{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T06:52:01Z","timestamp":1782370321684,"version":"3.54.5"},"reference-count":41,"publisher":"MDPI AG","issue":"7","license":[{"start":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T00:00:00Z","timestamp":1782259200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2021YFB4000505"],"award-info":[{"award-number":["2021YFB4000505"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Information"],"abstract":"<jats:p>Detecting and identifying faults in industrial chemical plants is essential for safe and stable operation, and modern monitoring systems increasingly rely on deep learning to classify faults from multivariate sensor data. A practical obstacle to adoption is trust: most deep-learning diagnosers reach their decisions through a classification layer that operators cannot inspect, making it hard to see how the model maps process signals to a particular fault. This study targets fault diagnosis on the Tennessee Eastman (TE) process, a standard benchmark of simulated chemical-plant sensor data, and asks whether this final decision stage can be made directly inspectable without sacrificing accuracy. We propose CNN\u2013Transformer\u2013KAN (CTKAN), a hybrid model that learns local temporal patterns with a one-dimensional convolutional encoder, captures global inter-time-step dependencies with a Transformer encoder, and classifies faults with a Kolmogorov\u2013Arnold Network (KAN) head whose learnable B-spline activations can be plotted and examined individually, in place of a conventional multi-layer perceptron (MLP). On the TE benchmark, CTKAN attains a Macro-F1 of 91.38 \u00b1 0.26% over ten independent runs, comparable to a CNN + Transformer + MLP ablation (91.21 \u00b1 0.32%) and a capacity-matched MLP-head variant (91.43 \u00b1 0.37%) within seed-to-seed variability. The main finding is therefore not a higher score: at matched capacity the KAN and MLP heads are statistically indistinguishable in accuracy, so the KAN head\u2019s value is to add a directly inspectable view of the classification stage at no measurable accuracy cost, helping process engineers sanity-check how the diagnoser separates faults in safety-critical settings.<\/jats:p>","DOI":"10.3390\/info17070626","type":"journal-article","created":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T05:48:16Z","timestamp":1782366496000},"page":"626","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["CNN\u2013Transformer\u2013KAN: A Hybrid Deep-Learning Framework with an Inspectable KAN Classification Head for Industrial Process Fault Diagnosis"],"prefix":"10.3390","volume":"17","author":[{"given":"Yujie","family":"Wu","sequence":"first","affiliation":[{"name":"College of Computer Science and Cyber Security, Chengdu University of Technology, Chengdu 610059, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maoyu","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Cyber Security, Chengdu University of Technology, Chengdu 610059, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aoxuan","family":"Ding","sequence":"additional","affiliation":[{"name":"College of Computer Science and Cyber Security, Chengdu University of Technology, Chengdu 610059, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Hua","sequence":"additional","affiliation":[{"name":"School of Chemical Engineering, Sichuan University, Chengdu 610065, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhehao","family":"Jin","sequence":"additional","affiliation":[{"name":"School of Chemical Engineering, Sichuan University, Chengdu 610065, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6000-9160","authenticated-orcid":false,"given":"Yiyang","family":"Dai","sequence":"additional","affiliation":[{"name":"School of Chemical Engineering, Sichuan University, Chengdu 610065, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,6,24]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1016\/S0098-1354(02)00160-6","article-title":"A review of process fault detection and diagnosis: Part I","volume":"27","author":"Venkatasubramanian","year":"2003","journal-title":"Comput. Chem. Eng."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"6418","DOI":"10.1109\/TIE.2014.2301773","article-title":"A review on basic data-driven approaches for industrial process monitoring","volume":"61","author":"Yin","year":"2014","journal-title":"IEEE Trans. Ind. Electron."