Vehicle control method and device, vehicle and storage medium

Abstract

The invention discloses a vehicle control method and device, a vehicle and a storage medium, and relates to the technical field of vehicles. The method comprises the following steps: determining an optimization parameter group in a plurality of initialization parameter groups of a back propagation BP neural network in a vehicle speed control system through a global optimization algorithm; determining a vehicle speed error according to the target vehicle speed and the actual vehicle speed of the vehicle, updating the optimization parameter group through a back propagation vehicle speed error until an iteration condition is met, and obtaining a target BP neural network; and the real-time speed of the vehicle is adjusted according to the vehicle speed adjustment amount output by the target PID controller optimized by the target BP neural network until the real-time speed reaches the target vehicle speed. According to the technical scheme, the real-time speed of the vehicle is adjusted according to the vehicle speed adjustment amount determined by the target PID controller optimized by the target BP neural network obtained through global optimization and network optimization, real-time accurate adjustment of the vehicle speed is achieved, and then accurate control over the vehicle is achieved.

Description

Technical Field

[0001] The present invention relates to the field of vehicle technology, and in particular to a vehicle control method, device, vehicle, and storage medium. Background Technology

[0002] Vehicle speed control has always been a hot topic in the field of autonomous driving. Due to the inability to build accurate vehicle models, the simulation of the longitudinal motion of vehicles is not accurate enough. Furthermore, the driving scenarios faced by vehicles on urban roads are extremely complex and varied, making speed control a difficult problem that needs to be solved.

[0003] In existing technologies, vehicle speed is typically controlled in real time using traditional proportional-integral-derivative (PID) control. However, the control parameters for traditional PID control need to be obtained through trial and error, which can easily lead to overshoot, instability, and other results that degrade the control performance.

[0004] Therefore, there is an urgent need for a vehicle control method to achieve real-time and precise control of vehicle speed. Summary of the Invention

[0005] This invention provides a vehicle control method, device, vehicle, and storage medium to achieve real-time and precise adjustment of vehicle speed, thereby achieving precise control of the vehicle.

[0006] In a first aspect, embodiments of the present invention provide a vehicle control method, comprising:

[0007] Multiple initialization parameter sets are determined for the back propagation (BP) neural network in the vehicle speed control system. An optimized parameter set for the BP neural network is determined from each of the initialization parameter sets using a global optimization algorithm. The vehicle speed control system consisting of the optimized BP neural network corresponding to the optimized parameter set and the proportional-integral-derivative PID controller determined based on the optimized BP neural network has the minimum vehicle speed error. The input information of the BP neural network includes the vehicle speed error between the target vehicle speed and the actual vehicle speed, and the output information includes the control parameters of the PID controller.

[0008] The vehicle speed error is determined based on the target vehicle speed and the actual vehicle speed determined by the speed adjustment amount output by the optimized PID controller. The optimized PID controller is obtained by updating the control parameters of the PID controller using the optimized BP neural network.

[0009] The optimized parameter set of the optimized BP neural network is updated by backpropagating the vehicle speed error until the iteration condition is met, thus obtaining the target BP neural network.

[0010] The target PID controller is obtained by updating the control parameters of the optimized PID controller according to the target BP neural network. The real-time speed of the vehicle is adjusted according to the vehicle speed adjustment amount output by the target PID controller until the real-time speed reaches the target vehicle speed.

[0011] The technical solution of this invention provides a vehicle control method, comprising: determining multiple initialization parameter sets of a backpropagation BP neural network in a vehicle speed control system; determining an optimized parameter set of the BP neural network in each of the initialization parameter sets using a global optimization algorithm, wherein the vehicle speed control system composed of the optimized BP neural network corresponding to the optimized parameter set and the proportional-integral-derivative PID controller determined based on the optimized BP neural network has the minimum vehicle speed error; the input information of the BP neural network includes the vehicle speed error between the target vehicle speed and the actual vehicle speed, and the output information includes the control parameters of the PID controller; determining the vehicle speed error based on the actual vehicle speed determined by the target vehicle speed and the vehicle speed adjustment amount output by the optimized PID controller, wherein the optimized PID controller is obtained by updating the control parameters of the PID controller through the optimized BP neural network; updating the optimized parameter set of the optimized BP neural network by backpropagation of the vehicle speed error until the iteration condition is met to obtain a target BP neural network; updating the control parameters of the optimized PID controller based on the target BP neural network to obtain a target PID controller; adjusting the real-time speed of the vehicle based on the vehicle speed adjustment amount output by the target PID controller until the real-time speed reaches the target vehicle speed. The above technical solution firstly uses a global optimization algorithm to determine the optimal parameter set from multiple initial parameter sets of the backpropagation BP neural network, achieving initial optimization of the BP neural network. The resulting optimized BP neural network can solve the problem of poor initial parameter quality in BP neural network self-optimization. Secondly, the optimized BP neural network can be self-optimized. Specifically, the vehicle speed error can be determined based on the target vehicle speed and the actual vehicle speed determined by the speed adjustment amount output by the optimized PID controller. The optimized parameter set of the optimized BP neural network is updated by backpropagating the speed error until the iteration condition is met, resulting in a target BP neural network. The speed error determined by the target vehicle speed and the actual vehicle speed determined by the speed adjustment amount output by the optimized PID controller achieves self-optimization of the BP neural network, resulting in a target BP neural network that can determine more accurate control parameters. Then, the target PID controller, obtained by updating the control parameters of the optimized PID controller based on the target BP neural network, determines the speed adjustment amount. The real-time speed of the vehicle is adjusted according to the speed adjustment amount until the real-time speed reaches the target speed, achieving real-time and accurate adjustment of vehicle speed, and thus achieving precise control of the vehicle.

[0012] Furthermore, several initialization parameter sets for the backpropagation BP neural network in the vehicle speed control system are determined, including:

[0013] Determine the value range of each parameter of the BP neural network;

[0014] Using each of the aforementioned value ranges as a search space, multiple initialization parameter groups are obtained by randomly initializing within each of the aforementioned search spaces.

