Multi-Class Taxonomy of Well Integrity Anomalies Applying Inductive Learning Algorithms: Analytical Approach for Artificial-Lift Wells

Artificial intelligence (AI) and machine learning (ML) are transforming industries, where low-cost, big data can utilize computing power to optimize system performance. Oil and gas (O&G) fields are getting mature, where well integrity (WI) problems become more common and field operations are now more challenging. Hence, they are good candidates for transformation due to the low cost of data storage, highlighting the oil market decline, along with dynamic risk posed during operations. This paper is presenting a comprehensive compilation of different ML applications in diverse disciplines of the petroleum industry. The pool of AI and ML with respect to different areas of applications along with publication years has been categorized. The main focus of this study is classifying well integrity failures where the authors found that the potential of AI and ML in predicting well integrity failures has not been efficiently tapped, and there is an explicit gap in the literature. First, the applications of AI, ML, and data analytics in the O&G industry are discussed thoroughly, so this paper can be a comprehensive reference for readers and future researchers. Then data preprocessing is explained. This includes data gathering, cleaning, and feature engineering. Next, the different ML models are compared and discussed. Finally, model performance evaluation and best model selection are described. This study would be a concrete foundation in the design and construction of ML programs that can be deployed for WI risk management. The developed model can be simply used for any well stock, providing quick and easy assessment instead of subjective and tedious assessment. The layout can be simply adjusted to reflect the risk profile of any well type or any field.

show abstract

Development of an Artificial Intelligence-Based Well Integrity Monitoring Solution

Aditama¹,

Koziol²,

Dillen³

2022

Day 3 Wed, November 02, 2022

View full text Add to dashboard Cite

The question of how to safeguard well integrity is one of the most important problems faced by oil and gas companies today. With the rise of Artificial Intelligence (AI) and Machine Learning (ML), many companies explore new technologies to improve well integrity and avoid catastrophic events. This paper presents the Proof of Concept (PoC) of an AI-based well integrity monitoring solution for gas lift, natural flow, and water injector wells. AI model prototypes were built to detect annulus leakage as incident-relevant anomalies from time series sensor data. The historical well annulus leakage incidents were classified based on well type and the incident relevant anomalies were categorized as short and long-term. The objective of the PoC is to build generalized AI models that could detect historical events and future events in unseen wells. The success criteria are discussed and agreed with the Subject Matter Experts (SMEs). Two statistical metrics were defined (Detected Event Rate – DER – and False Alarm Rate – FAR) to quantitively evaluate the model performance and decide if it could be used for the next phase. The high frequency sensor data were retrieved from the production historian. The importance of the sensor was aligned with the SMEs and only a small number of sensors was used as input variable. The raw data was pre-processed and resampled to improve model performance and increase computational efficiency. Throughout the PoC, the authors learnt that specific AI models needed to be implemented for different well types as generalization across well types could not be achieved. Depending on the number of available labels in the training dataset, either unsupervised or supervised ML models were developed. Deep learning models, based on LSTM (Long-Short Term Memory) autoencoder and classifier were used to detect complex anomalies. In cases where limited data were available and simplistic anomaly patterns were present, deterministic rules were implemented to detect well integrity-relevant incidents. The LIME (Local Interpretable Model-Agnostic Explanations) framework was used to derive the most important sensors causing the anomaly prediction to enable the users to critically validate the AI suggestion. The AI models for gas lift and natural flow wells achieved a sufficient level of performance with a minimum of 75% of historical events detected and less than one false positive per month per well.

show abstract

Multi-Class Taxonomy of Well Integrity Anomalies Applying Inductive Learning Algorithms: Analytical Approach for Artificial-Lift Wells

Cited by 4 publications

References 14 publications

Numerical-Based Model for Calculating the Risk of Well Integrity Failures in Mature Fields Operated by Gas Lift

Numerical-Based Model for Calculating the Risk of Well Integrity Failures in Mature Fields Operated by Gas Lift

Addressing Diverse Petroleum Industry Problems Using Machine Learning Techniques: Literary Methodology─Spotlight on Predicting Well Integrity Failures

Development of an Artificial Intelligence-Based Well Integrity Monitoring Solution

Contact Info

Product

Resources

About