A unified pipeline - coupling GA/LLM-driven synthesis with an LLM-based transformation agent - offers a feasible path toward end-to-end process design automation by producing validated, deployable outputs and substantially reduces manual engineering effort.
Abstract
Nowadays, the creation of a process flow diagram (PFD) and its subsequent transformation into a piping and instrumentation diagram (P&ID) is predominantly performed manually. Applying artificial intelligence in the task could potentially lead not only to process automation and time savings, but also to financial gains by exploring numerous diagram's topology options and reducing manual labor. This research presents P&ID Pilot - a practical end-to-end AI pipeline capable of handling flowsheet developing for both stages. The first stage focuses on PFD synthesis, whereas the second is directed toward modifying the generated PFD into P&ID. After comparing four different methods, the hybrid approach combining genetic algorithms (GA) and large language models (LLM) is shown to generate the optimal valid PFD topology, achieving the lowest loss value among all the methods, while satisfying the required outlet flow parameters without engineering-rule violations. For the second stage, the proposed LLM-based agent successfully transforms the generated PFD into a source-grounded P&ID by producing validated, executable modifications through a restricted engineering software development kit, achieving 100% execution success while maintaining compliance with domain-specific rules and reference graph structures. This unified pipeline - coupling GA/LLM-driven synthesis with an LLM-based transformation agent - offers a feasible path toward end-to-end process design automation by producing validated, deployable outputs and substantially reduces manual engineering effort.
The proposed model aims to support the formalization of model selection processes, improve decision-making, and enhance the traceability and transparency of LLMOps practices and forms part of a broader research effort toward the formalization of the entire LLMOps life cycle.
M. Chernigovskaya, A. Nahhas, Christian Haertel et al.· International Conference on...· 0 citations
Evaluated on real-world system-level requirements documents, comprising more than 720 requirements and 72 use cases, the approach generates system-level diagrams comparable to those created by experts and provides valuable architectural recommendations.
Bastian Franze, Dominik Fuchß, Friedrich Wattenberg et al.· IEEE International Requireme...· 0 citations
The chemical industry needs to transition from predominantly linear, carbon-emitting production routes to circular, carbon-reusing processes. Therefore, every current and future production process needs to be critically evaluated and potentially re-designed. Today, process design and assessment rely on detailed process simulations [1]. However, constructing these simulations remains a bottleneck, demanding a high degree of expertise and manual work. Here, we present an automated workflow which gathers process knowledge, generates process simulations, and evaluates process performance. The automated workflow consists of two data pipelines: The first pipeline systematically extracts information from literature [2] and prepares a knowledge base of established, industrially relevant chemical processes down to the level of unit operations and thermodynamic properties. This knowledge is aggregated into one text per process and fed into the second pipeline, “text2flowsheet” [3], which digitizes expert-level flowsheet graphs from natural-language descriptions. Both pipelines leverage LLMs' language comprehension capabilities, while the flowsheet digitization is further grounded in rigorous thermodynamic calculations. The digitized flowsheet graphs are systemically translated into simulations within an established commercial process simulator. Potential simplifications necessary to achieve convergence are recorded transparently. Missing information on operating parameters is augmented by systematic, unit-by-unit black-box optimization. We show that our integrated pipelines can faithfully collect and digitize chemical process information by comparing to expert-curated datasets and manually drawn flowsheets. Furthermore, the generated process simulations are on par with expert interpretations with significantly less manual effort. We present case studies illustrating how the results of the automatically generated process simulations can be used to assess process sustainability and derive optimization potential.
Jan-Frederic Laub· Proceedings of the 3rd Found...· 0 citations
To improve the current practices in modernizing CAD workflows within infrastructure projects, there is a need for transitioning from traditional practices characterized by inefficiencies towards intelligent automation and standardization of processes. In this regard, a three-stage framework consisting of intelligent dependency graph generation, optimization of design processes and automation of tasks within processes is proposed in this study. The first stage consists of the creation of the intelligent dependency graph utilizing knowledge graph transformers, which use graph neural networks along with transformer attention. The knowledge graph transformer learns the relationship between various CAD entities, layers, design standards and components of infrastructure to generate an intelligent dependency graph. Subsequently, the Process Mining Evolution Engine makes use of process discovery algorithms to detect inefficiencies, repetitious engineering activities, and approval processes to come up with an optimized workflow. Lastly, the Reinforcement Automation Orchestrator uses reinforcement learning to suggest the appropriate automation, task ordering, and validation timing of tasks within the workflow. As a result, the framework transforms CAD models, design standards, and process records into actionable recommendations. Consequently, the generated optimized infrastructure design workflow has an accuracy of 97.4%.
Janvi Vijaykumar Saddi, H. Lathiya, Akhilesh Korpe et al.· Journal of Intelligent Decis...· 0 citations
An automated HCPN modeling method is proposed that transforms Netflix Conductor workflow specifications into hierarchical HCPN models using predefined rules and preserves workflow structure, control flow, and data dependencies, and generates models suitable for formal verification.
Guoshuai Li, Tao Sun, Wenjie Zhong· Conference on Applications,...· 0 citations
The authors establish the main issues associated with scalability, security, and maintainability and show future research perspectives of sustainable adoption of RPA in large-scale enterprise settings.
Kenji Sato, Aiko Yamamoto· International Journal of Mod...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
