{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T00:59:14Z","timestamp":1775869154341,"version":"3.50.1"},"reference-count":33,"publisher":"MDPI AG","issue":"11","license":[{"start":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T00:00:00Z","timestamp":1763424000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Zhenjiang Science and Technology Program","award":["JC2024021"],"award-info":[{"award-number":["JC2024021"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Symmetry"],"abstract":"<jats:p>This paper pioneers the use of the symmetrical Hybrid-RAG strategy in the ship welding process domain, addressing the problems of fragmented, unstructured knowledge storage, as well as the limitations of traditional Retrieval-Augmented Generation (RAG), particularly high retrieval noise and low accuracy when answering complex procedural queries. This study proposes an intelligent three-stage symmetric \u201cGenerate\u2013Retrieve\u2013Generate\u201d framework for the ship welding process (SWP-Chat), supported by dual retrieval engines: a Neo4j knowledge graph for symbolic reasoning and a vector database for semantic retrieval. Unlike approaches that rely solely on LLM-based process planning, SWP-Chat uses the LLM to generate a logical form, then executes Cypher queries on Neo4j, enabling transparent traceability, precise entity\u2013relation constraints, and deterministic retrieval. Meanwhile, the vector channel supplements unstructured or contextual welding information to enhance semantic coverage. To further improve efficiency, principal component analysis (PCA) was employed for vector dimensionality reduction, reducing average retrieval latency by 31% while retaining more than 95% variance. In addition, an explainable structural\u2013confidence fusion formula integrates evidence from both engines to produce auditable and trustworthy industrial responses. Experimental evaluation demonstrates that the framework achieves an F1 score of 79.35%, greatly surpassing typical RAG systems.<\/jats:p>","DOI":"10.3390\/sym17111994","type":"journal-article","created":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T12:33:04Z","timestamp":1763469184000},"page":"1994","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Intelligent Q&amp;A System for Welding Processes Based on a Symmetric KG-DB Hybrid-RAG Strategy"],"prefix":"10.3390","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-9813-0739","authenticated-orcid":false,"given":"Shuxia","family":"Ye","sequence":"first","affiliation":[{"name":"School of Automation, Jiangsu University of Science and Technology, No. 666 Changhui Road, Zhenjiang 212114, China"},{"name":"Jiangsu Shipbuilding and Ocean Engineering Design and Research Institute, Zhenjiang 212100, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liwen","family":"Cai","sequence":"additional","affiliation":[{"name":"School of Automation, Jiangsu University of Science and Technology, No. 666 Changhui Road, Zhenjiang 212114, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7732-4033","authenticated-orcid":false,"given":"Yongwei","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Automation, Jiangsu University of Science and Technology, No. 666 Changhui Road, Zhenjiang 212114, China"},{"name":"Jiangsu Shipbuilding and Ocean Engineering Design and Research Institute, Zhenjiang 212100, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoqi","family":"Xin","sequence":"additional","affiliation":[{"name":"School of Automation, Jiangsu University of Science and Technology, No. 666 Changhui Road, Zhenjiang 212114, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Jiang","sequence":"additional","affiliation":[{"name":"School of Automation, Jiangsu University of Science and Technology, No. 666 Changhui Road, Zhenjiang 212114, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3678-4893","authenticated-orcid":false,"given":"Liang","family":"Qi","sequence":"additional","affiliation":[{"name":"School of Automation, Jiangsu University of Science and Technology, No. 666 Changhui Road, Zhenjiang 212114, China"},{"name":"Jiangsu Shipbuilding and Ocean Engineering Design and Research Institute, Zhenjiang 212100, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,11,18]]},"reference":[{"key":"ref_1","unstructured":"The State Council of the People\u2019s Republic of China (2025, November 12). China Remains World\u2019s Top Manufacturer for 15 Consecutive Years: Official, Available online: https:\/\/english.www.gov.cn\/archive\/statistics\/202507\/09\/content_WS686e064dc6d0868f4e8f3fe1.html."