[0015] Furthermore, the optimized parameter set of the BP neural network is determined in each of the initialization parameter sets using a global optimization algorithm, including:

[0016] The actual vehicle speed is determined based on the vehicle speed adjustment amount output by the PID controller, which is determined by the initialization BP neural network corresponding to each initialization parameter group. The vehicle speed steady-state error corresponding to each initialization parameter group is determined based on the vehicle's target speed and the actual vehicle speed.

[0017] The initial parameter set corresponding to the minimum vehicle speed steady-state error is taken as the current optimal parameter set;

[0018] By updating each parameter in each of the initialization parameter groups, the next parameter group corresponding to each initialization parameter group is obtained. Each of the next parameter groups is used as the initialization parameter group. The process returns to determine the actual vehicle speed based on the vehicle speed adjustment amount output by the PID controller determined by the initialization BP neural network corresponding to each initialization parameter group, until the update condition is met.

[0019] The current optimal parameter set when the update condition is met is determined as the optimized parameter set of the BP neural network.

[0020] Furthermore, when obtaining the next parameter group corresponding to each initialization parameter group by updating each parameter in each initialization parameter group, the method further includes:

[0021] If the updated value of any of the initialization parameters exceeds the value range corresponding to the parameter, a replacement value for the parameter is randomly generated with reference to the value range of the parameter, and the updated value is replaced based on the replacement value.

[0022] Further, updating the control parameters of the optimized PID controller based on the target BP neural network to obtain the target PID controller includes:

[0023] The target vehicle speed, the actual vehicle speed, and the speed error between the target vehicle speed and the actual vehicle speed are input into the target BP neural network so that the target BP neural network outputs target parameters.

[0024] The target PID controller is obtained by updating the control parameters of the optimized PID controller using the target parameters.

[0025] Furthermore, the parameters included in the parameter set of the BP neural network are the number of hidden layer nodes, learning rate, minimum error of the training target, and initial weight change.

[0026] Further, adjusting the real-time speed of the vehicle according to the speed adjustment amount output by the target PID controller includes:

[0027] The vehicle speed adjustment amount output by the target PID controller is sent to the vehicle control system so that the vehicle control system adjusts the real-time speed of the vehicle.

[0028] Secondly, embodiments of the present invention also provide a vehicle control device, comprising:

[0029] The execution module is used to determine multiple initialization parameter sets of the backpropagation BP neural network in the vehicle speed control system, and to determine the optimized parameter set of the BP neural network in each of the initialization parameter sets through a global optimization algorithm. The vehicle speed control system consisting of the optimized BP neural network corresponding to the optimized parameter set and the proportional-integral-derivative PID controller determined based on the optimized BP neural network has the smallest vehicle speed error. The input information of the BP neural network includes the vehicle speed error between the target vehicle speed and the actual vehicle speed, and the output information includes the control parameters of the PID controller.

[0030] The determination module is used to determine the vehicle speed error based on the target vehicle speed and the actual vehicle speed determined by the speed adjustment amount output by the optimized PID controller, wherein the optimized PID controller is obtained by updating the control parameters of the PID controller by the optimized BP neural network;

[0031] The update module is used to update the optimized parameter set of the optimized BP neural network by backpropagating the vehicle speed error until the iteration condition is met, and the target BP neural network is obtained.

[0032] The control module is used to update the control parameters of the optimized PID controller according to the target BP neural network to obtain the target PID controller, and adjust the real-time speed of the vehicle according to the vehicle speed adjustment amount output by the target PID controller until the real-time speed reaches the target vehicle speed.

[0033] Thirdly, embodiments of the present invention also provide a vehicle, the vehicle comprising:

[0034] At least one processor; and a memory communicatively connected to said at least one processor;

[0035] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the vehicle control method as described in any of the first aspects.

[0036] Fourthly, embodiments of the present invention also provide a storage medium containing computer-executable instructions, wherein the computer-executable instructions, when executed by a computer processor, are used to perform the vehicle control method as described in any of the first aspects.

[0037] Fifthly, this application provides a computer program product including computer instructions that, when executed on a computer, cause the computer to perform the vehicle control method as provided in the first aspect.

[0038] It should be noted that the aforementioned computer instructions may be stored, in whole or in part, on a computer-readable storage medium. This computer-readable storage medium may be packaged together with the processor of the vehicle control device, or it may be packaged separately from the processor of the vehicle control device; this application does not impose any limitations on this.

[0039] The descriptions of the second, third, fourth, and fifth aspects in this application can be referred to the detailed description of the first aspect; and the beneficial effects of the descriptions of the second, third, fourth, and fifth aspects can be referred to the analysis of the beneficial effects of the first aspect, which will not be repeated here.

[0040] In this application, the names of the aforementioned vehicle control devices do not limit the devices or functional modules themselves. In actual implementation, these devices or functional modules may appear under other names. As long as the functions of each device or functional module are similar to those in this application, they fall within the scope of the claims of this application and their equivalents.

[0041] These or other aspects of this application will become more readily apparent in the following description. Attached Figure Description

[0042] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0043] Figure 1 A flowchart of a vehicle control method provided in an embodiment of the present invention;

[0044] Figure 2A schematic diagram of a vehicle speed control system provided in an embodiment of the present invention;

[0045] Figure 3 A schematic diagram of a BP neural network provided in an embodiment of the present invention;

[0046] Figure 4 A flowchart of another vehicle control method provided in an embodiment of the present invention;

[0047] Figure 5 This is a schematic diagram of the structure of a vehicle control device provided in an embodiment of the present invention;

[0048] Figure 6 This is a structural schematic diagram of a vehicle provided in an embodiment of the present invention. Detailed Implementation

[0049] The present invention will now be described in further detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and not intended to limit it. Furthermore, it should be noted that, for ease of description, the accompanying drawings show only the parts relevant to the present invention, and not all of the structures.

[0050] In this article, the term "and / or" is merely a description of the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone.

