Image Based Monitoring for Combustion Systems

A novel method of on-line flame detection in video is proposed. It aims to early detect the current state of the combustion system and prevent the system from further degradation and occurrence of failure. The proposed method consists of hidden Markov model (HMM) and multiway principal component analysis (MPCA). MPCA is used to extract the cross-correlation among spatial relationships in the low dimensional space while HMM constructs the temporal behavior of the sequence of the spatial features. The probability distribution of the normal status can be trained by the images collected from the normal operation processes. The proposed method can generate simple probability monitoring charts to track the progress of the current transition state sequence and monitor the occurrence of the observable upsets. To demonstrate the performance of the proposed method, data from the monitoring practice in the real combustion systems are conducted.