Motor drive control method and electronic device for electric cross-country motorcycle

Abstract

The invention provides a motor drive control method of an electric cross-country motorcycle and an electronic device, and relates to the technical field of motor control, and the method comprises the steps: obtaining a target cross-country area of a target electric cross-country motorcycle, calling a GIS system to carry out the extraction of a terrain roughness distribution map based on the geographic position information of the target cross-country area, and obtaining a terrain roughness distribution map; obtaining a regional terrain roughness distribution map; obtaining a cross-country sub-region set; configuring a sensing monitoring frequency group set of the cross-country sub-region set; determining a real-time cross-country sub-region set; obtaining a real-time road feature set; and taking the real-time road feature set as a driving control analysis object, and carrying out adaptive driving control on the motor of the target electric cross-country motorcycle. The technical problems that in the prior art, electric cross-country motorcycle motor drive control is low in response speed and low in control accuracy to the actual road condition are solved, and the technical effects of improving the fitting degree of the motor drive control and the actual road condition and improving the response speed are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of motor control, and in particular to a motor drive control method and electronic equipment for an electric off-road motorcycle. Background Art

[0002] With the popularity of electric off-road motorcycles, the demand for their application in complex terrain environments has gradually increased. Electric off-road motorcycles usually need to cope with uneven and unpredictable off-road roads, and the motor drive control system needs to adjust the output power in real time to adapt to different terrains. However, the motor control systems in the prior art mostly rely on predetermined fixed control parameters and cannot be effectively adjusted according to the road terrain in real time. Especially in complex terrain environments, the existing motor control systems have a slow response speed and are difficult to respond to rapidly changing ground conditions in real time, resulting in poor driving experience, low control accuracy, and easy loss of control or instability.

[0003] Therefore, how to adjust the control parameters of the electric motor according to the road conditions of the target driving area of ​​the electric off-road motorcycle has become a technical problem that needs to be solved urgently. Summary of the invention

[0004] The present application provides a motor drive control method and electronic equipment for an electric off-road motorcycle, aiming to solve the technical problems in the prior art that the motor drive control of an electric off-road motorcycle has a slow response speed to actual road conditions and low control accuracy.

[0005] In a first aspect disclosed in the present application, a motor drive control method for an electric off-road motorcycle is provided, the method comprising: Obtaining a target off-road area for a target electric off-road motorcycle, and based on the geographical location information of the target off-road area, calling a GIS system to extract a terrain roughness distribution map to obtain a regional terrain roughness distribution map; Performing flood segmentation on the regional terrain roughness distribution map, dividing the target off-road area into sub-areas according to the ridge lines generated in the segmentation process, and obtaining an off-road sub-area set; Traversing the off-road sub-area set to perform a frequency analysis of the historical motorcycle driving out-of-control frequency, and configuring a sensor monitoring frequency group set of the off-road sub-area set according to the analysis result, wherein the off-road sub-area and the sensor monitoring frequency group correspond one to one; According to the GIS positioning component of the target electric off-road motorcycle, real-time positioning information is acquired, and the real-time positioning information is matched with the off-road sub-area set to determine the real-time off-road sub-area set; Based on the real-time sensor monitoring frequency group corresponding to the real-time off-road sub-area set in the sensor monitoring frequency group set, an asynchronous extraction dual channel is constructed, the road image collected by the depth camera of the target electric off-road motorcycle is asynchronously extracted by using the asynchronous extraction dual channel, and the road feature recognition is performed on the extraction result by using a fully connected network layer to obtain a real-time road feature set; The real-time road feature set is used as a driving control analysis object, and adaptive driving control is performed on the electric motor of the target electric off-road motorcycle.

[0006] The second aspect disclosed in the present application provides an electronic device, including a memory and a processor, wherein the memory stores executable instructions, and when the processor executes the executable instructions stored in the memory, any step of the first aspect disclosed in the present application is implemented.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages: The present application obtains a target off-road area for a target electric off-road motorcycle, and based on the geographical location information of the target off-road area, calls a GIS system to extract a terrain roughness distribution map to obtain a regional terrain roughness distribution map, and then performs flood segmentation on the regional terrain roughness distribution map, and divides the target off-road area into sub-areas according to the ridge lines generated during the segmentation process to obtain an off-road sub-area set, and then traverses the off-road sub-area set to perform a frequency analysis of the frequency of historical motorcycle driving out of control, and configures a sensor monitoring frequency group set of the off-road sub-area set according to the analysis results, wherein the off-road sub-areas and the sensor monitoring frequency groups correspond one to one, and then according to the target electric off-road motorcycle, the target off-road area is divided into sub-areas according to the ridge lines generated during the segmentation process to obtain an off-road sub-area set. The GIS positioning component of the trailer obtains real-time positioning information, matches the real-time positioning information with the off-road sub-area set, determines the real-time off-road sub-area set, and constructs an asynchronous extraction dual channel based on the real-time sensor monitoring frequency group corresponding to the real-time off-road sub-area set in the sensor monitoring frequency group set. The asynchronous extraction dual channel is used to asynchronously extract the road image collected by the depth camera of the target electric off-road motorcycle, and the fully connected network layer is used to identify the road features of the extraction results to obtain the real-time road feature set. Then, the real-time road feature set is used as the drive control analysis object to adaptively drive and control the motor of the target electric off-road motorcycle. The technical effect of improving the response speed of the motor drive control, adaptively adjusting the torque and speed of the motor in real time, making the performance of the electric motorcycle more stable and stable in different off-road environments, improving the degree of fit between the motor control and the actual road conditions, and improving the driving experience and safety is achieved.

