Unmanned vehicle health state detection system and detection method

Abstract

The invention relates to an unmanned vehicle health state detection method, and the system comprises a model building device which is used for building a deep convolutional neural network model, and the input data of the deep convolutional neural network model are amplitude parameters and frequency parameters corresponding to a preset number of collection time periods before a judgment moment, the output data is a fault number corresponding to the fault type of the engine of the special unmanned vehicle at the judgment moment; and the network training equipment comprises a first training unit, a second training unit, a third training unit, a fourth training unit and a fifth training unit and is used for training the deep convolutional neural network model. The invention also relates to an unmanned vehicle health state detection system. According to the method, the deep convolutional neural network can be introduced to intelligently analyze the current main fault type of the engine, and meanwhile, a targeted training mechanism and a hidden layer number selection mechanism considering various types of engines are introduced, so that the reliability and compatibility of the trained deep convolutional neural network are ensured.

Description

technical field [0001] The invention relates to the field of monitoring of special unmanned vehicles, in particular to a detection system and method for the health status of unmanned vehicles. Background technique [0002] With the birth of tanks, special unmanned vehicles with relatively weak firepower, protection and off-road performance lost their status as providing fire support for infantry on the battlefield, so they turned to other uses for development, but tanks are also a part of special unmanned vehicles. There are two types, but they are usually classified separately because of their combat use, and special unmanned vehicles mostly refer to vehicles with weaker protection and firepower than tanks. [0003] Special unmanned vehicles are classified according to their uses, and can be divided into infantry fighting vehicles and special personnel carriers. Special personnel carriers provide special protection for infantry and combat materials. Usually there are no hea...

AI Technical Summary

Problems solved by technology

[0005] As the most important power equipment of special unmanned vehicles, the health status monitoring of the engine is very important. It maintains the safety of special unmanned vehicles and the lives of special unmanned vehicle personnel. A healthy engine enables special unmanned vehicles to quickly evacuate from dangerous areas Create conditions. Once the engine fails, if it is in a safe area, it will cause a reduction in combat or transportation capabilities. If it is in a dangerous area, the consequences will be disastrous

[0006] However, in the prior art, the health status detection mechanism of special unmanned vehicle engines requires complex and cumbersome analysis of the status of each component part of the engine itself and the associated status of related parts in order to give the current main fault types of the engine. On the one hand, , this analysis mode is time-consuming and labor-intensive, resulting in the failure code is too slow to leave enough time for the troubleshooting of special unmanned vehicles. On the other hand, this analysis mode is too complicated, and the analysis accuracy is difficult to meet the current needs

Images