Gearbox gear ratio dynamic matching control method and system based on multi-sensor fusion

Abstract

The application discloses a gearbox gear ratio dynamic matching control method and system based on multi-sensor fusion, relates to the field of intelligent control of new energy vehicles, and comprises the following steps: setting a gear ratio control target, analyzing relevant factors of the structure and driving environment of the new energy vehicle, and establishing a correlation network diagram; multiple source sensors are arranged in and outside the vehicle, and a sensing mapping relationship with the monitoring target in the correlation network diagram is established; the gear ratio control target is used as a search engine, and path searching is performed according to the correlation network diagram and the sensing mapping relationship; a target function is established according to the data characteristics of each node in the matching influence relationship path and the gear ratio control target, gear ratio control matching calculation is performed in combination with real-time multi-source sensing data, and a matching gear ratio that satisfies the gear ratio control target and has the largest target evaluation result is obtained. The technical problem of poor accuracy and adaptability of the gearbox gear ratio dynamic matching of the existing new energy vehicle is solved, and the technical effect of improving the accuracy and adaptability of matching is achieved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of intelligent control of new energy vehicles, in particular to a gearbox speed ratio dynamic matching control method and system based on multi-sensor fusion. BACKGROUND

[0002] In the field of new energy vehicles, reasonable matching of gearbox speed ratio is crucial for improving the power performance, energy efficiency and driving experience of vehicles, and is one of the key factors affecting the competitiveness of new energy vehicles in the market. At present, the problem of dynamic matching of gearbox speed ratio is mainly solved by matching control methods based on single sensor data or simple rules, that is, part of the vehicle operating parameters are obtained through a specific sensor, and then the gearbox speed ratio is determined according to pre-set fixed rules or simple algorithms. However, this method relies only on a single data source and does not fully consider the complex correlation between the complex operating structure of new energy vehicles and the variable driving environment factors, resulting in the inability to comprehensively and accurately obtain various information affecting the gearbox speed ratio, and thus poor accuracy and adaptability of the gearbox speed ratio matching.

[0003] At present, the dynamic matching of gearbox speed ratio of new energy vehicles in related technologies has the technical problem of poor accuracy and adaptability. SUMMARY

[0004] The present application provides a gearbox speed ratio dynamic matching control method and system based on multi-sensor fusion, adopts multi-sensor fusion technology, constructs a correlation network graph and establishes a sensor mapping relationship, establishes a matching influence relationship path through path search, and combines a target function with real-time multi-source perception data for gearbox speed ratio control matching calculation, etc. Technical means, solves the technical problem of poor accuracy and adaptability of the existing dynamic matching of gearbox speed ratio of new energy vehicles, and achieves the technical effect of improving the accuracy and adaptability of the matching.

[0005] The present application provides a gearbox speed ratio dynamic matching control method based on multi-sensor fusion, comprising: setting a gearbox speed ratio control target, analyzing the associated factors of new energy vehicle structure and driving environment based on the gearbox speed ratio control target, and establishing a correlation network graph; based on the correlation network graph, multi-source sensors are arranged inside and outside the vehicle, and a sensor mapping relationship between the multi-source sensors and the monitoring targets in the correlation network graph is established; taking the gearbox speed ratio control target as a search engine, performing path search according to the correlation network graph and the sensor mapping relationship, and establishing a matching influence relationship path; according to the data characteristics of each node in the matching influence relationship path and the gearbox speed ratio control target, a target function is established, and based on the target function, real-time multi-source perception data are combined for gearbox speed ratio control matching calculation, a matching gearbox speed ratio that satisfies the gearbox speed ratio control target and has the maximum target evaluation result is obtained, and the matching gearbox speed ratio is used for gearbox speed ratio control of the vehicle.

[0006] In a possible implementation, the following processing is performed: the gear ratio control target comprises a power performance index, an energy efficiency threshold, a shift smoothness target, and a battery SOC safety range, wherein the gear ratio control target has a mode weight label.

[0007] In a possible implementation, based on the gear ratio control target, a new energy vehicle structure and a driving environment correlation factor are analyzed, a correlation network diagram is established, and the following processing is performed: based on the gear ratio control target, a hardware node, an environment node, and a correlation relationship are analyzed from a vehicle power system relationship, a vehicle state relationship, a driver operation relationship, an environmental parameter influence relationship, and an energy supply relationship, and a correlation node is determined; based on an influence relationship between the correlation node and the gear ratio control target, an edge between nodes is established, and the correlation network diagram is constructed.

[0008] In a possible implementation, based on the influence relationship between the correlation node and the gear ratio control target, an edge between nodes is established, and the following processing is performed: a gear ratio matching control relationship is taken as an intermediate transformation node, a gear ratio matching control relationship about the intermediate transformation node between the correlation node and the gear ratio control target is analyzed, and an edge attribute is established; based on the correlation relationship among the gear ratio control target, the intermediate transformation node, and the correlation node and the edge attribute, an edge between nodes is established.

[0009] In a possible implementation, based on the target function, real-time multi-source perception data are used for gear ratio control matching calculation, and the following processing is performed: when there are multiple matching influence relationship paths for the same gear ratio control target, matching relationship triggering is performed according to real-time perception data of the multiple matching influence relationship paths; when there is one matching influence relationship path triggered, the matching influence relationship path is triggered according to the perception data, gear ratio control matching parameter searching is performed according to the target function, and the matching gear ratio is obtained.

[0010] In a possible implementation, matching relationship triggering is performed according to real-time perception data of multiple matching influence relationship paths, and the following processing is further performed: when multiple matching influence relationships are triggered, relationship analysis is performed according to real-time multi-source perception data and multi-source sensing data fusion network, a matching influence relationship path with the greatest influence is selected as an execution path, and a verification path is set; real-time perception data of the execution path and the target function are used for gear ratio control matching parameter searching, and a matching gear ratio to be verified is obtained; real-time perception data of the verification path and the matching gear ratio to be verified are used for evaluation verification through the target function, and when a target evaluation requirement is met, the matching gear ratio is determined.

