{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T20:55:33Z","timestamp":1788814533210,"version":"build-2803163510"},"reference-count":18,"publisher":"MDPI AG","issue":"16","license":[{"start":{"date-parts":[[2026,8,16]],"date-time":"2026-08-16T00:00:00Z","timestamp":1786838400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["51674134"],"award-info":[{"award-number":["51674134"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"award":["51674134"],"award-info":[{"award-number":["51674134"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"publisher"}]},{"name":"\u201cKey Technology Research Project on Electro-Hydraulic Proportional Control System for Shearer Drum Height Adjustment\u201d","award":["24-2074"],"award-info":[{"award-number":["24-2074"]}]},{"name":"\u201cFundamental Research on Multimodal Perception and CPS Collaborative Control for Intelligent Cutting in Complex Coal Seams\u201d","award":["2025-BS-0402"],"award-info":[{"award-number":["2025-BS-0402"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Coal\u2013rock cutting state recognition is essential for adaptive cutting and intelligent speed regulation in shearers. To address the limited representational capability of individual signals, the confusion between adjacent gangue-bearing cutting conditions, and the domain discrepancy between simulation and experimental data, a vibration\u2013current multimodal fusion method based on CORRECT-Net is proposed. First, an EDEM\u2013RecurDyn\u2013MATLAB\/Simulink co-simulation system was developed to generate cutting records for four coal\u2013rock states. After screening for physical equivalence and label conflicts, 158 valid records were retained and grouped into 150 physical-condition groups, which were partitioned at the group level into training, validation, and test sets. Subsequently, SincNet was employed to extract frequency-band-constrained features, a Transformer was used to model long-range temporal dependencies, and a residual importance-guided GATv2 module was introduced to perform cross-modal fusion of vibration-impact and current-load features. On 2500 test windows, CORRECT-Net achieved an accuracy of 96.20% \u00b1 0.11%, a macro-F1 score of 95.14% \u00b1 0.21%, and a hazardous-condition miss rate of 0.58% \u00b1 0.13%. Compared with the multimodal 1D-CNN, TCN, and Bi-LSTM models, CORRECT-Net improved the accuracy by 8.80, 4.00, and 2.08 percentage points, respectively. In the progressive ablation study, the accuracy increased from 87.40% \u00b1 0.26% to 96.20% \u00b1 0.11%, while the macro-F1 score increased from 84.57% \u00b1 0.34% to 95.14% \u00b1 0.21%. Under Gaussian noise with a standard deviation of 0.05, the model retained an accuracy of 92.76% \u00b1 0.24%. When the vibration and current modalities were separately unavailable, the corresponding accuracies were 86.56% \u00b1 0.37% and 92.44% \u00b1 0.25%, respectively. A five-fold simulation-to-experiment transfer evaluation was further conducted at the independent-run level using five experimental records per class. Without adaptation using experimental samples, the model achieved an accuracy of 91.33% \u00b1 5.19%. When 20% and 50% of the experimental windows were used for adaptation, the accuracy increased to 96.33% \u00b1 0.75% and 98.67% \u00b1 1.39%, respectively. These results demonstrate that CORRECT-Net effectively integrates mechanical vibration responses and motor-load information and, under the present simulation and experimental conditions, achieves high recognition accuracy, a low hazardous-condition miss rate, and effective adaptability to the experimental domain.<\/jats:p>","DOI":"10.3390\/s26165181","type":"journal-article","created":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T11:00:05Z","timestamp":1786964405000},"page":"5181","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["CORRECT-Net: A Multimodal Vibration\u2013Current Fusion Network for Coal\u2013Rock Cutting State Recognition in Shearers"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-7950-3262","authenticated-orcid":false,"given":"Lijuan","family":"Zhao","sequence":"first","affiliation":[{"name":"School of Mechanical Engineering, Liaoning Technical University, Fuxin 123000, China"},{"name":"Liaoning Province Key Laboratory of Large-Scale Industrial and Mining Equipment, Fuxin 123000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhanpeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering, Liaoning Technical University, Fuxin 123000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yadong","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering, Liaoning Technical University, Fuxin 123000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-0398-8939","authenticated-orcid":false,"given":"Tiangu","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering, Liaoning Technical University, Fuxin 123000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Hao","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering, Liaoning Technical University, Fuxin 123000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,8,16]]},"reference":[{"key":"ref_1","first-page":"181","article-title":"System engineering and key technologies research and practice of smart mine","volume":"49","author":"Wang","year":"2024","journal-title":"J. China Coal Soc."