AutoChemSchematic AI: Agentic Physics-Aware Automation for Chemical Manufacturing Scale-Up

TL;DR

This paper introduces a physics-aware AI framework that automates the generation of detailed engineering schematics for chemical manufacturing scale-up, integrating specialized language models, knowledge graphs, and process simulation for validated, feasible process designs.

Contribution

It presents a novel closed-loop AI system combining domain-specific language models, knowledge graphs, and simulation to automate engineering schematic generation for chemical manufacturing.

Findings

High-fidelity process descriptions generated by the framework

Effective structural pruning reduces model size without losing accuracy

Simulator validation ensures process feasibility

Abstract

Recent advances in generative AI have accelerated the discovery of novel chemicals and materials. However, scaling these discoveries to industrial production remains a major bottleneck due to the synthesis gap -- the need to develop entirely new manufacturing processes. This challenge requires detailed engineering blueprints: PFDs for equipment layouts and material/energy flows, and PIDs for process plant operations. Current AI systems cannot yet reliably generate these critical engineering schematics, creating a fundamental obstacle to manufacturing scale-up of novel discoveries. We present a closed-loop, physics-aware framework for automated generation of industrially viable PFDs and PIDs. The framework integrates three key components: (1) domain-specialized small language models (SLMs) trained for auto-generation of PFDs and PIDs, (2) a hierarchical knowledge graph containing process flow and instrumentation descriptions for 1,020+ chemicals for Graph Retrieval-Augmented Generation (GRAG), and (3) an open-source chemical process simulator for modeling, simulation, optimization, and analysis of novel chemical processes. The SLMs are trained through a multi-stage pipeline on synthetic datasets, with process simulator-in-the-loop validation ensuring feasibility. To enhance computational efficiency, the framework implements structural pruning (width and depth) guided by importance heuristics to reduce language model size while preserving accuracy, followed by advanced inference optimizations including FlashAttention, Lookahead Decoding, PagedAttention with KV-cache quantization, and Test-Time Inference Scaling. Experimental results demonstrate that our framework generates simulator-validated process descriptions with high fidelity.