{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:41:30Z","timestamp":1760035290979,"version":"build-2065373602"},"reference-count":38,"publisher":"MDPI AG","issue":"7","license":[{"start":{"date-parts":[[2025,7,4]],"date-time":"2025-07-04T00:00:00Z","timestamp":1751587200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Design Ready Controls","award":["26199"],"award-info":[{"award-number":["26199"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Algorithms"],"abstract":"<jats:p>This paper explores the integration of Large Language Models (LLMs) and secure Gen-AI technologies within engineering design and manufacturing, with a focus on improving inventory management, component selection, and recommendation workflows. The system is intended for deployment and evaluation in a real-world industrial environment. It utilizes vector embeddings, vector databases, and Approximate Nearest Neighbor (ANN) search algorithms to implement Retrieval-Augmented Generation (RAG), enabling context-aware searches for inventory items and addressing the limitations of traditional text-based methods. Built on an LLM framework enhanced by RAG, the system performs similarity-based retrieval and part recommendations while preserving data privacy through selective obfuscation using the ROT13 algorithm. In collaboration with an industry sponsor, real-world testing demonstrated strong results: 88.4% for Answer Relevance, 92.1% for Faithfulness, 80.2% for Context Recall, and 83.1% for Context Precision. These results demonstrate the system\u2019s ability to deliver accurate and relevant responses while retrieving meaningful context and minimizing irrelevant information. Overall, the approach presents a practical and privacy-aware solution for manufacturing, bridging the gap between traditional inventory tools and modern AI capabilities and enabling more intelligent workflows in design and production processes.<\/jats:p>","DOI":"10.3390\/a18070414","type":"journal-article","created":{"date-parts":[[2025,7,7]],"date-time":"2025-07-07T04:43:37Z","timestamp":1751863417000},"page":"414","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["An Industry Application of Secure Augmentation and Gen-AI for Transforming Engineering Design and Manufacturing"],"prefix":"10.3390","volume":"18","author":[{"given":"Dulana","family":"Rupanetti","sequence":"first","affiliation":[{"name":"Department of Electrical & Computer Engineering, University of Saint Thomas, Saint Paul, MN 55105, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Corissa","family":"Uberecken","sequence":"additional","affiliation":[{"name":"Department of Electrical & Computer Engineering, University of Saint Thomas, Saint Paul, MN 55105, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Adam","family":"King","sequence":"additional","affiliation":[{"name":"Department of Electrical & Computer Engineering, University of Saint Thomas, Saint Paul, MN 55105, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hassan","family":"Salamy","sequence":"additional","affiliation":[{"name":"Department of Electrical & Computer Engineering, University of Saint Thomas, Saint Paul, MN 55105, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6278-0377","authenticated-orcid":false,"given":"Cheol-Hong","family":"Min","sequence":"additional","affiliation":[{"name":"Department of Electrical & Computer Engineering, University of Saint Thomas, Saint Paul, MN 55105, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Samantha","family":"Schmidgall","sequence":"additional","affiliation":[{"name":"College of Science and Engineering, University of Minnesota, Minneapolis, MN 55105, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,7,4]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Vysko\u010dil, J., Douda, P., Nov\u00e1k, P., and Wally, B. (2023). A Digital Twin-Based Distributed Manufacturing Execution System for Industry 4.0 with AI-Powered On-The-Fly Replanning Capabilities. Sustainability, 15.","DOI":"10.3390\/su15076251"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"609","DOI":"10.22214\/ijraset.2023.57376","article-title":"Challenges and solutions in integrating AI with legacy inventory systems","volume":"11","author":"Singh","year":"2023","journal-title":"Int. J. Res. Appl. Sci. Eng. Technol."