Automatic parking control system and method for new energy automobile

Abstract

The invention provides an automatic parking control system and method for a new energy automobile, and the method comprises the steps: determining a response priority for triggering a parking scene under a current working condition according to a vehicle load, a slope angle and a driving motor state, and activating a motor braking module and a mechanical braking module in a braking system when the response priority exceeds a preset threshold value, brake attention of the motor brake module and the mechanical brake module during cooperative brake control is determined; when the control delay of the execution response of the parking control instruction exceeds a set threshold value, fuzzy fault-tolerant constraint is carried out on the execution cost of executing a redundant parking path in a braking system through the response priority of the parking triggering scene and the braking attention, and a fault-tolerant constraint condition for executing the redundant parking path is obtained; and the execution weight between the automatic parking logic and the redundant parking logic in the braking system is adjusted based on the fault-tolerant constraint condition. By adopting the scheme of the invention, the balanced distribution of the logic intervention proportion between the automatic parking logic and the redundant parking logic can be realized.

Description

Technical Field

[0001] This application relates to the field of automatic parking technology, and more specifically, to an automatic parking control system and method for new energy vehicles. Background Technology

[0002] With the continuous improvement of the intelligence level of new energy vehicles, automatic parking control, as an important function to ensure the stationary safety of the whole vehicle and cope with complex working conditions, has become one of the key indicators for measuring the active safety performance of vehicles. In order to meet the safety requirements of multi-working-condition adaptation, rapid response and system redundancy and fault tolerance, the automatic parking control method urgently needs to realize multi-source information fusion judgment, dynamic braking path allocation and adaptive adjustment of braking system, so as to ensure the stability and accuracy of parking operation in any environment.

[0003] Existing automatic parking systems generally employ static logic and single-parameter triggering methods in their condition perception and response strategy design to achieve parking control. For example, they may directly activate the braking device after the vehicle is on a slope based on the slope sensor, or determine whether parking conditions are met based on the stop status of the drive motor. However, such control mechanisms lack dynamic modeling of the coupling relationship between vehicle load status, slope environment, and drive system. They cannot achieve risk level identification and response priority determination based on multi-dimensional condition characteristics. Consequently, under non-steady-state conditions such as sudden slope changes, rapid load changes, and unstable motor braking performance, the automatic parking system struggles to adaptively adjust the braking path execution strategy. Furthermore, although some automatic parking systems are equipped with multi-path braking structures that combine motor braking and mechanical braking, they lack dynamic evaluation methods based on response performance differences during collaborative control and have not established an optimized allocation mechanism for the performance weights of different braking modules. This results in low efficiency of redundant path scheduling and insufficient execution reliability. When faced with sudden situations such as braking execution lag or main path failure, the automatic parking system cannot achieve efficient path switching and error suppression. Therefore, how to achieve a balanced distribution of the logic intervention ratio between automatic parking logic and redundant parking logic, thereby improving the response robustness of the automatic parking system under changing operating conditions, has become a challenge for the industry. Summary of the Invention

[0004] This application provides an automatic parking control system and method for new energy vehicles, which can achieve a balanced distribution of the logic intervention ratio between automatic parking logic and redundant parking logic.

[0005] In a first aspect, this application provides an automatic parking control method for new energy vehicles, comprising the following steps: Determine whether the target vehicle is in a parked state. If it is in a parked state, send a parking control command to the braking system of the target vehicle. The response priority for triggering the parking scenario under the current working condition is determined based on the target vehicle load, slope angle, and drive motor status. When the response priority exceeds the preset priority threshold, the motor braking module and mechanical braking module in the braking system are activated through the vehicle controller in the target vehicle, and the braking attention of the motor braking module and the mechanical braking module during coordinated braking control is determined. The execution response of the parking control command is dynamically monitored. When the control delay of the execution response exceeds a set threshold, the execution cost of executing the redundant parking path in the braking system is subject to fuzzy fault tolerance constraint based on the response priority of the parking scenario and the braking attention, so as to obtain the fault tolerance constraint condition for executing the redundant parking path. Based on the aforementioned fault-tolerant constraints, the execution weights between the automatic parking logic and the redundant parking logic in the braking system are dynamically coordinated and controlled.

[0006] Preferably, determining the response priority for triggering the parking scenario under the current operating condition based on the target vehicle load, slope angle, and drive motor status specifically includes: The parking torque requirement of the target vehicle is calculated based on the target vehicle load and the slope angle. The parking torque requirement and the drive motor status are matched with a preset priority mapping table to obtain the response priority for triggering the parking scenario under the current operating conditions.

[0007] Preferably, the load of the target vehicle is collected by a weighing sensor.

[0008] Preferably, the slope angle of the target vehicle's location is collected using a slope sensor.

[0009] Preferably, determining the braking attention of the motor braking module and the mechanical braking module during coordinated braking control specifically includes: Obtain braking response parameters of the motor braking module and the mechanical braking module under different test conditions. The braking response parameters include maximum braking force, response time and braking stability index. An attention weight model reflecting the performance differences of each braking module is constructed based on the attention mechanism and the braking response parameters. Based on the braking response parameters under the current operating conditions, the braking attention weight matrix of the motor braking module and the mechanical braking module under the current operating conditions is generated through the attention weight model. The braking attention of the motor braking module and the mechanical braking module during coordinated braking control is determined by the braking attention weight matrix.