[0051] The terms "first" and "second," etc., used in the specification and drawings of this application are used to distinguish different objects or to distinguish different treatments of the same object, rather than to describe a specific order of objects.

[0052] Furthermore, the terms "comprising" and "having," and any variations thereof, used in the description of this application are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the steps or units listed, but may optionally include other steps or units not listed, or may optionally include other steps or units inherent to such process, method, product, or apparatus.

[0053] Before discussing the exemplary embodiments in more detail, it should be noted that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although the flowcharts describe the operations (or steps) as sequential processes, many of these operations can be performed in parallel, concurrently, or simultaneously. Furthermore, the order of the operations can be rearranged. The process can be terminated when its operation is completed, but may also have additional steps not included in the figures. The process can correspond to a method, function, procedure, subroutine, subroutine, etc. Moreover, embodiments and features in the embodiments of the present invention can be combined with each other without conflict.

[0054] It should be noted that in the embodiments of this application, the words "exemplary" or "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design scheme described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design schemes. Specifically, the use of the words "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0055] In the description of this application, unless otherwise stated, "a plurality of" means two or more.

[0056] Figure 1 This is a flowchart illustrating a vehicle control method provided in an embodiment of the present invention. This embodiment is applicable to situations requiring real-time and precise control of vehicle speed. The method can be executed by a vehicle control device, such as... Figure 1 As shown, the specific steps include the following:

[0057] Step 110: Determine multiple initialization parameter sets for the backpropagation BP neural network in the vehicle speed control system, and determine the optimized parameter set of the BP neural network in each of the initialization parameter sets using a global optimization algorithm.

[0058] Figure 2 A schematic diagram of a vehicle speed control system provided in an embodiment of the present invention, as shown below. Figure 2 As shown, the vehicle speed control system consists of a BP neural network and a PID controller. Figure 3 A schematic diagram of a BP neural network provided in an embodiment of the present invention, as shown below. Figure 3 As shown, the BP neural network consists of an input layer, a hidden layer, and an output layer. The input layer has three neurons, which are used to input the target vehicle speed r, the actual vehicle speed y, and the speed error e between the target and actual vehicle speeds. The hidden layer has four neurons, and the output layer has three neurons, which are used to output the three control parameters of the PID controller. , , .

[0059] Specifically, the parameters of a BP neural network include the number of hidden layer nodes, the learning rate, the minimum error of the training objective, and the initial weight change. Each parameter has a specific numerical range. Therefore, the parameter value can be determined within the numerical range of each parameter, and an initialization parameter set for the BP neural network can be determined based on the parameter values. In practical applications, N initialization parameter sets can be determined, where N is a positive integer, and the specific value of N is not specifically limited here.

[0060] Furthermore, parameter optimization can be performed based on multiple initial parameter sets. Specifically, a global optimization algorithm can be used to optimize multiple initial parameter sets. First, a set of control parameters for a PID controller can be determined based on the BP neural network corresponding to each initial parameter set. Then, the vehicle speed adjustment amount is determined based on the PID controller corresponding to this set of control parameters. The vehicle speed is adjusted using the vehicle speed adjustment amount to obtain the actual vehicle speed. Finally, the vehicle speed difference is determined based on the target vehicle speed and the actual vehicle speed, thus determining the vehicle speed difference corresponding to each initial parameter set. The initial parameter set corresponding to the minimum vehicle speed difference can then be determined as the optimized parameter set. The vehicle speed control system consisting of the optimized BP neural network corresponding to the optimized parameter set and the PID controller determined based on the optimized BP neural network has the minimum vehicle speed error.

[0061] In practical applications, after determining the optimized BP neural network, the optimized BP neural network can determine a set of PID control parameters based on the target vehicle speed, actual vehicle speed, and the speed error between the target vehicle speed and the actual vehicle speed in the input. The PID controller corresponding to the determined PID control parameters is the optimized controller.

[0062] In this embodiment of the invention, an optimization parameter set is determined from multiple initial parameter sets of the backpropagation BP neural network through a global optimization algorithm, thereby achieving preliminary optimization of the BP neural network. Furthermore, the resulting optimized BP neural network can solve the problem of poor quality of the initial parameters in the self-optimization of the BP neural network.

[0063] Step 120: Determine the vehicle speed error based on the target vehicle speed and the actual vehicle speed determined by the speed adjustment amount output by the optimized PID controller.

[0064] The optimized PID controller is obtained by updating the control parameters of the PID controller using the optimized BP neural network.

[0065] Specifically, an optimized PID controller can determine the vehicle speed adjustment amount based on the speed error between the target vehicle speed and the actual vehicle speed in the input, and then update the actual vehicle speed based on the speed adjustment amount to obtain the current actual vehicle speed, thereby achieving real-time control of vehicle speed.

[0066] Of course, the next speed error can be further determined based on the difference between the current actual speed and the target speed.

[0067] Step 130: Update the optimized parameter set of the optimized BP neural network by backpropagating the vehicle speed error until the iteration condition is met, and obtain the target BP neural network.

[0068] Specifically, the newly determined vehicle speed error can be backpropagated to the optimized BP neural network, and the optimized parameter set of the BP neural network can be updated with gradients until the preset number of iterations is met. Once the preset number of iterations is met, the target BP neural network can be obtained.

[0069] In this embodiment of the invention, the speed error determined by the actual speed based on the target vehicle speed and the speed adjustment amount output by the optimized PID controller is used to achieve self-optimization of the BP neural network, resulting in a target BP neural network that can determine more accurate control parameters.

[0070] Step 140: Update the control parameters of the optimized PID controller according to the target BP neural network to obtain the target PID controller, and adjust the real-time speed of the vehicle according to the vehicle speed adjustment amount output by the target PID controller until the real-time speed reaches the target vehicle speed.

