Automation of Gas Leak Detection: AI and Machine Learning Approaches for Gas Plant Safety
Safety and protection of the environment involve real-time gas leak detection. The paper discusses the improvement in the accuracy and speed of gas leak detection using AI based on pressure-based monitoring. The model will be performing a flow consistency check using machine learning techniques for instantaneous detection at distinct stages in flows. Extensive exploratory data analysis was performed to assess the data and to choose the right machine learning models. The findings showed a significant evolution of pressure differences over time; hence, refining the tolerance level for leakage detection down to a fractional ±0.166 window was necessary. The gas flow data was divided into training and testing datasets, which consisted of 80% and 20%, respectively. Several AI models were tested, such as linear regression, logistic regression, SVM, and Random Forest-all had a test accuracy of over 99%. This AI-powered monitoring system could trigger an alarm or immediate notification in the case of a pressure drop beyond the defined tolerance window, improving upon the traditional methods of inspection. All of these contribute to improved safety, operational efficiency, and even cost savings. Furthermore, the scalability of the model holds great promise for other industrial scenarios. The animated simulation of the proposed solution was demonstrated.
