Commercial vehicle full life cycle intelligent monitoring system and data processing method thereof
Through the full life cycle intelligent monitoring system of commercial vehicles, road-perceived lidar and cameras are used to obtain interference coefficient data, predict potential fault areas, and adjust driving paths through the BDS satellite system, solving the avoidance of driverless commercial vehicles on road surfaces of different flatness levels. The difficulties in dangerous areas have improved driving safety and system stability.
Patent Information
- Application Number
- CN202411455182.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-18
- Publication Date
- 2024-11-19
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Unmanned commercial vehicles are difficult to identify and avoid uneven dangerous areas on road surfaces of different flatness, resulting in defects in the intelligent driving system and the inability to effectively analyze and adjust the driving path according to their own status.
Adopt the full life cycle intelligent monitoring system of commercial vehicles, including data acquisition module, data processor and controller, and obtain interference coefficient data through road-aware lidar and camera, calculate the average value of each subsystem, predict potential fault areas, and pass BDS The satellite system adjusts its driving path to avoid dangerous areas.
It realizes that commercial vehicles automatically identify and avoid dangerous areas on road surfaces with different flatness, improves driving safety and system stability, and avoids subsystem failures.
Smart Images

Figure CN118980382A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of unmanned commercial vehicles, and in particular to a full life cycle intelligent monitoring system for commercial vehicles and a data processing method thereof. Background Art
[0002] Unmanned commercial vehicles refer to trucks and buses with more than 9 seats that do not require human drivers to take over driving and are responsible for the results. Their technical level is L4 and above. Among them, the application scenarios of unmanned commercial vehicles can be classified from two dimensions: driving speed and the degree of scene openness. In high-speed scenarios, trunk logistics and intra-city logistics are the main application areas of unmanned commercial vehicles, which are characterized by effectively improving the efficiency and safety of logistics transportation; in low-speed scenarios, unmanned commercial vehicles are more suitable for ports, mining areas, parks, municipal sanitation and terminal distribution.
[0003] In the prior art, common electric unmanned commercial vehicles mainly include tractors, trailers, hydraulic systems and surrounding equipment. Among them, multiple sets of tires are installed at the bottom of the tractor and the trailer respectively, and an environmental perception system, a path planning system and a motion control system are installed inside the tractor. The hydraulic system includes hydraulically driven brakes installed on the tractor and the trailer, hydraulically driven box door locks installed on the trailer, and hydraulically driven front locks installed between the front of the vehicle and the trailer; the surrounding equipment includes infrared proximity sensors, visual sensors, etc. installed on the tractor, and DBS positioning modules. In order to monitor the battery pack, hydraulic system, tires and surrounding equipment on the commercial vehicle, the commercial vehicle is often equipped with a battery pack power monitoring unit, a battery pack voltage monitoring unit, a battery pack temperature monitoring unit, a battery pack cooling monitoring unit, a brake hydraulic monitoring unit, a box door lock hydraulic monitoring unit, a front lock hydraulic monitoring unit, a tire temperature monitoring unit, and a tire pressure monitoring unit. Among them, the environmental perception system includes an environmental perception laser radar and an environmental perception camera that can be rotatably arranged on the top of the tractor, which are used to collect environmental information around the commercial vehicle body and perceive other vehicles, pedestrians, obstacles, etc. on the driving path.
[0004] When the commercial vehicle is carrying out actual transportation tasks, remote monitoring personnel monitor the operating status of the commercial vehicle through data collected by the battery pack power monitoring unit, battery pack voltage monitoring unit, battery pack temperature monitoring unit, battery pack cooling monitoring unit, brake hydraulic monitoring unit, door lock hydraulic monitoring unit, front lock hydraulic monitoring unit, tire temperature monitoring unit, and tire pressure monitoring unit.
[0005] However, the state of the commercial vehicle's internal subsystems is related to the load size, speed, road surface conditions, and driving time. During the actual transportation of commercial vehicles, commercial vehicles with different loads and speeds have different definitions of dangerous areas on the road that need to be detoured. Path planning only through the environmental perception system assisted path planning system can only control electric unmanned commercial vehicles to automatically avoid pedestrians, large roadblocks, vehicles and other large obstacles. For commercial vehicles with different loads, speeds, and driving times, it is difficult to identify whether there are uneven dangerous areas that need to be avoided on the driving path, and it is impossible to analyze the state of the commercial vehicle itself based on its driving state in areas of different flatness, resulting in certain defects in the intelligent driving system. Summary of the invention
[0006] In order to ensure that commercial vehicles can automatically identify the uneven dangerous areas that need to be avoided on the road surface of the commercial vehicle according to their own status on roads of different flatness and adjust the driving path, the present application provides a commercial vehicle full life cycle intelligent monitoring system.
[0007] The present application provides a commercial vehicle full life cycle intelligent monitoring system that adopts the following technical solutions: A full life cycle intelligent monitoring system for commercial vehicles, comprising an electric unmanned commercial vehicle, wherein the electric unmanned commercial vehicle comprises a tractor and a trailer, and: A data acquisition module is used to collect monitoring data of each subsystem in the commercial vehicle and interference coefficient data of each sub-area on the road ahead of the commercial vehicle; A data processor is located in the traction head, and its data input terminal is data-connected to the data output terminal of the data acquisition module, and is used to calculate the average value of the monitoring data of each internal subsystem when the commercial vehicle passes through the sub-areas with different interference coefficients; The controller is installed in the tractor head, and its data input end is data-connected with the data acquisition module, the data processor and the data output end of the BDS satellite system, and its data output end is data-connected with the motion control system in the tractor head, so as to determine the position information of the dangerous sub-area on the driving path of the commercial vehicle and transmit it to the motion control system.
[0008] By adopting the above technical solution, when the electric unmanned commercial vehicle is driving along the driving path, the data acquisition module in the commercial vehicle collects the monitoring data of each subsystem in the commercial vehicle and the image data and radar laser data on the road surface in front of the commercial vehicle on the driving path, so as to obtain the interference coefficient data of each sub-area on the path that the commercial vehicle will pass in front of; the data processor collects the average value of the monitoring data of each internal subsystem when the commercial vehicle passes through the sub-area with different interference coefficients on the driving path in the past, and the controller calculates the dangerous sub-area in front of the commercial vehicle that is likely to cause any subsystem failure in the commercial vehicle according to the change trend of the average value of the monitoring data of each internal subsystem when the commercial vehicle passes through the sub-area with different interference coefficients and the maintenance threshold of the different monitoring data of each subsystem in the commercial vehicle, and transmits the position information of the dangerous sub-area to the motion control system. The motion control system obtains the driving path data, position information, and driving speed information of the commercial vehicle through the BDS satellite system, and re-plans the driving path of the commercial vehicle based on the position information of the dangerous sub-area that the commercial vehicle will pass on the driving path, the vehicles, pedestrians, obstacles and other information around the commercial vehicle in combination with the surrounding equipment to control the commercial vehicle to avoid the dangerous sub-area. When a commercial vehicle is carrying out real-time transportation on its driving path, the interference coefficient of the sub-area that is likely to cause the monitoring data of any subsystem in the commercial vehicle to reach or exceed the maintenance threshold can be predicted by looking at the change trend of the average values of the monitoring data of each subsystem within the commercial vehicle when the commercial vehicle passes through sub-areas with different levels of interference coefficients in history, so as to determine the dangerous sub-area that the commercial vehicle will pass through on its driving path. Combined with the motion control system, it can assist the commercial vehicle in lane change planning to avoid the dangerous sub-area.