[0071] Specifically, after determining the target BP neural network, the control parameters of the PID controller can be updated and optimized based on the target BP neural network to obtain the target PID controller. Specifically, the target vehicle speed, the actual vehicle speed, and the speed error between the target vehicle speed and the actual vehicle speed can be input into the target BP neural network, and the target BP neural network can output the corresponding control parameters. The target PID controller can be obtained by updating and optimizing the PID controller based on the control parameters output by the target BP neural network. The target PID controller can determine the vehicle speed adjustment amount more accurately.

[0072] Then, the vehicle speed can be adjusted based on the target PID controller. Specifically, the target PID controller can determine the vehicle speed adjustment amount based on the speed error between the target vehicle speed and the current actual vehicle speed, and adjust the real-time vehicle speed based on the vehicle speed adjustment amount until the real-time speed reaches the target vehicle speed.

[0073] In this embodiment of the invention, the target PID controller, obtained by updating and optimizing the control parameters of the PID controller based on the target BP neural network, determines the vehicle speed adjustment amount. The real-time speed of the vehicle is adjusted according to the vehicle speed adjustment amount until the real-time speed reaches the target vehicle speed, thereby realizing real-time and precise adjustment of the vehicle speed and thus achieving precise control of the vehicle.

[0074] The vehicle control method provided in this invention includes: determining multiple initialization parameter sets of a backpropagation BP neural network in a vehicle speed control system; determining an optimized parameter set of the BP neural network in each of the initialization parameter sets using a global optimization algorithm; wherein the vehicle speed control system composed of the optimized BP neural network corresponding to the optimized parameter set and the proportional-integral-derivative PID controller determined based on the optimized BP neural network has the minimum vehicle speed error; the input information of the BP neural network includes the vehicle speed error between the target vehicle speed and the actual vehicle speed, and the output information includes the control parameters of the PID controller; determining the vehicle speed error based on the actual vehicle speed determined by the target vehicle speed and the vehicle speed adjustment amount output by the optimized PID controller; wherein the optimized PID controller is obtained by updating the control parameters of the PID controller using the optimized BP neural network; updating the optimized parameter set of the optimized BP neural network by backpropagating the vehicle speed error until the iteration condition is met to obtain a target BP neural network; updating the control parameters of the optimized PID controller based on the target BP neural network to obtain a target PID controller; and adjusting the real-time speed of the vehicle based on the vehicle speed adjustment amount output by the target PID controller until the real-time speed reaches the target vehicle speed. The above technical solution firstly uses a global optimization algorithm to determine the optimal parameter set from multiple initial parameter sets of the backpropagation BP neural network, achieving initial optimization of the BP neural network. The resulting optimized BP neural network can solve the problem of poor initial parameter quality in BP neural network self-optimization. Secondly, the optimized BP neural network can be self-optimized. Specifically, the vehicle speed error can be determined based on the target vehicle speed and the actual vehicle speed determined by the speed adjustment amount output by the optimized PID controller. The optimized parameter set of the optimized BP neural network is updated by backpropagating the speed error until the iteration condition is met, resulting in a target BP neural network. The speed error determined by the target vehicle speed and the actual vehicle speed determined by the speed adjustment amount output by the optimized PID controller achieves self-optimization of the BP neural network, resulting in a target BP neural network that can determine more accurate control parameters. Then, the target PID controller, obtained by updating the control parameters of the optimized PID controller based on the target BP neural network, determines the speed adjustment amount. The real-time speed of the vehicle is adjusted according to the speed adjustment amount until the real-time speed reaches the target speed, achieving real-time and accurate adjustment of vehicle speed, and thus achieving precise control of the vehicle.

[0075] Figure 4 This is a flowchart of another vehicle control method provided by an embodiment of the present invention. This embodiment is a specific modification based on the above embodiments. Figure 4 As shown, in this embodiment, the method may further include:

[0076] Step 410: Determine multiple initialization parameter sets for the backpropagation BP neural network in the vehicle speed control system.

[0077] The parameters included in the parameter set of the BP neural network are the number of hidden layer nodes, learning rate, minimum training error, and initial weight change.

[0078] In one embodiment, step 410 may specifically include:

[0079] Determine the value range of each parameter of the BP neural network; use each value range as a search space, and obtain multiple initialization parameter groups by randomly initializing within each search space.

[0080] Specifically, the range of values ​​for each parameter in the BP neural network can be determined first. Specifically, the range of values ​​for the hidden layer node number x1 is [1, 20], the learning rate x2 is [0.01, 0.2], the minimum training error x3 is [0.01, 0.1], and the initial weight change x4 is [0.05, 0.09]. This range can then be used as the search space for each parameter. Random initialization is performed within this search space to obtain the corresponding parameter values. Based on these values, an initial parameter set X(t) = [x1, x2, x3, x4] can be constructed. Of course, N initial parameter sets can be randomly constructed.

[0081] Step 420: Determine the actual vehicle speed based on the vehicle speed adjustment amount output by the PID controller determined by the initialization BP neural network corresponding to each initialization parameter group, and determine the vehicle speed steady-state error corresponding to each initialization parameter group based on the vehicle's target speed and the actual vehicle speed.

[0082] Specifically, after determining N initial parameter sets, parameter optimization can be performed based on multiple initial parameter sets. For example, parameter optimization can be performed based on the improved whale algorithm, that is, the N initial parameter sets can be used as the initial population. In the improved whale algorithm, the initial population size is N, the maximum number of iterations is M, the constant coefficient of the logarithmic spiral shape is b, the individual encoding length is L, and the current iteration number is t. The fitness function for optimization by the improved whale algorithm is the vehicle speed steady-state error, and the formula for the fitness function is: ,in, This represents the fitness value, which in practical applications... It can indicate the steady-state error of vehicle speed. Indicates the target vehicle speed. The actual vehicle speed is represented by t, and the current iteration number is represented by t. This indicates that discrete time tends to infinity.

[0083] When performing parameter set optimization based on the improved whale algorithm, a set of PID controller control parameters can be determined according to the BP neural network corresponding to each initial parameter set. The vehicle speed adjustment amount can be determined according to the PID controller corresponding to this set of control parameters. The vehicle speed is adjusted by adjusting the vehicle speed to obtain the actual vehicle speed. Then, the vehicle speed steady-state error corresponding to each initial parameter set is determined according to the target vehicle speed and the actual vehicle speed.