[0010] Preferably, the execution response of the parking control command is dynamically monitored through the vehicle controller.

[0011] Preferably, when the execution response has a control delay exceeding a set threshold, it means that the time interval between the issuance of the parking control command and the completion of the braking system feedback exceeds the upper limit of the safety response time preset in the system.

[0012] Preferably, based on the response priority of the parking scenario and the braking attention, a fuzzy fault-tolerant constraint is applied to the execution cost of executing the redundant parking path in the braking system, resulting in the following specific fault-tolerant constraint conditions for executing the redundant parking path: Based on automatic parking test data, fuzzy membership modeling is performed on the execution cost of redundant parking paths in new energy vehicles, and then a set of fault-tolerant constraint rules is constructed. Based on the fuzzy reasoning mechanism, the fault tolerance constraint rule set is reasoned by combining the response priority of the parking scenario and the braking attention to obtain the fault tolerance constraint parameters of the redundant parking path. The execution boundary conditions of the redundant parking path under the current operating conditions are determined by the fault tolerance constraint parameters, thereby obtaining the fault tolerance constraint conditions for executing the redundant parking path.

[0013] Preferably, parking control commands are sent to the braking system in the target vehicle via the controller bus.

[0014] Secondly, this application provides an automatic parking control system for new energy vehicles, comprising: The judgment module is used to determine whether the target vehicle is in a parking state. If it is in the parking state, it sends a parking control command to the braking system in the target vehicle. The processing module is used to determine the response priority of triggering the parking scenario under the current working condition based on the target vehicle load, slope angle and drive motor status. When the response priority exceeds the preset priority threshold, the motor braking module and mechanical braking module in the braking system are activated through the vehicle controller in the target vehicle, and the braking attention of the motor braking module and mechanical braking module when performing coordinated braking control is determined. The processing module is also used to dynamically monitor the execution response of the parking control command. When the execution response has a control delay exceeding a set threshold, it performs fuzzy fault-tolerant constraints on the execution cost of executing the redundant parking path in the braking system based on the response priority of the parking scenario and the braking attention, and obtains the fault-tolerant constraint conditions for executing the redundant parking path. The execution module is used to dynamically coordinate and control the execution weights between the automatic parking logic and the redundant parking logic in the braking system based on the fault-tolerant constraints.

[0015] Thirdly, this application provides a computer device, the computer device including a memory and a processor, the memory storing code, and the processor being configured to acquire the code and execute the above-described automatic parking control method for new energy vehicles.

[0016] Fourthly, this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described automatic parking control method for new energy vehicles.

[0017] The technical solutions provided by the embodiments disclosed in this application have the following beneficial effects: In this embodiment, it is first determined whether the target vehicle is in a parking state. If it is in a parking state, a parking control command is sent to the braking system in the target vehicle. The response priority of triggering the parking scenario under the current working condition is determined based on the target vehicle load, slope angle, and drive motor status. When the response priority exceeds a preset priority threshold, the motor braking module and mechanical braking module in the braking system are activated through the vehicle controller in the target vehicle, and the braking attention of the motor braking module and the mechanical braking module during coordinated braking control is determined. The execution response of the parking control command is then dynamically monitored. When the execution response has a control delay exceeding a set threshold, the execution cost of executing the redundant parking path in the braking system is subject to fuzzy fault-tolerant constraints based on the response priority of the parking scenario and the braking attention, resulting in fault-tolerant constraints for executing the redundant parking path. Based on the fault-tolerant constraints, the execution weights between the automatic parking logic and the redundant parking logic in the braking system are dynamically coordinated and controlled.

[0018] Therefore, this application uses fuzzy fault-tolerant constraints on the execution cost of redundant parking paths in the braking system by triggering the response priority of the parking scenario and the braking attention, thus obtaining the fault-tolerant constraints for executing the redundant parking paths. Based on these fault-tolerant constraints, the execution weights between the automatic parking logic and the redundant parking logic in the braking system are dynamically coordinated and controlled. First, the response priority of triggering the parking scenario under the current working condition is determined according to the target vehicle load, slope angle, and drive motor status. Based on a working condition perception mechanism using multi-source information fusion, the coupling characteristics between complex road environments and vehicle operating states can be accurately characterized, enabling dynamic adjustment of parking trigger conditions and effectively improving the accuracy of working condition identification. Then, the motor braking module and mechanical braking module in the braking system are activated by the on-board controller in the target vehicle, and the braking attention of the motor braking module and mechanical braking module during coordinated braking control is determined. If the response priority exceeds a preset threshold, the motor braking module and mechanical braking module are activated to work in parallel, and the attention mechanism is used to construct... A module performance difference model is established, and then braking attention evaluation is introduced into the braking cooperative control to obtain a performance weight allocation mechanism for the response capabilities of different braking paths. This fundamentally solves the drawbacks of rigid path selection and low scheduling efficiency in traditional braking systems. Finally, based on the response priority of the triggered parking scenario and the braking attention, fuzzy fault-tolerant constraints are applied to the execution cost of executing redundant parking paths in the braking system to obtain the fault-tolerant constraints for executing the redundant parking paths. When a delay occurs in the braking response, the scheme constructs an execution cost model of the redundant path through a fuzzy fault-tolerant modeling and reasoning mechanism, and dynamically generates the fault-tolerant constraints by combining the response priority and braking attention. This enables the braking path switching process to have scheduling adaptability to the current risk level and execution capability. Finally, the optimal allocation of redundant paths under the current operating conditions is achieved through an execution weight adjustment mechanism, effectively improving the stability and control accuracy of path switching. In summary, the scheme of this application can achieve a balanced allocation of the logic intervention ratio between automatic parking logic and redundant parking logic, thereby improving the control robustness of the automatic parking system. Attached Figure Description

