SENSOR LAYOUT METHOD FOR FAULT DIAGNOSIS OF PISTON-CONNECTING ROD SYSTEM

The present disclosure provides a sensor layout method for fault diagnosis of a piston-connecting rod system in a diesel engine, including: acquiring data in each sensor layout, and obtaining a feature vector of sensors through a data preprocessing module; taking the feature vector as an input of a long short-term memory (LSTM) neural network, taking actual faulty and normal operating condition codes as an output, and performing training to obtain a fault diagnosis model; taking a test dataset as an input of the fault diagnosis model, outputting a predicted operating condition code, and performing calculation to obtain a fault diagnosis accuracy rate; taking the fault diagnosis accuracy rate and the feature vector corresponding to each sensor layout as an input of a binary Aquila optimizer-based sensor network optimization module, and taking a binary code of an optimal sensor layout as an output.