[0084] Step 430: Take the initial parameter set corresponding to the minimum vehicle speed steady-state error as the current optimal parameter set.

[0085] Compare the vehicle speed steady-state errors corresponding to each initialization parameter set, and select the initialization parameter set corresponding to the minimum vehicle speed steady-state error. Determined as the current optimal parameter set .

[0086] Step 440: By updating each parameter in each initialization parameter group, the next parameter group corresponding to each initialization parameter group is obtained. Each next parameter group is used as the initialization parameter group. The process is then returned to execute the determination of the actual vehicle speed based on the vehicle speed adjustment amount output by the PID controller determined by the initialization BP neural network corresponding to each initialization parameter group, until the update condition is met.

[0087] Specifically, assuming the current iteration number t is no greater than the maximum iteration number M, the positions of the N initialization parameter groups can be updated. Specifically, the position update for each initialization parameter group can be based on the following formula 1.

[0088] Formula 1;

[0089] in, , 'a' represents the convergence factor that gradually decreases linearly from 2 to 0 during the iteration process. , and Represents a random number before [0, 1]. This represents adaptive inertia weights based on sine and cosine variations. k represents a constant coefficient. Represents a random number between [-1, 1]. Represents a random number between [0, 1]. This represents the optimal parameter set for generation t. This represents the parameter sets other than the optimal parameter set in generation t. Let represent the parameter set after the spatial location update, and D represent the search direction in generation t. , Let D' represent a random number in the range [0, 1], and let D′ represent the optimal search direction in generation t. .

[0090] In one embodiment, when obtaining the next parameter group corresponding to each initialization parameter group by updating each parameter in each initialization parameter group, the method further includes:

[0091] If the updated value of any of the initialization parameters exceeds the value range corresponding to the parameter, a replacement value for the parameter is randomly generated with reference to the value range of the parameter, and the updated value is replaced based on the replacement value.

[0092] judge Check if the value of each parameter exceeds the range of values ​​corresponding to that parameter. If it does, generate a random number within the range of values ​​corresponding to that parameter to replace the parameter value.

[0093] Of course, we can continue to calculate the... Each in the generation Vehicle speed steady-state error, the parameter set corresponding to the minimum vehicle speed steady-state error is determined as the first... The optimal parameter set in the generation Furthermore, comparisons are possible. and The corresponding steady-state error of vehicle speed, if The corresponding steady-state error of vehicle speed is less than The corresponding steady-state error of vehicle speed will be Update to the current optimal parameter set .

[0094] Specifically, in the Update to the current optimal parameter set Then, the current iteration number t can be updated to Then compare the next iteration number. And M, if Then each of the next parameter groups is used as the initialization parameter group, and the actual vehicle speed is determined by the speed adjustment amount of the PID controller output determined by the initialization BP neural network corresponding to each initialization parameter group, until the update condition is met.

[0095] Step 450: Determine the current optimal parameter set when the update condition is met as the optimized parameter set of the BP neural network.

[0096] The update condition can be that the number of iterations is not less than the maximum number of iterations M.

[0097] Specifically, in determining In this case, the current optimal parameter set determined at this time can be used as the optimized parameter set for the BP neural network.

[0098] Of course, after determining the optimal parameter set of the BP neural network, the BP neural network can be optimized based on the optimal parameter set to obtain an optimized BP neural network. The optimized BP neural network can determine the optimal control parameters based on the target vehicle speed, the actual vehicle speed, and the speed error between the target vehicle speed and the actual vehicle speed from the input. Then, the control parameters of the PID controller can be updated based on the optimized control parameters to obtain the optimized controller.

[0099] After optimizing the parameter set of the BP neural network using the improved whale algorithm, the optimized BP neural network is self-optimized to improve the efficiency of self-optimization, making the convergence speed of self-optimization faster, less prone to getting trapped in local minima, and more stable.

[0100] In this embodiment of the invention, the optimized parameter set is determined from multiple initial parameter sets of the backpropagation BP neural network by improving the whale algorithm, thereby achieving preliminary optimization of the BP neural network. Furthermore, the resulting optimized BP neural network can solve the problem of poor quality of the initial parameters in the self-optimization of the BP neural network.

[0101] Step 460: Determine the vehicle speed error based on the target vehicle speed and the actual vehicle speed determined by the speed adjustment amount output by the optimized PID controller.

[0102] Step 470: Update the optimized parameter set of the optimized BP neural network by backpropagating the vehicle speed error until the iteration condition is met, and obtain the target BP neural network.

[0103] Step 480: Update the control parameters of the optimized PID controller according to the target BP neural network to obtain the target PID controller.

[0104] In one implementation, step 480 may specifically include:

[0105] The target vehicle speed, actual vehicle speed, and the speed error between the target vehicle speed and the actual vehicle speed are input into the target BP neural network, so that the target BP neural network outputs target parameters; the control parameters of the optimized PID controller are updated through the target parameters to obtain the target PID controller.

[0106] Specifically, the target vehicle speed, the actual vehicle speed, and the speed error between the target and actual vehicle speeds are input into the target BP neural network. The target BP neural network can then output the corresponding control parameters, which are the optimal control parameters. .

[0107] This allows the control parameters of the PID controller to be optimized to the optimal control parameters. This allows us to obtain the target PID controller, which can then be used to determine the vehicle speed adjustment amount more precisely.

[0108] In this embodiment of the invention, the control parameters of the optimized PID controller are updated again based on the target BP neural network to obtain the target PID controller, thereby determining the target PID controller for more precise vehicle speed adjustment.

[0109] Step 490: Adjust the real-time speed of the vehicle according to the vehicle speed adjustment amount output by the target PID controller until the real-time speed reaches the target vehicle speed.