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Iatrou, C.P., Ketzel, L., Graube, M., H\u00e4fner, M., and Urbas, L. (2020, January 8\u201311). Design classification of aggregating systems in intelligent information system architectures. Proceedings of the 2020 25th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA), Vienna, Austria.","DOI":"10.1109\/ETFA46521.2020.9212101"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Wang, B., Wang, G., Huang, J., You, J., Leskovec, J., and Kuo, C.-C. (2021, January 18\u201322). Inductive learning on commonsense knowledge graph completion. Proceedings of the 2021 International Joint Conference on Neural Networks (IJCNN), Shenzhen, China.","DOI":"10.1109\/IJCNN52387.2021.9534355"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Zeng, Z., Cheng, Q., and Si, Y. (2023). Logical rule-based knowledge graph reasoning: A comprehensive survey. Mathematics, 11.","DOI":"10.3390\/math11214486"},{"key":"ref_5","unstructured":"Gao, Y., Xiong, Y., Gao, X., Jia, K., Pan, J., Bi, Y., Dai, Y., Sun, J., Wang, H., and Wang, H. (2023). Retrieval-augmented generation for large language models: A survey. arXiv."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Knollmeyer, S., Caymazer, O., and Grossmann, D. (2025). Document GraphRAG: Knowledge graph enhanced retrieval augmented generation for document question answering within the manufacturing domain. Electronics, 14.","DOI":"10.3390\/electronics14112102"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1016\/j.procir.2023.09.224","article-title":"Integration of product and manufacturing design: A systematic literature review","volume":"121","author":"Shaftee","year":"2023","journal-title":"Procedia CIRP"},{"key":"ref_8","first-page":"461","article-title":"A benchmark dataset with Knowledge Graph generation for Industry 4.0 production lines","volume":"15","author":"Yahya","year":"2024","journal-title":"Semant. Web"},{"key":"ref_9","unstructured":"Meckler, S. (2024). Procedure model for building knowledge graphs for industry applications. arXiv."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"121448","DOI":"10.1016\/j.eswa.2023.121448","article-title":"A method for constructing a machining knowledge graph using an improved transformer","volume":"237","author":"Guo","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Liu, X., and Wang, H. (2021, January 5\u20137). Knowledge Graph Construction and Decision Support Towards Transformer Fault Maintenance. Proceedings of the 2021 IEEE 24th International Conference on Computer Supported Cooperative Work in Design (CSCWD), Dalian, China.","DOI":"10.1109\/CSCWD49262.2021.9437847"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"103668","DOI":"10.1016\/j.compind.2022.103668","article-title":"Combining deep learning with knowledge graph for macro process planning","volume":"140","author":"Zhang","year":"2022","journal-title":"Comput. Ind."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"2911","DOI":"10.1038\/s41598-022-06940-y","article-title":"Process knowledge graph modeling techniques and application methods for ship heterogeneous models","volume":"12","author":"Dong","year":"2022","journal-title":"Sci. Rep."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1151","DOI":"10.1080\/0951192X.2021.1891572","article-title":"KGAssembly: Knowledge graph-driven assembly process generation and evaluation for complex components","volume":"35","author":"Zhou","year":"2022","journal-title":"Int. J. Comput. Integr. Manuf."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Shi, X., Tian, X., Gu, J., Yang, F., Ma, L., Chen, Y., and Su, T. (2022). Knowledge graph-based assembly resource knowledge reuse towards complex product assembly process. Sustainability, 14.","DOI":"10.3390\/su142315541"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"103208","DOI":"10.1016\/j.aei.2025.103208","article-title":"FD-LLM: Large language model for fault diagnosis of complex equipment","volume":"65","author":"Lin","year":"2025","journal-title":"Adv. Eng. Inform."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Meng, S., Wang, Y., Yang, C.-F., Peng, N., and Chang, K.