Data-Driven Based Gas Path Fault Diagnosis for Turbo-Shaft Engine

Abstract

In order to diagnose the starting fail fault of the certain turbo shaft engine which often occurs in daily use, the experiments for the micro pump and the fuel filter were carried out by the method of contrast test. Through the comparison and analysis, the differences between domestic components and French-made ones were found. The results showed that: The outlet pressure of domestic micro pump is smaller under the engine's working condition; the flux of it is significantly lower under high outlet pressure; the pressure-flux characteristic line of domestic micro pump can close to the French-made pump when the French-made fuel valve and regulating valve were installed on it; the structure size of domestic filter frame is very different from the French-made one, which leads to its greater flow resistance. According to the performance indicators of French-made components, the improvement measures were put forward in order to improve the success rate of engine ground starting.

Data‐driven sensor fault detection and isolation of nonlinear systems: Deep neural‐network Koopman operator

“…Besides, they need different types of faulty data to obtain classifiers for achieving fault isolation as in refs. [17,[27][28][29][30][31][32]. On the other hand, the methods which do not require faulty data are only concerned with the detection, like in refs.…”

Integration of Artificial Intelligence into Dempster Shafer Theory: A Review on Decision Making in Condition Monitoring

“…Besides machinery fault diagnosis, SVM-DS method were also used in character recognition research according to Guo and Zhang [11]. Another evolution of BPA selection is to use Least squares SVM (LSSVM) which Lu et al have compared the LSSVM with Back Propagation Neural Network (BPNN) and Radial Based Function Neural Network (RBF-NN) to compare the accuracy of LSSVM and D-S [12]. It was reported that the advantages of SVM technique as compare to other machine learning techniques such as can be used for small samples, sample's non-linearity, over fitting, local minimum value and also has excellent generalization ability.…”