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Navinchandran, M., Sharp, M., Brundage, M., and Sexton, T. (2019, January 21\u201326). Studies to predict maintenance time duration and important factors from maintenance workorder data. Proceedings of the Annual Conference of the PHM Society, Scottsdale, AZ, USA.","DOI":"10.36001\/phmconf.2019.v11i1.792"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Zhou, B., Svetashova, Y., Pychynski, T., Baimuratov, I., Soylu, A., and Kharlamov, E. (2020, January 14\u201319). SemFE: Facilitating ML pipeline development with semantics. Proceedings of the 2020 ACM SIGMOD International Conference on Management of Data, Portland, OR, USA.","DOI":"10.1145\/3340531.3417436"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Sexton, T., Hodkiewicz, M., and Brundage, M. (2019, January 21\u201326). Categorization errors for data entry in maintenance work-orders. Proceedings of the Annual Conference of the PHM Society, Scottsdale, AZ, USA.","DOI":"10.36001\/phmconf.2019.v11i1.790"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"35","DOI":"10.17509\/jlsc.v3i1.62069","article-title":"Information system design in warehouse inventory control","volume":"3","author":"Lubis","year":"2023","journal-title":"J. Logist. Supply Chain."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"46","DOI":"10.54209\/jatilima.v6i01.420","article-title":"Design of inventory information systems at cv company. Web-based berjaya jaya abadi","volume":"6","author":"Bisri","year":"2024","journal-title":"J. Multimed. Dan Teknol. Inf. (Jatilima)"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"282","DOI":"10.22214\/ijraset.2023.56503","article-title":"Advancements in AI-enhanced just-in-time inventory: Elevating demand forecasting accuracy","volume":"11","author":"Pal","year":"2023","journal-title":"Int. J. Res. Appl. Sci. Eng. Technol."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"81","DOI":"10.9734\/jamcs\/2024\/v39i41883","article-title":"AI-driven real-time quality monitoring and process optimization for enhanced manufacturing performance","volume":"39","author":"Okuyelu","year":"2024","journal-title":"J. Adv. Math. Comput. Sci."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"2635","DOI":"10.1007\/s10639-019-10063-9","article-title":"A systematic review: Machine learning based recommendation systems for e-learning","volume":"25","author":"Khanal","year":"2020","journal-title":"Educ. Inf. Technol."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"86578","DOI":"10.1109\/ACCESS.2022.3194536","article-title":"Recommendation Systems: An Insight Into Current Development and Future Research Challenges","volume":"10","author":"Marcuzzo","year":"2022","journal-title":"IEEE Access"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"He, X., Liao, L., Zhang, H., Nie, L., Hu, X., and Chua, T.S. (2017, January 3\u20137). Neural Collaborative Filtering. Proceedings of the 26th International Conference on World Wide Web (WWW \u201917), Perth, Australia.","DOI":"10.1145\/3038912.3052569"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Berretta, S., Tausch, A., Peifer, C., and Kluge, A. (2023). The job perception inventory: Considering human factors and needs in the design of human\u2014AI work. Front. Psychol., 14.","DOI":"10.3389\/fpsyg.2023.1128945"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"801","DOI":"10.51594\/farj.v6i6.1180","article-title":"Advanced financial modeling techniques for reducing inventory costs: A review of strategies and their effectiveness in manufacturing","volume":"6","author":"Adegbola","year":"2024","journal-title":"Financ. Account. Res. J."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"143657","DOI":"10.1109\/ACCESS.2023.3339553","article-title":"Unleashing the potential of conversational ai: Amplifyichat-gpt\u2019s capabilities and tackling technical hurdles","volume":"11","author":"Hassij","year":"2023","journal-title":"IEEE Access"},{"key":"ref_16","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., and Polosukhin, I. (2017). Attention Is All You Need. arXiv."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Sha, S. (2024). Navigating the web of disinformation and misinformation: Large language models as double-edged swords. IEEE Access, 1.","DOI":"10.1109\/ACCESS.2024.3406644"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"67738","DOI":"10.1109\/ACCESS.2024.3400164","article-title":"Revolutionizing higher education: Unleashing the potential of large language models for strategic transformation","volume":"12","author":"Idri","year":"2024","journal-title":"IEEE Access"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"8633","DOI":"10.1109\/ACCESS.2024.3349969","article-title":"Intelligent practices of large language models in digital government services","volume":"12","author":"Ha","year":"2024","journal-title":"IEEE Access"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"118698","DOI":"10.1109\/ACCESS.2023.3326474","article-title":"Exploring chatgpt capabilities and limitations: A survey","volume":"11","author":"Kouba","year":"2023","journal-title":"IEEE Access"},{"key":"ref_21","unstructured":"Mikolov, T., Chen, K., Corrado, G., and Dean, J. (2013). Efficient Estimation of Word Representations in Vector Space. arXiv."