[0008] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1 A schematic flow chart of a motor drive control method for an electric off-road motorcycle provided in an embodiment of the present application.

[0010] Figure 2 This is a diagram of the internal structure of an electronic device provided in an embodiment of the present application.

[0011] Description of the reference numerals: bus 300 , receiver 301 , processor 302 , transmitter 303 , memory 304 , bus interface 305 . DETAILED DESCRIPTION

[0012] The embodiments of the present application provide a motor drive control method for an electric off-road motorcycle, thereby solving the technical problems in the prior art that the motor drive control of an electric off-road motorcycle has a slow response speed to actual road conditions and low control accuracy.

[0013] After introducing the basic principles of the present application, various non-limiting implementation methods of the present application will be specifically introduced below in conjunction with the accompanying drawings of the specification. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0014] Examples, such as Figure 1 As shown, an embodiment of the present application provides a motor drive control method for an electric off-road motorcycle, wherein the method comprises: Step S100: acquiring a target off-road area of ​​a target electric off-road motorcycle, and based on the geographical location information of the target off-road area, calling a GIS system to extract a terrain roughness distribution map to obtain a regional terrain roughness distribution map; In one embodiment, the target electric off-road motorcycle refers to an electric off-road motorcycle that is traveling at a specific moment. The target off-road area refers to the geographical area where the target electric off-road motorcycle is expected to travel within a specific time, usually including multiple different terrains and road conditions. The geographic location information refers to the geographical coordinates or regional location of the target off-road area obtained through technologies such as the Global Positioning System (GPS), usually longitude and latitude coordinates. The GIS system (Geographic Information System) is a system for storing, analyzing and displaying geographic data, which can process geospatial information and generate different maps and analysis reports. The regional terrain roughness distribution map reflects the roughness distribution of the surface of the target off-road area, usually involving factors such as slope, obstacles, ups and downs.

[0015] In step S100, the area where the target electric off-road motorcycle is going to travel is first determined by obtaining the geographical location information of the target off-road area. Then, the GIS system is called using the location information to extract the terrain roughness distribution map of the area by analyzing the geographical data. The distribution map reflects the roughness of different terrains in the target off-road area, including the distribution of flat areas and rugged areas.

[0016] Accurate terrain information provides data support for subsequent control decisions, ensuring that the electric motorcycle's motor drive control can make timely and accurate adjustments in different terrains. Through this step, the system can understand the terrain characteristics of the target off-road area, laying the foundation for subsequent sub-area division and dynamic adjustment of motor control parameters.

[0017] Step S200: performing flood segmentation on the regional terrain roughness distribution map, dividing the target off-road area into sub-areas according to the ridge lines generated in the segmentation process, and obtaining an off-road sub-area set; Further, the regional terrain roughness distribution map is subjected to flood segmentation, and the target off-road area is divided into sub-areas according to the ridge lines generated in the segmentation process to obtain an off-road sub-area set. Step S200 of the embodiment of the present application further includes: Obtaining the lowest point of terrain roughness of the regional terrain roughness distribution map, taking the lowest point of terrain roughness as the flooding starting point, simulating water injection into the regional terrain roughness distribution map, and when the water surface overflows any terrain roughness distribution point in the regional terrain roughness distribution map, determining whether the roughness difference between the terrain roughness distribution point and the lowest point of terrain roughness is less than or equal to a preset roughness difference threshold, and if so, continuing to inject water into the regional terrain roughness distribution map; If not, after generating a regional dividing ridge line between the terrain roughness distribution point and the lowest point of the terrain roughness, continue to inject water into the regional terrain roughness distribution map until the water surface overflows the highest point of the terrain roughness in the regional terrain roughness distribution map, stop injecting water, and obtain a set of regional dividing ridge lines, wherein the regional dividing ridge lines rise as the water surface rises; The area dividing ridge line sets are connected to each other, and the target off-road area is divided into sub-areas to obtain the off-road sub-area set.