[0009] Preferably, the data acquisition module includes: Tire monitoring module, installed on the tractor and trailer, used to monitor the status of the tire subsystem on commercial vehicles; The hydraulic system monitoring module is installed on the tractor head to monitor the status of each hydraulic subsystem in the commercial vehicle; The battery pack monitoring module is installed on the traction head to monitor the status of the battery pack subsystem in the commercial vehicle; A road surface sensing laser radar is rotatably mounted on the top of the tractor head and is used to scan the road surface in front of the tractor head and generate road surface laser data; A road surface perception camera is rotatably mounted on the top of the tractor head and is used to continuously collect road surface image data on the path ahead of the tractor head; An automatic rotating base, the bottom of which is fixedly mounted on the traction head, for mounting the road surface sensing laser radar and the road surface sensing camera, and driving the road surface sensing laser radar and the road surface sensing camera to reciprocate within a fixed angle range; A road surface analyzer is installed in the tractor head, and its data input end is connected to the data output end of the road surface perception laser radar, the road surface perception camera, and the BDS satellite system, and is used to receive the road surface laser data, the road surface image data, and calculate the interference coefficient of each sub-area on the road surface of the commercial vehicle's driving path.
[0010] By adopting the above technical solution, when the commercial vehicle is driving on the driving path, the automatic rotating base drives the road surface perception laser radar and the road surface perception camera to rotate back and forth within a fixed angle range, the road surface perception laser radar continuously scans the road surface laser data on the driving path of the commercial vehicle, and the road surface perception camera continuously collects the road surface image data on the driving path of the commercial vehicle; after receiving the road surface laser data and road surface image data, the road surface analyzer divides the road surface of the form path into multiple sub-areas based on the number of lanes on the driving path according to the driving path information of the commercial vehicle, and calibrates the pit area and convex area in each sub-area according to the road surface laser data and road surface image data, and defines the pit area and convex area as interference area, and classifies the interference area into primary interference area, secondary interference area and tertiary interference area based on size, and calculates the interference coefficient of each sub-area on the driving path of the commercial vehicle according to the number of primary interference areas, secondary interference areas and tertiary interference areas in the sub-area, so that the controller can calibrate the dangerous sub-area according to the changing trend of the average value of the monitoring data of each subsystem.
[0011] Preferably, the tire monitoring module includes a tire temperature monitoring unit and a tire pressure monitoring unit; the hydraulic system monitoring module includes a front lock hydraulic monitoring unit, a box door lock hydraulic monitoring unit, and a brake hydraulic monitoring unit; the battery pack monitoring module includes a battery pack power monitoring unit, a battery pack voltage monitoring unit, a battery pack temperature monitoring unit, and a battery pack cooling monitoring unit; The data output ends of the tire temperature monitoring unit, tire pressure monitoring unit, front lock hydraulic monitoring unit, trunk door lock hydraulic monitoring unit, brake hydraulic monitoring unit, battery pack power monitoring unit, battery pack voltage monitoring unit, battery pack temperature monitoring unit, and battery pack cooling monitoring unit are data connected to a maintenance analysis module for calculating the nearest maintenance station. The data input end of the maintenance analysis module is also data connected to the BDS satellite system. The data output end of the maintenance analysis module is data connected to the data input end of the motion control system.
[0012] By adopting the above technical solution, during the transportation process of the commercial vehicle's driving route, the tire temperature monitoring unit and the tire pressure monitoring unit monitor the tire pressure and temperature data of the tires on the tractor and the trailer respectively; the box door lock hydraulic monitoring unit, the brake hydraulic monitoring unit, and the front lock hydraulic monitoring unit monitor the hydraulic data changes of the box door lock, brake, and front lock on the commercial vehicle respectively; the battery pack power monitoring unit, the battery pack voltage monitoring unit, the battery pack temperature monitoring unit, and the battery pack cooling monitoring unit monitor the battery pack power, voltage, temperature, and cooling system respectively. The maintenance analysis module collects the above data in real time and compares them respectively. When any monitoring data reaches or exceeds the maintenance threshold, the maintenance analysis module can calibrate the nearest maintenance station according to the commercial vehicle's location information, driving route information, and location information of maintenance stations around the driving route, and transmit the location information of the nearest maintenance station to the motion control system of the commercial vehicle. The motion control system plans the maintenance route of the commercial vehicle to the nearest maintenance station according to the location information of the commercial vehicle and the location information of the nearest maintenance station, so that the commercial vehicle automatically moves to the nearest maintenance station for repair and maintenance.
[0013] The present application also proposes a data processing method for a commercial vehicle full life cycle intelligent monitoring system, comprising the following steps: Step S1: Acquire the driving path data of the commercial vehicle, the road surface laser data and the road surface image data on the driving path of the commercial vehicle, divide the road surface of the driving path of the commercial vehicle into multiple sub-areas, and calculate the interference coefficient of each sub-area on the path that the commercial vehicle has passed through historically; Step S2: collecting monitoring data of each subsystem in the commercial vehicle, and calculating the average value of the monitoring data of each subsystem in the commercial vehicle when each subsystem in the commercial vehicle passes through sub-areas with different interference coefficients; Step S3: Calculating the dangerous sub-area on the road that the commercial vehicle is about to pass and needs to be avoided by the commercial vehicle; Step S4: Obtain the location information, driving path information, driving speed information, and location information of the dangerous sub-area of the commercial vehicle, and plan a route to avoid the dangerous sub-area.
[0014] By adopting the above technical solution, during the transportation of commercial vehicles on the driving path, the road surface laser data and road surface image data on the driving path of the commercial vehicle are respectively obtained through the road surface perception laser radar and the road surface perception camera on the commercial vehicle, and the driving path is divided into multiple sub-areas according to the location information and the number of lanes information of the driving path, and the interference coefficient of each sub-area on the driving path is calculated respectively; by analyzing the trend of the average value of the monitoring data of each subsystem when the commercial vehicle passes through the sub-areas with different interference coefficients, the interference coefficient of the corresponding sub-area when the monitoring data of each subsystem reaches the maintenance threshold can be predicted, and the sub-area that reaches the interference coefficient that the commercial vehicle will pass through later is defined as a dangerous sub-area, and the motion control system can plan a path to avoid the dangerous sub-area by analyzing the driving path information, the location information and the speed information of the commercial vehicle, and control the commercial vehicle to move along the path to avoid the dangerous sub-area to avoid the dangerous sub-area, so as to prevent the commercial vehicle from directly passing through the dangerous sub-area and causing any subsystem in the commercial vehicle to fail.
