:10.1016/j.ipm.2025.104199.
Yu H, Song WD, Zhang B, Zhu HB, Dai JG, Zhang JC. MMS-EF: A multi-scale modular extraction framework for enhancing deep learning models in remote sensing. Land. 2024 Nov; 13(11):1842. doi:10.3390/land13111842.
Kulkarni V, Nemade B, Patel S, Patel K, Velpula S. A short report on ADHD detection using convolutional neural networks. Front Psychiatry. 2024 Sep 5; 15:1426155. doi:10.3389/fpsyt.2024.1426155.
Tasci B. Multilevel hybrid handcrafted feature extraction based depression recognition method using speech. J Affect Disord. 2024 Nov 1; 364:9-19. doi:10.1016/j.jad.2024.08.002.
Ahanin Z, Ismail MA, Singh NSS, Al-Ashmori A, Syafrudin M, Alfian G, et al. Hybrid feature extraction for multi-label emotion classification in English text messages. Sustainability. 2023 Aug; 15(16):12539. doi:10.3390/su151612539.
Hu T, Wang HY, Law R, Geng J. Diverse feature extraction techniques in internet search query to forecast tourism demand: an in-depth comparison. Tour Manag Perspect. 2023 Jun; 47:101116. doi:10.1016/j.tmp.2023.101116.
Htun HH, Biehl M, Petkov N. Survey of feature selection and extraction techniques for stock market prediction. Financ Innov. 2023 Jan 12; 9(1):26. doi:10.1186/s40854-022-00441-7.
Chen J, Zhao ZX, Shu QF, Cai GL. Feature extraction based on microstate sequences for EEG-based emotion recognition. Front Psychol. 2022 Dec 23; 13:1065196. doi:10.3389/fpsyg.2022.1065196.
Doerig A, Krahmer B, Bosch V, Kietzmann TC. Emergence of topographic organization in a non-convolutional deep neural network. Perception. 2022 Dec; 51 Suppl 1:74-75.
He WP, Zhang PP, Liu X, Chen BQ, Guo BL. Group-sparse feature extraction via ensemble generalized minimax-concave penalty for wind-turbine-fault diagnosis. Sustainability. 2022 Dec; 14(24):16793. doi:10.3390/su142416793.
Zeman A, Leers T, De Beeck HO. Mooney face image processing in deep convolutional neural networks compared to humans. Perception. 2022 Dec; 51 Suppl 1:17-18.
Montero-Salgado JP, Muñoz-Sanz J, Arenas-Ramírez B, Alén-Cordero C. Identification of the mechanical failure factors with potential influencing road accidents in Ecuador. Int J Environ Res Public Health. 2022 Jul; 19(13):7787. doi:10.3390/ijerph19137787.
Wu Z, Qiao Y, Huang S, Liu HC. CVaR prediction model of the investment portfolio based on the convolutional neural network facilitates the risk management of the financial market. J Glob Inf Manag. 2022; 30(7). doi:10.4018/JGIM.293288.
Cortinovis D, De Beeck HO, Bracci S. The organization of body-parts representations in deep convolutional neural networks. Perception. 2021 Dec; 50 Suppl 1:123.
Tuo S, Chen TR, He H, Feng ZY, Zhu YL, Liu F, et al. A regional industrial economic forecasting model based on a deep convolutional neural network and big data. Sustainability. 2021 Nov; 13(22):12789. doi:10.3390/su132212789.
Xing BB, Xiao FY, Korogi YT, Ishimaru T, Xia Y. Direction-dependent mechanical-electrical-thermal responses of large-format prismatic Li-ion battery under mechanical abuse. J Energy Storage. 2021 Nov; 43:103270. doi:10.1016/j.est.2021.103270.
Heydari SM, Aris TNM, Yaakob R, Hamdan H. Data-driven forecasting and modeling of runoff flow to reduce flood risk using a novel hybrid wavelet-neural network based on feature extraction. Sustainability. 2021 Oct; 13(20):11537. doi:10.3390/su132011537.
Yu LA, Yu LH, Yu KT. A high-dimensionality-trait-driven learning paradigm for high dimensional credit classification. Financ Innov. 2021 Apr 30; 7(1):32. doi:10.1186/s40854-021-00249-x.
Lloret I, Troyano JA, Enríquez F, González-de-la-Rosa JJ. Two deep learning approaches to forecasting disaggregated freight flows: convolutional and encoder-decoder recurrent. Soft Comput. 2021 Jun; 25(12):7769-84. doi:10.1007/s00500-021-05678-5.
Yin HF, Ma S, Li HG, Wen GL, Santhanagopalan S, Zhang C. Modeling strategy for progressive failure prediction in lithium-ion batteries under mechanical abuse. eTransportation. 2021 Feb; 7:100098. doi:10.1016/j.etran.2020.100098.
Fan Y, Wake H, Taba J, Cooper E. Research on extracting mental lexicon from legal cases of players based on text features. Rev Psicol Deporte. 2021; 30(3):276-84.
Sanca S, Ostir K, Mangafic A. Building detection with convolutional networks trained with transfer learning. Geod Vestn. 2021; 65(4):559-93. doi:10.15292/geodetski-vestnik.2021.04.559-593.
DOI:
https://doi.org/10.31449/inf.v49i25.11327Downloads
Published
How to Cite
Issue
Section
License
I assign to Informatica, An International Journal of Computing and Informatics ("Journal") the copyright in the manuscript identified above and any additional material (figures, tables, illustrations, software or other information intended for publication) submitted as part of or as a supplement to the manuscript ("Paper") in all forms and media throughout the world, in all languages, for the full term of copyright, effective when and if the article is accepted for publication. This transfer includes the right to reproduce and/or to distribute the Paper to other journals or digital libraries in electronic and online forms and systems.
I understand that I retain the rights to use the pre-prints, off-prints, accepted manuscript and published journal Paper for personal use, scholarly purposes and internal institutional use.
In certain cases, I can ask for retaining the publishing rights of the Paper. The Journal can permit or deny the request for publishing rights, to which I fully agree.
I declare that the submitted Paper is original, has been written by the stated authors and has not been published elsewhere nor is currently being considered for publication by any other journal and will not be submitted for such review while under review by this Journal. The Paper contains no material that violates proprietary rights of any other person or entity. I have obtained written permission from copyright owners for any excerpts from copyrighted works that are included and have credited the sources in my article. I have informed the co-author(s) of the terms of this publishing agreement.
Copyright © Slovenian Society Informatika
