{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T22:15:26Z","timestamp":1784240126256,"version":"3.55.0"},"reference-count":48,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100005045","name":"Ministry of Finance of the People's Republic of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100005045","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007765","name":"Shenyang Science and Technology Bureau","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100007765","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Expert Systems with Applications"],"published-print":{"date-parts":[[2027,1]]},"DOI":"10.1016\/j.eswa.2026.133481","type":"journal-article","created":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T15:41:14Z","timestamp":1783698074000},"page":"133481","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PC","title":["MLRE-WDD: A lightweight mixture of low-rank experts framework for weld defect detection in intelligent pipeline systems"],"prefix":"10.1016","volume":"332","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-1103-8341","authenticated-orcid":false,"given":"Zhen","family":"Zhao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1256-1337","authenticated-orcid":false,"given":"Jinhai","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4682-4278","authenticated-orcid":false,"given":"Shuai","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1573-1015","authenticated-orcid":false,"given":"Liwei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0595-7314","authenticated-orcid":false,"given":"Fengyuan","family":"Zuo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.eswa.2026.133481_bib0001","unstructured":"Achiam, O. J., Adler, S., Agarwal, S., Ahmad, L., & Akkaya, I. (2023). GPT-4 technical report. https:\/\/api.semanticscholar.org\/CorpusID:257532815."},{"key":"10.1016\/j.eswa.2026.133481_bib0002","series-title":"2024\u202fIEEE\/CVF conference on computer vision and pattern recognition (CVPR)","first-page":"16196","article-title":"MTLoRA: A low-rank adaptation approach for efficient multi-task learning","author":"Agiza","year":"2024"},{"key":"10.1016\/j.eswa.2026.133481_bib0003","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., & Zagoruyko, S. (2020). End-to-end object detection with transformers. ArXiv:abs\/2005.12872. https:\/\/api.semanticscholar.org\/CorpusID:218889832.","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"10.1016\/j.eswa.2026.133481_bib0004","first-page":"1","article-title":"DLA-Net: A dynamically learnable attention network for intelligent surface visual inspection of aero-engine blades","volume":"74","author":"Chen","year":"2025","journal-title":"IEEE Transactions on Instrumentation and Measurement"},{"key":"10.1016\/j.eswa.2026.133481_bib0005","series-title":"2023\u202fIEEE\/CVF international conference on computer vision (ICCV)","first-page":"17300","article-title":"AdaMV-MoE: Adaptive multi-task vision mixture-of-experts","author":"Chen","year":"2023"},{"key":"10.1016\/j.eswa.2026.133481_bib0006","unstructured":"Comanici, G., Bieber, E., Schaekermann, M., & Pasupat, I. (2025). Gemini 2.5: Pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities. arXiv: 2507.06261. https:\/\/api.semanticscholar.org\/CorpusID:280151524."},{"key":"10.1016\/j.eswa.2026.133481_bib0007","unstructured":"DeepSeek-AI, Liu, A., Feng, B., Xue, B., & Wang, B.-L. (2024). DeepSeek-V3 technical report. https:\/\/api.semanticscholar.org\/CorpusID:282749848."