[0011] In a possible implementation, the relationship is analyzed according to real-time multi-source perception data and a multi-source sensor data fusion network, a matching influence relationship path with the greatest influence is selected as an execution path, a verification path is set, and the following processing is performed: based on volatility of the real-time multi-source perception data, consistency and volatility of sensor data of each path are evaluated according to the multi-source sensor data fusion network, and a path with strong consistency and great volatility is selected as the execution path, where the volatility refers to a data change range, and the consistency refers to whether the data conforms to an expected regularity; after the execution path is selected, errors of remaining paths and influence of a target function are evaluated, and the matching influence relationship path with small errors and great influence of the target function is selected as the verification path.

[0012] In a possible implementation, the real-time perception data of the verification path is combined with the to-be-verified matching gear ratio, and evaluation verification is performed through the target function, and the following processing is further performed: when the target evaluation requirement is not met, influence data of the gear ratio control target is weighted and calculated according to multi-path real-time perception data, and a weighted average result is obtained; and the matching gear ratio is determined by using the weighted average result.

[0013] In a possible implementation, the matching gear ratio is used for gear ratio control of an automobile gearbox, and the following processing is further performed: based on the gearbox control of the matching gear ratio, tracking monitoring is performed through multi-source sensors; the control verification result is obtained by performing gear ratio control target verification according to the tracking monitoring multi-source sensor data; and the control verification result is used as interaction data to calibrate and optimize the data of the target function or the matching gear ratio.

[0014] The application also provides a multi-sensor fusion gearbox gear ratio dynamic matching control system, which includes: a correlation network graph establishment module, configured to set a gear ratio control target, analyze new energy automobile structures and driving environment correlation factors based on the gear ratio control target, and establish a correlation network graph; a multi-source sensor arrangement module, configured to arrange multi-source sensors in and outside an automobile based on the correlation network graph, and establish a sensing mapping relationship between the multi-source sensors and a monitoring target in the correlation network graph; a matching influence relationship path establishment module, configured to use the gear ratio control target as a search engine, search a path according to the correlation network graph and the sensing mapping relationship, and establish a matching influence relationship path; and a gear ratio control matching calculation module, configured to establish a target function according to data features of each node in the matching influence relationship path and the gear ratio control target, perform gear ratio control matching calculation based on the target function and real-time multi-source perception data, obtain a matching gear ratio that satisfies the gear ratio control target and has the greatest target evaluation result, and use the matching gear ratio for gear ratio control of an automobile gearbox.

[0015] The multi-sensor fusion gearbox gear ratio dynamic matching control method and system provided by the application first sets a gear ratio control target, analyzes new energy vehicle structure and driving environment related factors based on the gear ratio control target, establishes a correlation network diagram, then arranges multi-source sensors inside and outside the vehicle based on the correlation network diagram, and establishes a sensing mapping relationship between the multi-source sensors and the monitoring targets in the correlation network diagram, then takes the gear ratio control target as a search engine, performs path search according to the correlation network diagram and the sensing mapping relationship, establishes a matching influence relationship path, finally establishes a target function according to the data characteristics of each node in the matching influence relationship path and the gear ratio control target, performs gear ratio control matching calculation based on the target function combined with real-time multi-source sensing data, obtains a matching gear ratio that satisfies the gear ratio control target and has the largest target evaluation result, and uses the matching gear ratio to control the gear ratio of the vehicle gearbox. The technical effect of improving the accuracy and adaptability of matching is achieved. BRIEF DESCRIPTION OF DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the application, the drawings of the embodiments of the application will be briefly introduced below. The flowchart is used to illustrate the operations performed by the system according to the embodiments of the application in this application. It should be understood that the foregoing or the following operations are not necessarily performed in sequence. On the contrary, various steps can be processed in reverse order or at the same time according to needs. At the same time, other operations can be added to these processes, or one or more steps of operations can be removed from these processes.

[0017] Figure 1 The flowchart of the multi-sensor fusion gearbox gear ratio dynamic matching control method provided by the embodiments of the application.

[0018] Figure 2 The structural diagram of the multi-sensor fusion gearbox gear ratio dynamic matching control system provided by the embodiments of the application.

[0019] Explanation of reference signs: correlation network diagram establishment module 10, multi-source sensor arrangement module 20, matching influence relationship path establishment module 30, and gear ratio control matching calculation module 40. DETAILED DESCRIPTION

[0020] The above description is only a summary of the technical solutions of the application. In order to more clearly understand the technical means of the application, the embodiments of the application can be implemented according to the content of the specification, and in order to make the above and other purposes, characteristics and advantages of the application more obvious and easy to understand, the following specific embodiments of the application are described.

[0021] In order to make the purposes, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the drawings, and the described embodiments should not be regarded as limitations of the present application. All other embodiments obtained by those of ordinary skill in the art without creative labor fall within the scope of protection of the present application.

[0022] In the following description, "some embodiments" are related to a subset of all possible embodiments, but it can be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments, and can be combined with each other without conflict. The terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or server including a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or modules that are not clearly listed or inherent to these processes, methods, products or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as understood by those skilled in the art to which the present application belongs. The terms used herein are only for the purpose of describing the embodiments of the present application.

[0023] The embodiments of the present application provide a multi-sensor fusion gearbox gear ratio dynamic matching control method, as shown in Figure 1 The method comprises the following steps:

[0024] Step S100, set the gear ratio control target, analyze the new energy vehicle structure, driving environment related factors based on the gear ratio control target, and establish a related network diagram.