[0018] In a possible embodiment, the regional terrain roughness distribution map is segmented into multiple sub-areas by simulating the process of water surface rise. In this process, the water surface expands from the lowest point to the surrounding areas until a certain segmentation condition is reached. The ridge line generated in the segmentation process is used to define the boundaries of different terrain areas. By obtaining the off-road sub-area set, the regional terrain roughness distribution map is divided, paving the way for the subsequent setting of the road image extraction frequency for motor drive control for off-road sub-areas of different terrains.

[0019] In an embodiment of the present application, the roughness difference refers to the roughness difference between two terrain roughness distribution points, which is used to determine whether to continue water surface expansion or generate ridge lines. The terrain roughness distribution point refers to each specific point in the regional terrain roughness distribution map, and each specific point has a roughness feature (such as slope, undulation, etc.). The preset roughness difference threshold is a threshold set by technicians in this field based on experience or algorithm. When the difference between the terrain roughness distribution point and the lowest point is greater than this threshold, the water surface rising process will temporarily stop, and a ridge line will be generated to divide the area. The regional division ridge line set is used to divide the target off-road area into sub-areas, reflecting the boundaries of each sub-area.

[0020] In step S200, firstly, the terrain roughness distribution map is segmented for flooding, and the lowest point of terrain roughness is found from the map and used as the starting point of flooding. Then, the water surface is simulated to expand to the surrounding area and water is gradually added. When the water surface overflows a certain terrain roughness distribution point, it is determined whether the roughness difference between the point and the lowest point is less than or equal to the preset roughness difference threshold. If the conditions are met, water continues to be added to the regional terrain roughness distribution map, and the water surface continues to expand; if the conditions are not met, the system will generate a ridge line between the two compared points, and continue to add water until the water surface overflows the highest point of terrain roughness. This process generates a set of regional partition ridge lines, which divides different areas into multiple off-road sub-areas. Finally, all the generated ridge lines are connected to each other to complete the sub-area division of the target off-road area, thereby obtaining an off-road sub-area set.

[0021] By efficiently dividing different sub-areas according to the roughness differences of different terrains in the area, more detailed geographic data support is provided for subsequent monitoring and drive control, ensuring that the control system can adaptively obtain the road conditions of the target electric off-road motorcycle when driving in different sub-areas, and quickly adjust the control parameters of the motor according to the characteristics of different terrains.

[0022] Furthermore, the area division ridge line sets are connected to each other, the target off-road area is divided into sub-areas, and the off-road sub-area set is obtained. Step S200 of the embodiment of the present application further includes: Connecting the area dividing ridge line sets to each other, dividing the target off-road area according to the connection results, and obtaining an initial off-road sub-area set; Traversing the initial off-road sub-region set to perform sub-region area statistics to obtain an initial off-road sub-region area set; When the area set of the initial off-road sub-regions is less than or equal to the preset off-road sub-region area threshold, the corresponding initial off-road sub-region is added to the off-road sub-region set to be merged; When the area set of the initial off-road sub-region is larger than the preset off-road sub-region area threshold, the corresponding initial off-road sub-region is added into the fused off-road sub-region set; Initial off-road sub-region fusion is performed based on the sub-region positions of the off-road sub-region set to be fused and the off-road sub-region set that can be fused, so as to obtain the off-road sub-region set.

[0023] Further, initial off-road sub-region fusion is performed based on the sub-region positions of the off-road sub-region set to be fused and the off-road sub-region set that can be fused to obtain the off-road sub-region set. Step S200 of the embodiment of the present application further includes: Randomly extracting a first off-road sub-region to be fused from the set of off-road sub-regions to be fused; According to the sub-region position, the neighborhood of the first off-road sub-region to be fused is matched from the set of off-road sub-regions that can be fused, so as to obtain the neighborhood of the first off-road sub-region that can be fused; Acquire a first fused off-road sub-region neighborhood area set of the first fused off-road sub-region neighborhood; Traversing and counting the distances from the first fused off-road sub-region neighborhood to the first to-be-fused off-road sub-region, to obtain a first fused off-road sub-region neighborhood distance set; Performing weighted calculation on the first fused off-road sub-region neighborhood area set and the first fused off-road sub-region neighborhood distance set to obtain a first fused off-road sub-region neighborhood fusion coefficient set; The first off-road sub-region to be fused is integrated into the off-road sub-region that can be fused corresponding to the maximum value in the neighborhood fusion coefficient set of the first off-road sub-region that can be fused, to obtain the first off-road sub-region; The sub-region positions of the off-road sub-region set to be merged and the off-road sub-region set that can be merged are initially merged into an off-road sub-region to obtain the off-road sub-region set.