},{"key":"10.1016\/j.eswa.2026.133481_bib0008","doi-asserted-by":"crossref","first-page":"10088","DOI":"10.52202\/075280-0441","article-title":"QLoRA: Efficient finetuning of quantized llms","volume":"36","author":"Dettmers","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"4","key":"10.1016\/j.eswa.2026.133481_bib0009","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1007\/s10921-015-0315-7","article-title":"GDXray: The database of X-ray images for nondestructive testing","volume":"34","author":"Domingo","year":"2015","journal-title":"Journal of Nondestructive Evaluation"},{"key":"10.1016\/j.eswa.2026.133481_bib0010","series-title":"2025\u202fIEEE\/CVF conference on computer vision and pattern recognition (CVPR)","first-page":"30534","article-title":"CL-LoRA: Continual low-rank adaptation for rehearsal-free class-incremental learning","author":"He","year":"2025"},{"issue":"2","key":"10.1016\/j.eswa.2026.133481_bib0011","first-page":"3","article-title":"LoRA: Low-rank adaptation of large language models","volume":"1","author":"Hu","year":"2022","journal-title":"ICLR"},{"issue":"1","key":"10.1016\/j.eswa.2026.133481_bib0012","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1162\/neco.1991.3.1.79","article-title":"Adaptive mixtures of local experts","volume":"3","author":"Jacobs","year":"1991","journal-title":"Neural Computation"},{"key":"10.1016\/j.eswa.2026.133481_bib0013","doi-asserted-by":"crossref","DOI":"10.1016\/j.ndteint.2022.102764","article-title":"Defects detection in weld joints based on visual attention and deep learning","volume":"133","author":"Ji","year":"2023","journal-title":"NDT and E International"},{"key":"10.1016\/j.eswa.2026.133481_bib0014","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.123254","article-title":"Casting defect region segmentation method based on dual-channel encoding\u2013fusion decoding network","volume":"247","author":"Jiang","year":"2024","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.133481_bib0015","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.125402","article-title":"Nondestructive inspection method of welding rate for heat sink fins with complex structure via infrared thermography principle and deep learning method","volume":"260","author":"Jiang","year":"2025","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.133481_bib0016","unstructured":"Jocher, G. (2022). ultralytics\/yolov5: V7.0 - YOLOv5 SOTA realtime instance segmentation,. 10.5281\/zenodo.7347926."},{"key":"10.1016\/j.eswa.2026.133481_bib0017","unstructured":"Lei, M., Li, S., Wu, Y., Hu, H., Zhou, Y., Zheng, X., Ding, G., Du, S., Wu, Z., & Gao, Y. (2025). YOLOv13: Real-time object detection with hypergraph-enhanced adaptive visual perception. ArXiv:abs\/2506.17733. https:\/\/api.semanticscholar.org\/CorpusID:279999878."},{"key":"10.1016\/j.eswa.2026.133481_bib0018","doi-asserted-by":"crossref","DOI":"10.1016\/j.ymssp.2023.110484","article-title":"Defect detection method for high-resolution weld based on wandering Gaussian and multi-feature enhancement fusion","volume":"199","author":"Li","year":"2023","journal-title":"Mechanical Systems and Signal Processing"},{"key":"10.1016\/j.eswa.2026.133481_bib0019","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2024.108379","article-title":"Synthetic data augmentation for high-resolution X-ray welding defect detection and classification based on a small number of real samples","volume":"133","author":"Li","year":"2024","journal-title":"Engineering Applications of Artificial Intelligence"},{"key":"10.1016\/j.eswa.2026.133481_bib0020","series-title":"2024\u202fIEEE\/CVF conference on computer vision and pattern recognition (CVPR)","first-page":"23638","article-title":"InfLoRA: Interference-free low-rank adaptation for continual learning","author":"Liang","year":"2024"},{"key":"10.1016\/j.eswa.2026.133481_bib0021","unstructured":"Lin, X., Peng, J., Gan, Z., Zhu, J., & Liu, J. (2025). YOLO-master: MoE-accelerated with specialized transformers for enhanced real-time detection. https:\/\/api.semanticscholar.org\/CorpusID:284312288."