[0025] Specifically, the software algorithm sets the gear ratio control target, which indicates the performance indicators that the gear ratio of the gearbox needs to achieve, including power indicators, energy efficiency thresholds, shift smoothness targets, battery SOC safety ranges, etc. Different control targets are assigned weight labels, and the weights can be dynamically adjusted according to the driving mode. For example, in economy mode, the energy efficiency threshold weight is the highest (e.g. 0.6), the power indicator weight is lower (e.g. 0.2), the shift smoothness target weight is medium (e.g. 0.1), and the battery SOC safety range weight is the lowest (e.g. 0.1); in sports mode, the power indicator weight is the highest (e.g. 0.6), the energy efficiency threshold weight is lower (e.g. 0.2), the shift smoothness target weight is medium (e.g. 0.1), and the battery SOC safety range weight is the lowest (e.g. 0.1). The mode switching interface allows the driver to select different driving modes and dynamically adjust the weights through the software interface. For example, through the vehicle's central control system or driving mode switching button, the driver is allowed to select different driving modes, and after the driver presses the "economy mode" button, the system automatically adjusts the weight distribution to prioritize energy efficiency. The motor controller monitors the motor's output power and torque in real time, and sets the maximum power and torque as the power indicator. For example, assuming the goal is for the vehicle to respond quickly when accelerating, the power indicator can be set to have the motor output power reach 80% or more. Through the battery management system (BMS) and energy consumption calculation module, the upper limit of unit mileage energy consumption is set. For example, in economy mode, the energy efficiency threshold can be set to no more than 0.2 degrees of electricity per kilometer. Through the software algorithm of the transmission control unit (TCU), the shock degree and vibration frequency during shifting are calculated, and the shift smoothness indicator is set. For example, the goal is to have a shock degree of no more than 0.1g (g-force) during shifting. The BMS monitors the battery's remaining capacity (SOC) in real time to ensure it is within a safe range. For example, the battery SOC safety range is set to 20% to 90%, and when the SOC is below 20%, the system will prompt the driver to charge.

[0026] Based on the set gear ratio control target, the associated factors in the new energy vehicle structure and driving environment are analyzed. Among them, the new energy vehicle structure factors include motor parameters (rated power, rated torque, efficiency, etc.), battery parameters (battery capacity, energy density, charge and discharge characteristics, etc.), transmission parameters (number of gears, gear ratio, shift characteristics, etc.), vehicle mass (vehicle kerb mass, affecting power output and energy consumption). Driving environment factors include road slope (affecting vehicle power demand), speed limit (affecting vehicle operating mode), traffic conditions (frequent start-stop affecting energy consumption and shift frequency), driving habits (aggressive or moderate driving style affecting power output and energy consumption).

[0027] The parsed associated factors are constructed into an associated network graph by a software algorithm to clearly show the mutual relationship between the factors. For example, the nodes of the associated network graph include dynamic performance indicators, energy efficiency thresholds, shift smoothness targets, battery SOC safety ranges, motor parameters, battery parameters, gearbox parameters, road slopes, speed limits, etc. The relationship between the nodes includes: when the road slope increases, the weight of the dynamic performance indicators increases, and the weight of the energy efficiency thresholds decreases; when the battery SOC approaches the lower limit, the weight of the shift smoothness target decreases to prioritize battery safety.

[0028] In a possible implementation, based on the gear ratio control target, the new energy vehicle structure and the driving environment associated factors are parsed, and an associated network graph is established. Step S100 further includes step S110. Based on the gear ratio control target, the hardware nodes and the environment nodes are analyzed from the vehicle power system relationship, the vehicle state relationship, the driver operation relationship, the environmental parameter influence relationship, and the energy supply relationship to determine the associated nodes. Specifically, the software algorithm is used to analyze the associated relationship of the vehicle power system, the vehicle state, the driver operation, the environmental parameter, and the energy supply. According to the analysis result, the hardware nodes and the environment nodes related to the gear ratio control target are determined. The vehicle power system nodes include the motor (the speed and torque output of the motor), the transmission (the current gear and gear ratio of the transmission), the tire (the torque and speed of the tire), etc. For example, the motor speed directly affects the output torque, the output torque further affects the tire torque, and finally affects the vehicle acceleration. The vehicle state nodes include the speed (the current driving speed of the vehicle), the acceleration (the acceleration or deceleration of the vehicle), the slope (the slope of the road where the vehicle is located), etc. For example, the speed and acceleration are key indicators for measuring the dynamic performance of the vehicle, and the slope affects the power demand of the vehicle. The driver operation nodes include the accelerator pedal (the depth of the accelerator pedal pressed by the driver), the brake pedal (the depth of the brake pedal pressed by the driver), the steering (the steering angle of the steering wheel), etc. For example, the accelerator pedal opening directly affects the power demand, and further affects the shift control strategy. The environmental nodes include the road slope (the slope of the current road), the traffic condition (the traffic congestion on the road), the road adhesion coefficient (the friction coefficient of the road), etc. For example, the road slope and the road adhesion coefficient affect the traction demand of the vehicle, and further affect the gear ratio adjustment. The energy system nodes include the battery SOC (the remaining capacity of the battery), the current (the charging and discharging current of the battery), the voltage (the voltage of the battery), etc. For example, the battery SOC directly affects the energy efficiency and power output of the vehicle, and the current and voltage are used to monitor the health status of the battery.

[0029] Step S120, according to the influence relationship between the associated nodes and the transmission ratio control target, edges between nodes are established, and the associated network graph is constructed. Specifically, edges between nodes are established through software algorithms according to the physical relationship or control influence between associated nodes. All nodes and edges are combined into a complete associated network graph.

[0030] For example, the motor speed influences the output torque through the torque controller, the output torque influences the tire torque through the transmission system, and the tire torque finally influences the vehicle acceleration. According to this influence relationship, the relationship of motor speed output torque tire torque vehicle acceleration can be established. For example, the accelerator pedal opening influences the power demand through the power management system, and the power demand adjusts the transmission ratio through the transmission control strategy. According to this influence relationship, the relationship of pedal opening power demand transmission control strategy can be established. For example, the road slope influences the traction demand through the power management system, and the traction demand adjusts the transmission ratio through the transmission control strategy. According to this influence relationship, the relationship of slope traction demand transmission ratio adjustment can be established.

