Fault prediction method and device based on diagnosis fault code evolution graph

Abstract

The invention relates to a fault prediction method and device based on a diagnosis fault code evolution graph, and belongs to the technical field of data processing. The method comprises the following steps: acquiring historical fault code data of a vehicle within a first preset time; processing the historical fault code data, and constructing a fault map; and analyzing the fault map, screening key fault codes, and determining the probability that the vehicle enters the station for maintenance within a second predetermined time in the future. The method can accurately predict the probability of entering the station for maintenance due to the fact that a certain part of the automobile breaks down in real time, and the economic cost is reduced.

Description

technical field [0001] The invention belongs to the technical field of data processing, and in particular relates to a fault prediction method and device based on a diagnostic fault code evolution map. Background technique [0002] Cars are becoming more and more popular in people's life and work. At present, the number of cars in the country is 200 million. However, accidents occur frequently during the use of automobiles. Although most of them are caused by improper operation of drivers, some of them are also caused by automobile failures. Human factors are uncontrollable, but injuries caused by car failures can be effectively avoided. [0003] Common faults in automobiles occur in engines, transmissions, brakes and electrical systems. Before using the car, the driver performs an effective fault detection on the car, which can ensure that the car will not break down during driving. However, for the inspection of the above systems, the traditional detection method takes ...

AI Technical Summary

Problems solved by technology

[0005] None of the existing fault prediction schemes use the DTC (Diagnostic Trouble Code) evolution map to predict vehicle faults, but are mainly divided into the following three categories: The first category is to use the vehicle's historical driving information and machine learning to predict future faults The time of occurrence, but its disadvantage is that it cannot accurately predict the specific faulty parts, and at the same time, the model is easily in an over-fitting state, resulting in inaccurate prediction results and bringing certain troubles to the business; the second type is to use Historical driving data and current driving data are based on machine learning models to detect whether there is a fault in the current vehicle. The disadvantage of this method is also the over-fitting phenomenon of the model. The first type of scheme cannot give specific faulty parts, and the third type installs multiple sensors at the key parts of the vehicle to transmit signals in real time, and then uses the traditional fault identification, that is, spectrum analysis method to predict vehicle faults. The disadvantages of this method It is necessary to install multiple sensors, which consumes a lot of economic costs

Images