},{"key":"10.1016\/j.eswa.2026.133481_bib0022","first-page":"1","article-title":"A flexible multitask framework with decoupled training paradigm for radiographic weld images","volume":"74","author":"Liu","year":"2025","journal-title":"IEEE Transactions on Instrumentation and Measurement"},{"key":"10.1016\/j.eswa.2026.133481_bib0023","doi-asserted-by":"crossref","DOI":"10.1016\/j.compind.2021.103559","article-title":"A lightweight and accurate recognition framework for signs of X-ray weld images","volume":"135","author":"Liu","year":"2022","journal-title":"Computers in Industry"},{"key":"10.1016\/j.eswa.2026.133481_sbref0024","series-title":"European conference on computer vision","article-title":"Grounding DINO: Marrying DINO with grounded pre-training for open-set object detection","author":"Liu","year":"2023"},{"key":"10.1016\/j.eswa.2026.133481_bib0025","series-title":"Forty-first international conference on machine learning","article-title":"DoRA: Weight-decomposed low-rank adaptation","author":"Liu","year":"2024"},{"key":"10.1016\/j.eswa.2026.133481_bib0026","unstructured":"Lv, W., Zhao, Y., Chang, Q., Huang, K., Wang, G., & Liu, Y. (2024). RT-DETRv2: Improved baseline with bag-of-freebies for real-time detection transformer. https:\/\/arxiv.org\/abs\/2407.17140."},{"key":"10.1016\/j.eswa.2026.133481_bib0027","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2023.121700","article-title":"WeldNet: A deep learning based method for weld seam type identification and initial point guidance","volume":"238","author":"Ma","year":"2024","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.133481_bib0028","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106940","article-title":"An object detection-based model for automated screening of stem-cells senescence during drug screening","volume":"183","author":"Ren","year":"2025","journal-title":"Neural Networks"},{"key":"10.1016\/j.eswa.2026.133481_bib0029","doi-asserted-by":"crossref","DOI":"10.1016\/j.aei.2025.103125","article-title":"Feature knowledge distillation-based model lightweight for prohibited item detection in X-ray security inspection images","volume":"65","author":"Ren","year":"2025","journal-title":"Advanced Engineering Informatics"},{"key":"10.1016\/j.eswa.2026.133481_bib0030","first-page":"8583","article-title":"Scaling vision with sparse mixture of experts","volume":"34","author":"Riquelme","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.133481_bib0031","article-title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer","author":"Shazeer","year":"2017","journal-title":"CoRR"},{"issue":"7","key":"10.1016\/j.eswa.2026.133481_bib0032","doi-asserted-by":"crossref","first-page":"9725","DOI":"10.1109\/TII.2024.3383513","article-title":"MFANet: Multifeature aggregation network for cross-granularity few-shot seamless steel tubes surface defect segmentation","volume":"20","author":"Song","year":"2024","journal-title":"IEEE Transactions on Industrial Informatics"},{"key":"10.1016\/j.eswa.2026.133481_bib0033","unstructured":"Tian, Y., Ye, Q., & Doermann, D. S. (2025). YOLOv12: Attention-centric real-time object detectors. ArXiv:abs\/2502.12524. https:\/\/api.semanticscholar.org\/CorpusID:276422323."},{"issue":"12","key":"10.1016\/j.eswa.2026.133481_bib0034","doi-asserted-by":"crossref","first-page":"14114","DOI":"10.1109\/TII.2024.3441638","article-title":"Large-scale visual language model boosted by contrast domain adaptation for intelligent industrial visual monitoring","volume":"20","author":"Wang","year":"2024","journal-title":"IEEE Transactions on Industrial Informatics"},{"key":"10.1016\/j.eswa.2026.133481_bib0035","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.126386","article-title":"On the effect of the attention mechanism for automatic welding defects detection based on deep learning","volume":"268","author":"Wang","year":"2025","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.133481_bib0036","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1016\/j.jmapro.2025.02.039","article-title":"A comprehensive review of welding defect recognition from x-ray images","volume":"140","author":"Wang","year":"2025","journal-title":"Journal of Manufacturing Processes"},{"key":"10.1016\/j.eswa.2026.133481_bib0037","series-title":"2025\u202fIEEE\/CVF conference on computer vision and pattern recognition (CVPR)","first-page":"10203","article-title":"dFLMoE: Decentralized federated learning via mixture of experts for medical data analysis","author":"Xie","year":"2025"},{"key":"10.1016\/j.eswa.2026.133481_bib0038","unstructured":"Yang, A., Li, A., Yang, B., & Zhang, B. (2025). Qwen3 technical report. ArXiv:abs\/2505.09388. https:\/\/api.semanticscholar.org\/CorpusID:278602855."