[0024] In one embodiment, the preset off-road sub-region area threshold is an area value predetermined by a person skilled in the art, and is used to determine whether a certain sub-region needs further processing (such as merging). First, the region division ridge line sets are connected to each other, and the target off-road region is segmented according to the connection result to obtain an initial off-road sub-region set, that is, a plurality of sub-regions preliminarily divided according to the terrain roughness distribution map. Next, these initial off-road sub-regions are traversed, the area of ​​each initial off-road sub-region is counted, and the area is compared with the preset off-road sub-region area threshold. If the area of ​​a certain sub-region is less than or equal to the preset off-road sub-region area threshold, it indicates that the area of ​​the initial off-road sub-region is too small, and the sub-region is added to the off-road sub-region set to be fused; if the area is greater than the preset off-road sub-region area threshold, it indicates that the area of ​​the initial off-road sub-region is qualified and does not need to be actively merged, and the sub-region is added to the off-road sub-region set that can be fused. According to the area and sub-region position of these off-road sub-region sets to be fused and the off-road sub-region set that can be fused, the initial off-road sub-region is fused to obtain the off-road sub-region set.

[0025] Optionally, a first off-road sub-region to be fused is randomly extracted from the off-road sub-region set to be fused, and the neighborhood of the first off-road sub-region to be fused is matched from the off-road sub-region set to be fused according to the sub-region position to obtain the neighborhood of the first off-road sub-region to be fused. A first off-road sub-region neighborhood area set to be fused is obtained for the neighborhood of the first off-road sub-region to be fused, and then, the distance from each off-road sub-region to be fused in the neighborhood of the first off-road sub-region to be fused is counted to obtain a first off-road sub-region neighborhood distance set to be fused.

[0026] Then, the first fused off-road sub-region neighborhood area set and the first fused off-road sub-region neighborhood distance set are weightedly calculated according to the weights pre-set by those skilled in the art to obtain the first fused off-road sub-region neighborhood fusion coefficient set. The first fused off-road sub-region neighborhood fusion coefficient set reflects the fusion quality of each fused off-road sub-region in the first fused off-road sub-region neighborhood. The larger the coefficient, the higher the fusion quality. According to the maximum value of the fusion coefficient, the best merging object is selected, and the area to be fused is merged with it, so as to finally obtain the optimized first off-road sub-region.

[0027] The first off-road sub-region to be integrated is integrated into the off-road sub-region that can be integrated corresponding to the maximum value in the neighborhood integration coefficient set of the first off-road sub-region that can be integrated, so as to obtain the first off-road sub-region. Based on the same principle as obtaining the first off-road sub-region, the sub-region positions of the off-road sub-region set to be integrated and the off-road sub-region set that can be integrated are initially integrated into the off-road sub-region to obtain the off-road sub-region set.

[0028] By refining and optimizing the initially divided areas, the off-road sub-area division is made more reasonable and accurate through fusion operations, thereby improving the adaptability and control accuracy of electric motorcycles in different off-road environments.

[0029] Step S300: traversing the off-road sub-area set to perform a frequency analysis of the historical motorcycle driving out-of-control frequency, and configuring a sensor monitoring frequency group set of the off-road sub-area set according to the analysis result, wherein the off-road sub-area and the sensor monitoring frequency group correspond one to one; Further, the off-road sub-area set is traversed to perform a frequency analysis of the historical motorcycle driving out-of-control frequency, and the sensor monitoring frequency group set of the off-road sub-area set is configured according to the analysis result. Step S300 of the embodiment of the present application also includes: Analyzing the frequency of historical motorcycle driving out-of-control in the off-road sub-area set according to a preset out-of-control index set to determine a sub-area historical driving out-of-control frequency set; Dividing the historical driving out-of-control frequency of each sub-region in the historical driving out-of-control frequency set of the sub-regions by the sum of the historical driving out-of-control frequency set of the sub-regions, respectively, to obtain an out-of-control coefficient set; The out-of-control coefficient set is multiplied by the preset sensor monitoring frequency group set respectively to obtain the sensor monitoring frequency group set.

[0030] In one embodiment of the present application, the frequency of driving out of control of the electric off-road motorcycles passing through the off-road sub-area set in the historical time is counted and analyzed, with the purpose of understanding which sub-areas have a higher frequency of driving out of control, thereby providing a basis for subsequent monitoring and control. The sensor monitoring frequency group set reflects the frequency group situation of the target electric off-road motorcycle when passing through different off-road sub-areas. Among them, the off-road sub-areas and the sensor monitoring frequency groups correspond one to one.

[0031] Optionally, the preset out-of-control index set refers to a set of indicators pre-set by a technician in this field, which is used to measure whether the electric off-road motorcycle loses control during off-road driving. These indicators may include abnormal vehicle speed, wheel slippage, insufficient power, steering failure, etc. The sub-area historical driving out-of-control frequency set is a frequency data set of out-of-control events in each off-road sub-area during historical driving, reflecting the out-of-control frequency in different areas. The out-of-control coefficient set is a set of coefficients obtained by proportionally calculating the out-of-control frequency of each sub-area and the sum of the out-of-control frequencies of all sub-areas. Each out-of-control coefficient reflects the proportion of the out-of-control risk of each sub-area relative to the entire area. The preset sensor monitoring frequency group set is a set of sensor monitoring frequencies preset by a technician in this field.