},{"key":"ref_22","unstructured":"Xiao, S., Liu, Z., Zhang, P., and Muennighoff, N. (2023). C-Pack: Packaged Resources To Advance General Chinese Embedding. arXiv."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Sitikhu, P., Pahi, K., Thapa, P., and Shakya, S. (2019, January 5). A Comparison of Semantic Similarity Methods for Maximum Human Interpretability. Proceedings of the 2019 Artificial Intelligence for Transforming Business and Society (AITB), Kathmandu, Nepal.","DOI":"10.1109\/AITB48515.2019.8947433"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"1704","DOI":"10.12928\/telkomnika.v16i4.9062","article-title":"News Reliability Evaluation Using Latent Semantic Analysis","volume":"16","author":"Guo","year":"2018","journal-title":"Telkomnika (Telecommun. Comput. Electron. Control)"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"692","DOI":"10.3844\/jcssp.2015.692.698","article-title":"Performance Evaluation of Search Engines Using Enhanced Vector Space Model","volume":"11","author":"Singh","year":"2015","journal-title":"J. Comput. Sci."},{"key":"ref_26","first-page":"1","article-title":"The Nexus of AI and Vector Databases: Revolutionizing NLP with LLMs","volume":"8","author":"Shaik","year":"2024","journal-title":"Int. J. Sci. Res. Eng. Manag."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Schubert, E. (2021). A Triangle Inequality for Cosine Similarity. arXiv.","DOI":"10.1007\/978-3-030-89657-7_3"},{"key":"ref_28","first-page":"125744","article-title":"Vector Databases for Efficient Semantic Search in Natural Language Processing","volume":"10","author":"Coyne","year":"2022","journal-title":"IEEE Access"},{"key":"ref_29","unstructured":"AWS (2025, March 01). What Is a Vector Database?. Available online: https:\/\/aws.amazon.com\/what-is\/vector-databases\/."},{"key":"ref_30","first-page":"3952","article-title":"Scaling Vector Databases for Real-Time Applications","volume":"34","author":"Jimenez","year":"2022","journal-title":"IEEE Trans. Data Knowl. Eng."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Shi, W., Cui, A., Li, E., Jia, R., and Yu, Z. (2021). Selective differential privacy for language modeling. arXiv.","DOI":"10.18653\/v1\/2022.naacl-main.205"},{"key":"ref_32","first-page":"208","article-title":"Model Pengembangan Keamanan Data dengan Algoritma ROT13 Extended Vernam Cipher dan Stream Cipher","volume":"7","author":"Milian","year":"2023","journal-title":"J. Teknol. Inf. Dan Komun. (JTIK)"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Reimers, N., and Gurevych, I. (2019, January 3\u20137). Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), Hong Kong, China.","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Reimers, N., and Gurevych, I. (2019). Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. arXiv.","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref_35","unstructured":"Douze, M., Guzhva, A., Deng, C., Johnson, J., Szilvasy, G., Mazar\u00e9, P.E., Lomeli, M., Hosseini, L., and J\u00e9gou, H. (2024). The Faiss library. arXiv."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Hsieh, C.Y., Li, C.L., Yeh, C.K., Nakhost, H., Fujii, Y., Ratner, A., Krishna, R., Lee, C.Y., and Pfister, T. (2023). Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes. arXiv.","DOI":"10.18653\/v1\/2023.findings-acl.507"},{"key":"ref_37","unstructured":"Confident-AI (2025, March 01). GitHub\u2014Confident-AI\/Deepeval: The LLM Evaluation Framework. Available online: https:\/\/github.com\/confident-ai\/deepeval."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Xu, J., Luo, S., Chen, X., Huang, H., Hou, H., and Song, L. (2025). RALLRec: Improving Retrieval Augmented Large Language Model Recommendation with Representation Learning. arXiv.","DOI":"10.1145\/3701716.3715508"}],"container-title":["Algorithms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-4893\/18\/7\/414\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:04:40Z","timestamp":1760033080000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-4893\/18\/7\/414"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,4]]},"references-count":38,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2025,7]]}},"alternative-id":["a18070414"],"URL":"https:\/\/doi.org\/10.3390\/a18070414","relation":{},"ISSN":["1999-4893"],"issn-type":[{"type":"electronic","value":"1999-4893"}],"subject":[],"published":{"date-parts":[[2025,7,4]]}}}