[0031] In one possible implementation, according to the influence relationship between the associated nodes and the transmission ratio control target, edges between nodes are established, and step S120 further includes step S121, taking the matching regulation relationship of the transmission ratio as an intermediate transformation node, analyzing the transmission ratio matching regulation relationship between the associated nodes and the transmission ratio control target with respect to the intermediate transformation node, and establishing an edge attribute. Specifically, the matching regulation relationship of the transmission ratio is defined as an intermediate transformation node, such as a “transmission ratio adjustment strategy” or a “transmission ratio optimization module”, which is used to connect the associated nodes and the transmission ratio control target. For example, the intermediate transformation node is a software module responsible for calculating the optimal transmission ratio according to the input associated node data (such as vehicle speed, slope, battery SOC, etc.). The regulation relationship between the associated nodes and the transmission ratio control target is analyzed through a software algorithm, for example, when the vehicle speed increases, the transmission ratio needs to be adjusted to maintain power output; when the slope increases, the transmission ratio needs to be adjusted to provide more torque; and when the battery SOC is low, the transmission ratio needs to be adjusted to optimize energy consumption. According to the properties of the regulation relationship (such as linear, nonlinear, delay, etc.), an attribute is assigned to each edge. For example, if the edge attribute is a linear relationship, when the vehicle speed increases, the transmission ratio decreases linearly; if the edge attribute is a nonlinear relationship, when the slope increases, the transmission ratio increases nonlinearly; and if the edge attribute is a delay characteristic, when the battery SOC is low, the transmission ratio is adjusted with a delay to optimize energy consumption.

[0032] Step S122, according to the variable ratio control target, the intermediate transformation node, the association relationship of the associated node and the edge attribute, the edge between the nodes is established. Specifically, the edge between the nodes is established by software algorithm according to the associated node, the intermediate transformation node and the edge attribute. All nodes and edges are combined into a complete association network graph.

[0033] Step S200, based on the association network graph, multi-source sensors are arranged inside and outside the vehicle, and a sensing mapping relationship between the multi-source sensors and the monitoring target in the association network graph is established.

[0034] Specifically, a variety of sensors are arranged inside and outside the vehicle, including a vehicle speed sensor, a torque sensor, a battery SOC sensor, an environmental sensor (such as a camera, a radar), etc. Among them, the vehicle speed sensor is installed on the wheel, the vehicle speed is calculated through the wheel speed sensor, and the data is transmitted to the vehicle control unit (VCU). The torque sensor is installed on the motor output shaft, monitors the output torque of the motor, and transmits the data to the motor controller. The battery SOC sensor is integrated in the battery management system (BMS), which monitors the remaining capacity of the battery in real time, and transmits the data to the VCU. The environmental sensor is installed outside the vehicle, such as a camera and a radar, which monitors the road conditions, traffic signals and obstacles.

[0035] The sensors are mapped to the monitoring targets in the association network graph through a software algorithm, ensuring that the data of each sensor can be mapped to a specific monitoring target. For example, the vehicle speed sensor is mapped to the "vehicle speed" node in the association network graph, the torque sensor is mapped to the "power index" node, and the camera is mapped to the "road slope" node.

[0036] For example, during driving, the vehicle speed sensor monitors the vehicle speed of 60km / h, the torque sensor monitors the motor output torque of 200N·m, and the camera monitors the road slope in front of 10%. These sensor data are transmitted to the corresponding nodes through the sensing mapping relationship, and the vehicle control unit (VCU) dynamically adjusts the variable ratio according to these data.

[0037] Step S300, taking the variable ratio control target as a search engine, a path search is performed according to the association network graph and the sensing mapping relationship, and a matching influence relationship path is established.

[0038] Specifically, a path search algorithm (e.g., Dijkstra algorithm or A* algorithm) is used to search for the optimal path from the target of the gear ratio control to each monitoring target in the associated network graph. For example, the Dijkstra algorithm is used to search for the path from the "power indicator" to the "vehicle speed" and "torque". According to the path search result, the matching influence relationship path between each node is established. For example, the path search result shows that the vehicle speed and torque have a direct influence on the power indicator, while the road slope indirectly influences the power indicator through the vehicle speed.

[0039] For example, when the vehicle is climbing a slope, the path search algorithm finds that the vehicle speed and torque are the key factors affecting the power indicator, while the road slope indirectly influences the power indicator through the vehicle speed. The system establishes the matching influence relationship path according to these paths, ensuring that the vehicle speed and torque are adjusted first to meet the power indicator when climbing a slope.

[0040] Step S400, according to the data characteristics of each node in the matching influence relationship path and the target of the gear ratio control, a target function is established, and based on the target function, real-time multi-source perception data is combined to perform gear ratio control matching calculation, to obtain a matching gear ratio that satisfies the target of the gear ratio control and has the maximum target evaluation result, and the matching gear ratio is used for automobile gearbox gear ratio control.

[0041] Specifically, according to the data characteristics of each node in the matching influence relationship path and the target of the gear ratio control, a target function is established for optimization calculation. For example, the target function can be expressed as: Maximize f(x)=w1·power indicator+w2·energy efficiency threshold+w3·shift smoothness target+w4·battery SOC safety range, where w1, w2, w3, w4 are the weights of each target. An optimization algorithm (such as linear programming, genetic algorithm, etc.) is used to perform gear ratio control matching calculation to solve the target function and obtain the optimal gear ratio. According to the result of the optimization algorithm, the gear ratio of the gearbox is adjusted through the transmission control unit (TCU).

[0042] In a possible implementation, the target function is combined with real-time multi-source perception data for the calculation of the variable ratio control matching, and step S400 further includes step S410. When there are multiple matching influence relationship paths for the same variable ratio control target, the matching relationship trigger is performed according to the real-time perception data of the multiple matching influence relationship paths. Specifically, when there are multiple matching influence relationship paths, the data on the multiple matching influence relationship paths is monitored in real time by multi-source sensors (such as a vehicle speed sensor, a torque sensor, an environmental sensor, etc.). For example, path 1: vehicle speed, slope, battery SOC. Path 2: vehicle speed, traffic condition, battery SOC. Path 3: vehicle speed, road adhesion coefficient, battery SOC. According to the real-time perception data, the path that is most matched with the current working condition is selected. For example, when the vehicle is driving on an uphill road section, the perception data of path 1 (vehicle speed, slope, battery SOC) is more consistent with the current working condition, and therefore path 1 is triggered. When the vehicle is driving on a congested urban road, the perception data of path 2 (vehicle speed, traffic condition, battery SOC) is more consistent with the current working condition, and therefore path 2 is triggered.

