Well integrity (WI) impairments in oil and gas (O&G) wells are one of the most formidable challenges in the petroleum industry. Managing WI for different groups of well services necessitates precise assessment of risk level. When WI classification and risk assessment are performed using traditional methods such as spreadsheets, failures of well barriers will result in complicated and challenging WI management, especially in mature O&G fields.
Industrial practices, then, started moving toward likelihood/ severity matrices which turned out later to be misleading in many cases due to possibility of having skewness in failure data. Developing a reliable model for classifying level of WI impairment is becoming more crucial for the industry. Artificial intelligence (AI) includes advanced algorithms that use machine learning (ML) and computing powers efficiently for predictive analytics.
The main objective of this work is to develop ML models for the detection of integrity anomalies and early recognition of well failures. Most common ML algorithms in data science include; random forest, logistic regression, quadratic discriminant analysis, and boosting techniques. This model establishment comes after initial data gathering, pre-processing, and feature engineering. These models can iterate different failure scenarios considering all barrier elements that could contribute to the WI envelope. Thousands of WI data arrays can be literally collected and fed into ML models after being processed and structured properly.
The new model presented in this paper can detect different WI anomalies and accurate analysis of failures can be achieved. This emphasizes that managing overall risks of WI failures is a robust and practical approach for direct implementation in mature fields. It also, creates additional enhancement for WI management. This perspective will improve efficiency of operations in addition to having the privilege of universality, where it can be applicable for different well groups. The rising wave of digitalization is anticipated to improve field operations, business performance, and production safety.