[0032] In step S300, the frequency analysis of the historical motorcycle driving out-of-control frequency is first performed on the off-road sub-area set. The purpose of this analysis is to identify which sub-areas have a higher frequency of driving out-of-control by statistics of historical data. This step requires evaluating the historical out-of-control frequency of each sub-area according to the preset out-of-control index set to determine the sub-area historical driving out-of-control frequency of each sub-area and obtain the sub-area historical driving out-of-control frequency set. Then, by calculating the ratio of the number of historical driving out-of-control times to the total number of times in each sub-area, the out-of-control coefficient set is obtained. These out-of-control coefficients reflect the relative risk of out-of-control in each area.

[0033] Next, the greater the loss of control coefficient, the higher the risk of motor drive loss of control in the area, and the higher the sensor monitoring frequency should be. The loss of control coefficient set is multiplied by the preset sensor monitoring frequency group set to generate a sensor monitoring frequency group set corresponding to each sub-area. Specifically, areas with high loss of control coefficients (i.e., high-risk areas) will correspond to higher sensor monitoring frequencies, and areas with low loss of control coefficients (i.e., low-risk areas) will correspond to lower monitoring frequencies.

[0034] By intelligently adjusting the operating frequency of the sensor based on historical out-of-control data, the monitoring of high-risk areas can be made more frequent and accurate, thereby improving the driving safety of electric off-road motorcycles in complex off-road environments.

[0035] Step S400: acquiring real-time positioning information according to the GIS positioning component of the target electric off-road motorcycle, matching the real-time positioning information with the off-road sub-area set, and determining the real-time off-road sub-area set; In a possible embodiment, the GIS positioning component refers to a global positioning system (GPS) or other positioning technology module equipped by the target electric off-road motorcycle, which can obtain the motorcycle's geographic location information in real time. The GIS (Geographic Information System) system is used to process and analyze this geographic information.

[0036] First, the geographic location information of the target electric off-road motorcycle is obtained in real time through the GIS positioning component. This location information may include parameters such as the longitude, latitude, and altitude of the motorcycle. Next, this real-time positioning information is matched with the previously generated off-road sub-area set. The location matching process is to determine the specific sub-area where the motorcycle is located by comparing the current geographic location of the motorcycle with the boundaries of each off-road sub-area.

[0037] Through this process, the system can determine the real-time off-road sub-area set that the motorcycle is in at each moment. This information is critical because different off-road sub-areas may have different terrain characteristics and driving requirements. Real-time positioning information can help the system dynamically adjust the motorcycle's motor drive control parameters (such as torque and speed) to ensure stability and safety during driving.

[0038] Step S500: constructing an asynchronous extraction dual channel based on the real-time sensor monitoring frequency group corresponding to the real-time off-road sub-area set in the sensor monitoring frequency group set, using the asynchronous extraction dual channel to asynchronously extract the road image collected by the depth camera of the target electric off-road motorcycle, and using a fully connected network layer to perform road feature recognition on the extraction result to obtain a real-time road feature set; In one embodiment, the real-time sensor monitoring frequency group is a set of sensor monitoring frequencies matched to the real-time off-road sub-area. This frequency set determines the frequency of the system monitoring the motorcycle road environment under real-time conditions. Asynchronous extraction dual-channel means that the two channels can work in parallel, but their extraction processes are not completely synchronized. This method can accelerate data processing and improve processing efficiency. The road image is image data collected by the depth camera of the target electric off-road motorcycle, which usually contains information such as road texture, obstacles, slope, etc. The fully connected network layer is a neural network structure, which is usually used to process image data. In this layer, all input nodes and output nodes are fully connected, and feature learning can be performed on the extraction results through these connections. The real-time road feature set is a feature set of the road image processed by the fully connected network layer, and these feature information is used to analyze the current road conditions, including road conditions, obstacles, etc.

[0039] In step S500, the asynchronous extraction frequency of the road image collected by the depth camera is first determined according to the real-time sensor monitoring frequency group corresponding to the current real-time off-road sub-area set. The real-time sensor monitoring frequency group specifies how often the collected road images are collected and extracted so as to be properly controlled according to the terrain conditions. Next, an asynchronous extraction dual channel is constructed, that is, asynchronously extracting road image information from two different data streams in parallel to avoid the delay that may be caused by synchronous processing.

[0040] These road images are collected by the electric off-road motorcycle's depth camera, which can generate images with depth information, allowing the system to clearly perceive the road surface features. Next, the image data will be analyzed and processed by a fully connected network layer to extract useful road features (such as rough roads, obstacles, slopes, etc.). These extracted real-time road feature sets provide a basis for subsequent motor drive control.