[0019] Figure 1 This is an exemplary flowchart of an automatic parking control method for new energy vehicles according to some embodiments of this application; Figure 2 This is a flowchart illustrating the process of determining response priority according to some embodiments of this application; Figure 3 This is a flowchart illustrating the determination of fault-tolerant constraints according to some embodiments of this application; Figure 4 This is a schematic diagram of the structure of an automatic parking control system for new energy vehicles, according to some embodiments of this application; Figure 5 This is a schematic diagram of the structure of a computer device for implementing an automatic parking control method for new energy vehicles, according to some embodiments of this application. Detailed Implementation

[0020] To better understand the technical solution of this application, the technical solution of this application will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0021] refer to Figure 1 The figure is an exemplary flowchart of an automatic parking control method for new energy vehicles according to some embodiments of this application. The automatic parking control method 100 for new energy vehicles mainly includes the following steps: In step 101, it is determined whether the target vehicle is in a parking state. If it is in the parking state, a parking control command is sent to the braking system in the target vehicle.

[0022] It should be noted that the parking state in this application refers to the control trend of the target vehicle showing that the system is about to enter parking or stop under the current operating conditions. Its function is to serve as the triggering premise for parking control logic. By identifying state signals such as vehicle speed approaching zero, no acceleration operation, and shifting to parking-related gears, it ensures that the triggering of parking commands is based on the true intention, thereby avoiding erroneous actions and improving the safety and response accuracy of the control system.

[0023] In specific implementation, determining whether the target vehicle is in a parked state can be achieved in the following way: First, the vehicle control unit (VCU) continuously collects the vehicle's basic operating parameters, including the current vehicle speed, longitudinal acceleration, and brake pedal opening. It should be further noted that in this application, the current vehicle speed can be collected using wheel speed sensors, the longitudinal acceleration can be collected using an inertial measurement unit, and the brake pedal opening can be collected using a brake position sensor. Then, the onboard controller inputs the collected basic operating parameters into a logic module based on a rule-based judgment model. This logic module can judge item by item according to the following rules: 1. When the vehicle speed is below 0.3 km / h, where 0.3 km / h represents the normal stationary threshold; 2. And the longitudinal acceleration value is within [-0.1, 0.1] m / s². 2The jitter tolerance range; 3. And the brake pedal is not pressed down significantly, which is to avoid misjudging it as emergency braking; When the logic module performs rule judgment, if all three of the above conditions are met, the parking state is output as 1, where 1 indicates that the parking state is true; if any of the above three conditions are not met, the parking state is output as 0, where 0 indicates that the parking state is false; It should be noted that the judgment logic used in this application belongs to a common state fusion judgment framework. Its advantage is that it does not rely on complex prediction models and can make quick decisions only through real-time signal condition combinations. It is convenient to achieve high-frequency and low-latency operation in embedded systems, while ensuring that the recognition of driving intentions has high accuracy and interpretability, providing a reliable prerequisite for the accurate triggering of the subsequent parking control module.

[0024] It should be noted that the method of sending parking control commands to the braking system of the target vehicle in this application is usually that after the vehicle controller recognizes the parking state, it transmits the parking control commands to the braking execution module through the controller bus inside the vehicle. The commands are generated by the vehicle controller according to the current operating conditions, and the specific contents include the braking mode, control level and execution channel identifier. It should also be noted that the parking control commands in this application refer to the control signals used to activate the braking system to enter the parking holding state.

[0025] In step 102, the response priority for triggering the parking scenario under the current working condition is determined based on the target vehicle load, slope angle, and drive motor status. When the response priority exceeds a preset priority threshold, the motor braking module and mechanical braking module in the braking system are activated through the vehicle controller in the target vehicle, and the braking attention of the motor braking module and the mechanical braking module during coordinated braking control is determined.

[0026] In some embodiments, reference Figure 2 As shown in the figure, this is a flowchart illustrating the process of determining response priority in some embodiments of this application. In this embodiment, determining the response priority of triggering the parking scenario under the current operating condition based on the target vehicle load, slope angle, and drive motor status can be achieved through the following steps: In step 1021, the parking torque requirement of the target vehicle is calculated based on the target vehicle load and the slope angle. In step 1022, the parking torque requirement and the drive motor status are matched with a preset priority mapping table to obtain the response priority for triggering the parking scenario under the current operating conditions.

