{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T16:17:25Z","timestamp":1765383445567,"version":"3.46.0"},"reference-count":32,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T00:00:00Z","timestamp":1765324800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Shenzhen University of Information Technology","award":["SZIIT2025KJ022","SZIIT2025KJ021","SZIIT2025KJ057"],"award-info":[{"award-number":["SZIIT2025KJ022","SZIIT2025KJ021","SZIIT2025KJ057"]}]},{"DOI":"10.13039\/501100001809","name":"Major Research Plan of the National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["92467204"],"award-info":[{"award-number":["92467204"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Algorithms"],"abstract":"<jats:p>Predominant fault diagnosis in industrial robots depends on dedicated vibration or acoustics sensors. However, their practical deployment is often limited by installation constraints, susceptibility to environmental noise, and cost considerations. Applying Energy-Based Maintenance (EBM) principles to achieve enhanced fault diagnosis under practical industrial conditions, we propose a hybrid deep learning framework, the Multi-head Graph Attention Network (MGAT) with Multi-scale CNNBiLSTM Fusion (MGAT-MCNNBiLSTM) for industrial robots. This approach obviates the need for additional dedicated sensors, effectively mitigating associated deployment complexities. The framework embodies four core innovations: (1) Based on the EBM paradigm, motor current is established as the most effective and practical choice for enabling cost-efficient and scalable industrial robot fault diagnosis. A corresponding dataset of motor current has been acquired from industrial robots operating under diverse fault scenarios. (2) An integrated MGAT-MCNNBiLSTM architecture that synergistically models multiscale local features and complex dynamics through its MCNNBiLSTM module while capturing nonlinear interdependencies via MGAT. This comprehensive feature representation enables robust and highly accurate fault detection. (3) The study found that the application of spectral preprocessing techniques yields a marked and statistically significant enhancement in diagnostic performance. A comprehensive and systematic analysis was undertaken to uncover the underlying reasons for this observed performance improvement. (4) To emulate challenging industrial settings and cost-sensitive implementations, noise signal injection was employed to evaluate model robustness in high-electromagnetic-interference environments and low-cost, low-resolution ADC implementations. Experimental validation on real-world industrial robot datasets demonstrates that MGAT-MCNNBiLSTM achieves a superior diagnostic accuracy of 90.7560%. This performance marks a significant absolute improvement of 1.51\u20138.55% over competing models, including LCNNBiLSTM, SCNNBiLSTM, MCCBiLSTM, GAT, and MGAT. Under challenging noise and low-resolution conditions, the proposed model consistently outperforms CNNBiLSTM variants, GAT, and MGAT with an improvement of 1.37\u201310.26% and enhanced industrial utility and deployment potential.<\/jats:p>","DOI":"10.3390\/a18120779","type":"journal-article","created":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T16:11:18Z","timestamp":1765383078000},"page":"779","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Hybrid Deep Learning Framework for Enhanced Fault Diagnosis in Industrial Robots"],"prefix":"10.3390","volume":"18","author":[{"given":"Jun","family":"Wu","sequence":"first","affiliation":[{"name":"School of Sino-German Robotics, Shenzhen University of Information Technology, Shenzhen 518172, China"},{"name":"Inovance Industrial Robot Reliability Technology Research Institute, Shenzhen University of Information Technology, Shenzhen 518172, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9178-1372","authenticated-orcid":false,"given":"Yuepeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Sino-German Robotics, Shenzhen University of Information Technology, Shenzhen 518172, China"},{"name":"Inovance Industrial Robot Reliability Technology Research Institute, Shenzhen University of Information Technology, Shenzhen 518172, China"}]},{"given":"Bo","family":"Gao","sequence":"additional","affiliation":[{"name":"School of Sino-German Robotics, Shenzhen University of Information Technology, Shenzhen 518172, China"},{"name":"Inovance Industrial Robot Reliability Technology Research Institute, Shenzhen University of Information Technology, Shenzhen 518172, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4132-5954","authenticated-orcid":false,"given":"Linzhong","family":"Xia","sequence":"additional","affiliation":[{"name":"School of Sino-German Robotics, Shenzhen University of Information Technology, Shenzhen 518172, China"},{"name":"Inovance Industrial Robot Reliability Technology Research Institute, Shenzhen University of Information Technology, Shenzhen 