Assessment of ChatGPT for Engineering Statics Analysis

TL;DR

This paper evaluates ChatGPT's ability to perform engineering statics analysis, showing promising results but also highlighting current limitations in accuracy and reasoning for complex problems.

Contribution

It introduces a customized prompting approach that improves ChatGPT's performance in engineering statics tasks, surpassing student averages.

Findings

ChatGPT achieved 82% accuracy with optimized prompts.

LLMs still make errors in nuanced or open-ended problems.

Tailored prompts significantly enhance AI performance in engineering analysis.

Abstract

Large language models (LLMs) such as OpenAI's ChatGPT hold potential for automating engineering analysis, yet their reliability in solving multi-step statics problems remains uncertain. This study evaluates the performance of ChatGPT-4o and ChatGPT-o1-preview on foundational statics tasks, from simple calculations of Newton's second law of motion to beam and truss analyses and compares their results to first-year engineering students on a typical statics exam. To enhance accuracy, we developed a Custom GPT, embedding refined prompts directly into its instructions. This optimized model achieved an 82% score, surpassing the 75% student average, demonstrating the impact of tailored guidance. Despite these improvements, LLMs continued to exhibit errors in nuanced or open-ended problems, such as misidentifying tension and compression in truss members. These findings highlight both the promise and current limitations of AI in structural analysis, emphasizing the need for improved reasoning, multimodal capabilities, and targeted training data for future AI-driven automation in civil and mechanical engineering.