|
| Prediction of Urea Injection Rates Based on Remote Monitoring Data of Heavy-Duty Diesel Vehicles |
| DOI：10.13949/j.cnki.nrjgc.2024.04.008 |
| Key Words:heavy-duty diesel vehicle remote monitoring ammonia slip ureainjection random forest |
|
| Hits: 991 |
| Download times: 799 |
| Abstract:Based on the remote monitoring data of a M3 heavy-duty diesel vehicle， a urea injection rate prediction model was constructed， and the prediction of urea injection rate missing in the remote monitoring data was studied by using the random forest regression algorithm. The results indicate that there are multiple sets of highly correlated variables with Spearman correlation coefficients exceeding 0.85. Based on this， the input parameters of the model were screened. Because urea supply is aimed at controlling ammonia storage， and ammonia storage changes at a low frequency， the per-second urea injection rate is difficult to predict accurately. The results of predicting the average urea injection rate in different periods show that the model’s prediction accuracy tends to stabilize when the period duration exceeds 40 seconds. Finally， the generalization ability of the prediction model was verified through the sliding window method. In all 27 windows， the coefficient of determination R2 is higher than 0.96， the mean absolute error is within 0.7%， and the root mean square error is less than 1%. The predicted urea injection rate values agree with the actual measured values. |
| View Full Text View/Add Comment Download reader |