Open Access
Conceptual Framework of LLM-Based Copilots in EPC Firms for Automated P&ID Generation to Reduce Design Time and Increase Standardization
Rohit Shinde
1
4
Lamar University, University of Texas at Austin, USA
4
Lamar University
Abstract
Traditional P&ID workflows in EPC firms are labor-intensive and error-prone, causing design inconsistencies that impact safety and efficiency. This analytical study proposes a conceptual framework for integrating Large Language Model (LLM)-based copilots to automate P&ID generation, enhance design efficiency, and ensure adherence to industry standards. The methodology details a rigorous conceptual training regimen and a multi-layered system architecture, including a Chatbot Interface, Planning Agent, Graph-RAG Knowledge Base, Execution Module, and Visualization. Modeled outcomes, derived from comparative analysis using industry benchmarks, anticipate significant efficiency gains, including a 30.5x overall productivity improvement factor, 96.7% average time savings for individual elements, and a 3.1x project acceleration. Projected error reductions are substantial, with critical error rates for missing safety devices estimated to decrease from 9.2% to 0.9% in a simulated environment. These findings suggest LLM-based copilots can transform manual P&ID drafting, mitigating project inefficiencies. Successful AI adoption, however, hinges on resolving challenges related to data security, integration costs, and legal liabilities for safety-critical designs, moving beyond conceptual feasibility towards industrial-grade reliability and robust human oversight.
How to Cite
Shinde, R., & Bhosale, S. (2026). Conceptual Framework of LLM-Based Copilots in EPC Firms for Automated P&ID Generation to Reduce Design Time and Increase Standardization. Frontiers in Emerging Engineering & Technologies, 3(02), 01–24. https://doi.org/10.64917/feet/Volume03Issue02-01
References
(Junhyung Byun et al. 2025) Junhyung Byun, Bonggu Kang, Duhwan Mun, Gwang Lee, Hyungki Kim, Optimizing image format piping and instrumentation diagram recognition: Integrating symbol and text recognition with a single backbone architecture, Journal of Computational Design and Engineering, Volume 12, Issue 6, June 2025, Pages 55–72, https://doi.org/10.1093/jcde/qwaf053
(Schlegl, T et al. 2022) Schlegl, T., Tomaselli, D., Schlegl, S., West, N., & Deuse, J. (2022). Automated search of process control limits for fault detection in time series data. Journal of Process Control, 117, 52-64.
(Dzhusupova, Z et al., 2024) Dzhusupova, R., Banotra, R., Bosch, J., & Olsson, H.H. (2023). Using artificial intelligence to find design errors in the engineering drawings. Journal of Software: Evolution and Process, 35.
(Werheid et al., 2024) Werheid, J., Melnychuk, O., Zhou, H., Huber, M., Rippe, C., Joosten, D., ... & Schmitt, R. H. (2025). Designing an llm-based copilot for manufacturing equipment selection. Manufacturing Letters. https://doi.org/10.1016/j.mfglet.2025.10.017
(Ghosh, D. 2025) Vibe Engineering Automafion (VEA) and Orchestrafion (VEO): An AI-driven framework for design integrafion in EPC projects https://doi.org/10.13140/RG.2.2.32917.64482
(Moreno-Garcia et al., n.d.) Moreno-García, C. F., Johnston, P., & Garkuwa, B. (2020, July). Pixel-based layer segmentation of complex engineering drawings using convolutional neural networks. In 2020 International joint conference on neural networks (IJCNN) (pp. 1-7). IEEE. https://doi.org/10.1109/ijcnn48605.2020.9207479
(Gowaikar et al., 2024) Gowaikar, S., Iyengar, S., Segal, S., & Kalyanaraman, S. (2024b). An Agentic Approach to Automatic Creation of P&ID Diagrams from Natural Language Descriptions. Arxiv.Org, 2412.12898 https://arxiv.org/abs/2412.12898
(Schulze Balhorn et al., 2025) Schulze Balhorn, L., Seijsener, N., Dao, K., Kim, M., Goldstein, D. P., Driessen, G. H. M., & Schweidtmann, A. M. (2025). Rule-based autocorrection of Piping and Instrumentation Diagrams (P&IDs) on graphs. Proceedings of the 35th European Symposium on Computer Aided Process Engineering (ESCAPE35). arXiv. https://doi.org/10.48550/arXiv.2502.18493
(Han et al. 2024) Han, H., Wang, Y., Shomer, H., Guo, K., Ding, J., Lei, Y., Halappanavar, M., Rossi, R. A., Mukherjee, S., Tang, X., He, Q., Hua, Z., Long, B., Zhao, T., Shah, N., Javari, A., Xia, Y., & Tang, J. (2024). Retrieval-Augmented Generation with Graphs (GraphRAG). arXiv preprint. https://doi.org/10.48550/arXiv.2501.00309
(Almohaimeed, S et al. 2024) Almohaimeed, S., & Wang, L. Gat-sql: An advanced prompt engineering approach for effective text-to-sql interactions. In 2024 IEEE Congress on Evolutionary Computation (CEC) (pp. 1-10). IEEE. DOI: 10.1109/CEC60901.2024.10611969
(Kathiresan, G. 2025) Human-in-the-Loop Testing for LLM-Integrated Software: A Quality Engineering Framework for Trust and Safety. Authorea Preprints. https://www.techrxiv.org/doi/full/10.36227/techrxiv.174702077.78864934
(Liu, X. et al., 2025) Liu, X., Zhang, Y., Wang, L., Gu, L., Xu, Y., Zheng, K., Cai, Q., & Zhou, G. LLMs driven fusion AI-AD system for mechanical design: From understanding to generation. Advanced Engineering Informatics, 68, 103745. https://doi.org/10.1016/j.aei.2025.103745