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Rakholia, R., Suarez-Cetrulo, A.L., Singh, M., and Simon Carbajo, R. (2025). Integrating AI and IoT for predictive maintenance in Industry 4.0 manufacturing environments: A practical approach. Information, 16.","DOI":"10.3390\/info16090737"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"116","DOI":"10.3390\/info10030116","article-title":"A self-learning fault diagnosis strategy based on multi-model fusion","volume":"10","author":"Wang","year":"2019","journal-title":"Information"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Daga, A.P., and Garibaldi, L. (2019). Machine vibration monitoring for diagnostics through hypothesis testing. Information, 10.","DOI":"10.3390\/info10060204"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"202","DOI":"10.3390\/info11040202","article-title":"SOPHIA: An event-based IoT and machine learning architecture for predictive maintenance in Industry 4.0","volume":"11","author":"Calabrese","year":"2020","journal-title":"Information"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Fernandes, S., Antunes, M., Santiago, A.R., Barraca, J.P., Gomes, D., and Aguiar, R.L. (2020). Forecasting appliances failures: A machine-learning approach to predictive maintenance. Information, 11.","DOI":"10.3390\/info11040208"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Solanes, J.E., Frances-Falip, A., Gracia, L., and Munoz, A. (2026). Bridging virtual and physical realms in industrial metaverses for enhanced process control. Information, 17.","DOI":"10.3390\/info17010071"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1016\/0098-1354(93)80018-I","article-title":"A plant-wide industrial process control problem","volume":"17","author":"Downs","year":"1993","journal-title":"Comput. Chem. Eng."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1016\/0169-7439(95)00076-3","article-title":"Disturbance detection and isolation by dynamic principal component analysis","volume":"30","author":"Ku","year":"1995","journal-title":"Chemom. Intell. Lab. Syst."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"327","DOI":"10.1016\/S0098-1354(02)00162-X","article-title":"A review of process fault detection and diagnosis: Part III","volume":"27","author":"Venkatasubramanian","year":"2003","journal-title":"Comput. Chem. Eng."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1016\/j.ymssp.2018.05.050","article-title":"Deep learning and its applications to machine health monitoring","volume":"115","author":"Zhao","year":"2019","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1016\/j.compchemeng.2018.04.009","article-title":"Deep convolutional neural network model based chemical process fault diagnosis","volume":"115","author":"Wu","year":"2018","journal-title":"Comput. Chem. Eng."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1016\/j.jprocont.2020.01.004","article-title":"One-dimensional convolutional auto-encoder-based feature learning for fault diagnosis of multivariate processes","volume":"87","author":"Chen","year":"2020","journal-title":"J. Process Control"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"824","DOI":"10.1021\/acs.iecr.9b05885","article-title":"Bidirectional recurrent neural network-based chemical process fault diagnosis","volume":"59","author":"Mou","year":"2020","journal-title":"Ind. Eng. Chem. Res."},{"key":"ref_17","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., and Polosukhin, I. (2017). Attention is all you need. Proceedings of the Advances in Neural Information Processing Systems, NIPS Foundation."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"8575","DOI":"10.1007\/s00521-021-06711-2","article-title":"Generalized transformer in fault diagnosis of Tennessee Eastman process","volume":"34","author":"Zhang","year":"2022","journal-title":"Neural Comput. Appl."},{"key":"ref_19","unstructured":"Labbaf-Khaniki, M.A., Manthouri, M., and Ajami, M. (2024). Twin Transformer using gated dynamic learnable attention mechanism for fault detection and diagnosis in the Tennessee Eastman process. arXiv."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"783","DOI":"10.1016\/j.psep.2024.04.012","article-title":"Fault detection of complicated processes based on an enhanced transformer network with graph attention mechanism","volume":"186","author":"Cao","year":"2024","journal-title":"Process Saf. Environ. Prot."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Xu, M., Wang, S., Guo, X., Gao, J., and Hu, A.P. (2025). Sequence-aware vision transformer with feature fusion for fault diagnosis in complex industrial processes. Entropy, 27.","DOI":"10.3390\/e27020181"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"34389","DOI":"10.1021\/acsomega.2c04017","article-title":"Fault diagnosis of the dynamic chemical process based on the optimized CNN-LSTM network","volume":"7","author":"Chen","year":"2022","journal-title":"ACS Omega"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"883","DOI":"10.1007\/s10489-025-06711-y","article-title":"Supervised deep learning algorithms for process fault detection and diagnosis under different temporal subsequence length of process data","volume":"55","author":"Kai","year":"2025","journal-title":"Appl. Intell."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1109\/TII.2023.3240601","article-title":"Explainable artificial intelligence for fault diagnosis of industrial processes","volume":"21","author":"Jang","year":"2025","journal-title":"IEEE Trans. Ind. Inform."