Search Results

Intelligent sweeper vehicle is gradually applied to human life, in which the accuracy of garbage identification and classification can improve cleaning efficiency and save labor cost. Although Deep Learning has made significant progress in computer vision and the application of semantic network segmentation can improve waste identification rate and classification accuracy. Due to the loss of some spatial information during the convolution process, coupled with the lack of specific datasets for garbage identification, the training of the network and the improvement of recognition and classification accuracy are affected. Based on the Unet algorithm, in this paper we adjust the number of input and output channels in the convolutional layer to improve the speed during the feature extraction part. In addition, manually generated datasets are used to greatly improve the robustness of the model.

Urea-based selective catalytic reduction (SCR) of nitric oxides (NOx) is a key technology for heavy-duty diesel engines to achieve the increasingly stringent NOx emission standards. The aqueous urea injection control is critical for urea-SCR systems in order to achieve high NOx conversion efficiency while restricting the tailpipe ammonia (NH3) slip. For Euro VI emission regulation, an advanced control strategy is essential for SCR systems since its NOx emission limits are tighter and test procedure are more stringent compared to Euro IV and Euro V. The complex chemical kinetics of the SCR process has motivated model-based control design approaches. However, the model is too complex to allow real-time implementation. Therefore, it is very important to have a reduced order model for SCR control system.