[0015] Preferably, step S1 comprises the following steps: Step S11: Acquire the driving path information of the commercial vehicle, and divide the driving path of the commercial vehicle into multiple sub-areas according to the lane planning of the driving path; Step S12: collecting image data of the sub-area on the driving path of the commercial vehicle and transmitting it to the YOLO v5 algorithm model for target detection, preliminarily identifying the pothole area and the convex area on the road surface in the image, and obtaining a 2D prediction frame; Step S13: Collect the laser radar point cloud data of the sub-area on the driving path of the commercial vehicle, remove the point cloud data of the ground plane on the driving path based on the RANSAC algorithm model, and perform Euclidean clustering to obtain the 3D bounding box and center point parameters (x, y, z, l, w, h) of each, where (x, y, z) is the coordinate of the center point of the 3D bounding box, l is the length of the 3D bounding box, w is the width of the 3D bounding box, and h is the height of the 3D bounding box; Step S14: Project the coordinates of the upper left corner and the lower right corner of the 3D bounding box of the point cloud data in the Y-axis direction into the two-dimensional image to form a 2D bounding box, and calculate the IoU value with the 2D prediction box. When the IoU value is greater than a certain threshold, the point cloud of each 3D bounding box matches the corresponding pit area and convex area; Step S15: traverse each point cloud data, and sort them according to the Z-axis size to obtain the coordinates of the highest point and the lowest point; calculate the maximum Z-axis distance between the point clouds in each pit area and the convex area, and when the maximum Z-axis distance between the point clouds is greater than a certain threshold, it is defined as an interference area, otherwise it is not an interference area, and it is removed from the 2D prediction box in the two-dimensional image; Step S16: Based on the absolute value of the maximum value of the width, length and height of each pit area and bump area, the size of the interference area is calculated by multiplying the absolute value of the maximum value of the length, width and height, and the interference area is classified into a primary interference area, a secondary interference area and a tertiary interference area in order from small to large size; Step S17: Count the number of primary interference areas j, the number of secondary interference areas k, and the number of tertiary interference areas e in each sub-area, and calculate i according to the formula i=j+2*k+3*e, where i is the interference coefficient in the sub-area.
[0016] By adopting the above technical solution, the sub-areas on the driving path of commercial vehicles are identified by combining 2D prediction frames and 3D prediction frames to identify the pit areas and bump areas, so as to achieve the technical effect of accurately monitoring the interference areas in the sub-areas. The size of the interference area is calculated according to the product of the absolute values of the length, width and height of the interference area, and the interference areas are classified into primary interference areas, secondary interference areas and tertiary interference areas according to the size from small to large. The number of primary interference areas and secondary interference areas in the sub-areas is counted, and based on the number of primary interference areas, secondary interference areas and tertiary interference areas in the sub-areas, the interference coefficient in each sub-area can be calculated.
[0017] Preferably, step S2 comprises the following steps: Step S21: obtaining the location information, driving path data, and driving speed information of the commercial vehicle, obtaining the sub-areas on the path that the commercial vehicle has passed through historically, and continuously calibrating the starting time of the commercial vehicle passing through each sub-area as t1, t2, t3, ... tn, where n is a positive integer; Step S22: collecting monitoring data of each subsystem in the commercial vehicle when the commercial vehicle passes through each sub-area at a time interval of 0.02s and calculating the average value of the monitoring data of each subsystem in the commercial vehicle; Step S23: Obtain the interference coefficient information of each sub-area on the path that the commercial vehicle has passed through historically, and obtain the average value of the monitoring data of each subsystem when the commercial vehicle passes through each sub-area.
[0018] By adopting the above technical solution, the start time of each sub-area on the path passed by the commercial vehicle is calibrated, and the start time and end time of the commercial vehicle passing through each sub-area can be obtained. The monitoring data of each subsystem in the commercial vehicle is collected at a time interval of 0.02s between the start time and the end time. The average value of the monitoring data of each internal subsystem when the commercial vehicle passes through sub-areas with different interference coefficients can be obtained by summing and averaging the monitoring data.
[0019] Preferably, step S3 comprises the following steps: Step S31: Obtain the maintenance thresholds of each subsystem in the commercial vehicle, and calculate the interference coefficient range of the dangerous subregion based on the interference coefficient information of the subregions that the commercial vehicle has passed through in the past and the average monitoring data of each subsystem when the commercial vehicle passes through each subregion; Step S32: Obtain the interference coefficient of each sub-area that the commercial vehicle will pass through on the driving path and compare it with the interference coefficient range of the dangerous sub-area, and mark the sub-area within the interference coefficient range as the dangerous sub-area.
[0020] By adopting the above technical solution, based on the average value data of each subsystem monitoring data when the commercial vehicle passes through different sub-areas in the past, the interference coefficient corresponding to when the maintenance threshold is reached or exceeded can be predicted according to the change trend of the monitoring data of each subsystem of the commercial vehicle in the sub-areas with different interference coefficients. If there is a sub-area with a coefficient greater than the interference coefficient, it can be marked as a dangerous area.
[0021] Preferably, the step S31 comprises the following steps: Step S311: taking the average value of monitoring data of each subsystem in the commercial vehicle when the interference coefficient i in the sub-region is 10, 15, 20, 25, 30, 35, 40, 45, 50, 55 as sampling data; Step S312: putting the sampled data into a linear regression algorithm model for prediction, and obtaining the predicted value of the monitoring data of each subsystem in the commercial vehicle when the interference coefficient i=55+5*d, where d is a positive integer greater than or equal to 1; Step S313: comparing the predicted values of monitoring data of each subsystem in the commercial vehicle one by one, and when the predicted value of monitoring data of any subsystem reaches or exceeds the maintenance threshold, calibrating i0, where i0 is the interference coefficient corresponding to the predicted value of monitoring data of any subsystem; Step S314: calibrate the interference coefficient range of the dangerous sub-area to be i≥i0.
[0022] By adopting the above technical solution, by comparing the predicted values of the monitoring data of each subsystem in the commercial vehicle when the commercial vehicle passes through sub-areas with different interference coefficients, when the predicted value of the monitoring data of any subsystem in the commercial vehicle reaches or exceeds the maintenance threshold, it can be determined that the internal subsystem of the commercial vehicle is prone to failure when the commercial vehicle passes through the sub-area with an interference coefficient i greater than or equal to i0, and the monitoring data of each subsystem in the commercial vehicle in the area with different interference coefficients can be predicted through a linear regression algorithm model.
