Vehicle performance data cleaning system and method based on artificial neural network

Abstract

The present invention discloses a vehicle performance data cleaning system based on an artificial neural network, and a method thereof. The vehicle performance data cleaning system comprises a data input module, a sample training module, a data cleaning module and a data prediction module. The data input module is used for inputting original data of vehicle performance. The sample training module is used for calling the original data, carrying out artificial neural network training on the original data, and transmitting the neural network information of the trained original data to the data cleaning module. The data cleaning module is used for cleaning abnormal data of the neural network information according to relative errors, and feeding back the cleaned original data to the sample training module. The sample training module is used for learning and training cleaned original data information samples according to an artificial neural network algorithm, and the vehicle performance is predicted through the data prediction module. Abnormal data in regular measured data can be detected, and can be rapidly detected and cleaned under a large data size condition.

Description

technical field [0001] The present invention relates to a technology in the field of data cleaning, in particular to an artificial neural network-based vehicle performance data cleaning system and method thereof. Background technique [0002] As vehicles are indispensable in contemporary life, the estimation of vehicle performance is particularly important. Vehicles play a key role in many cases. If the performance cannot meet the required standards, or even the vehicle breaks down when the vehicle is urgently needed, it will have an impact on the smooth progress of production and life. It may not be possible to accurately predict the performance of the vehicle when traveling to less frequented places. The prediction of vehicle performance can be achieved through machine learning methods. [0003] Machine learning mainly studies how computers simulate human learning behaviors and obtain useful knowledge from a large amount of information. Through machine learning, such as...

AI Technical Summary

Problems solved by technology

However, the calculation of this technology is complex, and additional algorithms are required to make predictions based on clean data; and for some regular data, it is impossible to learn according to different original data characteristics and discover potential laws between data, so as to more accurately Identify outlier data

Images