[0110] In one embodiment, adjusting the real-time speed of the vehicle according to the speed adjustment amount output by the target PID controller includes:

[0111] The vehicle speed adjustment amount output by the target PID controller is sent to the vehicle control system so that the vehicle control system adjusts the real-time speed of the vehicle.

[0112] Specifically, the target PID controller can determine the vehicle speed adjustment amount based on the vehicle speed error in the input, and can also send the vehicle speed adjustment amount to the vehicle control system, that is, to the throttle and brake control system in the vehicle control system, and control the actuator to adjust the real-time vehicle speed based on the throttle and brake control system.

[0113] In practical applications, the actual vehicle speed can be obtained through a speed sensor, and the speed error between the actual speed and the target speed can be used as a new input to the target PID controller. This process is repeated until the real-time vehicle speed reaches the target speed.

[0114] In this embodiment of the invention, the target PID controller adjusts the real-time speed of the vehicle according to the vehicle speed adjustment amount until the real-time speed reaches the target vehicle speed, thereby achieving real-time and precise adjustment of the vehicle speed and thus achieving precise control of the vehicle.

[0115] In practical applications, the vehicle's acceleration can be adjusted in real time using a BP neural network and a PID controller. Specifically, the acceleration error between the target acceleration and the real-time acceleration can be determined. The optimized parameter set of the BP neural network is updated and optimized by backpropagating the acceleration error until the iteration condition is met, resulting in an acceleration BP neural network used to update the control parameters of the acceleration PID controller for acceleration adjustment. Furthermore, the control parameters of the acceleration PID controller can be optimized based on the acceleration BP neural network. The acceleration adjustment amount is determined based on the optimized acceleration PID controller, and the acceleration is adjusted based on the acceleration adjustment amount to obtain the real-time acceleration until the real-time acceleration matches the target acceleration, thus achieving real-time acceleration updates.

[0116] It should be noted that the vehicle's speed and acceleration can also be adjusted simultaneously. After determining the real-time speed based on the speed adjustment output of the target PID controller and the real-time acceleration based on the acceleration adjustment output of the optimized acceleration PID controller, the vehicle control system can be jointly controlled by the real-time speed and real-time acceleration. The vehicle control system then controls the actuators to adjust the vehicle's real-time speed and real-time acceleration.

[0117] The vehicle control method provided in this invention includes: determining multiple initialization parameter sets of a backpropagation BP neural network in a vehicle speed control system; determining the actual vehicle speed based on the vehicle speed adjustment amount output by the PID controller determined by the initialization BP neural network corresponding to each initialization parameter set; determining the vehicle speed steady-state error corresponding to each initialization parameter set based on the vehicle's target vehicle speed and the actual vehicle speed; taking the initialization parameter set corresponding to the minimum vehicle speed steady-state error as the current optimal parameter set; obtaining the next parameter set corresponding to each initialization parameter set by updating each parameter in each initialization parameter set; taking each next parameter set as the initialization parameter set; and returning to execute the initialization BP neural network determined by each initialization parameter set. The actual vehicle speed is determined by the speed adjustment amount output by the PID controller until an update condition is met. The current optimal parameter set when the update condition is met is determined as the optimized parameter set of the BP neural network. The vehicle speed error is determined based on the target vehicle speed and the actual vehicle speed determined by the speed adjustment amount output by the optimized PID controller. The optimized parameter set of the optimized BP neural network is updated by backpropagating the speed error until the iteration condition is met, resulting in a target BP neural network. The control parameters of the optimized PID controller are updated based on the target BP neural network to obtain a target PID controller. The real-time speed of the vehicle is adjusted based on the speed adjustment amount output by the target PID controller until the real-time speed reaches the target vehicle speed. The above technical solution firstly optimizes the BP neural network by determining the optimal parameter set from multiple initial parameter sets in the backpropagation BP neural network through an improved whale algorithm. This initial optimization solves the problem of poor initial parameter quality in BP neural network self-optimization. Secondly, the optimized BP neural network can be self-optimized. Specifically, the vehicle speed error can be determined based on the target vehicle speed and the actual vehicle speed determined by the speed adjustment amount output by the optimized PID controller. The optimized parameter set of the BP neural network is updated by backpropagating the speed error until the iteration condition is met, resulting in the target BP neural network. The speed error determined by the target vehicle speed and the actual vehicle speed determined by the speed adjustment amount output by the optimized PID controller enables self-optimization of the BP neural network, resulting in a target BP neural network that can determine more accurate control parameters. Then, the target PID controller, obtained by updating the control parameters of the optimized PID controller based on the target BP neural network, determines the speed adjustment amount. The real-time speed of the vehicle is adjusted according to the speed adjustment amount until the real-time speed reaches the target speed, achieving real-time and precise adjustment of vehicle speed, and thus achieving precise control of the vehicle.

[0118] Furthermore, the use of BP neural network and PID controller to control vehicle speed has strong adaptive capability and good robustness, and can effectively control nonlinear, time-varying, and multi-interference systems.

[0119] Figure 5 This is a schematic diagram of a vehicle control device provided in an embodiment of the present invention. This device is suitable for situations requiring real-time and precise control of vehicle speed. The device can be implemented through software and / or hardware and is generally integrated into the vehicle.

[0120] like Figure 5 As shown, the device includes:

[0121] The execution module 510 is used to determine multiple initialization parameter sets of the backpropagation BP neural network in the vehicle speed control system, and to determine the optimized parameter set of the BP neural network in each of the initialization parameter sets through a global optimization algorithm. The vehicle speed control system consisting of the optimized BP neural network corresponding to the optimized parameter set and the proportional-integral-derivative PID controller determined based on the optimized BP neural network has the smallest vehicle speed error. The input information of the BP neural network includes the vehicle speed error between the target vehicle speed and the actual vehicle speed, and the output information includes the control parameters of the PID controller.

[0122] The determination module 520 is used to determine the vehicle speed error based on the target vehicle speed and the actual vehicle speed determined by the vehicle speed adjustment amount output by the optimized PID controller, wherein the optimized PID controller is obtained by updating the control parameters of the PID controller by the optimized BP neural network.

