This paper deals with non linear system monitoring, based on a combined use of Principal Components Analysis (PCA) and fuzzy logic to process and quality monitoring. PCA coupled to fuzzy logic was used to estimate the fault or defect according to the dynamic changes in the process inputs outputs characterized by T2 Hoteling and Squared Prediction Error (SPE). Correlation between the relevant process variables and the importance of defects/faults was obtained by a reliable selection of a reduced set of relevant descriptors. The effectiveness of the computing procedure based on fuzzy rule proved by its application to quality estimation of the solidification process in continuous casting
Modern manufacturing facilities are large scale, highly complex, and operate with large number of variables under closed loop control. Early and accurate fault detection and diagnosis for these plants can minimise down time, increase the safety of plant operations, and reduce manufacturing costs. Fault detection and isolation is more complex particularly in the case of the faulty analog control systems. Analog control system are not equipped with monitoring function where the process parameters are continually visualised. We consider in this paper an approach to fault detection and isolation in the pickling process in cold rolling. The fault appeared on one of the power unit driving a rotary machine, this machine can not track a reference speed given by another machine. Using a computerised data acquisition system, the main machine parameters have been monitored. The fault has been detected and isolated on basis of analysis of monitored data. Normal and faulty situation have been obtained by an artificial neural network (ANN) model which is implemented to simulate the normal and faulty status of rotary machine.
-A new approach for fault detection and monitoring based on the parameters identification coupled to the Principal Component Analysis (PCA) is proposed in this paper. The proposed Fault Detection and Monitoring consists to apply the PCA method on the dynamic of the identified parameters. Conventional PCA uses the process inputs and outputs as variables which are used in the computing procedure. Using the process parameters behaviour as variables in the PCA computing procedure improve the detect ability by reducing the wrong faults generating by the noise effects. Application on the rotary machines in skin pass machines of cold rolling will be developed in this work.
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.