[0027] It should be noted that the slope angle in this application refers to the angle of inclination of the road where the target vehicle is currently located relative to the horizontal plane; the parking torque requirement in this application refers to the minimum braking torque that the braking system must provide to prevent slippage in order to keep the vehicle stationary under the current slope and load conditions; and the response priority in this application is an indicator that measures the urgency of the parking control system in prioritizing the allocation of braking resources under different operating conditions to ensure the safe parking of the vehicle.

[0028] It should also be noted that the slope angle of the target vehicle's location can be collected by a slope sensor in this application in the following ways: an inertial measurement unit (IMU) can be used to collect the slope angle of the road where the target vehicle is located in real time. In other embodiments, other types of sensors can also be used to collect the slope angle of the road where the vehicle is located, which is not specifically limited here. In this application, the load of the target vehicle is collected by a weighing sensor. In other embodiments, other types of sensors can also be used to collect the vehicle load, which is not specifically limited here.

[0029] In specific implementation, firstly, the parking torque requirement of the target vehicle can be calculated based on the target vehicle load and the slope angle in the following way: Combining the vehicle's current load information, which can be obtained through weighing sensors located on the chassis, the vehicle's total mass, gravitational acceleration, tire radius, and slope angle are used as inputs to the torque calculation formula. The required parking torque is calculated based on the static balance principle, and the calculated torque is used as the parking torque requirement. Then, the parking torque requirement and the drive motor status are matched with a preset priority mapping table to obtain the parking scenario triggered under the current operating conditions. The response priority can be implemented in the following way: read the current working state of the drive motor, such as whether there is regenerative braking capability and torque output capability, and then match the parking torque requirement, motor status, and current output torque of the motor with a preset response priority mapping table. The response priority mapping table is established by the vehicle manufacturer during the test calibration phase. It can divide various combined working conditions into different response levels based on simulation or measured working condition data. Finally, the parking response priority corresponding to the current working condition is output from the matching result, and the parking response priority is used as the response priority for triggering the parking scenario under the current working condition.

[0030] It should be noted that the preset priority threshold in this application refers to a critical value under a set of weighted scores used to determine whether the coordinated parking brake needs to be activated. It represents whether there is sufficient danger or necessity for parking under the current working condition to trigger the parking control logic. This priority threshold can be set through simulation analysis and real vehicle test data during the system design phase. The specific setting method includes: first, based on a large amount of typical working condition data, such as different combinations of load, slope, and motor state, a priority scoring model is constructed. The priority scoring model can adopt a weighted linear combination method. Then, the vehicle stability index corresponding to different score values ​​is verified through experiments. The vehicle stability index in this application is specifically the slip distance. The lowest score that causes obvious slip or instability is set as the trigger threshold, which is the priority threshold in this application.

[0031] In some embodiments, when the response priority exceeds a preset priority threshold, the activation of the motor braking module and mechanical braking module in the braking system by the vehicle controller in the target vehicle can be achieved in the following manner: after the vehicle controller receives the response priority, it compares the response priority with the preset priority threshold stored in the control strategy module. When the response priority value is higher than the preset priority threshold, the vehicle controller sends a reverse torque command to the drive motor controller through the controller bus to realize motor braking output. The vehicle controller issues a braking execution command to the electronic parking brake system to control the drive motor of the electronic parking brake system to drive the brake caliper to clamp the brake disc and realize mechanical braking.

[0032] In some embodiments, determining the braking attention of the electric braking module and the mechanical braking module during coordinated braking control can be achieved through the following steps: Obtain braking response parameters of the motor braking module and the mechanical braking module under different test conditions. The braking response parameters include maximum braking force, response time and braking stability index. An attention weight model reflecting the performance differences of each braking module is constructed based on the attention mechanism and the braking response parameters. Based on the braking response parameters under the current operating conditions, the braking attention weight matrix of the motor braking module and the mechanical braking module under the current operating conditions is generated through the attention weight model. The braking attention of the motor braking module and the mechanical braking module during coordinated braking control is determined by the braking attention weight matrix.

[0033] It should be noted that the braking stability index in this application refers to the smoothness of the braking force output during the braking process, which is measured by the degree of change in braking force fluctuation during the braking process; the braking attention weight matrix in this application refers to the weight distribution structure that reflects the relative importance and participation of the motor braking and mechanical braking modules in different control stages; and the braking attention in this application is an index that measures the degree of contribution of each braking module to the braking effect in the coordinated control.

