Optimizing Corrosion Protection: A Data-Driven Approach to Impressed Current Cathodic Protection (ICCP) Systems for Large Crude Carriers

Abstract The use of Impressed Current Cathodic Protection (ICCP) systems in large crude carriers such as very large crude carriers (VLCC) and ultra large crude carriers (ULCC) is universally regarded as an effective means of corrosion protection. However, traditional ICCP systems have certain drawbacks that can be overcome by using data-driven methodologies. This research describes a unique data-driven ICCP system aimed to optimise energy consumption and ICCP system efficacy for large crude carriers. The objective of this project was to develop an AI-based ICCP system that could address existing ICCP system shortcomings such as overprotection, inefficiency, maintenance, corrosion detection, and environmental factors. To achieve this objective, we employed a machine learning approach that utilized historical data to train our AI-based ICCP system. Our methodology involved collecting data on the environmental conditions, the ICCP system output, and the corrosion rates for several large crude carriers. We then utilised this data to train machine learning algorithms that could anticipate the best current output needed to protect the hull while consuming the least amount of energy. The procedures involved testing the AI-based ICCP system in a simulated setting. Our study shows that the data-driven ICCP system provides significant benefits for the corrosion protection of large crude carriers. Our results demonstrate that the AI-ML approach is effective in reducing overprotection and optimizing energy consumption, while also predicting maintenance requirements, detecting localized corrosion, and adjusting the ICCP system output based on real-time environmental data. Our observations show that the data-driven ICCP system is able to detect localized corrosion more accurately than traditional ICCP systems, which can lead to early detection and prevention of corrosion. The system is also able to adjust the current output based on real-time environmental data, providing better protection against external factors such as temperature, salinity, and currents. This research describes a revolutionary data-driven approach to ICCP systems that tackles the shortcomings of standard ICCP systems used in large crude carriers. Our research delivers new insights into optimising energy consumption, reducing overprotection, forecasting maintenance requirements, identifying localised corrosion, and changing the ICCP system output based on real-time environmental data by utilising AI-ML technologies. These results have the potential to significantly help the oil and gas industry by improving the efficiency and effectiveness of corrosion prevention for large crude transporters.