[0041] Further, based on the real-time sensor monitoring frequency group corresponding to the real-time off-road sub-area set in the sensor monitoring frequency group set, an asynchronous extraction dual channel is constructed, and the road image collected by the depth camera of the target electric off-road motorcycle is asynchronously extracted by using the asynchronous extraction dual channel, and the extraction result is subjected to road feature recognition by using a fully connected network layer to obtain a real-time road feature set. Step S500 of the embodiment of the present application also includes: Extracting a first real-time sensing monitoring frequency and a second real-time sensing monitoring frequency from the real-time sensing monitoring frequency group, wherein the first real-time sensing monitoring frequency is less than the second real-time sensing monitoring frequency; Acquire a plurality of sample road image sets and a plurality of sample first asynchronous extraction results obtained after extracting the plurality of sample road image sets according to a first real-time sensing monitoring frequency, and construct a first asynchronous extraction subchannel; Acquire multiple sample road image sets and multiple sample second asynchronous extraction results obtained after extracting the multiple sample road image sets according to a second real-time sensing monitoring frequency, and construct a second asynchronous extraction sub-channel; The first asynchronous extraction sub-channel and the second asynchronous extraction sub-channel are connected in parallel to obtain the asynchronous extraction dual-channel.

[0042] Furthermore, step S500 of the embodiment of the present application further includes: Acquire a plurality of sample road feature sets corresponding to the plurality of sample road image sets; Based on the multiple sample road feature sets, the multiple sample first asynchronous extraction results and the multiple sample second asynchronous extraction results, network layer training is performed until convergence to obtain the trained fully connected network layer.

[0043] In one embodiment of the present application, the real-time sensing monitoring frequency group includes a first real-time sensing monitoring frequency and a second real-time sensing monitoring frequency. The two respectively represent different data collection frequencies for road images in real-time monitoring. The image extracted by the first real-time sensing monitoring frequency is used to monitor the overall terrain features, and the image extracted by the second real-time sensing monitoring frequency is used to monitor instantaneous dynamic changes.

[0044] A plurality of sample road image sets and a plurality of sample first asynchronous extraction results obtained after extracting the plurality of sample road image sets according to a first real-time sensing monitoring frequency are obtained. The plurality of sample road image sets, the first real-time sensing monitoring frequency and the plurality of sample first asynchronous extraction results are used as training data, and a framework constructed based on a convolutional neural network is trained using a back propagation algorithm, and network parameters are gradually adjusted so that the network can more accurately extract images according to the first real-time sensing monitoring frequency until the training converges, and a trained first asynchronous extraction subchannel is obtained.

[0045] A plurality of sample road image sets and a plurality of sample second asynchronous extraction results obtained after extracting the plurality of sample road image sets according to a second real-time sensing monitoring frequency are obtained. The plurality of sample road image sets, the second real-time sensing monitoring frequency and the plurality of sample second asynchronous extraction results are used as training data, and the second asynchronous extraction sub-channel is trained based on the same principle as that of obtaining the first asynchronous extraction sub-channel.

[0046] Optionally, the first asynchronous extraction sub-channel is used to extract the road image captured by the depth camera according to the first real-time sensing monitoring frequency to obtain a first asynchronous extraction result. The second asynchronous extraction sub-channel is used to extract the road image captured by the depth camera according to the second real-time sensing monitoring frequency to obtain a second asynchronous extraction result. Then, the two sub-channels are combined together in parallel to realize the overall operation of the asynchronous extraction dual channels. The first asynchronous extraction result and the second asynchronous extraction result are used as inputs to the fully connected network layer. By training with a large amount of sample data, the network can optimize its feature extraction capabilities and learn more accurate road features. The purpose of this process is to ensure that the system can accurately identify and understand road features according to changes in the real-time environment, and provide accurate information support for subsequent motor control.

[0047] In one possible embodiment, deep learning training is performed by obtaining multiple sample road feature sets and corresponding multiple sample first asynchronous extraction results and multiple sample second asynchronous extraction results. The goal of network training is to use these data to optimize the weights of the fully connected network layer and improve the ability to recognize different road features. The fully connected network layer is trained by the back propagation algorithm, and its parameters are gradually adjusted so that the network can more accurately identify road features. This process will continue during training until the network reaches the optimal state, that is, convergence. Through such training, the system can better extract useful information from road images, improve the accuracy of road feature recognition, and provide more accurate data support for the motor drive control of electric motorcycles.

[0048] Step S600: taking the real-time road feature set as a driving control analysis object, adaptively driving the motor of the target electric off-road motorcycle.

