3: The Implementation of a Structural Style Identification Expert System
Structural style analysis while providing the basis for determining the tectonic evolution and framework of a basin also helps seismic interpreters in selecting appropriate structural models to guide interpretation of profiles and preparation of maps. Research results on structural style identification have been documented in many conference and journal papers. If a thorough knowledge of the identification criteria and a systematic application of this knowledge could be captured using the expert systems approach, this expertise could be widely distributed.
An expert system on structural style identification was built on an HP-320 AI workstation. The knowledge base contains map and profile criteria for identifying a style, differentiating a style from possible pitfalls, and refuting pitfalls. The identification procedure presents the user with general profile characteristics to nominate a potential style. This nomination is checked with detailed identification criteria. If the checking is positive, then pitfalls are tested and refuted. A confirmation is reached if the support of the nomination is strong and if all pitfalls either are tested negative, or are refuted. Otherwise, an alternate style is nominated, and the same procedure is repeated.
A commercial expert system shell is used to organize and test the acquired knowledge base. The knowledge base is separated into three parts: procedure, criteria, and certainty combination rules. They are treated as strategic, factual, and judgmental knowledge, respectively. This segregation of knowledge makes the development of the knowledge base very adaptive to the frequent editorial changes made by the domain expert.
In the final system, the expert system shell serves as an inference engine. The system also contains two other major components: a user interface and a data base manager. The user interface is completely mouse driven and is built upon the X-window system, which also provides the communication between the user, the inference engine, and the data base. All the style identification criteria and their corresponding sketches are stored in the data base. At each stage of consultation, all the criteria pertinent to a structural style are listed in a panel. By clicking the mouse on the selection box of each of these criteria, the data base manager retrieves corresponding sketches and displays them in a different window. In the meantime, the inference engine deduces an intermediate decision and moves on to the next stage of consultation. At the end of a consultation, the user can save the consultation in the case history file in the data base.
Figures & Tables
Expert Systems in Exploration
“So far as the laws of mathematics refer to reality they are not certain; and so far as they are certain, they don’t refer to reality.” This quote from Albert Einstein explains the difficulties associated with a mathematical description of many subjective rules used by human experts in reaching a decision. This fact, combined with the multidisciplinary nature of oil exploration, has prevented wide spread use of expert systems in the oil industry. Alternative approaches, that can account for uncertainty and are better equipped for integrating data and rules from different disciplines, should be used to allow expert systems to become viable tools in our applications.
This book examines a diverse set of petroleum exploration problems that properly designed expert systems can help solve. Chapter 1 provides an extensive review of current state-of-the-art expert systems as pertains to oil industry problems. Emphasis is given to how uncertainty and inexactness of data and rules from different disciplines could be handled by expert systems. The chapter suggests that fuzzy logic, evidential reasoning, and neural networks will prove essential in the design of many expert systems that are capable of solving more practical exploration problems. The problem of automatic picking of stacking velocities, using a rule based system, is addressed in Chapter 2. The expert system automates the task of picking the extreme of the velocity spectrum. The system incorporates common sense rules to distinguish primary reflection related peaks in the spectrum from those related to multiples and noise.