The main purpose of this paper is to present a new integration framework for on-line incipient process fault diagnosis (IPFD) based on data rectification(DR). Significant amount of efforts have been made to investigate DR and IPDF during the last two decades. Integration of DR and IPFD has seldom been addressed in detail even though DR has been recognized as an important foundation for successful IPFD since IPFD based on raw data is lack of reliability and therefore can generate false alarms. In this framework, there are five major components: process state identification (PSI) [1], Gross error detection and identification, sensor fault diagnosis(SFD), dynamic data reconciliation (DDR)[2-3] and IPFD. Through PSI, the process is identified as steady state or dynamic one. Under the dynamic states, the gross error detection and identification is carried out. If the bias type of gross errors exists, then the zero drift or malfunction of the instruments may occur, which presents the base of the detection of sensor fault diagnosis. The Optegrity platform is used here for SFD. It is a new commercial package from Gensym corporation designed for abnormal situation management of chemical processes based on its well-known flagship product G2. It includes intelligent objects with built-in fault diagnosis capability of common equipments such as sensors, heat exchangers, heaters, pumps and so on. If no sensor fault is identified, the data containing gross errors should be firstly treated properly and then reconciled through DDR to remove random errors. The reconciled data is then fed into the IPFD model. The cause-effect IPFD model is also configured based on Optegrity. The benefit of using Optegrity for IPFD is that the reasoning is done automatically by the platform once the cause-effect model is established. Therefore, development and implementation of IPFD is greatly eased. The framework is demonstrated by an industrial case study. The simulation results indicate that the number of false alarms of IFD is significantly reduced by using the framework proposed.

References

1.Jiang TW, Chen BZ, He XR, Stuart P. Application of steady- state detection method based on wavelet transform, Computers & Chemical Engineering, 2003, 27(4): 569-578

2.Kong Mingfang, Chen Bingzhen, Li Bo. An Integral approach to dynamic data rectification. Computers and Chemical Engineering, 2000, 24(2-7):749-753.

3.Kong Mingfang, Chen Bingzhen, Xiaorong He, Shanying Hu, Gross error identification for dynamic system, Computers & Chemical Engineering, 2004, 29(1), p191�`197;