[0049] In one embodiment, the previously acquired real-time road feature set is used as the drive control analysis object to perform motor adaptive drive control. That is, according to the road information (such as slope, ground roughness, obstacles, etc.) acquired in real time, the motor of the electric motorcycle is dynamically adjusted to change the torque and speed of the motor. This adjustment can make the motorcycle better adapt to the current road conditions and improve the driving stability and safety. For example, in rough terrain, the output of the motor may need to be increased to provide greater driving force, while on a flat road, the output of the motor may be appropriately reduced to save energy.

[0050] In summary, the motor drive control method for an electric off-road motorcycle provided in the embodiment of the present application has the following technical effects: This application obtains the terrain roughness distribution map and sensor data, dynamically adjusts the driving parameters of the motor (such as torque and speed), and achieves rapid response to different off-road terrains, thereby improving the stability and driving experience of the motorcycle in complex environments. At the same time, it uses a depth camera and asynchronous extraction dual channels to efficiently extract road features, and uses a fully connected neural network for accurate identification to grasp the road conditions in real time, providing an accurate basis for motor control, and combined with historical out-of-control frequency analysis, adaptive monitoring frequencies are configured according to different off-road sub-areas to improve the efficiency and accuracy of sensor data acquisition, thereby achieving the technical effect of improving the fit between the motor drive control and the actual road and improving the control quality.

[0051] Embodiment 2, as Figure 2 As shown, it is a schematic diagram of the structure of an exemplary electronic device of the present application, in Figure 2 In the embodiment, the bus architecture is represented by bus 300, which may include any number of interconnected buses and bridges, and bus 300 connects various circuits including one or more processors represented by processor 302 and memory represented by memory 304. Bus 300 may also connect various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. Bus interface 305 provides an interface between bus 300 and receiver 301 and transmitter 303. Receiver 301 and transmitter 303 may be the same element, namely a transceiver, providing a unit for communicating with various other devices over a transmission medium. Processor 302 is responsible for managing bus 300 and general processing, while memory 304 may be used to store data used by processor 302 when performing operations.

[0052] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0053] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A motor drive control method for an electric off-road motorcycle, characterized in that: The method comprises: Obtaining a target off-road area for a target electric off-road motorcycle, and based on the geographical location information of the target off-road area, calling a GIS system to extract a terrain roughness distribution map to obtain a regional terrain roughness distribution map; Performing flood segmentation on the regional terrain roughness distribution map, dividing the target off-road area into sub-areas according to the ridge lines generated in the segmentation process, and obtaining an off-road sub-area set; Traversing the off-road sub-area set to perform a frequency analysis of the historical motorcycle driving out-of-control frequency, and configuring a sensor monitoring frequency group set of the off-road sub-area set according to the analysis result, wherein the off-road sub-area and the sensor monitoring frequency group correspond one to one; According to the GIS positioning component of the target electric off-road motorcycle, real-time positioning information is acquired, and the real-time positioning information is matched with the off-road sub-area set to determine the real-time off-road sub-area set; Based on the real-time sensor monitoring frequency group corresponding to the real-time off-road sub-area set in the sensor monitoring frequency group set, an asynchronous extraction dual channel is constructed, the road image collected by the depth camera of the target electric off-road motorcycle is asynchronously extracted by using the asynchronous extraction dual channel, and the road feature recognition is performed on the extraction result by using a fully connected network layer to obtain a real-time road feature set; The real-time road feature set is used as a driving control analysis object, and adaptive driving control is performed on the electric motor of the target electric off-road motorcycle.

2. The motor drive control method of an electric off-road motorcycle according to claim 1, characterized in that: Performing flood segmentation on the regional terrain roughness distribution map, dividing the target off-road area into sub-areas according to the ridge lines generated in the segmentation process, and obtaining an off-road sub-area set, including: Obtaining the lowest point of terrain roughness of the regional terrain roughness distribution map, taking the lowest point of terrain roughness as the flooding starting point, simulating water injection into the regional terrain roughness distribution map, and when the water surface overflows any terrain roughness distribution point in the regional terrain roughness distribution map, determining whether the roughness difference between the terrain roughness distribution point and the lowest point of terrain roughness is less than or equal to a preset roughness difference threshold, and if so, continuing to inject water into the regional terrain roughness distribution map; If not, after generating a regional dividing ridge line between the terrain roughness distribution point and the lowest point of the terrain roughness, continue to inject water into the regional terrain roughness distribution map until the water surface overflows the highest point of the terrain roughness in the regional terrain roughness distribution map, stop injecting water, and obtain a set of regional dividing ridge lines, wherein the regional dividing ridge lines rise as the water surface rises; The area dividing ridge line sets are connected to each other, and the target off-road area is divided into sub-areas to obtain the off-road sub-area set.