[0023] In summary, the present application provides a commercial vehicle full life cycle intelligent monitoring system including at least one of the following beneficial technical effects: 1. The data acquisition module collects image data and radar laser data on the road ahead of the commercial vehicle on its driving path, thereby obtaining interference coefficient data of each sub-area on the path that the commercial vehicle will pass in front of it; the data processor obtains the average value of monitoring data of each internal subsystem when the commercial vehicle passes through sub-areas with different interference coefficients on the driving path in the past, and the controller calculates the dangerous sub-area in front of the commercial vehicle that is likely to cause any subsystem failure in the commercial vehicle based on the change trend of the average value of monitoring data of each internal subsystem when the commercial vehicle passes through sub-areas with different interference coefficients and the maintenance threshold of different monitoring data of each subsystem in the commercial vehicle, and transmits the position information of the dangerous sub-area to the motion control system. The motion control system obtains the driving path data, position information, and driving speed information of the commercial vehicle through the BDS satellite system, and replans the driving path of the commercial vehicle based on the position information of the dangerous sub-area that the commercial vehicle will pass on its driving path in combination with the surrounding equipment, and the information of vehicles, pedestrians, obstacles, etc. around the commercial vehicle to control the commercial vehicle to avoid the dangerous sub-area; 2. Through the combination and use of road surface perception lidar and road surface perception camera, the potholes and bumps on the road surface along the driving path of commercial vehicles can be more accurately identified in a two-dimensional and three-dimensional manner, and the potholes and bumps can be marked as interference areas. BRIEF DESCRIPTION OF THE DRAWINGS
[0024] Figure 1 It is a schematic diagram of an embodiment of the present application for demonstrating internal data transmission of a commercial vehicle.
[0025] Figure 2 It is a schematic diagram of an embodiment of the present application for illustrating the overall structure of a commercial vehicle.
[0026] Figure 3 It is a flowchart of the steps of the data processing method of the monitoring system used in the embodiment of the present application.
[0027] Figure 4 It is a schematic diagram of the specific process of step 1 of the data processing method of the monitoring system in an embodiment of the present application.
[0028] Figure 5 It is a schematic diagram of the specific process of step 2 of the data processing method of the monitoring system in the embodiment of the present application.
[0029] Figure 6 It is a schematic diagram of the specific process of step 3 of the data processing method of the monitoring system in the embodiment of the present application.
[0030] Figure 7 It is a schematic diagram of the specific process of step 31 of the data processing method of the monitoring system in the embodiment of the present application.
[0031] Figure 8This is a chart of the embodiment of the present application for displaying tire temperature monitoring data when a commercial vehicle passes through one of the sub-areas on its driving path.
[0032] Fig. 9 This is a chart of an embodiment of the present application for displaying average value data of tire temperature monitoring data when a commercial vehicle passes through different interference coefficients on a driving path.
[0033] Explanation of the accompanying drawings: 1. Tractor head; 2. Trailer; 3. Environment perception laser radar and environment perception camera assembly; 4. Road surface perception laser radar and road surface perception camera assembly. DETAILED DESCRIPTION
[0034] The following combination Figure 1-Figure 9 This application is described in further detail.
[0035] Example 1: This application example discloses a commercial vehicle full life cycle intelligent monitoring system. Figure 1 and Figure 2 The utility model comprises an electric unmanned commercial vehicle, and the commercial vehicle is composed of a tractor 1 and a trailer 2, and the tractor and the trailer are connected by a hydraulically driven front lock.
[0036] Reference Figure 1 The electric unmanned commercial vehicle also includes a data acquisition module, a data processor, and a controller.
[0037] The data acquisition module includes a tire monitoring module, a hydraulic system monitoring module, a battery pack monitoring module, a road surface perception laser radar, a road surface perception camera, an automatic rotating base and a road surface analyzer installed on a commercial vehicle.
[0038] Among them, the tire monitoring module consists of a tire temperature monitoring unit and a tire pressure monitoring unit, which are mainly used to monitor the tires on the tractor and trailer during the driving and transportation of commercial vehicles; the hydraulic system monitoring module includes a front lock hydraulic monitoring unit installed on the tractor for monitoring the front lock, a box door lock hydraulic monitoring unit installed on the trailer for monitoring the box door lock on the trailer, and a brake lock hydraulic monitoring unit installed on the tractor and trailer for monitoring the brake lock; the battery pack monitoring module includes a battery pack power monitoring unit and a battery pack voltage monitoring unit electrically connected to the power supply circuit of the battery pack, and also includes a battery pack temperature monitoring unit installed on the chassis of the tractor for monitoring the battery pack temperature, and a battery pack cooling monitoring unit for monitoring the performance of the battery pack cooling system. In addition, the commercial vehicle is also equipped with peripheral equipment consisting of multiple cameras, infrared proximity sensors, and BDS positioning modules.
[0039] When a commercial vehicle is transporting goods along a predetermined route, the tire monitoring module, hydraulic system monitoring module, battery pack monitoring module, and hydraulic system monitoring module monitor the hydraulic system, tire system, and battery pack system in the commercial vehicle in real time. The surrounding equipment can sense pedestrians, obstacles, road signs, and other obstacles around the commercial vehicle when the commercial vehicle changes lanes or enters and exits the warehouse.
[0040] The assembly of the road surface perception laser radar and the road surface perception camera is installed on an automatic rotating base, which is fixed to the front end of the tractor of the commercial vehicle by screws. When the commercial vehicle is transported along the driving path, the rotating base drives the road surface perception laser radar and the road surface perception camera to reciprocate within a fixed angle range of 180°. When the commercial vehicle is transported along the driving path, the road surface perception laser radar and the road surface perception camera respectively continuously collect road surface laser data and road surface image data in front of the commercial vehicle.
[0041] The data output ends of the road surface perception laser radar and the road surface perception camera are connected to the road surface analyzer installed in the traction head of the commercial vehicle through a wireless network communication module. The road surface analyzer receives the road surface laser data and road surface image data in front of the commercial vehicle.
[0042] After receiving the road surface laser data and the road surface image data, the road surface analyzer divides the road surface of the form path into multiple sub-areas based on the number of lanes on the driving path according to the commercial vehicle's driving path information, and calibrates the pothole areas and convex areas in each sub-area according to the road surface laser data and the road surface image data, and defines the pothole areas and convex areas as interference areas, and classifies the interference areas into primary interference areas, secondary interference areas, and tertiary interference areas based on their sizes, and calculates the interference coefficient of each sub-area on the commercial vehicle's driving path according to the number of primary interference areas, secondary interference areas, and tertiary interference areas in the sub-area, so that the controller can calibrate the dangerous sub-area according to the changing trend of the average value of the monitoring data of each subsystem.