[0043] Step S420, when the triggered matching influence relationship path is one, the matching influence relationship path is triggered according to the perception data, the variable ratio control matching parameter search is performed according to the target function, and the matching variable ratio is obtained. Specifically, when the triggered matching influence relationship path is one, the matching influence relationship path is triggered according to the triggered matching influence relationship path, and the variable ratio control matching parameter search is performed according to the target function. For example, it is assumed that the triggered path is path 1 (vehicle speed, slope, battery SOC), and the optimal variable ratio is calculated by searching according to the real-time perception data of path 1 (vehicle speed is 60 km / h, slope is 10%, and battery SOC is 70%) and combining the target function.

[0044] In a possible implementation, the matching relationship trigger is performed according to the real-time perception data of the multiple matching influence relationship paths, and step S400 further includes step S430. When multiple matching influence relationship paths are triggered, the relationship analysis is performed according to the real-time multi-source perception data and the multi-source sensing data fusion network, the matching influence relationship path with the greatest influence is selected as the execution path, and the verification path is set. Specifically, whether multiple matching influence relationship paths are triggered simultaneously is detected by a software algorithm, for example, it is assumed that path 1 (vehicle speed, slope, battery SOC) and path 2 (vehicle speed, traffic condition, battery SOC) are triggered simultaneously. The influence weight of each path is analyzed by the multi-source sensing data fusion network, for example, the weight of path 1 is 0.6 (the slope has a greater influence), and the weight of path 2 is 0.4 (the traffic condition has a smaller influence). The path with the greatest weight is selected as the execution path, and the other paths are set as the verification paths, for example, path 1 is selected as the execution path, and path 2 is set as the verification path.

[0045] Step S440, search the gear ratio control matching parameter according to the real-time sensing data of the execution path and the target function, and obtain a to-be-verified matching gear ratio. Specifically, search the gear ratio control matching parameter according to the real-time sensing data of the execution path and the target function. For example, using a linear programming algorithm, the to-be-verified matching gear ratio is calculated as 3.5 by combining the real-time sensing data and the target function.

[0046] Step S450, evaluate and verify the to-be-verified matching gear ratio by the target function according to the real-time sensing data of the verification path, and determine the matching gear ratio when the target evaluation requirement is met. Specifically, evaluate and verify the to-be-verified matching gear ratio by the target function according to the real-time sensing data of the verification path. For example, the evaluation result is that the power performance index meets the requirement, and the energy efficiency threshold is slightly high but still within the acceptable range. According to the evaluation result, it is decided whether to determine the matching gear ratio, that is, if the evaluation result meets the target evaluation requirement, the system determines that the matching gear ratio is 3.5, and if the evaluation result does not meet the requirement, the system will re-search the matching gear ratio.

[0047] In a possible implementation, the relationship is analyzed according to the real-time multi-source perception data and the multi-source sensor data fusion network, the matching influence relationship path with the greatest influence is selected as the execution path, and a verification path is set, and step S430 further includes step S431. According to the volatility of the real-time multi-source perception data, the consistency and volatility of the sensor data of each path are evaluated according to the multi-source sensor data fusion network, and the path with strong consistency and large volatility is selected as the execution path, wherein the volatility refers to the change amplitude of the data, and the consistency refers to whether the data conforms to the expected regularity. Specifically, the change amplitude of each sensor data on each path is calculated by a software algorithm. For example, path 1 (vehicle speed, slope, battery SOC): the vehicle speed data volatility is 10% (for example, the vehicle speed changes between 50-60 km / h), the slope data volatility is 5% (for example, the slope changes between 5%-10%), and the battery SOC volatility is 2% (for example, the SOC changes between 68%-70%). Path 2 (vehicle speed, traffic condition, battery SOC): the vehicle speed data volatility is 5%, the traffic condition data volatility is 15% (for example, the traffic congestion degree changes between slight congestion and heavy congestion), and the battery SOC volatility is 2%. Whether each sensor data on each path conforms to the expected regularity is evaluated by a software algorithm. For example, path 1: the vehicle speed and slope data conform to the expected regularity (the vehicle speed decreases when climbing and increases when descending), and the consistency score is 0.9. Path 2: the vehicle speed and traffic condition data conform to the expected regularity (the vehicle speed decreases when congested and increases when smooth), and the consistency score is 0.8. The path with strong consistency and large volatility is selected as the execution path. For example, the volatility score of path 1 is 0.6 (vehicle speed volatility 10%, slope volatility 5%), and the consistency score is 0.9. The volatility score of path 2 is 0.7 (traffic condition volatility 15%), and the consistency score is 0.8. After comprehensive evaluation, path 1 is selected as the execution path because it performs better in terms of volatility and consistency.

[0048] Step S432, after selecting the execution path, the error and the influence of the objective function of the remaining path are evaluated, and the matching influence relationship path with small error and large influence of the objective function is selected as the verification path. Specifically, the deviation between the actual value and the expected value of each sensor data on the remaining path is calculated by a software algorithm. For example, the error evaluation result of path 2 is: the vehicle speed error is 2% (the deviation between the actual vehicle speed and the expected vehicle speed), the traffic condition error is 3%, and the battery SOC error is 1%. The influence of the remaining path on the objective function is evaluated by a software algorithm. For example, the influence of path 2 on the objective function is evaluated as: the influence on the power performance index is 0.4, the influence on the energy efficiency threshold is 0.3, the influence on the shift smoothness target is 0.2, and the influence on the battery SOC safety range is 0.1. The path with small error and large influence on the objective function is selected as the verification path. For example, the error score of path 2 is 0.06 (vehicle speed error 2%, traffic condition error 3%, battery SOC error 1%), and the influence on the objective function is 0.7. After comprehensive evaluation, path 2 is selected as the verification path because it performs better in terms of error and influence on the objective function.

