A vehicle exhaust concentration estimation method based on an improved stacking model

Abstract

The invention relates to a vehicle exhaust concentration estimation method based on an improved Stacking model. On the basis of the Stacking model, the exhaust emission concentration estimation results of the Stacking model and the estimation results of some single models are weighted and summed to obtain the final vehicle exhaust Estimated results of emission concentrations. Among them, the Stacking model, the first layer is trained by multiple machine learning models using 5-fold cross-validation to obtain a new training sample set and a new test sample set, and the simple linear regression model is used as the second layer estimation model to train the new training sample set of the first layer , the estimation model generated by training estimates the new test sample set, and obtains the exhaust gas concentration estimation result. The invention can quickly and accurately estimate the CO or HC exhaust emission concentration of the vehicle, and the estimation performance of the improved Stacking model is greatly improved compared with the estimation accuracy of the Stacking model or a single machine learning model used in the Stacking model.

Description

technical field [0001] The invention relates to a vehicle tail gas concentration estimation method based on an improved Stacking model, and belongs to the field of vehicle tail gas discharge concentration estimation and pattern recognition. Background technique [0002] Excessive emission of motor vehicle exhaust is one of the main causes of air pollution. As the number of individuals owning a car has grown significantly. According to data from the Traffic Management Bureau of the Ministry of Public Security of China, the number of newly registered motor vehicles nationwide in 2018 was 31.72 million, and the number of motor vehicles reached 327 million. The rapid increase in the number of these vehicles has increased the emission of exhaust gas and caused serious environmental pollution problems. Vehicle exhaust contains a large amount of harmful gases. Some of these harmful car exhausts can also negatively impact human health. In particular, exhaust will cause certain d...

AI Technical Summary

Problems solved by technology

[0005] The technical problem of the present invention is to provide a vehicle exhaust concentration estimation method based on the improved Stacking model in view of the defects of conventional exhaust emission concentration detection and the low accuracy of concentration estimation by existing artificial intelligence technology

Images