Outline of a fault diagnosis system for a large-scale board machine

Abstract

Global competition forces process industries to continuously optimize plant operation. One of the latest trends for efficiency and plant availability improvement is to set up fault diagnosis and maintenance systems for online industrial use. This paper presents a methodology for developing industrial fault detection and diagnosis (FDD) systems. Since model or data-based diagnosis of all components cannot be achieved online on a large-scale basis, the focus must be narrowed down to the most likely faulty components responsible for abnormal process behavior. One of the key elements here is fault analysis. The paper describes and briefly discusses also other development phases, process decomposition, and the selection of FDD methods. The paper ends with an FDD case study of a large-scale industrial board machine including a description of the fault analysis and FDD algorithms for the resulting focus areas. Finally, the testing and validation results are presented and discussed.