[0049] In a possible implementation, the real-time sensing data of the verification path is combined with the to-be-verified matching gear ratio to evaluate the verification through the target function, and then step S400 further includes step S460: when the target evaluation requirement is not met, the influence data of the gear ratio control target is calculated according to the weighted average of the multi-path real-time sensing data. Specifically, the to-be-verified matching gear ratio is evaluated and verified through the real-time sensing data of the verification path and the target function. For example, the verification path is path 2 (vehicle speed, traffic condition, battery SOC), the real-time sensing data is vehicle speed 60 km / h, traffic condition is congestion, and battery SOC is 70%. The to-be-verified matching gear ratio 3.5 is evaluated using the target function, and it is found that the energy efficiency threshold does not meet the requirement (the actual energy consumption is higher than the expectation). When the verification result does not meet the target evaluation requirement, the influence data of the gear ratio control target is calculated according to the weighted average of the multi-path real-time sensing data. For example, it is assumed that the real-time sensing data of path 1 (vehicle speed, slope, battery SOC) and path 2 (vehicle speed, traffic condition, battery SOC) is as follows: path 1: vehicle speed 60 km / h, slope 10%, battery SOC 70%. Path 2: vehicle speed 60 km / h, traffic condition is congestion, battery SOC 70%. The influence data of each path is calculated by weighting: the weight of path 1 is 0.6 (the slope has a greater influence), and the weight of path 2 is 0.4 (the traffic condition has a smaller influence). The weighted average result is calculated: dynamic performance index: 0.6*dynamic performance index 1+0.4*dynamic performance index 2; energy efficiency threshold: 0.6*energy efficiency threshold 1+0.4*energy efficiency threshold 2; shift smoothness target: 0.6*shift smoothness target 1+0.4*shift smoothness target 2; battery SOC safety range: 0.6*battery SOC safety range 1+0.4*battery SOC safety range 2.

[0050] Step S470: the matching gear ratio is determined by using the weighted average result. Specifically, the final matching gear ratio is determined according to the weighted average result by using an optimization algorithm. For example, the linear programming algorithm is used to perform optimization calculation according to the weighted average result (dynamic performance index, energy efficiency threshold, shift smoothness target, battery SOC safety range). It is assumed that the weighted average result is: dynamic performance index: 0.6*dynamic performance index 1+0.4*dynamic performance index 2=80%; energy efficiency threshold: 0.6*energy efficiency threshold 1+0.4*energy efficiency threshold 2=0.18 kWh / km; shift smoothness target: 0.6*shift smoothness target 1+0.4*shift smoothness target 2=0.08 g; battery SOC safety range: 0.6*battery SOC safety range 1+0.4*battery SOC safety range 2=70%. The optimization algorithm calculates that the final matching gear ratio is 3.2. The system adjusts the gear ratio to 3.2 according to the result of the optimization algorithm to meet the requirements of dynamic performance, energy efficiency, shift smoothness and battery SOC safety range.

[0051] In one possible implementation, the matching gear ratio is used for transmission ratio control of an automobile gearbox. The method further includes: tracking and monitoring the transmission control based on the matching gear ratio using multi-source sensors; verifying the gear ratio control target based on the tracking and monitoring multi-source sensor data to obtain control verification results; and using the control verification results as interactive data to calibrate and optimize the objective function or the matching gear ratio execution data.

[0052] Specifically, the TCU adjusts the gearbox gears based on the matching gear ratio determined by the optimization algorithm. For example, assuming the matching gear ratio determined by the optimization algorithm is 3.2, the TCU adjusts the gearbox to the corresponding gear. The vehicle's operating status after gearbox control is monitored in real time using multiple sensors (such as vehicle speed sensors, torque sensors, and battery SOC sensors). Software algorithms analyze the monitored data to verify whether the gear ratio control achieves the expected goals. For example, it verifies whether vehicle speed and torque meet the expected targets, whether energy consumption per unit mile is within the expected range, whether the shift shock is within the expected range, and whether the battery SOC is within the safe range. Control verification results are generated, recording whether each indicator of the objective function is met. For example, the power performance indicator meets the requirements, the energy efficiency threshold is slightly higher than expected but still within an acceptable range, the shift smoothness target meets the requirements, and the battery SOC safety range meets the requirements. The control verification results are fed back to the system as interactive data, and the objective function or matching gear ratio execution data is calibrated and optimized based on the interactive data. For example, if the energy efficiency threshold is slightly higher than expected, the system can adjust the energy efficiency weight in the objective function, giving it greater priority in subsequent optimizations. Alternatively, the system can adjust the execution data for matching the gear ratio, fine-tuning the gear ratio to optimize energy efficiency; for example, adjusting the gear ratio from 3.2 to 3.1 to further optimize energy efficiency. By tracking, monitoring, and verifying the control target, the system can evaluate the effectiveness of gear ratio control in real time and perform calibration and optimization based on the verification results, achieving closed-loop control and ensuring that the system can continuously optimize performance to adapt to different driving environments and operating conditions.

[0053] This application employs multi-sensor fusion technology to construct an associated network graph and establish sensor mapping relationships. It establishes matching influence relationship paths through path search and then combines objective functions with real-time multi-source sensing data to perform gear ratio control matching calculations. This solves the technical problems of poor accuracy and adaptability in the dynamic matching of gear ratios in existing new energy vehicles, and achieves the technical effect of improving the accuracy and adaptability of matching.

[0054] In the above text, refer to Figure 1 A multi-sensor fusion method for dynamic matching control of gearbox shift ratios according to embodiments of the present invention is described in detail. Next, reference will be made to... Figure 2A gearbox gear ratio dynamic matching control system based on multi-sensor fusion is described.

[0055] The gearbox gear ratio dynamic matching control system based on multi-sensor fusion according to the embodiment of the present application is used to solve the technical problem of poor accuracy and adaptability of the existing gearbox gear ratio dynamic matching of new energy vehicles, and achieve the technical effect of improving the accuracy and adaptability of matching. The gearbox gear ratio dynamic matching control system based on multi-sensor fusion comprises an associated network graph establishing module 10, a multi-source sensor layout module 20, a matching influence relationship path establishing module 30, and a gear ratio control matching calculation module 40.

