A Consistency Method of Motor Vehicle Exhaust Remote Measurement and Vehicle Inspection Results Based on Co-Training

Abstract

The invention discloses a method for the consistency of motor vehicle exhaust telemetry and vehicle inspection results based on common training, comprising the following steps: using BP neural network model to train the influence of environment-related variables on the difference between motor vehicle exhaust telemetry data and vehicle inspection results; At the same time, the support vector machine algorithm is used to analyze the difference between the motor vehicle exhaust telemetry data and the vehicle inspection results by using the relevant variables of motor vehicle information; the prediction probability matrices trained by the two methods are linearly fitted, and finally the motor vehicle exhaust telemetry results are compared with the vehicle inspection results. The test results were consistent.

Description

technical field [0001] The invention belongs to the field of environmental detection technology processing, and in particular relates to a method for consistency between motor vehicle exhaust telemetry and vehicle inspection results based on common training. Background technique [0002] With the rapid development of the national economy and the improvement of the people's economic level, the number of motor vehicles has increased year by year. The problem of air pollution in my country is becoming more and more serious. Severe haze occurs from time to time, especially in the Beijing-Tianjin-Hebei region. Motor vehicle exhaust is one of the main sources of urban air pollution, and its negative effects mainly include: causing human respiratory diseases, high levels of surface ozone, aggravating the urban heat island effect, and producing photochemical smog. Therefore, my country urgently needs remote sensing detection equipment for motor vehicle exhaust and formulates corresp...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to solve the problem that the remote sensing monitoring equipment for motor vehicle exhaust is affected by various environments and complex meteorological conditions at the installation point of the remote sensing monitoring equipment when performing remote measurement of motor vehicle exhaust, resulting in inconsistent data and vehicle inspection results. A method based on joint training for the consistency of motor vehicle exhaust telemetry data and vehicle inspection results. The two influencing factors are discussed separately, which effectively reduces the correlation between different types of variables, making it possible to find the above-mentioned variables more accurately after training. Dataset Consistency

Images