518172, China"}]},{"given":"Xueli","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Sino-German Robotics, Shenzhen University of Information Technology, Shenzhen 518172, China"},{"name":"Inovance Industrial Robot Reliability Technology Research Institute, Shenzhen University of Information Technology, Shenzhen 518172, China"}]},{"given":"Hui","family":"Wang","sequence":"additional","affiliation":[{"name":"Inovance Industrial Robot Reliability Technology Research Institute, Shenzhen University of Information Technology, Shenzhen 518172, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3018-9751","authenticated-orcid":false,"given":"Xiongbo","family":"Wan","sequence":"additional","affiliation":[{"name":"School of Automation, China University of Geosciences, Wuhan 430074, China"}]}],"member":"1968","published-online":{"date-parts":[[2025,12,10]]},"reference":[{"key":"ref_1","unstructured":"IFR (2025, October 28). World Robotics 2025. Available online: https:\/\/ifr.org\/downloads\/press_docs\/PressConference2025_presentation.pdf."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"218","DOI":"10.3390\/vibration6010014","article-title":"Deep transfer learning models for industrial fault diagnosis using vibration and acoustic sensors data: A review","volume":"6","author":"Bhuiyan","year":"2023","journal-title":"Vibration"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"124169","DOI":"10.1016\/j.eswa.2024.124169","article-title":"Review of rotating machinery elements condition monitoring using acoustic emission signal","volume":"252","author":"Kundu","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Chauhan, S., Vashishtha, G., and Kaur, P. (2025). An Effective Approach to Rotatory Fault Diagnosis Combining CEEMDAN and Feature-Level Integration. Algorithms, 18.","DOI":"10.3390\/a18100644"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"233","DOI":"10.1016\/j.jmsy.2022.12.001","article-title":"In-situ fault diagnosis for the harmonic reducer of industrial robots via multi-scale mixed convolutional neural networks","volume":"66","author":"He","year":"2023","journal-title":"J. Manuf. Syst."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"114451","DOI":"10.1016\/j.measurement.2024.114451","article-title":"Extracting random forest features with improved adaptive particle swarm optimization for industrial robot fault diagnosis","volume":"229","author":"Wu","year":"2024","journal-title":"Measurement"},{"key":"ref_7","first-page":"1","article-title":"Harmonic reducer fault detection with acoustic emission","volume":"72","author":"Liu","year":"2023","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Hu, Q., Zhang, Y., Xie, X., Su, W., Li, Y., Shan, L., and Yu, X. (2022). Optimal placement of vibration sensors for industrial robots based on Bayesian theory. Appl. Sci., 12.","DOI":"10.3390\/app12126086"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Elahi, M., Afolaranmi, S.O., Mohammed, W.M., and Martinez Lastra, J.L. (2022). Energy-Based Prognostics for Gradual Loss of Conveyor Belt Tension in Discrete Manufacturing Systems. Energies, 15.","DOI":"10.3390\/en15134705"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"137177","DOI":"10.1016\/j.jclepro.2023.137177","article-title":"From predictive to energy-based maintenance paradigm: Achieving cleaner production through functional-productiveness","volume":"408","author":"Oros","year":"2023","journal-title":"J. Clean. Prod."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Howell, M.T., and Alshakhshir, F. (2020). Energy Centered Maintenance: A Green Maintenance System, River Publishers.","DOI":"10.1201\/9781003151371"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Ma, Z., and Fu, L. (2025). A Review of Key Signal Processing Techniques for Structural Health Monitoring: Highlighting Non-Parametric Time-Frequency Analysis, Adaptive Decomposition, and Deconvolution. Algorithms, 18.","DOI":"10.20944\/preprints202502.1299.v1"},{"key":"ref_13","first-page":"417","article-title":"Mechanical fault detection based on machine learning for robotic RV reducer using electrical current signature analysis: A data-driven approach","volume":"9","author":"Raouf","year":"2022","journal-title":"J. Comput. Des. Eng."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Lee, I., Park, H.J., Jang, J.-W., Kim, C.-W., and Choi, J.-H. (2023). System-level fault diagnosis for an industrial wafer transfer robot with multi-component failure modes. Appl. Sci., 13.","DOI":"10.3390\/app131810243"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1483","DOI":"10.1007\/s10845-021-01736-9","article-title":"A kmap optimized VMD-SVM model for milling chatter detection with an industrial robot","volume":"33","author":"Wang","year":"2022","journal-title":"J. Intell. Manuf."