[0056] The associated network graph establishing module 10 is used to set a gear ratio control target, analyze new energy vehicle structure and driving environment associated factors based on the gear ratio control target, and establish an associated network graph. The multi-source sensor layout module 20 is used to layout multi-source sensors inside and outside the vehicle based on the associated network graph, and establish a sensing mapping relationship between the multi-source sensors and the monitoring targets in the associated network graph. The matching influence relationship path establishing module 30 is used to take the gear ratio control target as a search engine, search a path according to the associated network graph and the sensing mapping relationship, and establish a matching influence relationship path. The gear ratio control matching calculation module 40 is used to establish an objective function according to the data characteristics of each node in the matching influence relationship path and the gear ratio control target, perform gear ratio control matching calculation based on the objective function combined with real-time multi-source sensing data, obtain a matching gear ratio that satisfies the gear ratio control target and has the largest target evaluation result, and perform vehicle gearbox gear ratio control using the matching gear ratio.

[0057] In the following, the specific configuration of the associated network graph establishing module 10 will be described in detail. As described above, the associated network graph establishing module 10 can further comprise a gear ratio control target setting unit for setting a gear ratio control target, wherein the gear ratio control target comprises a power index, an energy efficiency threshold, a gear shifting smoothness target, and a battery SOC safety range, and the gear ratio control target has a mode weight label.

[0058] The associated network graph establishing module 10 can further comprise a node association relationship analysis unit for analyzing the association relationship between hardware nodes and environment nodes based on the gear ratio control target, from the relationships of vehicle power systems, vehicle states, driver operations, environmental parameters, and energy supply, determining associated nodes, and a network graph construction unit for establishing edges between nodes according to the influence relationship between the associated nodes and the gear ratio control target, and constructing the associated network graph.

[0059] According to the influence relationship between the associated node and the gear ratio control target, the edge between the nodes is established, and the associated network graph construction unit can further include: an edge attribute establishment sub-unit for establishing the gear ratio matching regulation relationship as an intermediate transformation node, analyzing the gear ratio matching regulation relationship about the intermediate transformation node from the associated node to the gear ratio control target, and establishing edge attributes; an edge establishment sub-unit for establishing the edge between the nodes according to the association relationship of the gear ratio control target, the intermediate transformation node, and the associated node and the edge attributes thereof.

[0060] In the following, the specific configuration of the gear ratio control matching calculation module 40 will be described in detail. As described above, based on the target function combined with real-time multi-source perception data for gear ratio control matching calculation, the gear ratio control matching calculation module 40 can further include: a matching relationship triggering unit for triggering the matching relationship according to the real-time perception data of multiple matching influence relationship paths when there are multiple matching influence relationship paths for the same gear ratio control target; a gear ratio control matching parameter searching unit for searching the gear ratio control matching parameter according to the target function when the triggered matching influence relationship path is one, and obtaining the matching gear ratio.

[0061] According to the real-time perception data of multiple matching influence relationship paths, the matching relationship triggering unit can further include: a relationship analysis sub-unit for analyzing the relationship according to real-time multi-source perception data and multi-source sensor data fusion network when multiple matching influence relationships are triggered, selecting the matching influence relationship path with the greatest influence as the execution path, and setting the verification path; a to-be-verified matching gear ratio acquisition sub-unit for searching the gear ratio control matching parameter with the real-time perception data of the execution path and the target function, and obtaining the to-be-verified matching gear ratio; an evaluation verification sub-unit for evaluating and verifying the to-be-verified matching gear ratio with the real-time perception data of the verification path and the target function, and determining the matching gear ratio when the target evaluation requirement is met.

[0062] Wherein, according to real-time multi-source sensing data and multi-source sensing data fusion network, the relationship is analyzed, the matching influence relationship path with the greatest influence is selected as the execution path, and the verification path is set, and the relationship analysis subunit can further include: the execution path determination component is used for evaluating the consistency and volatility of the sensing data of each path based on the volatility of real-time multi-source sensing data according to the multi-source sensing data fusion network, and selecting the path with strong consistency and great volatility as the execution path, wherein the volatility refers to the data change amplitude, and the consistency refers to whether the data conforms to the expected regularity; the verification path determination component is used for selecting the error and the target function influence of the remaining path after selecting the execution path, and selecting the matching influence relationship path with small error and large target function influence as the verification path.

[0063] Wherein, the real-time sensing data of the verification path is combined with the to-be-verified matching gear ratio to evaluate and verify through the target function, and then the matching relationship triggering unit can further include: a weighted calculation subunit for performing weighted calculation on the influence data of the gear ratio control target according to the multi-path real-time sensing data when the target evaluation requirement is not met, to obtain a weighted average result; and a matching gear ratio determination subunit for determining the matching gear ratio by using the weighted average result.

[0064] Wherein, the matching gear ratio is used for automobile gearbox gear ratio control, and then the system can further include: a tracking monitoring module for tracking monitoring through the multi-source sensor based on the gearbox control of the matching gear ratio; a gear ratio control target verification module for performing gear ratio control target verification according to the tracking monitoring multi-source sensing data to obtain a control verification result; and a calibration optimization module for calibrating and optimizing the target function or the matching gear ratio execution data by taking the control verification result as interaction data.

[0065] The multi-sensor fusion gearbox gear ratio dynamic matching control system provided by the embodiments of the application can execute the multi-sensor fusion gearbox gear ratio dynamic matching control method provided by any embodiment of the application, and has the corresponding function modules and beneficial effects of the execution method.

[0066] Although various references are made in this application to certain modules in the system according to the embodiments of the application, however, any number of different modules can be used and run on the user terminal and / or server, and each unit and module included is only divided according to the functional logic, but is not limited to the above division, as long as the corresponding functions can be realized; in addition, the specific names of each functional unit are only for the convenience of mutual differentiation, and do not limit the protection scope of the application.