},{"key":"10.1016\/j.eswa.2026.133481_bib0039","doi-asserted-by":"crossref","DOI":"10.1016\/j.measurement.2023.113619","article-title":"Generalized weld bead region of interest localization and improved faster R-CNN for weld defect recognition","volume":"222","author":"Yang","year":"2023","journal-title":"Measurement"},{"key":"10.1016\/j.eswa.2026.133481_bib0040","series-title":"2024\u202fIEEE\/CVF conference on computer vision and pattern recognition (CVPR)","first-page":"27927","article-title":"Multi-task dense prediction via mixture of low-rank experts","author":"Yang","year":"2024"},{"key":"10.1016\/j.eswa.2026.133481_bib0041","unstructured":"Zhang, H., Li, F., Liu, S., Zhang, L., Su, H., Zhu, J.-J., Ni, L. M.-s., & Shum, H.-y. (2022). DINO: DETR with improved denoising anchor boxes for end-to-end object detection. ArXiv:abs\/2203.03605. https:\/\/api.semanticscholar.org\/CorpusID:247292561."},{"key":"10.1016\/j.eswa.2026.133481_bib0042","unstructured":"Zhang, Q., Chen, M., Bukharin, A., Karampatziakis, N., He, P., Cheng, Y., Chen, W., & Zhao, T. (2023). AdaLoRA: Adaptive budget allocation for parameter-efficient fine-tuning. arXiv preprint arXiv: 2303.10512."},{"key":"10.1016\/j.eswa.2026.133481_bib0043","article-title":"Research on X-ray weld seam defect detection and size measurement method based on neural network self-optimization","volume":"133","author":"Zhang","year":"2024","journal-title":"Engineering Applications of Artificial Intelligence"},{"issue":"2","key":"10.1016\/j.eswa.2026.133481_bib0044","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1007\/s10921-025-01186-w","article-title":"SWRD: A dataset of radiographic image of seam weld for defect detection","volume":"44","author":"Zhao","year":"2025","journal-title":"Journal of Nondestructive Evaluation"},{"key":"10.1016\/j.eswa.2026.133481_bib0045","series-title":"2024 second international conference on cyber-energy systems and intelligent energy (ICCSIE)","first-page":"1","article-title":"A lightweight network for sign detection on radiographic weld images","author":"Zhao","year":"2024"},{"key":"10.1016\/j.eswa.2026.133481_bib0046","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., & Dai, J. (2020). Deformable DETR: Deformable transformers for end-to-end object detection. arXiv preprint arXiv: 2010.04159."},{"key":"10.1016\/j.eswa.2026.133481_bib0047","first-page":"1","article-title":"STMA-Net: A spatial transformation-based multiscale attention network for complex defect detection with X-ray images","volume":"73","author":"Zuo","year":"2024","journal-title":"IEEE Transactions on Instrumentation and Measurement"},{"issue":"3","key":"10.1016\/j.eswa.2026.133481_bib0048","doi-asserted-by":"crossref","first-page":"1753","DOI":"10.1109\/TMECH.2024.3408337","article-title":"An X-ray-based multiexpert inspection method for automatic welding defect assessment in intelligent pipeline systems","volume":"30","author":"Zuo","year":"2025","journal-title":"IEEE\/ASME Transactions on Mechatronics"}],"container-title":["Expert Systems with Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426023900?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426023900?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T21:55:22Z","timestamp":1784238922000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0957417426023900"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2027,1]]},"references-count":48,"alternative-id":["S0957417426023900"],"URL":"https:\/\/doi.org\/10.1016\/j.eswa.2026.133481","relation":{},"ISSN":["0957-4174"],"issn-type":[{"value":"0957-4174","type":"print"}],"subject":[],"published":{"date-parts":[[2027,1]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"MLRE-WDD: A lightweight mixture of low-rank experts framework for weld defect detection in intelligent pipeline systems","name":"articletitle","label":"Article Title"},{"value":"Expert Systems with Applications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.eswa.2026.133481","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"133481"}}