Multi-sensor monitoring based on-line diesel engine anomaly detection with baseline deviation

摘要

For the low-speed diesel engine monitoring with multi-sensor information on ship, the on-line anomaly detection as the fault symptom pre-warning is mainly considered in this paper. The stable operating condition is firstly identified by the ADF test. Then, the on-line anomaly detection with baseline deviation is modeled by the Auto associative Kernel Regression (AAKR) method, where the baseline is constructed by the proper memory matrix with stable operating process, and the anomaly is timely diagnosed using the model estimation deviation compared to the normal monitoring. Our results with presented AAKR model are verified by the studies of the real low-speed diesel engine monitoring case.