},{"key":"ref_25","first-page":"100905","article-title":"Explainable AI for industrial fault diagnosis: A systematic review","volume":"47","author":"Cacao","year":"2025","journal-title":"J. Ind. Inf. Integr."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Liu, Z., Wang, Y., Vaidya, S., Ruehle, F., Halverson, J., Soljacic, M., Hou, T.Y., and Tegmark, M. (2025). KAN: Kolmogorov-Arnold Networks. Proceedings of the ICLR, ICLR.","DOI":"10.1103\/4t7t-v19l"},{"key":"ref_27","first-page":"953","article-title":"On the representation of continuous functions of many variables by superposition of continuous functions of one variable and addition","volume":"114","author":"Kolmogorov","year":"1957","journal-title":"Dokl. Akad. Nauk SSSR"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"7585","DOI":"10.3390\/s24237585","article-title":"Kolmogorov-Arnold network in the fault diagnosis of oil-immersed power transformers","volume":"24","author":"Cabral","year":"2024","journal-title":"Sensors"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"403","DOI":"10.3390\/e27040403","article-title":"Explainable fault classification and severity diagnosis in rotating machinery using Kolmogorov-Arnold Networks","volume":"27","author":"Rigas","year":"2025","journal-title":"Entropy"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"3672","DOI":"10.3390\/pr13113672","article-title":"Exploring Kolmogorov-Arnold networks for unsupervised anomaly detection in industrial processes","volume":"13","author":"Morales","year":"2025","journal-title":"Processes"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"1567","DOI":"10.1016\/j.jprocont.2012.06.009","article-title":"A comparison study of basic data-driven fault diagnosis and process monitoring methods on the benchmark Tennessee Eastman process","volume":"22","author":"Yin","year":"2012","journal-title":"J. Process Control"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"395","DOI":"10.1016\/j.compchemeng.2017.02.041","article-title":"A deep belief network based fault diagnosis model for complex chemical processes","volume":"107","author":"Zhang","year":"2017","journal-title":"Comput. Chem. Eng."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Chadha, G.S., and Schwung, A. (2017). Comparison of deep neural network architectures for fault detection in the Tennessee Eastman process. Proceedings of the IEEE International Conference on Emerging Technologies and Factory Automation (ETFA), IEEE.","DOI":"10.1109\/ETFA.2017.8247619"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"18489","DOI":"10.1038\/s41598-026-47377-x","article-title":"A multistage transfer learning framework for intelligent fault diagnosis of rotating machinery under variable operating conditions","volume":"16","author":"Siddique","year":"2026","journal-title":"Sci. Rep."},{"key":"ref_35","first-page":"100216","article-title":"Fault detection in Tennessee Eastman process with temporal deep learning models","volume":"23","author":"Lomov","year":"2021","journal-title":"J. Ind. Inf. Integr."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"17488","DOI":"10.1038\/s41598-026-48227-6","article-title":"Early-warning industrial fault detection based on physics-guided residual learning and calibrated CRNNs","volume":"16","author":"Khan","year":"2026","journal-title":"Sci. Rep."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"6448","DOI":"10.3390\/s24196448","article-title":"KAN-HyperMP: An enhanced fault diagnosis model for rolling bearings in noisy environments","volume":"24","author":"Wang","year":"2024","journal-title":"Sensors"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"3022","DOI":"10.3390\/math12193022","article-title":"C-KAN: A new approach for integrating convolutional layers with Kolmogorov-Arnold networks for time-series forecasting","volume":"12","author":"Livieris","year":"2024","journal-title":"Mathematics"},{"key":"ref_39","unstructured":"Kingma, D.P., and Ba, J. (2015). Adam: A method for stochastic optimization. Proceedings of the ICLR, ICLR."},{"key":"ref_40","unstructured":"Loshchilov, I., and Hutter, F. (2017). SGDR: Stochastic gradient descent with warm restarts. Proceedings of the ICLR, ICLR."},{"key":"ref_41","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Hinton","year":"2008","journal-title":"J. Mach. Learn. Res."}],"container-title":["Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2078-2489\/17\/7\/626\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T06:45:38Z","timestamp":1782369938000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2078-2489\/17\/7\/626"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,24]]},"references-count":41,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2026,7]]}},"alternative-id":["info17070626"],"URL":"https:\/\/doi.org\/10.3390\/info17070626","relation":{},"ISSN":["2078-2489"],"issn-type":[{"value":"2078-2489","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,24]]}}}