[0034] In practical implementation, firstly, the braking response parameters of the motor braking module and the mechanical braking module under different test conditions, including maximum braking force, response time, and braking stability indicators, can be obtained in the following way: Multiple representative test conditions can be pre-designed, including different vehicle loads, slope angles, and ambient temperatures, to cover typical scenarios in actual use. Then, using a braking test bench or actual vehicle testing equipment, braking commands are applied to the motor braking module and the mechanical braking module respectively, and braking response data is collected in real time, including the magnitude of the braking force output, the response time from the issuance of the command to the braking force reaching a stable value, and the force fluctuation during the braking process. The braking stability indicator can be obtained by collecting wheel slip ratio change data and calculating its standard deviation as a volatility quantification indicator. After data acquisition, noise is removed through filtering and signal processing techniques to obtain... To obtain accurate maximum braking force, response time, and stability indicators, all test data are categorized and organized according to operating conditions, establishing a database containing performance parameters of the two braking modules under each test condition. Secondly, an attention-weighted model reflecting the performance differences of each braking module is constructed based on the attention mechanism and the aforementioned braking response parameters. This can be achieved as follows: Braking response parameters of the motor braking and mechanical braking modules are extracted from the established multi-condition performance database, including the maximum braking force, response time, and braking stability indicators after Z-score standardization. These parameters form two performance feature vectors, which are then input into a shared feedforward neural network scoring function. A common structure is a two-layer fully connected network; the first layer is used for feature compression, and the second layer outputs the performance score of each module. The activation function can be a rectified linear unit (RCU). To enhance nonlinear expression, the two scoring results are further input into the Softmax function for normalization, resulting in the relative attention weights of the two modules under the current operating condition. Finally, the weight coefficients of the two modules are combined to form a two-dimensional attention matrix, with each row corresponding to a braking module and each column representing the attention distribution for different control objectives. This two-dimensional attention matrix is ​​used as the attention weight model. Then, combined with the braking response parameters under the current operating condition, the braking attention weight matrix of the motor braking module and the mechanical braking module under the current operating condition can be generated through the attention weight model in the following way: The braking response parameters (including maximum braking force, response time, and braking stability index) of the motor braking and mechanical braking modules collected under the current operating condition can be constructed into normalized feature vectors and input into the aforementioned attention weight model. The attention weight model scores the performance of the two modules through a feedforward neural network, and then normalizes them through the Softmax function to obtain the attention weight coefficients of the two under the current operating condition. The weight results are then arranged in a structured manner according to the control task requirements to generate a two-dimensional braking attention weight matrix.Finally, determining the braking attention of the motor braking module and the mechanical braking module during coordinated braking control using the braking attention weight matrix can be achieved in the following way: the braking attention weight matrix can be used as the braking attention of the motor braking module and the mechanical braking module during coordinated braking control.

[0035] It should be noted that the attention weight model in this application refers to a parameterized mapping structure built on the attention mechanism to quantify the performance differences of different braking modules. Its technical principle is to take the braking response parameters (including maximum braking force, response time and braking stability index) of the electric motor braking and mechanical braking modules under different working conditions as input features, score the performance of each module through scoring functions such as feedforward neural networks, and then use the Softmax function to normalize the scores to generate a weight distribution, thereby forming an attention weight model that reflects the relative superiority or inferiority of the module performance. This attention weight model can dynamically infer the current performance parameters in actual working conditions and output the attention weight results of the two modules (including the electric motor braking module and the mechanical braking module) to guide the subsequent braking force distribution and cooperative control strategy formulation.

[0036] In step 103, the execution response of the parking control command is dynamically monitored. When the control delay of the execution response exceeds a set threshold, the execution cost of executing the redundant parking path in the braking system is subject to fuzzy fault-tolerant constraints based on the response priority of the parking scenario and the braking attention, thereby obtaining the fault-tolerant constraint conditions for executing the redundant parking path.

[0037] In some embodiments, dynamic monitoring of the execution response of the parking control command can be achieved by the following method: the status signals of the motor braking and mechanical braking modules can be read in real time through the execution feedback detection module built into the vehicle controller, and the time difference between the issuance of the command and the actual execution can be dynamically monitored in combination with a timer.

[0038] It should be noted that when the execution response has a control delay exceeding the set threshold, it means that the time interval between the issuance of the parking control command and the completion of the braking system feedback exceeds the upper limit of the safety response time preset in the system; it should be further noted that the threshold in this application can be set according to actual test data, which will not be elaborated here.

[0039] In some embodiments, reference Figure 3 As shown in the figure, this is a flowchart illustrating the determination of fault-tolerant constraints in some embodiments of this application. In this embodiment, based on the response priority of the parking scenario and the braking attention, fuzzy fault-tolerant constraints are applied to the execution cost of executing the redundant parking path in the braking system. The fault-tolerant constraints for executing the redundant parking path can be obtained by the following steps: In step 1031, the execution cost of redundant parking paths in new energy vehicles is modeled using fuzzy membership based on automatic parking test data, thereby constructing a set of fault-tolerant constraint rules. In step 1032, the fault-tolerant constraint rule set is inferred based on the fuzzy reasoning mechanism, combined with the response priority of the triggered parking scenario and the braking attention, to obtain the fault-tolerant constraint parameters of the redundant parking path. In step 1033, the execution boundary conditions of the redundant parking path under the current operating conditions are determined by the fault tolerance constraint parameters, thereby obtaining the fault tolerance constraint conditions for executing the redundant parking path.

