Abstract
Health, Safety and Environment (HSE) operations can be greatly enhanced by reducing the uncertainty inherent in quantifying human activity. One way to do this is by using artificial intelligence (AI) techniques, in particular natural language processing (NLP), on HSE data to identify hidden trends, uncover and quantify textual data and, ultimately create a smart system that can alert users to risk before that risk is realized. This allows an organization to better target their resources, such as safety coaches, more effectively to prevent an adverse event, protecting vital equipment and potentially saving lives. One important aspect inherent in this process is the need to establish trust in the AI system among the users. This is especially the case during data collection, system rollout and user adoption.
In order to realize the goal of an AI driven HSE workflow, a system was implemented which allowed for a) the easy collection, structuring and preprocessing of data associated with the performance of management observations, and for b) the development and implementation of a robust set of AI tools that allowed the users to enhance their existing workflows to better be able to identify, quantify and address HSE risk. This created a new set of leading indicators for HSE awareness. While management observations were the first set of data considered as they were the most robust data set, the adaptable system was constructed in such a way that work orders, audits, and near misses could be easily incorporated in the future.
This study is part of a pilot project with Petroleum Development Oman (PDO) for IHTIMAM, which is a process that creates a safety partnership between the workforce and management that continually focuses everyone's attention and actions on their own and others daily safety ‘behaviour’. It was unique and innovative, because it took an auto ethnographic approach in the analysis of the AI, drawing on a team with multidisciplinary expertise.
A novel, comprehensive approach for HSE data collection and development of industry specific AI models to is presented. In addition, a novel approach was identified to leverage user adoption and use case in terms of both method and application.