-W. (2024). LLM-A*: Large language model enhanced incremental heuristic search on path planning. arXiv.","DOI":"10.21203\/rs.3.rs-4613568\/v1"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"311","DOI":"10.1016\/j.eng.2025.04.003","article-title":"Intelligent fault diagnosis for CNC through the integration of large language models and domain knowledge graphs","volume":"53","author":"Liu","year":"2025","journal-title":"Engineering"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Werheid, J., Melnychuk, O., Zhou, H., Huber, M., Rippe, C., Joosten, D., Keskin, Z., Wittstamm, M., Subramani, S., and Drescher, B. (2024). Designing an LLM-based copilot for manufacturing equipment selection. arXiv.","DOI":"10.1016\/j.mfglet.2025.10.017"},{"key":"ref_20","first-page":"29948","article-title":"RAGraph: A general retrieval-augmented graph learning framework","volume":"37","author":"Jiang","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_21","unstructured":"Wang, J., Fu, J., Wang, R., Song, L., and Bian, J. (2025). PIKE-RAG: SPecIalized KnowledgE and Rationale augmented generation. arXiv."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Barron, R.C., Grantcharov, V., Wanna, S., Eren, M.E., Bhattarai, M., Solovyev, N., Tompkins, G., Nicholas, C., Rasmussen, K.\u00d8., and Matuszek, C. (2024, January 18\u201320). Domain-specific retrieval-augmented generation using vector stores, knowledge graphs, and tensor factorization. Proceedings of the 2024 International Conference on Machine Learning and Applications (ICMLA), Miami, FL, USA.","DOI":"10.1109\/ICMLA61862.2024.00258"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Opoku, D.O., Sheng, M., and Zhang, Y. (2025). DO-RAG: A domain-specific QA framework using knowledge graph-enhanced retrieval-augmented generation. arXiv.","DOI":"10.36227\/techrxiv.174837976.69904638\/v1"},{"key":"ref_24","unstructured":"Russell-Gilbert, A. (2025). RAAD-LLM: Adaptive Anomaly Detection Using LLMs and RAG Integration. [Ph.D. Dissertation, Mississippi State University]."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Sarmah, B., Mehta, D., Hall, B., Rao, R., Patel, S., and Pasquali, S. (2024, January 14\u201317). HybridRAG: Integrating knowledge graphs and vector retrieval augmented generation for efficient information extraction. Proceedings of the ICAIF\u201924: 5th ACM International Conference on AI in Finance Brooklyn NY USA.","DOI":"10.1145\/3677052.3698671"},{"key":"ref_26","unstructured":"Tram, M.H.B. (2025). Efficacy of GraphRAG (Knowledge Graph-enhanced RAG) Beyond Keyword Matching for Information Retrieval. [Ph.D. Dissertation, University of Jyv\u00e4skyl\u00e4]."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"525","DOI":"10.1142\/S0218194025500147","article-title":"Approximate Query for Industrial Fault Knowledge Graph Based on Vector Index","volume":"35","author":"Zhai","year":"2025","journal-title":"Int. J. Softw. Eng. Knowl. Eng."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Berant, J., Chou, A., Frostig, R., and Liang, P. (2013, January 18\u201321). Semantic parsing on Freebase from question-answer pairs. Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, Seattle, DC, USA.","DOI":"10.18653\/v1\/D13-1160"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"21709","DOI":"10.1007\/s11042-020-10447-x","article-title":"Human activity classification using decision tree and na\u00efve Bayes classifiers","volume":"80","author":"Maswadi","year":"2021","journal-title":"Multimed. Tools Appl."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"103089","DOI":"10.1109\/ACCESS.2022.3209066","article-title":"Relationship extraction and processing for knowledge graph of welding manufacturing","volume":"10","author":"Guan","year":"2022","journal-title":"IEEE Access"},{"key":"ref_31","unstructured":"China Classification Society (2024). Rules for Materials and Welding (2024) released by China Classification Society (CCS). Ship Stand. Eng., 57, 2. (In Chinese with English abstract)."},{"key":"ref_32","unstructured":"Hu, E.J., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, L., Chen, W., and Chen, Y. (2021). LoRA: Low-Rank Adaptation of Large Language Models. arXiv."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Ben Zaken, E., Goldberg, Y., and Ravfogel, S. (2022). BitFit: Simple Parameter-Efficient Fine-Tuning for Transformer-Based Masked Language-Models. arXiv.","DOI":"10.18653\/v1\/2022.acl-short.1"}],"container-title":["Symmetry"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-8994\/17\/11\/1994\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T12:46:37Z","timestamp":1763469997000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-8994\/17\/11\/1994"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,18]]},"references-count":33,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2025,11]]}},"alternative-id":["sym17111994"],"URL":"https:\/\/doi.org\/10.3390\/sym17111994","relation":{},"ISSN":["2073-8994"],"issn-type":[{"value":"2073-8994","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,18]]}}}