[0040] It should be noted that, in this application, execution cost refers to a quantitative evaluation index of system performance loss and control delay caused by redundant parking paths completing parking tasks under specific operating conditions; the fault tolerance constraint rule set in this application is a set of fuzzy logic rules used to describe the variation law of execution cost of redundant parking paths under different operating conditions; the fault tolerance constraint parameter in this application is a quantitative control index used to limit the acceptable execution range of redundant parking paths; and the fault tolerance constraint condition in this application refers to the set of executable boundary conditions jointly limited by the fault tolerance constraint parameters of each redundant parking path under the current operating condition.

[0041] In specific implementation, firstly, based on the automatic parking test data, fuzzy membership modeling is performed on the execution cost of redundant parking paths in new energy vehicles, and then a fault-tolerant constraint rule set is constructed. This can be achieved through the following steps: collecting actual parking response data of the test vehicle under different working conditions through automatic parking tests. The different working conditions in this application specifically include different slope angles, different loads, and different parking speeds. The parking response data specifically includes key indicators such as braking response time, path yaw, and braking deceleration of the redundant parking paths corresponding to motor braking, electronic parking braking, and hydraulic master cylinder. Furthermore, the system combines vehicle state parameters (including slope, load, and motor operating status) to extract the contact points under each working condition. The response priority in parking scenarios and the braking attention of the motor braking module and the mechanical braking module during coordinated braking control are analyzed. Based on these test data, fuzzy membership functions are established, and the execution costs of different paths are modeled as fuzzy sets. Execution costs include, for example, delay risk and energy consumption burden. A fuzzy C-means clustering algorithm is used to classify the execution costs into three levels: "low," "medium," and "high." A fault-tolerant constraint rule base is constructed, where each rule is written into the fuzzy controller logic in IF-THEN format. It should be further noted that the specific rule format in this application is: IF (priority, high) AND (attention, low) THEN (execution cost, high). Secondly, based on the fuzzy inference mechanism, the fault-tolerant constraint rule set is inferred by combining the response priority of the parking scenario and the braking attention. The fault-tolerant constraint parameters of the redundant parking path can be obtained in the following way: the fault-tolerant constraint rule set is used as the fuzzy inference rule base of the Mamdani model, and the response priority and braking attention under the current parking condition are used as the input variables of the Mamdani model. The membership degree of the input variables in each fuzzy set is calculated through the membership function of the input variables. The fuzzy inference engine activates all rules that meet the conditions according to the min-max synthesis method to obtain the execution cost (high / medium / low) of each type in the output fuzzy set. The comprehensive membership distribution of the redundant parking path is obtained and defuzzified using the centroid method. The output result is used as the fault tolerance constraint parameter of the redundant parking path. Then, the execution boundary condition of the redundant parking path under the current working condition is determined by the fault tolerance constraint parameter. The fault tolerance constraint condition for executing the redundant parking path can be implemented in the following way: The fault tolerance constraint parameter of the redundant parking path is input into the multi-objective boundary modeling module. Based on the intersection of path performance and fault tolerance requirements, the execution boundary condition of the redundant parking path under the current working condition is determined, and the execution boundary condition is used as the fault tolerance constraint condition of the current working condition. The fault tolerance constraint condition can be used for the path weight allocation control of the parking controller.It should be further explained that the multi-objective boundary modeling module in this application refers to constructing a set of feasible solution boundaries that satisfy the trade-offs between different performance requirements, based on the quantified fault-tolerance constraint parameters corresponding to redundant parking paths. Its core technical principle is based on multi-objective optimization and Pareto optimality theory. The multi-objective boundary modeling module uses the fault-tolerance constraint parameters of redundant parking paths (including response delay and braking intensity) as optimization variables, searches for the optimal solution set in the solution space using a non-dominated sorting genetic algorithm (such as NSGA-II), and generates a Pareto front that is not simultaneously superior to any other solution. Each solution represents an optimal boundary combination for the execution of redundant parking paths under the current operating conditions. Ultimately, this is used to determine which solution sets can be enabled for safe fault tolerance under the current conditions, achieving fine-grained fault-tolerance screening of redundant parking paths.

[0042] It should be noted that, compared to existing automatic parking technologies where redundant parking path activation strategies rely on preset rules or fixed priorities, making it difficult to achieve targeted control under complex dynamic conditions, this application's solution addresses the lack of real-time adaptability and condition differentiation in redundant parking path selection in existing technologies through a fuzzy modeling mechanism based on response priority and braking attention. By constructing a fault-tolerant constraint rule set and a fuzzy inference system, the execution costs of different redundant parking paths are dynamically evaluated, further resolving the technical difficulties of unquantifiable execution path performance boundaries and the inability to integrate multi-objective trade-offs. By establishing path execution boundary conditions in conjunction with fault-tolerant constraint parameters, the system can determine and schedule path combinations such as motor braking priority, mechanical braking backup, and delayed parking lock activation, effectively improving the system's fault tolerance and stability under abnormal conditions such as steep slopes, high latency, or insufficient braking power.

[0043] In step 104, the execution weights between the automatic parking logic and the redundant parking logic in the braking system are dynamically coordinated and controlled based on the fault-tolerant constraints.

