Automated standardization of bridge inspection data using generative AI

This paper presents a method leveraging generative AI and natural language processing to standardize bridge inspection data, transforming it into a ready-to-use format for direct use in condition assessment, predictive modeling, and informed decision-making. This entails capturing and evaluating severity levels of reinforced concrete bridge defects from textual inspection data, such as comments provided by inspection personnel regarding type, location, and intensity of these defects. This paper employs three models: (1) a baseline generative pre-trained transformer model, which leverages OpenAI’s large language models to process textual inspection data through an optimized prompt engineering procedure; (2) a fine-tuned generative pre-trained transformer model, which builds upon the baseline by incorporating domain-specific training before being deployed to improve its performance; and (3) a newly developed natural language processing model, which employs conventional natural language processing techniques, providing a benchmark for comparison with the generative AI models. These models are implemented and validated to standardize vast amounts of inspection data extracted from 2255 inspection reports spanning five years (2018–2022) for a set of bridges in Québec, Canada. The fine-tuned model is found to outperform other models in terms of performance, stability, and reliability in detecting and standardizing the severity of different types of concrete defects in bridge decks. It achieves accuracy rates of 98.79 % for corrosion of reinforcing bars, 99.09 % for concrete delamination, and 98.64 % for cracking, scaling, and spalling of concrete. This paper demonstrates the potential for integrating generative AI into infrastructure asset management, an application that has yet to be realized. • A method uses GPT and NLP to transform unstructured inspection data into a ready-to-use format. • Fine-tuned GPT model improves the standardization of bridge deck defects with over 98 % accuracy. • Results demonstrated the potential for integrating GenAI and LLMs into asset management. • Data generated from this study can be used for various applications in asset management.