},{"key":"ref_2","first-page":"296","article-title":"Research progress and development trends in adaptive cutting technology for shearers","volume":"53","author":"Wang","year":"2025","journal-title":"Coal Sci. Technol."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"628","DOI":"10.1038\/s41597-024-03422-w","article-title":"A near-infrared spectroscopy dataset of coal and coal-measure rock under diverse conditions","volume":"11","author":"Lv","year":"2024","journal-title":"Sci. Data"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Yang, J., Zhang, Y., Wang, K., Tong, Y., Liu, J., and Wang, G. (2024). Coal\u2013rock data recognition method based on spectral dimension transform and CBAM-VIT. Appl. Sci., 14.","DOI":"10.3390\/app14020593"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"47646","DOI":"10.1021\/acsomega.3c05798","article-title":"Coal and gangue classification based on laser-induced breakdown spectroscopy and deep learning","volume":"8","author":"Xu","year":"2023","journal-title":"ACS Omega"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"80794","DOI":"10.1109\/ACCESS.2023.3300243","article-title":"Coal\u2013rock image recognition method for complex and harsh environment in coal mine using deep learning models","volume":"11","author":"Sun","year":"2023","journal-title":"IEEE Access"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"115834","DOI":"10.1016\/j.measurement.2024.115834","article-title":"Research on recognition of abnormal areas in infrared thermal images of coal and rock failure based on deep learning","volume":"242","author":"Zhao","year":"2025","journal-title":"Measurement"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"116861","DOI":"10.1016\/j.measurement.2025.116861","article-title":"A multi-module fusion network for coal\u2013rock interface recognition","volume":"247","author":"Qiao","year":"2025","journal-title":"Measurement"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1057","DOI":"10.1016\/j.ijmst.2025.05.009","article-title":"A novel coal\u2013rock recognition method in coal mining face based on fusing laser point cloud and images","volume":"35","author":"Liu","year":"2025","journal-title":"Int. J. Min. Sci. Technol."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"117139","DOI":"10.1016\/j.measurement.2025.117139","article-title":"Dynamic recognition of coal\u2013rock interface based on hardness characteristic preference and multisensor information fusion","volume":"250","author":"Wang","year":"2025","journal-title":"Measurement"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1007\/s40789-024-00704-x","article-title":"Research on coal\u2013rock identification method and data augmentation algorithm of comprehensive working face based on FL-Segformer","volume":"11","author":"Zhang","year":"2024","journal-title":"Int. J. Coal Sci. Technol."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"3489","DOI":"10.1038\/s41598-023-30617-9","article-title":"Analysis and construction of the coal and rock cutting state identification system in coal mine intelligent mining","volume":"13","author":"Zhang","year":"2023","journal-title":"Sci. Rep."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"115261","DOI":"10.1016\/j.measurement.2024.115261","article-title":"Traction resistance analysis and cutting state recognition of shearer based on numerical simulation","volume":"237","author":"Li","year":"2024","journal-title":"Measurement"},{"key":"ref_14","first-page":"200","article-title":"Analysis and experimental study on the vibration characteristics of the spiral drum of a shearer based on two-way coupling method","volume":"52","author":"Zhang","year":"2024","journal-title":"Coal Sci. Technol."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"26507","DOI":"10.1038\/s41598-024-77538-9","article-title":"Research on coal rock parameter calibration based on discrete element method","volume":"14","author":"Wang","year":"2024","journal-title":"Sci. Rep."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Ravanelli, M., and Bengio, Y. (2018). Speaker recognition from raw waveform with SincNet. 2018 IEEE Spoken Language Technology Workshop (SLT), Athens, Greece, 18\u201321 December 2018, IEEE.","DOI":"10.1109\/SLT.2018.8639585"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Moroto, Y., Maeda, K., Togo, R., Ogawa, T., and Haseyama, M. (2024). Multimodal Transformer model using time-series data to classify winter road surface conditions. Sensors, 24.","DOI":"10.3390\/s24113440"},{"key":"ref_18","unstructured":"Brody, S., Alon, U., and Yahav, E. (2022, January 25\u201329). How attentive are graph attention networks?. Proceedings of the Tenth International Conference on Learning Representations (ICLR 2022), Virtual Event."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/16\/5181\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T11:05:21Z","timestamp":1786964721000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/16\/5181"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,16]]},"references-count":18,"journal-issue":{"issue":"16","published-online":{"date-parts":[[2026,8]]}},"alternative-id":["s26165181"],"URL":"https:\/\/doi.org\/10.3390\/s26165181","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,16]]}}}