Engine compartment state real-time monitoring and evaluating method

Abstract

The invention discloses an engine compartment state real-time monitoring and evaluating method. The method comprises the steps; acquiring various state data of an engine compartment by multiple sensors; slicing the state data according to the time dimension; extracting the spatial features of the data slices by using a convolutional neural network with a sensor data calibration module; using a gated recurrent neural network with a fault category analysis module for further extracting a feature sequence representing time from the spatial features, so as to obtain a fault parameter; sequentiallyprocessing each data slice to realize the extraction of the fault type and the fault parameter; and finally, according to an entropy method, calculating a total evaluation score of the operation state of the engine compartment by utilizing the fault parameter of the current state data in the next period of time. According to the method, the fault type and the fault parameter representing fault severity can be obtained at one time by using a small amount of sensor data, the score representing the operation state of the engine compartment is calculated, and monitoring and evaluation of the state of the engine compartment are completed.

Description

technical field [0001] The invention relates to the technical field of automatic detection, in particular to a method for real-time monitoring and evaluation of the state of a power cabin. Background technique [0002] The power compartment is one of the most important core components of a car. It is mainly composed of an engine, a gearbox, a cooling system, etc., and is used to provide power for the entire vehicle. Such an important component naturally needs more attention and protection, so an accurate fault diagnosis algorithm is very necessary. Finding problems before loading can prevent the manufacture of problematic vehicles; finding problems on running vehicles can protect other parts of the system and the personal safety of drivers. [0003] The existing mature methods generally only judge the fault category of the power cabin, but there is no suitable judgment method for the severity of the fault, and the severity of the fault is also a key factor affecting the tre...

AI Technical Summary

Problems solved by technology

[0003]The existing mature methods generally only judge the fault category of the power cabin, but there is no suitable judgment method for the severity of the fault, and the seriousness of the fault The extent is also a key factor influencing treatment measures

Images