[0123] The update module 530 is used to update the optimized parameter set of the optimized BP neural network by backpropagating the vehicle speed error until the iteration condition is met, and the target BP neural network is obtained.

[0124] The control module 540 is used to update the control parameters of the optimized PID controller according to the target BP neural network to obtain the target PID controller, and adjust the real-time speed of the vehicle according to the vehicle speed adjustment amount output by the target PID controller until the real-time speed reaches the target vehicle speed.

[0125] The vehicle control device provided in this embodiment determines multiple initialization parameter sets for the backpropagation BP neural network in the vehicle speed control system. An optimized parameter set for the BP neural network is determined from each of the initialization parameter sets using a global optimization algorithm. The vehicle speed control system formed by the optimized BP neural network corresponding to the optimized parameter set and the proportional-integral-derivative PID controller determined based on the optimized BP neural network has the minimum vehicle speed error. The input information of the BP neural network includes the speed error between the target vehicle speed and the actual vehicle speed, and the output information includes the control parameters of the PID controller. The vehicle speed error is determined based on the actual vehicle speed determined by the target vehicle speed and the speed adjustment amount output by the optimized PID controller. The optimized PID controller is obtained by updating the control parameters of the PID controller using the optimized BP neural network. The optimized parameter set of the optimized BP neural network is updated by backpropagating the speed error until the iteration condition is met, resulting in a target BP neural network. The control parameters of the optimized PID controller are updated based on the target BP neural network to obtain a target PID controller. The real-time speed of the vehicle is adjusted based on the speed adjustment amount output by the target PID controller until the real-time speed reaches the target vehicle speed. The above technical solution firstly uses a global optimization algorithm to determine the optimal parameter set from multiple initial parameter sets of the backpropagation BP neural network, achieving initial optimization of the BP neural network. The resulting optimized BP neural network can solve the problem of poor initial parameter quality in BP neural network self-optimization. Secondly, the optimized BP neural network can be self-optimized. Specifically, the vehicle speed error can be determined based on the target vehicle speed and the actual vehicle speed determined by the speed adjustment amount output by the optimized PID controller. The optimized parameter set of the optimized BP neural network is updated by backpropagating the speed error until the iteration condition is met, resulting in a target BP neural network. The speed error determined by the target vehicle speed and the actual vehicle speed determined by the speed adjustment amount output by the optimized PID controller achieves self-optimization of the BP neural network, resulting in a target BP neural network that can determine more accurate control parameters. Then, the target PID controller, obtained by updating the control parameters of the optimized PID controller based on the target BP neural network, determines the speed adjustment amount. The real-time speed of the vehicle is adjusted according to the speed adjustment amount until the real-time speed reaches the target speed, achieving real-time and accurate adjustment of vehicle speed, and thus achieving precise control of the vehicle.

[0126] Based on the above embodiments, the execution module 510 is specifically used for:

[0127] The process involves: determining the value range of each parameter in the BP neural network; using each value range as a search space, and randomly initializing the parameters within each search space to obtain multiple initialization parameter sets; determining the actual vehicle speed based on the speed adjustment amount output by the PID controller determined by the initialization BP neural network corresponding to each initialization parameter set; determining the vehicle speed steady-state error corresponding to each initialization parameter set based on the vehicle's target speed and the actual speed; using the initialization parameter set corresponding to the minimum vehicle speed steady-state error as the current optimal parameter set; obtaining the next parameter set corresponding to each initialization parameter set by updating each parameter in each initialization parameter set; using each next parameter set as the initialization parameter set; and returning to execute the process of determining the actual vehicle speed based on the speed adjustment amount output by the PID controller determined by the initialization BP neural network corresponding to each initialization parameter set, until an update condition is met; and determining the current optimal parameter set when the update condition is met as the optimized parameter set of the BP neural network.

[0128] In one embodiment, when obtaining the next parameter group corresponding to each initialization parameter group by updating each parameter in each initialization parameter group, the method further includes:

[0129] If the updated value of any of the initialization parameters exceeds the value range corresponding to the parameter, a replacement value for the parameter is randomly generated with reference to the value range of the parameter, and the updated value is replaced based on the replacement value.

[0130] Based on the above embodiments, the control module 540 is specifically used for:

[0131] The target vehicle speed, actual vehicle speed, and the speed error between the target and actual vehicle speeds are input into the target BP neural network to output target parameters. The control parameters of the optimized PID controller are updated using the target parameters to obtain the target PID controller. The vehicle speed adjustment output by the target PID controller is sent to the vehicle control system to adjust the real-time speed of the vehicle.

[0132] In one embodiment, the parameter set of the BP neural network includes parameters such as the number of hidden layer nodes, learning rate, minimum training error, and initial weight change.

[0133] The vehicle control device provided in the embodiments of the present invention can execute the vehicle control method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the vehicle control method.

[0134] It is worth noting that in the above embodiments of the vehicle control device, the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of each functional unit are only for easy differentiation and are not used to limit the scope of protection of the present invention.

[0135] Figure 6 This is a structural schematic diagram of a vehicle provided in an embodiment of the present invention. Figure 6 A block diagram of an exemplary vehicle 6 suitable for implementing embodiments of the present invention is shown. Figure 6 The vehicle 6 shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of the present invention.

[0136] like Figure 6 As shown, vehicle 6 is represented in the form of a general-purpose computing electronic device. The components of vehicle 6 may include, but are not limited to: one or more processors or processing units 16, system memory 28, and bus 18 connecting different system components (including system memory 28 and processing unit 16).

[0137] Bus 18 represents one or more of several bus architectures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of the various bus architectures. For example, these architectures include, but are not limited to, the Industry Standard Architecture (ISA) bus, the Micro Channel Architecture (MAC) bus, the Enhanced ISA bus, the Video Electronics Standards Association (VESA) local bus, and the Peripheral Component Interconnect (PCI) bus.

