This contribution describes a combined analytical/fuzzy model-based fault diagnosis concept which has been applied to the high-pressure-preheater line of a power plant.The key idea is to divide the whole system under supervision into several subsystems and to employ all available analytical knowledge to generate residuals for each subsystem seperately. Thereby the necessary observers for fault detection are of a handable size. For fault isolation, the residual evaluation is done by applying qualitative knowledge about the fault effects on the residuals and about the interaction of the different subsystems. Here a rule base is evaluated using fuzzy logic. With this method a complex system can be supervised without the need for a complex analytical model of the whole system. Furthermore, the presentation of the fault isolation results leaves the final decision about a fault alarm to the human operator. Results from a power plant prove the successful application of the proposed supervision concept.
In this paper we suggest a novel philosophy of process supervision based on knowledge based redundancy. The key idea is to replace the conventional residual evaluator of the fault diagnosis system based on crisp logic, by both a decision maker with fuzzy logic for residual evaluation and the human operator to make the final decisions using his natural intelligence, experience and common sense. The purpose of the employment of fuzzy logic for residual evaluation is to release only weighted alarms instead of yes-no decisions, such that (by definition) no false alarms can be produced; besides this the manmachine interaction becomes much easier. In contrast to the conventional expert system approach, the proposed concept leaves the final yes-no decisions to the natural intelligence, capability and responsibility of the human operator. In addition this method can be seen as an extension to the quantitative model-based techniques.Nevertheless the huge amount of information, which is normally given by most of the fault diagnosis schemes, should be both, filtered and reduced in the sense of the detectability and reliability of an FDI scheme. As an application example this concept has been applied to a part of a power plant in order to prove this theory.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.