[0043] The road surface analyzer is connected to the data processor via a data cable. The data input end of the data processor is also connected to the data output ends of the tire monitoring module, the hydraulic system monitoring module, and the battery pack monitoring module. The data processor receives the interference coefficient of each sub-area on the driving path of the commercial vehicle and calculates the average value of the monitoring data of each subsystem in the commercial vehicle when the commercial vehicle passes through each sub-area.
[0044] The data processor is connected to the controller through a data cable. The data input end of the controller is also connected to the data output end of the road analyzer, surrounding equipment and the BDS satellite system. The controller calculates the dangerous sub-area in front of the commercial vehicle that is likely to cause any subsystem failure in the commercial vehicle based on the changing trend of the average value of the monitoring data of each internal subsystem when the commercial vehicle passes through each sub-area and the maintenance threshold of the different monitoring data of each subsystem in the commercial vehicle, and transmits the position information of the dangerous sub-area to the motion control system. The motion control system obtains the driving path data, position information, and driving speed information of the commercial vehicle through the BDS satellite system, and re-plans the driving path of the commercial vehicle based on the position information of the dangerous sub-area that the commercial vehicle will pass through on the driving path in combination with the surrounding equipment, and the information of vehicles, pedestrians, obstacles and other information around the commercial vehicle to control the commercial vehicle to avoid the dangerous sub-area.
[0045] When a commercial vehicle is carrying out real-time transportation on its driving path, the interference coefficient of the sub-area that is likely to cause the monitoring data of any subsystem in the commercial vehicle to reach or exceed the maintenance threshold can be predicted by looking at the change trend of the average values of the monitoring data of each subsystem within the commercial vehicle when the commercial vehicle passes through sub-areas with different levels of interference coefficients in history, so as to determine the dangerous sub-area that the commercial vehicle will pass through on its driving path. Combined with the motion control system, it can assist the commercial vehicle in lane change planning to avoid the dangerous sub-area.
[0046] It should be noted that, refer to Figure 2 In this embodiment, the environment perception laser radar and the environment perception camera assembly 3 are installed on the top of the tractor head 1. The rotation angle of the environment perception laser radar and the bottom of the environment perception camera is 360°. They are mainly used to detect pedestrians, structures, road signs, roadblocks, etc. around the commercial vehicle. The scanning radius is 80 meters; and the road surface perception laser radar and the road surface perception camera assembly 4 are installed at the upper front end of the tractor head 1. They are mainly used to detect dangerous sub-areas on the road surface that need to be avoided. The scanning radius is 20 meters.
[0047] The implementation principle of a full life cycle intelligent monitoring system for commercial vehicles in an embodiment of the present application is as follows: when a commercial vehicle is traveling along a driving path to transport goods, a data acquisition module collects image data and radar laser data on the road surface in front of the commercial vehicle on the driving path, thereby obtaining interference coefficient data of each sub-area on the path that the commercial vehicle will pass in front of; a data processor collects the average value of monitoring data of each internal subsystem when the commercial vehicle has historically passed through sub-areas with different interference coefficients on the driving path, and a controller calculates a dangerous sub-area in front of the commercial vehicle that is likely to cause a failure of any subsystem in the commercial vehicle based on the changing trend of the average value of monitoring data of each internal subsystem when the commercial vehicle passes through each sub-area and the maintenance threshold of different monitoring data of each internal subsystem of the commercial vehicle, and transmits the position information of the dangerous sub-area to the motion control system, which obtains the driving path data, position information, and driving speed information of the commercial vehicle through the BDS satellite system, and replans the driving path of the commercial vehicle based on the position information of the dangerous sub-area that the commercial vehicle will pass through on the driving path in combination with surrounding equipment, and information such as vehicles, pedestrians, and obstacles around the commercial vehicle to control the commercial vehicle to avoid the dangerous sub-area. When a commercial vehicle is carrying out real-time transportation on its driving path, the interference coefficient of the sub-area that is likely to cause the monitoring data of any subsystem in the commercial vehicle to reach or exceed the maintenance threshold can be predicted by looking at the change trend of the average values of the monitoring data of each subsystem within the commercial vehicle when the commercial vehicle passes through sub-areas with different levels of interference coefficients in history, so as to determine the dangerous sub-area that the commercial vehicle will pass through on its driving path. Combined with the motion control system, it can assist the commercial vehicle in lane change planning to avoid the dangerous sub-area.
[0048] This embodiment also proposes a data processing method for a commercial vehicle full life cycle intelligent monitoring system. Figure 3 , the data processing method mainly includes the following steps: Step S1: Acquire the driving path data of the commercial vehicle, the road surface laser data and the road surface image data on the driving path of the commercial vehicle, divide the road surface of the driving path of the commercial vehicle into multiple sub-areas, and calculate the interference coefficient of each sub-area on the path that the commercial vehicle has passed through historically; Step S2: Collect the monitoring data of each subsystem in the commercial vehicle, and calculate the average value of the monitoring data of each subsystem in the commercial vehicle when the subsystem in the commercial vehicle passes through the sub-areas with different interference coefficients; Step S3: Calculating the dangerous sub-area on the road that the commercial vehicle is about to pass and needs to be avoided by the commercial vehicle; Step S4: Obtain the location information, driving path information, driving speed information, and location information of the dangerous sub-area of the commercial vehicle, and plan a route to avoid the dangerous sub-area.
