Artificial Intelligence (AI) is a scientific subject investigating and developing theories, methods, technologies, and application systems to simulate, extend, and expand human intelligence. Research in AI includes robotics, language recognition, image recognition, natural language processing, and expert systems. As a comprehensive frontier technology, machine Learning (ML), an essential part of AI, has drawn widespread attention. This chapter discusses the application of ML in process safety and asset integrity management (AIM). It gives a brief literature review of the state-of-the-art of AI in process safety and AIM and describes the use of ML approaches in probabilistic risk assessment. The chapter also presents a conceptual model for big-data-driven AIM. Failure mode and effect analysis is used for damage mode identification and cause and effect characterization. Random forest regressor is an ensemble algorithm that comprises a set of decision trees built independently and with a different structure.@en

Identification of credible failure modes and associated damage mechanisms is a critical part of asset integrity management program for the process units in the oil and gas industry. The Failure Mode and Effect Analysis (FMEA) has been widely used for these purposes. At the stages of units’ design and early operation, subject matter expert’s opinions (SMEs) with qualitative or semi-quantitative approaches for the damage risk assessment are often used. However, the quality of the assessment can be heavily dependent on the experts’ knowledge and information available for the studied system. The present study aims to improve the reliability of the existing credible failure mode identification by using machine learning techniques of regression and feature engineering in the framework. The developed model assesses the contribution of individual damage mechanisms to the overall component’s risk level given the available operational, design, and inspection metrics. By means of feature engineering, the limited input information is expanded for damage factor/applicable mechanism analysis by API RP 581 and API RP 571, used as a reference. Meanwhile, the several regression techniques will be used for risk analysis of individual damage mechanisms, in terms of their relative probabilities of occurrence and consequences. Based on which, the damage mechanisms are prioritized. The performance of the model will be tested on the example of several process units, including sour gas treatment, thermal cracking, separators, and several simulated flowlines.@en

Corrosion is a significant concern causing tremendous losses to all pipeline operators. To combat this operational issue, new methods and tools are needed to analyze and model degradation, to predict failure, and finally to develop strategies for prevention, control, and mitigation of corrosion in pipelines. A practical inspection and maintenance program is crucial to prevent pipeline failures due to corrosion. Risk-based inspection (RBI) is an increasingly popular and trusted method to assess and develop inspection plans. However, the determination of optimal inspection intervals is still challenging in RBI. The present study aims to develop a dynamic Bayesian network (DBN)-based approach for optimization of inspection intervals. Based on inline inspection data and analytical corrosion propagation models, DBN is applied for the estimation of both the internal and external corrosion damage as well as the probability of failure (PoF). The cost of failure (CoF) is estimated based on typical cost categories relevant to pipeline accidents. Risk is calculated as the product of PoF and CoF. A utility function to combine both the risk and the annual cost of the inspection program is also developed. The optimal interval can be found based on the curve of the utility function. The proposed approach is demonstrated through a real-world case study on an operating pipeline.

@en