[0067] The foregoing DETAILED DESCRIPTION, including the above section titled "Detailed Description," is not to be taken as limiting the scope of the application. Various modifications, combinations, and equivalents can be apparent to those skilled in the art and can be made once the nature of the application is understood. Any modification, combination, or equivalent, which falls within the principles and the scope of the present application, is intended to be included in the present application. In some instances, the actions or steps can be performed in different order from those described herein, and still achieve desirable results. Additionally, the process depicted in the figures can not necessarily require the particular order shown or sequential order to achieve the desired results. In certain implementations, multitasking and parallel processing can be advantageous.

Claims

1. A method for dynamic matching control of transmission gear ratio by multi-sensor fusion, characterized in that, The application relates to a new energy vehicle transmission ratio control method. The application comprises the following steps: Setting a transmission ratio control target, analyzing new energy vehicle structure and driving environment related factors based on the transmission ratio control target, and establishing a related network diagram; Based on the related network diagram, multiple source sensors are arranged inside and outside the vehicle, and a sensing mapping relationship between the multiple source sensors and the monitoring target in the related network diagram is established; The transmission ratio control target is used as a search engine, path searching is performed according to the related network diagram and the sensing mapping relationship, a matching influence relationship path is established, and a target function is established according to the data characteristics of each node in the matching influence relationship path and the transmission ratio control target; Based on the target function and real-time multi-source sensing data, transmission ratio control matching calculation is performed, a matching transmission ratio that meets the transmission ratio control target and has the largest target evaluation result is obtained, and the matching transmission ratio is used for vehicle transmission ratio control; When there are multiple matching influence relationship paths for the same transmission ratio control target, real-time sensing data of the multiple matching influence relationship paths is used for matching relationship triggering; When there is only one matching influence relationship path, the matching influence relationship path is triggered according to the sensing data, transmission ratio control matching parameter searching is performed according to the target function, and the matching transmission ratio is obtained; When multiple matching influence relationship paths are triggered, relationship analysis is performed according to real-time multi-source sensing data and a multi-source sensing data fusion network, the matching influence relationship path with the largest influence is selected as an execution path, and a verification path is set; Real-time sensing data of the execution path and the target function are used for transmission ratio control matching parameter searching, and a matching transmission ratio to be verified is obtained; Real-time sensing data of the verification path and the matching transmission ratio to be verified are used for evaluation verification through the target function, and when the target evaluation requirement is met, the matching transmission ratio is determined; Based on the fluctuation of real-time multi-source sensing data, the consistency and fluctuation of sensing data of each path are evaluated according to the multi-source sensing data fusion network, and the path with large fluctuation and strong consistency is selected as the execution path, wherein the fluctuation refers to the data change amplitude, and the consistency refers to whether the data conforms to the expected regularity; After the execution path is selected, the error of the remaining paths and the influence of the target function are evaluated, and the matching influence relationship path with small error and large target function influence is selected as the verification path; After evaluation verification through the target function, the following steps are further included: When the target evaluation requirement is not met, the influence data of the transmission ratio control target is weighted and calculated according to the real-time sensing data of multiple paths, and a weighted average result is obtained; The matching transmission ratio is determined by using the weighted average result. The transmission ratio control target comprises a power index, an energy efficiency threshold, a gear shifting smoothness target and a battery SOC safety range, and the transmission ratio control target has a mode weight label.

2. The multi-sensor fusion-based dynamic gear ratio matching control method for a gearbox according to claim 1, characterized in that, ​ 3. The multi-sensor fusion-based dynamic gear ratio matching control method for a gearbox according to claim 2, characterized in that, Based on the gear ratio control target, the structure of a new energy vehicle, and the driving environment related factors are analyzed, and a related network graph is established, including: Based on the gear ratio control target, the hardware nodes, environmental nodes, and their related relationships are analyzed from the vehicle power system relationship, vehicle state relationship, driver operation relationship, environmental parameter influence relationship, and energy supply relationship, and the related nodes are determined; According to the influence relationship between the related nodes and the gear ratio control target, the edges between the nodes are established, and the related network graph is constructed.

4. The multi-sensor fusion-based dynamic gear ratio matching control method for a gearbox according to claim 3, characterized in that, According to the influence relationship between the related nodes and the gear ratio control target, the edges between the nodes are established, including: The matching and regulation relationship of the gear ratio is taken as an intermediate transformation node, the gear ratio matching and regulation relationship between the related nodes and the gear ratio control target about the intermediate transformation node is analyzed, and the edge attribute is established; According to the correlation and edge attribute of the gear ratio control target, intermediate transformation node, and related nodes, the edges between the nodes are established.

5. The multi-sensor fusion-based dynamic gear ratio matching control method for a gearbox according to claim 1, characterized in that, The matching gear ratio is used for vehicle gearbox gear ratio control, and then includes: Based on the matching gear ratio gearbox control, tracking monitoring is performed through multi-source sensors; According to the tracking monitoring multi-source sensor data, the gear ratio control target is verified, and the control verification result is obtained; The control verification result is taken as interaction data, and the data of the target function or matching gear ratio are calibrated and optimized.

6. A multi-sensor fusion-based gearbox gear ratio dynamic matching control system, characterized in that, The system is used to implement the multi-sensor fusion gearbox gear ratio dynamic matching control method of any one of claims 1-5, and the system includes: A related network graph establishment module is used to set a gear ratio control target, analyze the related factors of a new energy vehicle structure and driving environment based on the gear ratio control target, and establish a related network graph; A multi-source sensor layout module is used to layout multi-source sensors inside and outside the vehicle based on the related network graph, and establish a sensing mapping relationship between the multi-source sensors and the monitoring targets in the related network graph; A matching influence relationship path establishment module is used to take the gear ratio control target as a search engine, search a path according to the related network graph and sensing mapping relationship, and establish a matching influence relationship path; A gear ratio control matching calculation module is used to establish a target function according to the data characteristics of each node in the matching influence relationship path and the gear ratio control target, perform gear ratio control matching calculation based on the target function and real-time multi-source sensing data, obtain a matching gear ratio that satisfies the gear ratio control target and has the largest target evaluation result, and use the matching gear ratio for vehicle gearbox gear ratio control.

Images