| As the development of modern sciences and technology, cryogenic industrial systems are becoming larger, more complex and automatic. The widely applications of these complex systems in industrial produce huge economic benefit, but also cause a whole series of problems. The investment and the maintenance cost of complex systems are high, the losses of stopping machines are heavy and the accident consequences are serious. So fault detection and fault diagnosis of cryogenic systems are attached more and more importance.This paper presents a real-time approach to the problem of fault detection in cryogenic systems, to identify faults by relating patterns of fault signatures to their causes. The fault detection system was designed to operate based on steady state and transient responses was obtained by monitoring sensitive parameters of the cryogenic system. The steady signal acts as a stimulus. When the signal exceeds a predetermined threshold it will initiate a non-destructive test on the system during which a transient response of a five-second sensitive parameter will be captured. The transient pattern will be compared with the database of the patterns of fault signatures. The closest match will determine the cause of fault.The technology of fault diagnosis for cryogenic system, including concept, principle, key technology, method and so on, is discussed in this paper. The features of the running of cryogenic system are analyzed, and the field knowledge base is established based on these.The fault diagnosis expert system for cryogenic systems was developed with Borland Delphi 7.0 and SQL server 2000.A universal fault diagnosis expert system for expansion machine was developed in this paper under the base of fully study of the structure and principle of expert system. Design and implement of module of expansion machine has been done. A practical expert system for fault diagnosis of expansion machine has been realized, and the fault diagnostic result was illustrated. |
PDF Full Text Request