(Ya-Ting Chuang et al., 2025) Chuang, Ya-Ting & Chiang, Hua-Ling & Lin, An-Pan. Insights from the Job Demands–Resources Model: AI's dual impact on employees’ work and life well-being. International Journal of Information Management. 83. 102887. 10.1016/j.ijinfomgt.2025.102887
(AliResources, 2024). How a leading EPC company streamlines projects with iConstruct. https://aliresources.hexagon.com/articles-blogs/how-a-leading-epc-company-streamlines-projects-with-iconstruct
(McKinsey & Company (a), 2017). McKinsey & Company. Reinventing construction: A route to higher productivity. https://www.mckinsey.com/~/media/mckinsey/business%20functions/operations/our%20insights/reinventing%20construction%20through%20a%20productivity%20revolution/mgi-reinventing-construction-a-route-to-higher-productivity-full-report.pdf
(McKinsey & Company (b), 2017) McKinsey & Company. Reinventing construction through a productivity revolution. https://www.mckinsey.com/capabilities/operations/our-insights/reinventing-construction-through-a-productivity-revolution
(Controls Drives & Automation, 2024). Automation could deliver time savings. https://www.controlsdrivesautomation.com/Automation-could-deliver-time-savings
(Aras., 2024). Embracing the digital thread in engineering procurement and construction: A paradigm shift. https://aras.com/en/blog/embracing-the-digital-thread-in-engineering-procurement-and-construction-a-paradigm-shift
(Grupo Giga., 2024). The role of AI in engineering design. https://grupo-giga.com/blog/the-role-of-ai-in-engineering-design/
(Neural Concept., 2024). Transforming engineering design with AI: A new era of possibilities. https://www.neuralconcept.com/post/transforming-engineering-design-with-ai-a-new-era-of-possibilities
(Scribd., 2019). Piping engineering manhours estimation: Hours per activity. https://fr.scribd.com/document/406440318/Piping-Engineering-Manhours-Estimation-Hours-Per-Activity
(PMI. ,2011). Performance metrics standardized benchmarking system. https://www.pmi.org/learning/library/performance-metrics-standardized-benchmarking-system-6532
(Construction Industry Institute., n.d.-a). CII best practices. https://www.construction-institute.org/cii-best-practices
(Construction Industry Institute., n.d.-b). Benchmarking metrics summary report. https://www.construction-institute.org/benchmarking-metrics-summary-report
(Rishabh Engineering., 2024). Chemical process design. https://www.rishabheng.com/blog/chemical-process-design/
(The Chemical Engineer., 2023). The design process from concept to heat and mass balance.https://www.thechemicalengineer.com/features/the-design-process-from-concept-to-heat-and-mass-balance/
(MDPI (a)., 2022). Sustainability, 14(11), 6938. https://www.mdpi.com/2071-1050/14/11/6938
(MDPI (b)., 2022). Buildings, 12(9), 1486. https://www.mdpi.com/2075-5309/12/9/1486
(LinkedIn (a)., 2024). Driving digital transformation in EPC industry. https://www.linkedin.com/pulse/driving-digital-transformation-epc-industry-tectree-tectree-ytoec
(LinkedIn (b)., 2024). Drawing as-built P&ID from scratch. https://www.linkedin.com/pulse/drawing-as-built-pid-from-scratch-nick-howard-fs-eng
(OnePetro., 2022). SPE annual digital industries conference. https://onepetro.org/SPEADIP/proceedings/22ADIP/22ADIP/D021S054R002/513475
(Becht., 2024). Piping and instrument diagrams (P&IDs) Part 2: Causes and management of change. https://becht.com/becht-blog/entry/piping-and-instrument-diagrams-pids-part-2-causes-and-management-of-change/
(Jedson., 2023). P&IDs: The neglected best practice. https://jedson.com/wp-content/uploads/PIDs-The-Neglected-Best-Practice.pdf
(Ghasemi et al., 2022) Ghasemi, M., Nejad, M. G., Alsaadi, N., Abdel-Jaber, M. T., Ab Yajid, M. S., & Habib, M. (2022). Performance measurment and lead‐time reduction in epc project‐based organizations: a mathematical modeling approach. Mathematical Problems in Engineering, 2022(1), 5767356.
(IEEE., 2025). https://ieeexplore.ieee.org/document/10418736/
(Huang, L et al., 2025). Huang, L., Yu, W., Ma, W., Zhong, W., Feng, Z., Wang, H., ... & Liu, T. (2025). A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions. ACM Transactions on Information Systems, 43(2), 1-55.
(Gelfand & Rao, 2025) Gelfand, N., & Rao, A. The clinicians' guide to large language models: A general framework for the safe implementation of LLMs in clinical care. Interact J Med Res, 14, e59823.
(Zhang, R et al., 2025) Zhang, R., Li, H. W., Qian, X. Y., Jiang, W. B., & Chen, H. X. (2025). On large language models safety, security, and privacy: A survey. Journal of Electronic Science and Technology, 23(1), 100301.
(Shah et al., 2023) Shah, A., Zafar, A., Wu, J., Shaikh, M. B., Irfan, M., Hadi, M. U., Akhtar, N., Qureshi, R., Mirjalili, S., Muneer, A., & Tashi, Q. A. (2023). Large Language Models: A Comprehensive Survey of its Applications, Challenges, Limitations, and Future Prospects. [TechRxiv preprint]. Institute of Electrical and Electronics Engineers. https://doi.org/10.36227/techrxiv.23589741
(Srinivas et al., 2024) Srinivas, S. S., Vaikunth, V. S., & Runkana, V. (2024). Knowledge Graph Modeling-Driven Large Language Model Operating System (LLM OS) for Task Automation in Process Engineering Problem-Solving. Journal, 222–232.