[0049] Reference Figure 4 , step S1 consists of the following steps: Step S11: Acquire the driving path information of the commercial vehicle, and divide the driving path of the commercial vehicle into multiple sub-areas according to the lane planning of the driving path; specifically, divide the road surface into sub-areas according to the lane width on the driving path of the commercial vehicle. For example, in the embodiment of the present application, the driving path of the commercial vehicle is four-lane, and the width standard of each lane is 4 meters. Then, the road surface along the driving path of the commercial vehicle can be divided into several groups of four parallel sub-areas, and the length of the sub-area is set to 4 meters. Then, the road surface of the driving path of the commercial vehicle consists of several groups of four parallel sub-areas of 4*4 meters; Step S12: collecting image data of sub-areas on the driving path of the commercial vehicle and transmitting them to the YOLO v5 algorithm model for target detection, preliminarily identifying the pothole area and the convex area on the road surface in the image, and obtaining a 2D prediction frame; specifically, continuously collecting video data on the road surface in front of the driving path of the commercial vehicle, continuously extracting frames, splicing, and stitching the video data to obtain 4*8m road surface image data, segmenting the road surface image data to obtain image data of separate sub-areas, and performing target detection based on the image data of the separate sub-areas by using the YOLO v5 algorithm model trained with the road surface data set, identifying the pothole area and the convex area in each sub-area, and obtaining the 2D prediction frame of the pothole area and the convex area; Step S13: Collect the laser radar point cloud data of the sub-area on the driving path of the commercial vehicle, remove the point cloud data of the ground plane on the driving path based on the RANSAC algorithm model, and perform Euclidean clustering to obtain each 3D bounding box and center point parameters (x, y, z, l, w, h), where (x, y, z) is the coordinate of the center point of the 3D bounding box, l is the length of the 3D bounding box, w is the width of the 3D bounding box, and h is the height of the 3D bounding box; Step S14: Project the coordinates of the upper left corner and the lower right corner of the 3D bounding box of the point cloud data in the Y-axis direction into the two-dimensional image to form a 2D bounding box, and calculate the IoU value with the 2D prediction box. When the IoU value is greater than a certain threshold, the point cloud of each 3D bounding box matches the corresponding pit area and convex area; Step S15: traverse each point cloud data, and sort them according to the Z-axis size to obtain the coordinates of the highest point and the lowest point; calculate the maximum Z-axis distance between the point clouds in each pit area and the convex area, and when the maximum Z-axis distance between the point clouds is greater than a certain threshold, it is defined as an interference area, otherwise it is not an interference area, and it is removed from the 2D prediction box in the two-dimensional image; Step S16: Based on the absolute value of the maximum value of the width, length and height of each pit area and bump area, the size of the interference area is calculated by multiplying the absolute value of the maximum value of the length, width and height, and the interference area is classified into a primary interference area, a secondary interference area and a tertiary interference area in order from small to large size; Step S17: Count the number of primary interference areas j, the number of secondary interference areas k, and the number of tertiary interference areas e in each sub-area, and calculate i according to the formula i=j+2*k+3*e, where i is the interference coefficient in the sub-area.
[0050] In this embodiment, the product range of the absolute values of the maximum values of the length, width and height of the first-level interference area, the second-level interference area and the third-level interference area (i.e., the size range) is 5-20 cm³, 21-50 cm³ and 51-81 cm³, respectively.
[0051] For example, one of the interference areas in the sub-area that the commercial vehicle passes through has a length of l=2cm, a width of w=2.5cm, and an absolute value of height |h|=2cm. The product of the absolute values of the maximum length, width, and height of the interference area = 2*2.5*2=10cm³, and the interference area can be calibrated as a first-level interference area.
[0052] If the numbers of the first-level interference areas, the second-level interference areas, and the third-level interference areas in the sub-area are 21, 10, and 2 respectively, then the interference coefficient i of the sub-area is 21+2*10+3*2=47.
[0053] Among them, according to the interference intensity caused by sub-areas of different sizes to the driving of commercial vehicles, weights from small to large are added to the first-level interference area, the second-level interference area, and the third-level interference area, and the interference coefficient for evaluating the unevenness of the sub-area can be obtained. In some other embodiments, the weights of the first-level interference area, the second-level interference area, and the third-level interference area can be modified according to the range divided by the size of the interference area, which is not limited or elaborated here.
[0054] Reference Figure 5 , step S2 comprises the following steps: Step S21: obtaining the location information, driving path data, and driving speed information of the commercial vehicle, obtaining the sub-areas on the path that the commercial vehicle has passed through historically, and continuously calibrating the starting time of the commercial vehicle passing through each sub-area as t1, t2, t3, ... tn, where n is a positive integer; Step S22: collecting monitoring data of each subsystem in the commercial vehicle when the commercial vehicle passes through each sub-area at a time interval of 0.02s and calculating the average value of the monitoring data of each subsystem in the commercial vehicle; Step S23: Obtain the interference coefficient information of each sub-area on the path that the commercial vehicle has passed through historically, and obtain the average value of the monitoring data of each subsystem when the commercial vehicle passes through each sub-area.
[0055] For example, the tire temperature monitoring data distance of one of the tires of a commercial vehicle, the maintenance temperature of the tire is 80°C, the starting time of the commercial vehicle passing through one of the sub-areas on the driving path is 23min43.3s, and the interference coefficient of the sub-area i=30, and the end time of completely passing through the sub-area is 23min43.7s. During the period of passing through the sub-area, the tire temperature data collected by the tire temperature monitoring unit from 23min43.3s to 23min43.7s is as follows Figure 8 As shown in the figure, the average value of the tire temperature monitoring data when the commercial vehicle passes through the sub-area is (42.7+42.6+42.7+42.6+42.6+42.7+42.9+42.9+42.8+42.9+42.9+43.9+42.9+42.9+42.9+42.8+42.7+42.8+42.9+42.8) / 20=42.8℃. Based on the average value of the monitoring data of the commercial vehicle passing through the sub-area with an interference coefficient of 30 in history, the average value of the historical tire temperature average values in the chart is taken again, and the total average value of the tire temperature monitoring data of the commercial vehicle passing through all the sub-areas with an interference coefficient i=30 in history can be obtained.
[0056] Reference Figure 6 , step S3 comprises the following steps: Step S31: Obtain the maintenance thresholds of each subsystem in the commercial vehicle, and calculate the interference coefficient range of the dangerous subregion based on the interference coefficient information of the subregions that the commercial vehicle has passed through in the past and the average monitoring data of each subsystem when the commercial vehicle passes through each subregion; Step S32: Obtain the interference coefficient of each sub-area that the commercial vehicle will pass through on the driving path and compare it with the interference coefficient range of the dangerous sub-area, and mark the sub-area within the interference coefficient range as the dangerous sub-area.
[0057] Reference Figure 7 , step S31 specifically includes the following steps: S311: taking the average value of monitoring data of each subsystem in the commercial vehicle when the interference coefficient i in the sub-region is 10, 15, 20, 25, 30, 35, 40, 45, 50, 55 as sampling data; Step S312: putting the sampled data into a linear regression algorithm model for prediction, and obtaining the predicted value of the monitoring data of each subsystem in the commercial vehicle when the interference coefficient i=55+5*d, where d is a positive integer greater than or equal to 1; Step S313: comparing the predicted values of monitoring data of each subsystem in the commercial vehicle one by one, and when the predicted value of monitoring data of any subsystem reaches or exceeds the maintenance threshold, calibrating i0, where i0 is the interference coefficient corresponding to the predicted value of monitoring data of any subsystem; Step S314: calibrate the interference coefficient range of the dangerous sub-area to be i≥i0.
[0058] For example, see Fig. 9 , is the data of the commercial vehicle passing through the interference coefficient i=10, 15, 20, 25, 30, 35, 40, 45, 50, 55 in this embodiment. The linear regression algorithm predicts that d is equal to 1, 2, 3, 4, 5, 6, 7, 8, 9, 10 respectively, that is, the predicted value of tire temperature when the interference coefficient i=60, 65, 70, 75, 80, 85, 90, 95, 100, 105.