[0044] In some embodiments, the dynamic coordination control of the execution weights between the automatic parking logic and the redundant parking logic in the braking system based on the fault-tolerant constraints can be achieved by the following steps: The target execution weight of the redundant parking path in the braking system is determined based on the aforementioned fault-tolerant constraints. The execution weights of the redundant parking paths in the braking system are adjusted by the target execution weights, thereby achieving coordinated control of the execution weights between the automatic parking logic and the redundant parking logic in the braking system.

[0045] It should be noted that the target execution weight in this application refers to the reference priority control parameter allocated to each parking execution module to achieve optimal coordination control and execution efficiency among redundant parking paths under the current fault tolerance constraints.

[0046] In specific implementation, determining the target execution weight of the redundant parking path in the braking system based on the fault-tolerant constraints can be achieved in the following way: First, initialize a weight adjustment model for adjusting the weights of each module in the redundant parking path. Use the fault-tolerant constraints as input parameters of the weight adjustment model. Compare the standard fault-tolerant constraint parameters trained in the weight adjustment model with the input fault-tolerant constraints. Output the adjusted execution weights through the weight adjustment model and use the adjusted execution weights as the target execution weights of the redundant parking path. It should be further noted that the weight adjustment model in this application can be based on the supervised regression mechanism in machine learning. Typically, a support vector regression algorithm can be used to construct the model framework. During the training phase, the weight adjustment model uses historical data... The fault-tolerant constraint parameters extracted from the automatic parking test data are used as input, and the optimal execution weight distribution under different working conditions is used as output to complete the learning of the mapping relationship. In actual operation, the real-time fault-tolerant constraints are input, and the weight adjustment model can output the target weight of the path that conforms to the current working condition by performing vectorized comparison and nonlinear mapping with the standard features learned during the training process. This output weight reflects the execution priority of the redundant path under the current fault tolerance capability, which can realize the dynamic optimization of path scheduling. The execution weight of the redundant parking path in the braking system can be adjusted by means of the target execution weight, that is, the target execution weight can be used as the execution weight of the redundant parking path in the braking system, and finally realize the coordinated control of the execution weight between the automatic parking logic and the redundant parking logic in the braking system.

[0047] On the other hand, in some embodiments, this application provides an automatic parking control system for new energy vehicles, with reference to... Figure 4 The figure is a schematic diagram of the structure of an automatic parking control system for new energy vehicles according to some embodiments of this application. The automatic parking control system 400 for new energy vehicles includes: a judgment module 401, a processing module 402, and an execution module 403, which are described below: The judgment module 401 in this application is mainly used to determine whether the target vehicle is in a parking state. If it is in the parking state, a parking control command is sent to the braking system in the target vehicle. The processing module 402 in this application is used to determine the response priority of triggering the parking scenario under the current working condition based on the target vehicle load, slope angle and drive motor status. When the response priority exceeds the preset priority threshold, the motor braking module and mechanical braking module in the braking system are activated through the vehicle controller in the target vehicle, and the braking attention of the motor braking module and the mechanical braking module when performing coordinated braking control is determined. In this application, the processing module 402 is also used to dynamically monitor the execution response of the parking control command. When the execution response has a control delay exceeding a set threshold, the execution cost of executing the redundant parking path in the braking system is subject to fuzzy fault tolerance constraint based on the response priority of the parking scenario and the braking attention, so as to obtain the fault tolerance constraint condition for executing the redundant parking path. The execution module 403 in this application is mainly used to dynamically coordinate and control the execution weights between the automatic parking logic and the redundant parking logic in the braking system based on the fault-tolerant constraints.

[0048] In addition, this application also provides a computer device, which includes a memory and a processor. The memory stores code, and the processor is configured to acquire the code and execute the above-described automatic parking control method for new energy vehicles.

[0049] In some embodiments, reference Figure 5 The figure is a schematic diagram of the structure of a computer device implementing an automatic parking control method for new energy vehicles, according to some embodiments of this application. The automatic parking control method for new energy vehicles in the above embodiments can be implemented through... Figure 5 The computer device shown is used to implement this, and the computer device 500 includes at least one processor 501, a communication bus 502, a memory 503, and at least one communication interface 504.

[0050] Processor 501 can be a general-purpose central processing unit (CPU) or an application-specific integrated circuit (ASIC).

[0051] The communication bus 502 can be used to transmit information between the aforementioned components.

[0052] Memory 503 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CDROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital versatile optical discs, Blu-ray discs, etc.), magnetic disks or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto. Memory 503 may exist independently and be connected to processor 501 via communication bus 502. Memory 503 may also be integrated with processor 501.

[0053] The memory 503 stores program code for executing the solution of this application, and its execution is controlled by the processor 501. The processor 501 executes the program code stored in the memory 503. The program code may include one or more software modules. The automatic parking control method for new energy vehicles in the above embodiments can be implemented by the processor 501 and one or more software modules in the program code in the memory 503.

[0054] Communication interface 504 uses any transceiver-like device to communicate with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.

[0055] In a specific implementation, as one example, a computer device may include multiple processors, each of which may be a single-core (single CPU) processor or a multi-core (multi CPU) processor. Here, a processor may refer to one or more devices, circuits, and / or processing cores used to process data (e.g., computer program instructions).

