Case-Based Reasoning Approach for Well Failure Diagnostics and Planning

Abstract

Abstract Case-based reasoning, also known as computer reasoning by analogy, is a simple and practical technique that solves new problems by comparing them to ones that have already been solved in the past, thus saving time and money. The technique constantly incorporates dynamic data, which empowers the system to learn and adapt from new experiences. A general framework for case-based reasoning is presented, along with a review of the four-step cycle that characterizes the technology: retrieve, reuse, revise and retrain. This paper presents a specific application of case-based reasoning to determine the optimum cleaning technique (bailing, washback, or foaming) for sanded/seized well failures. The methodology extracts only the most relevant information from the historical database, utilizes a rule-based system to make adaptations, and then suggests the most appropriate solution for a given well intervention. This technique was used for production operations as a front end tool for well workover planning and design and was applied to sample data from a large oil field where the main artificial lift system is rod pump. This simple case demonstrates how case-based reasoning can be applied to improve the planning and execution of well interventions, thus reducing cost, rig time, and well turnaround time, while maximizing reliability and production. Introduction In large fields with thousands of wells, an immense amount of data and experience build up in databases over time. Typically engineers have access to this data, but rarely have time to analyze the entire dataset before making a recommendation for a well intervention or job. Furthermore, much of the data is irrelevant to a given case and reviewing it can waste the engineer's highly valuable time. Even human memory is of little help in a field with a high activity level or significant turnover where the same engineer, operator, or crew rarely works on the same set of wells. In any and all of the above cases, the well failure dataset represents a tremendous amount of knowledge that can and should be exploited for better decision-making. Case-based reasoning is an excellent technique to maximize the value of historical data for better decisions regarding well intervention planning and execution. Case-Based Reasoning. Case-based reasoning (CBR) is a basic problem solving technique that uses and adapts the solutions of analogous past problems to solve new problems. Its roots are steeped in human cognitive research from the early 1980s, and the technique has gained traction in the last decade. CBR can be described as a common human problem-solving behavior that has been adapted for computer use. It is based on recall and reuse of specific "cases" and offers techniques for acquiring, representing and managing previous experiences. The formalized four-step process of retrieve, reuse, revise, and retain is detailed below and depicted in Figure 1.Retrieve: The process of finding cases, and their corresponding solutions, in the dataset or knowledge base that are most relevant to the given case.Reuse: The process of mapping the most common solution from the knowledge base for the given case. The reuse process also allows for adaptation of the most common solution, as needed, through the use of rules or "if statements" incorporated into the system.Revise: The process of testing the new solution. If the new solution is successful, the process moves directly to retain. If the new solution does not work as expected or needs additional fine-tuning, the solution is further adapted to achieve the desired result.Retain: The process of storing the new case and its final solution in the knowledge base for future use in the case-based reasoning process.