3. The motor drive control method of the electric off-road motorcycle according to claim 2, characterized in that: Connecting the area dividing ridge line sets to each other, dividing the target off-road area into sub-areas, and obtaining the off-road sub-area set, including: Connecting the area dividing ridge line sets to each other, dividing the target off-road area according to the connection results, and obtaining an initial off-road sub-area set; Traversing the initial off-road sub-region set to perform sub-region area statistics to obtain an initial off-road sub-region area set; When the area set of the initial off-road sub-regions is less than or equal to the preset off-road sub-region area threshold, the corresponding initial off-road sub-region is added to the off-road sub-region set to be merged; When the area set of the initial off-road sub-region is larger than the preset off-road sub-region area threshold, the corresponding initial off-road sub-region is added into the fused off-road sub-region set; Initial off-road sub-region fusion is performed based on the sub-region positions of the off-road sub-region set to be fused and the off-road sub-region set that can be fused, so as to obtain the off-road sub-region set.

4. The motor drive control method for an electric off-road motorcycle according to claim 3, characterized in that: Performing initial off-road sub-region fusion based on the sub-region positions of the off-road sub-region set to be fused and the off-road sub-region set that can be fused to obtain the off-road sub-region set includes: Randomly extracting a first off-road sub-region to be fused from the set of off-road sub-regions to be fused; According to the sub-region position, the neighborhood of the first off-road sub-region to be fused is matched from the set of off-road sub-regions that can be fused, so as to obtain the neighborhood of the first off-road sub-region that can be fused; Acquire a first fused off-road sub-region neighborhood area set of the first fused off-road sub-region neighborhood; Traversing and counting the distances from the first fused off-road sub-region neighborhood to the first to-be-fused off-road sub-region, to obtain a first fused off-road sub-region neighborhood distance set; Performing weighted calculation on the first fused off-road sub-region neighborhood area set and the first fused off-road sub-region neighborhood distance set to obtain a first fused off-road sub-region neighborhood fusion coefficient set; The first off-road sub-region to be fused is integrated into the off-road sub-region that can be fused corresponding to the maximum value in the neighborhood fusion coefficient set of the first off-road sub-region that can be fused, to obtain the first off-road sub-region; The sub-region positions of the off-road sub-region set to be merged and the off-road sub-region set that can be merged are initially merged into an off-road sub-region to obtain the off-road sub-region set.

5. The motor drive control method for an electric off-road motorcycle according to claim 1, characterized in that: Traversing the off-road sub-area set to perform a frequency analysis of the historical motorcycle driving out-of-control frequency, and configuring the sensor monitoring frequency group set of the off-road sub-area set according to the analysis result, including: Analyzing the frequency of historical motorcycle driving out-of-control in the off-road sub-area set according to a preset out-of-control index set to determine a sub-area historical driving out-of-control frequency set; Dividing the historical driving out-of-control frequency of each sub-region in the historical driving out-of-control frequency set of the sub-regions by the sum of the historical driving out-of-control frequency set of the sub-regions, respectively, to obtain an out-of-control coefficient set; The out-of-control coefficient set is multiplied by the preset sensor monitoring frequency group set respectively to obtain the sensor monitoring frequency group set.

6. The motor drive control method for an electric off-road motorcycle according to claim 1, characterized in that: Based on the real-time sensor monitoring frequency group corresponding to the real-time off-road sub-area set in the sensor monitoring frequency group set, an asynchronous extraction dual channel is constructed, and the road image collected by the depth camera of the target electric off-road motorcycle is asynchronously extracted by using the asynchronous extraction dual channel, and the road feature recognition is performed on the extraction result by using a fully connected network layer to obtain a real-time road feature set, including: Extracting a first real-time sensing monitoring frequency and a second real-time sensing monitoring frequency from the real-time sensing monitoring frequency group, wherein the first real-time sensing monitoring frequency is less than the second real-time sensing monitoring frequency; Acquire a plurality of sample road image sets and a plurality of sample first asynchronous extraction results obtained after extracting the plurality of sample road image sets according to a first real-time sensing monitoring frequency, and construct a first asynchronous extraction subchannel; Acquire multiple sample road image sets and multiple sample second asynchronous extraction results obtained after extracting the multiple sample road image sets according to a second real-time sensing monitoring frequency, and construct a second asynchronous extraction sub-channel; The first asynchronous extraction sub-channel and the second asynchronous extraction sub-channel are connected in parallel to obtain the asynchronous extraction dual-channel.

7. The motor drive control method for an electric off-road motorcycle according to claim 6, characterized in that: include: Acquire a plurality of sample road feature sets corresponding to the plurality of sample road image sets; Based on the multiple sample road feature sets, the multiple sample first asynchronous extraction results and the multiple sample second asynchronous extraction results, network layer training is performed until convergence to obtain the trained fully connected network layer.

8. An electronic device, characterized in that: The electronic device comprises: A memory for storing executable instructions; The processor is used to implement the motor drive control method of the electric off-road motorcycle according to any one of claims 1 to 7 when executing the executable instructions stored in the memory.

Images