[0059] Among them, the average value T0 of the average temperature data of the sub-areas where commercial vehicles have historically passed through i=10, 15, 20, 25, 30, 35, 40, 45, 50, and 55 are 35.4℃, 36.3℃, 36.7℃, 38.4℃, 39.2℃, 42.3℃, 44.1℃, 49.0℃, 52.3℃, and 56.6℃, respectively, and T0 represents the average value of the average tire temperature data of each sub-area under the same interference coefficient.
[0060] It can be seen from the data in the chart that when the danger coefficient i=100, the tire temperature prediction value calculated by the linear regression algorithm model is 80.9℃, which exceeds the maintenance threshold of the tire temperature of the commercial vehicle, so i0 can be calibrated to 100. Therefore, when there is a sub-area with a danger coefficient i greater than or equal to 100 on the path ahead of the commercial vehicle, the sub-area is calibrated as a dangerous sub-area, and the commercial vehicle's internal environment perception system, path planning system, and motion control system can plan the route of the commercial vehicle to avoid the dangerous sub-area based on the location information of the sub-area, so that the commercial vehicle passes through the sub-area with a smaller interference coefficient.
[0061] By calculating the average value of tire temperature monitoring data of sub-areas on the historical paths of commercial vehicles and matching it with the interference coefficient of the sub-areas, the tire temperature status of commercial vehicles with different loads, different driving speeds, different road conditions, and different driving times can be monitored and predicted, and effective avoidance of dangerous sub-areas can be performed.
[0062] Embodiment 2: In this embodiment, the data output ends of the tire temperature monitoring unit, tire pressure monitoring unit, front lock hydraulic monitoring unit, trunk door lock hydraulic monitoring unit, brake hydraulic monitoring unit, battery pack power monitoring unit, battery pack voltage monitoring unit, battery pack temperature monitoring unit, and battery pack cooling monitoring unit in the commercial vehicle are data connected to a maintenance analysis module for calculating the nearest maintenance station. The data input end of the maintenance analysis module is also data connected to the BDS satellite system. The data output end of the maintenance analysis module is data connected to the data input end of the motion control system of the commercial vehicle.
[0063] During the transportation process of the commercial vehicle's driving route, the tire temperature monitoring unit and the tire pressure monitoring unit monitor the tire pressure and temperature data of the tires on the tractor and the trailer respectively; the box door lock hydraulic monitoring unit, the brake hydraulic monitoring unit, and the front lock hydraulic monitoring unit monitor the hydraulic data changes of the box door lock, brake, and front lock on the commercial vehicle respectively; the battery pack power monitoring unit, the battery pack voltage monitoring unit, the battery pack temperature monitoring unit, and the battery pack cooling monitoring unit monitor the battery pack power, voltage, temperature, and cooling system respectively. The maintenance analysis module collects the above data in real time and compares them respectively. When any monitoring data reaches or exceeds the maintenance threshold, the maintenance analysis module can calibrate the nearest maintenance station according to the commercial vehicle's location information, driving route information, and the location information of the maintenance stations around the driving route, and transmit the location information of the nearest maintenance station to the commercial vehicle's motion control system. The motion control system plans the maintenance route of the commercial vehicle to the nearest maintenance station according to the location information of the commercial vehicle and the location information of the nearest maintenance station, so that the commercial vehicle automatically moves to the nearest maintenance station for repair and maintenance.
[0064] Embodiment 3: In the embodiment of the present application, a pre-established cloud platform is included, which stores the location information, name information, type information of maintenance items in the maintenance station, and price information of items in the maintenance station of each maintenance station. The signal input end of the environmental perception system, path planning system, and motion control system on the commercial vehicle is connected to the cloud platform signal. When the commercial vehicle plans the path to the maintenance station, the type information of maintenance items in the maintenance station and the price information of items in the maintenance station can be included in the reference factors for selecting the maintenance station, so as to facilitate the determination of the location of the maintenance station with a lower price and a suitable distance.
[0065] The above are all preferred embodiments of the present application, and the protection scope of the present application is not limited thereto. Therefore, any equivalent changes made according to the structure, shape, and principle of the present application should be included in the protection scope of the present application.
Claims
1. A full life cycle intelligent monitoring system for commercial vehicles, including electric unmanned commercial vehicles, characterized in that: The electric unmanned commercial vehicle includes a tractor and a trailer, as well as: A data acquisition module is used to collect monitoring data of each subsystem in the commercial vehicle and interference coefficient data of each sub-area on the road ahead of the commercial vehicle; A data processor is located in the tractor head, and its data input terminal is data-connected to the data output terminal of the data acquisition module, and is used to calculate the average value of the monitoring data of each internal subsystem when the commercial vehicle passes through the sub-areas with different interference coefficients; The controller is installed in the tractor head, and its data input end is data-connected with the data acquisition module, the data processor and the data output end of the BDS satellite system, and its data output end is data-connected with the motion control system in the tractor head, and is used to determine the position information of the dangerous sub-area on the driving path of the commercial vehicle and transmit it to the motion control system.
2. According to claim 1, a commercial vehicle full life cycle intelligent monitoring system is characterized in that: The data acquisition module comprises: Tire monitoring module, installed on the tractor and trailer, used to monitor the status of the tire subsystem on commercial vehicles; The hydraulic system monitoring module is installed on the tractor head to monitor the status of each hydraulic subsystem in the commercial vehicle; The battery pack monitoring module is installed on the traction head to monitor the status of the battery pack subsystem in the commercial vehicle; A road surface sensing laser radar is rotatably mounted on the top of the tractor head and is used to scan the road surface in front of the tractor head and generate road surface laser data; A road surface perception camera is rotatably mounted on the top of the tractor head and is used to continuously collect road surface image data on the path ahead of the tractor head; An automatic rotating base, the bottom of which is fixedly mounted on the traction head, for mounting the road surface sensing laser radar and the road surface sensing camera, and driving the road surface sensing laser radar and the road surface sensing camera to reciprocate within a fixed angle range; A road surface analyzer is installed in the tractor head, and its data input end is connected to the data output end of the road surface perception laser radar, the road surface perception camera, and the BDS satellite system, and is used to receive the road surface laser data, the road surface image data, and calculate the interference coefficient of each sub-area on the road surface of the commercial vehicle's driving path.