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Peng, B., Bi, Y., Xue, B., Zhang, M., and Wan, S. (2022). A Survey on Fault Diagnosis of Rolling Bearings. Algorithms, 15.","DOI":"10.3390\/a15100347"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"44","DOI":"10.21595\/jve.2023.23391","article-title":"A comprehensive review of mechanical fault diagnosis methods based on convolutional neural network","volume":"26","author":"Hou","year":"2024","journal-title":"J. Vibroengineering"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"94250","DOI":"10.1109\/ACCESS.2024.3425166","article-title":"A comprehensive review of convolutional neural networks for defect detection in industrial applications","volume":"12","author":"Khanam","year":"2024","journal-title":"IEEE Access"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1007\/s43684-022-00031-5","article-title":"Fault diagnosis of industrial robot based on dual-module attention convolutional neural network","volume":"2","author":"Lu","year":"2022","journal-title":"Auton. Intell. Syst."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Pan, J., Qu, L., and Peng, K. (2021). Sensor and actuator fault diagnosis for robot joint based on deep CNN. Entropy, 23.","DOI":"10.3390\/e23060751"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"102068","DOI":"10.1016\/j.jksuci.2024.102068","article-title":"RNN-LSTM: From applications to modeling techniques and beyond\u2014Systematic review","volume":"36","author":"Hassan","year":"2024","journal-title":"J. King Saud Univ. Comput. Inf. Sci."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"5929","DOI":"10.1007\/s10462-020-09838-1","article-title":"A review on the long short-term memory model","volume":"53","author":"Mosquera","year":"2020","journal-title":"Artif. Intell. Rev."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"121136","DOI":"10.1016\/j.eswa.2023.121136","article-title":"Data-driven and knowledge-based predictive maintenance method for industrial robots for the production stability of intelligent manufacturing","volume":"234","author":"Wang","year":"2023","journal-title":"Expert Syst. Appl."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"1477","DOI":"10.1007\/s00170-022-10792-1","article-title":"A novel method for bearing fault diagnosis based on BiLSTM neural networks","volume":"125","author":"Nacer","year":"2023","journal-title":"Int. J. Adv. Manuf. Technol."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"15292","DOI":"10.1109\/JSEN.2024.3377234","article-title":"Intelligent joint actuator fault diagnosis for heavy-duty industrial robots","volume":"24","author":"Wang","year":"2024","journal-title":"IEEE Sens. J."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"2572","DOI":"10.1109\/JSEN.2021.3137992","article-title":"Fault detection of the harmonic reducer based on CNN-LSTM with a novel denoising algorithm","volume":"22","author":"Zhi","year":"2021","journal-title":"IEEE Sens. J."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"102644","DOI":"10.1016\/j.aei.2024.102644","article-title":"Advanced AIoT for failure classification of industrial diesel generators based hybrid deep learning CNN-BiLSTM algorithm","volume":"62","author":"Thanh","year":"2024","journal-title":"Adv. Eng. Inform."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"108653","DOI":"10.1016\/j.ymssp.2021.108653","article-title":"The emerging graph neural networks for intelligent fault diagnostics and prognostics: A guideline and a benchmark study","volume":"168","author":"Li","year":"2022","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Liu, Z., and Zhou, J. (2022). Introduction to Graph Neural Networks, Springer Nature.","DOI":"10.1007\/978-981-16-6054-2_27"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"5286","DOI":"10.1038\/s41598-023-32369-y","article-title":"A graph neural network-based bearing fault detection method","volume":"13","author":"Xiao","year":"2023","journal-title":"Sci. Rep."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Vrahatis, A.G., Lazaros, K., and Kotsiantis, S. (2024). Graph attention networks: A comprehensive review of methods and applications. Future Internet, 16.","DOI":"10.3390\/fi16090318"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"075012","DOI":"10.1088\/1361-6501\/ac56f1","article-title":"Bearing fault diagnosis method based on a multi-head graph attention network","volume":"33","author":"Jiang","year":"2022","journal-title":"Meas. Sci. Technol."}],"container-title":["Algorithms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-4893\/18\/12\/779\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T16:12:58Z","timestamp":1765383178000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-4893\/18\/12\/779"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,10]]},"references-count":32,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["a18120779"],"URL":"https:\/\/doi.org\/10.3390\/a18120779","relation":{},"ISSN":["1999-4893"],"issn-type":[{"value":"1999-4893","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,10]]}}}