Recognition Of Pavement Garbage On Sweeping Vehicle And Research On Loading System Energy Saving Strategy

As environmental and energy issues become increasingly acute,electric vehicles have become a hot topic in the current automotive industry.Passenger car and commercial vehicle companies are fully implementing electrified layouts.Road sweepers are also actively responding to the call for "energy saving and emission reduction".Currently,the sweeping vehicle development in the stage of transition to electric sweepers from traditional fuel-type sweepers.However,simply achieving electrification of sweepers is not the ultimate solution for energy conservation.When it comes to Road sweepers,energy-saving still have immense potential on the market.At present,electric cleaning vehicles on the market generally weak in intelligence.In the actual cleaning operation,the situation of garbage on the road and the road conditions change in real time,but the operating executive of the bodywork system cannot make use of this information.Automatically adjust the operating intensity of the cleaning system,resulting in unnecessary energy loss,and the current target detection technology is becoming increasingly mature and gradually applied in various fields.Therefore,the intelligentization and energy saving of road cleaning vehicles have become a current research hotspot.In order to improve the intelligence of the cleaning truck and finally achieve the purpose of energy saving,this paper takes a certain type of electric cleaning truck as the research object.Firstly,based on visual detection of target detection technology,the type of garbage and the coverage rate of the garbage are the operating characteristics.Recognize the object and develop a road job feature recognition algorithm to implement the function of the road sweeper to obtain the situation of pavement waste.Using this as an input,an energy-saving control strategy for the bodywork system based on fuzzy control is proposed to realize the real-time operation of the work motor according to the waste situation and road conditions.The cleaning intensity of the actuator was controlled to achieve the effect of energy saving.Finally,simulation and real vehicle tests were designed for verification and evaluation.The main research work and content of this article are summarized as follows:1?Identification of types of pavement garbage.First,research and analyze various types of target detection algorithms from the theory.Through comparison,Faster R-CNN algorithm based on deep learning and convolutional neural network is used to identify the types of garbage.Establish specifications for the establishment of pavement garbage sample library.In addition,use the checkerboard calibration method to correct camera distortion,take sample pictures and label them,complete the establishment of the garbage sample library,and use the sample library to train the garbage recognition model.Recognition rate of garbage types.2?Pavement garbage coverage detection.To identify the coverage of garbage,you need to detect the outline of the garbage.First use Gaussian blur to denoise the image,and then process the color picture into a gray picture by graying.In addition,use Sobel operator to perform image edge detection on the processed gray picture to distinguish the image foreground and background.Sobel After the operator generates a grayscale image,each pixel in the image is subjected to threshold processing to generate a binary image.Then,the image is first closed and then eroded to obtain an accurate garbage edge contour.Finally,the pixels of the detected garbage are used to calculate the coverage of the garbage.3?Research on energy-saving strategy of the work motor of the bodywork system based on fuzzy control.Firstly,the feasibility of applying fuzzy control to torque control of work motor is analyzed from the theoretical level.Then,the structure of the fuzzy controller of the actuator motor,the fuzzy set of the input and output,and the membership function are studied in depth,and the fuzzy control rules for the energy saving strategy are formulated.Finally,the fuzzy logic toolbox of Matlab is used to establish the cleaning motor Fuzzy controller for subsequent simulation experiments.4?Verification and evaluation by simulation and real vehicle tests.Use Matlab / Simulink to build a fuzzy controller for the motor of the operating actuator and a simulation model of the operating motor of the bodywork system,and establish a cleaning condition.Based on the operating condition,simulate the cleaning power of the actuator,and build a real vehicle platform to carry out energy-saving control strategies.Test verification.The simulation and real vehicle test results in this paper show that the algorithm used can obtain better recognition effect on the types and coverage of road debris.The energy-saving strategy based on fuzzy control can effectively reduce the energy loss of the operating system of the bodywork system on the premise of ensuring the cleanliness of the cleaning system.The research results are of great significance in the intelligent control of the bodywork system of the cleaning vehicle and the improvement of energy-saving effects.