3. The intelligent monitoring system for the entire life cycle of a commercial vehicle according to claim 2 is characterized in that: The tire monitoring module includes a tire temperature monitoring unit and a tire pressure monitoring unit; the hydraulic system monitoring module includes a front lock hydraulic monitoring unit, a box door lock hydraulic monitoring unit, and a brake hydraulic monitoring unit; the battery pack monitoring module includes a battery pack power monitoring unit, a battery pack voltage monitoring unit, a battery pack temperature monitoring unit, and a battery pack cooling monitoring unit; The data output ends of the tire temperature monitoring unit, tire pressure monitoring unit, front lock hydraulic monitoring unit, trunk door lock hydraulic monitoring unit, brake hydraulic monitoring unit, battery pack power monitoring unit, battery pack voltage monitoring unit, battery pack temperature monitoring unit, and battery pack cooling monitoring unit are data connected to a maintenance analysis module for calculating the nearest maintenance station. The data input end of the maintenance analysis module is also data connected to the BDS satellite system. The data output end of the maintenance analysis module is data connected to the data input end of the motion control system.
4. A data processing method for a commercial vehicle full life cycle intelligent monitoring system based on any one of claims 1 to 3, characterized in that: The following steps are involved: Step S1: Acquire the driving path data of the commercial vehicle, the road surface laser data and the road surface image data on the driving path of the commercial vehicle, divide the road surface of the driving path of the commercial vehicle into multiple sub-areas, and calculate the interference coefficient of each sub-area on the path that the commercial vehicle has passed through historically; Step S2: collecting monitoring data of each subsystem in the commercial vehicle, and calculating the average value of the monitoring data of each subsystem in the commercial vehicle when each subsystem in the commercial vehicle passes through sub-areas with different interference coefficients; Step S3: Calculating the dangerous sub-area on the road that the commercial vehicle is about to pass and needs to be avoided by the commercial vehicle; Step S4: Obtain the location information, driving path information, driving speed information, and location information of the dangerous sub-area of the commercial vehicle, and plan a route to avoid the dangerous sub-area.
5. The data processing method of a commercial vehicle full life cycle intelligent monitoring system according to claim 4 is characterized in that: The step S1 comprises the following steps: Step S11: Acquire the driving path information of the commercial vehicle, and divide the driving path of the commercial vehicle into multiple sub-areas according to the lane planning of the driving path; Step S12: collecting image data of the sub-area on the driving path of the commercial vehicle and transmitting it to the YOLO v5 algorithm model for target detection, preliminarily identifying the pothole area and the convex area on the road surface in the image, and obtaining a 2D prediction frame; Step S13: Collect the laser radar point cloud data of the sub-area on the driving path of the commercial vehicle, remove the point cloud data of the ground plane on the driving path based on the RANSAC algorithm model, and perform Euclidean clustering to obtain the 3D bounding box and center point parameters (x, y, z, l, w, h) of each, where (x, y, z) is the coordinate of the center point of the 3D bounding box, l is the length of the 3D bounding box, w is the width of the 3D bounding box, and h is the height of the 3D bounding box; Step S14: Project the coordinates of the upper left corner and the lower right corner of the 3D bounding box of the point cloud data in the Y-axis direction into the two-dimensional image to form a 2D bounding box, and calculate the IoU value with the 2D prediction box. When the IoU value is greater than a certain threshold, the point cloud of each 3D bounding box matches the corresponding pit area and convex area; Step S15: traverse each point cloud data, and sort them according to the Z-axis size to obtain the coordinates of the highest point and the lowest point; calculate the maximum Z-axis distance between the point clouds in each pit area and the convex area, and when the maximum Z-axis distance between the point clouds is greater than a certain threshold, it is defined as an interference area, otherwise it is not an interference area, and it is removed from the 2D prediction box in the two-dimensional image; Step S16: Based on the absolute value of the maximum value of the width, length and height of each pit area and bump area, the size of the interference area is calculated by multiplying the absolute value of the maximum value of the length, width and height, and the interference area is classified into a primary interference area, a secondary interference area and a tertiary interference area in order from small to large size; Step S17: Count the number of primary interference areas j, the number of secondary interference areas k, and the number of tertiary interference areas e in each sub-area, and calculate i according to the formula i=j+2*k+3*e, where i is the interference coefficient in the sub-area.
6. The data processing method of a commercial vehicle full life cycle intelligent monitoring system according to claim 5 is characterized in that: The step S2 comprises the following steps: Step S21: obtaining the location information, driving path data, and driving speed information of the commercial vehicle, obtaining the sub-areas on the path that the commercial vehicle has passed through historically, and continuously calibrating the starting time of the commercial vehicle passing through each sub-area as t1, t2, t3, ... tn, where n is a positive integer; Step S22: collecting monitoring data of each subsystem in the commercial vehicle when the commercial vehicle passes through each sub-area at a time interval of 0.02s and calculating the average value of the monitoring data of each subsystem in the commercial vehicle; Step S23: Obtain the interference coefficient information of each sub-area on the path that the commercial vehicle has passed through historically, and obtain the average value of the monitoring data of each subsystem when the commercial vehicle passes through each sub-area.
7. The data processing method of a commercial vehicle full life cycle intelligent monitoring system according to claim 6 is characterized in that: The step S3 comprises the following steps: Step S31: Obtain the maintenance thresholds of each subsystem in the commercial vehicle, and calculate the interference coefficient range of the dangerous subregion based on the interference coefficient information of the subregions that the commercial vehicle has passed through in the past and the average monitoring data of each subsystem when the commercial vehicle passes through each subregion; Step S32: Obtain the interference coefficient of each sub-area that the commercial vehicle will pass through on the driving path and compare it with the interference coefficient range of the dangerous sub-area, and mark the sub-area within the interference coefficient range as the dangerous sub-area.
8. The data processing method of a commercial vehicle full life cycle intelligent monitoring system according to claim 7 is characterized in that: The step S31 comprises the following steps: Step S311: taking the average value of monitoring data of each subsystem in the commercial vehicle when the interference coefficient i in the sub-region is 10, 15, 20, 25, 30, 35, 40, 45, 50, 55 as sampling data; Step S312: putting the sampled data into a linear regression algorithm model for prediction, and obtaining the predicted value of the monitoring data of each subsystem in the commercial vehicle when the interference coefficient i=55+5*d, where d is a positive integer greater than or equal to 1; Step S313: comparing the predicted values of monitoring data of each subsystem in the commercial vehicle one by one, and when the predicted value of monitoring data of any subsystem reaches or exceeds the maintenance threshold, calibrating i0, where i0 is the interference coefficient corresponding to the predicted value of monitoring data of any subsystem; Step S314: calibrate the interference coefficient range of the dangerous sub-area to be i≥i0.
Citation Information
Patent Citations
Unmanned driving system and unmanned driving method for full electric special vehicle
CN107719356A
Integrated multi-sensor integrated automatic driving intelligent sensing device
CN113313154A
Vehicle front anti-collision system based on drivable area
CN114537374A
Port tractor unmanned transportation short-toppling system and method
CN115129050A
Mine area unmanned driving safety intelligent management and control system based on artificial intelligence
CN115959159A