[0056] The aforementioned computer device can be a general-purpose computer device or a special-purpose computer device. In specific implementations, the computer device can be a desktop computer, a portable computer, a network server, a handheld digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device, or an embedded device. This application does not limit the type of computer device.

[0057] In addition, this application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described automatic parking control method for new energy vehicles.

[0058] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.

[0059] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. An automatic parking control method for new energy vehicles, characterized in that, Includes the following steps: Determine whether the target vehicle is in a parked state. If it is in a parked state, send a parking control command to the braking system of the target vehicle. The response priority for triggering the parking scenario under the current working condition is determined based on the target vehicle load, slope angle, and drive motor status. When the response priority exceeds the preset priority threshold, the motor braking module and mechanical braking module in the braking system are activated through the vehicle controller in the target vehicle, and the braking attention of the motor braking module and the mechanical braking module during coordinated braking control is determined. The execution response of the parking control command is dynamically monitored. When the control delay of the execution response exceeds a set threshold, the execution cost of executing the redundant parking path in the braking system is subject to fuzzy fault tolerance constraint based on the response priority of the parking scenario and the braking attention, so as to obtain the fault tolerance constraint condition for executing the redundant parking path. Based on the aforementioned fault-tolerant constraints, the execution weights between the automatic parking logic and the redundant parking logic in the braking system are dynamically coordinated and controlled.

2. The method as described in claim 1, characterized in that, The response priority for triggering the parking scenario under the current operating conditions is determined based on the target vehicle load, slope angle, and drive motor status. Specifically, this includes: The parking torque requirement of the target vehicle is calculated based on the target vehicle load and the slope angle. The parking torque requirement and the drive motor status are matched with a preset priority mapping table to obtain the response priority for triggering the parking scenario under the current operating conditions.

3. The method as described in claim 1, characterized in that, The load of the target vehicle is collected by a weighing sensor.

4. The method as described in claim 1, characterized in that, The slope angle of the target vehicle's location is collected using a slope sensor.

5. The method as described in claim 1, characterized in that, Determining the braking attention of the motor braking module and the mechanical braking module during coordinated braking control specifically includes: Obtain braking response parameters of the motor braking module and the mechanical braking module under different test conditions. The braking response parameters include maximum braking force, response time and braking stability index. An attention weight model reflecting the performance differences of each braking module is constructed based on the attention mechanism and the braking response parameters. Based on the braking response parameters under the current operating conditions, the braking attention weight matrix of the motor braking module and the mechanical braking module under the current operating conditions is generated through the attention weight model. The braking attention of the motor braking module and the mechanical braking module during coordinated braking control is determined by the braking attention weight matrix.

6. The method as described in claim 1, characterized in that, The vehicle controller dynamically monitors the execution response of the parking control commands.

7. The method as described in claim 1, characterized in that, When the execution response has a control delay exceeding a set threshold, it means that the time interval between the issuance of the parking control command and the completion of the braking system feedback exceeds the upper limit of the safety response time preset in the system.

8. The method as described in claim 1, characterized in that, Based on the response priority of the parking scenario and the braking attention, a fuzzy fault-tolerant constraint is applied to the execution cost of executing the redundant parking path in the braking system. The specific fault-tolerant constraint conditions for executing the redundant parking path include: Based on automatic parking test data, fuzzy membership modeling is performed on the execution cost of redundant parking paths in new energy vehicles, and then a set of fault-tolerant constraint rules is constructed. Based on the fuzzy reasoning mechanism, the fault tolerance constraint rule set is reasoned by combining the response priority of the parking scenario and the braking attention to obtain the fault tolerance constraint parameters of the redundant parking path. The execution boundary conditions of the redundant parking path under the current operating conditions are determined by the fault tolerance constraint parameters, thereby obtaining the fault tolerance constraint conditions for executing the redundant parking path.

9. The method as described in claim 1, characterized in that, Parking control commands are sent to the braking system in the target vehicle via the controller bus.

10. An automatic parking control system for new energy vehicles, characterized in that, include: The judgment module is used to determine whether the target vehicle is in a parking state. If it is in the parking state, it sends a parking control command to the braking system in the target vehicle. The processing module is used to determine the response priority of triggering the parking scenario under the current working condition based on the target vehicle load, slope angle and drive motor status. When the response priority exceeds the preset priority threshold, the motor braking module and mechanical braking module in the braking system are activated through the vehicle controller in the target vehicle, and the braking attention of the motor braking module and mechanical braking module when performing coordinated braking control is determined. The processing module is also used to dynamically monitor the execution response of the parking control command. When the execution response has a control delay exceeding a set threshold, it performs fuzzy fault-tolerant constraints on the execution cost of executing the redundant parking path in the braking system based on the response priority of the parking scenario and the braking attention, and obtains the fault-tolerant constraint conditions for executing the redundant parking path. The execution module is used to dynamically coordinate and control the execution weights between the automatic parking logic and the redundant parking logic in the braking system based on the fault-tolerant constraints.

Images