[0138] Vehicle 6 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by vehicle 6, including volatile and non-volatile media, removable and non-removable media.

[0139] System memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. Vehicle 6 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 34 may be used to read and write non-removable, non-volatile magnetic media (…). Figure 6 Not shown; usually referred to as a "hard drive"). Although Figure 6As not shown, disk drives for reading and writing to removable non-volatile disks (e.g., "floppy disks") and optical disc drives for reading and writing to removable non-volatile optical discs (e.g., CD-ROMs, DVD-ROMs, or other optical media) may be provided. In these cases, each drive may be connected to bus 18 via one or more data media interfaces. System memory 28 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of the present invention.

[0140] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in system memory 28. Such program modules 42 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment. Program modules 42 typically perform the functions and / or methods described in the embodiments of the present invention.

[0141] Vehicle 6 can also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), and with one or more devices that enable a user to interact with vehicle 6, and / or with any device that enables vehicle 6 to communicate with one or more other computing devices (e.g., network card, modem, etc.). This communication can be performed through input / output (I / O) interface 22. Furthermore, vehicle 6 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 20. Figure 6 As shown, network adapter 20 communicates with other modules of vehicle 6 via bus 18. It should be understood that, although... Figure 6 As not shown in the diagram, other hardware and / or software modules may be used in conjunction with vehicle 6, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0142] Processing unit 16 executes various functional applications and page displays by running programs stored in system memory 28, such as implementing the vehicle control method provided in this embodiment of the invention, which includes:

[0143] Multiple initialization parameter sets for the backpropagation BP neural network in the vehicle speed control system are determined. An optimized parameter set for the BP neural network is determined from each of the initialization parameter sets using a global optimization algorithm. The vehicle speed control system consisting of the optimized BP neural network corresponding to the optimized parameter set and the proportional-integral-derivative PID controller determined based on the optimized BP neural network has the smallest vehicle speed error. The input information of the BP neural network includes the vehicle speed error between the target vehicle speed and the actual vehicle speed, and the output information includes the control parameters of the PID controller.

[0144] The vehicle speed error is determined based on the target vehicle speed and the actual vehicle speed determined by the speed adjustment amount output by the optimized PID controller. The optimized PID controller is obtained by updating the control parameters of the PID controller using the optimized BP neural network.

[0145] The optimized parameter set of the optimized BP neural network is updated by backpropagating the vehicle speed error until the iteration condition is met, thus obtaining the target BP neural network.

[0146] The target PID controller is obtained by updating the control parameters of the optimized PID controller according to the target BP neural network. The real-time speed of the vehicle is adjusted according to the vehicle speed adjustment amount output by the target PID controller until the real-time speed reaches the target vehicle speed.

[0147] Of course, those skilled in the art will understand that the processor can also implement the technical solutions of the vehicle control method provided in any embodiment of the present invention.

[0148] This invention provides a computer-readable storage medium storing a computer program thereon. When executed by a processor, the program implements, for example, the vehicle control method provided in this invention, which includes:

[0149] Multiple initialization parameter sets for the backpropagation BP neural network in the vehicle speed control system are determined. An optimized parameter set for the BP neural network is determined from each of the initialization parameter sets using a global optimization algorithm. The vehicle speed control system consisting of the optimized BP neural network corresponding to the optimized parameter set and the proportional-integral-derivative PID controller determined based on the optimized BP neural network has the smallest vehicle speed error. The input information of the BP neural network includes the vehicle speed error between the target vehicle speed and the actual vehicle speed, and the output information includes the control parameters of the PID controller.

[0150] The vehicle speed error is determined based on the target vehicle speed and the actual vehicle speed determined by the speed adjustment amount output by the optimized PID controller. The optimized PID controller is obtained by updating the control parameters of the PID controller using the optimized BP neural network.

[0151] The optimized parameter set of the optimized BP neural network is updated by backpropagating the vehicle speed error until the iteration condition is met, thus obtaining the target BP neural network.

[0152] The target PID controller is obtained by updating the control parameters of the optimized PID controller according to the target BP neural network. The real-time speed of the vehicle is adjusted according to the vehicle speed adjustment amount output by the target PID controller until the real-time speed reaches the target vehicle speed.

[0153] The computer storage medium of this invention can be any combination of one or more computer-readable media. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0154] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of sending, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.

[0155] Program code contained on a computer-readable medium may be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0156] Computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages—such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0157] Those skilled in the art will understand that the modules or steps of the present invention described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. Optionally, they can be implemented using computer-executable program code, thereby allowing them to be stored in a storage device for execution by a computing device, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0158] Furthermore, the acquisition, storage, use, and processing of data in the technical solution of this invention all comply with relevant laws and regulations.

[0159] Note that the above description is merely a preferred embodiment of the present invention and the technical principles employed. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions can be made without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments, and may include many other equivalent embodiments without departing from the concept of the present invention, the scope of which is determined by the scope of the appended claims.

Claims

1. A vehicle control method, characterized in that, include: Multiple initialization parameter sets for the backpropagation BP neural network in the vehicle speed control system are determined. An optimized parameter set for the BP neural network is determined from each of the initialization parameter sets using a global optimization algorithm. The vehicle speed control system consisting of the optimized BP neural network corresponding to the optimized parameter set and the proportional-integral-derivative PID controller determined based on the optimized BP neural network has the smallest vehicle speed error. The input information of the BP neural network includes the vehicle speed error between the target vehicle speed and the actual vehicle speed, and the output information includes the control parameters of the PID controller. The vehicle speed error is determined based on the target vehicle speed and the actual vehicle speed determined by the speed adjustment amount output by the optimized PID controller. The optimized PID controller is obtained by updating the control parameters of the PID controller using the optimized BP neural network. The optimized parameter set of the optimized BP neural network is updated by backpropagating the vehicle speed error until the iteration condition is met, thus obtaining the target BP neural network. The target PID controller is obtained by updating the control parameters of the optimized PID controller according to the target BP neural network. The real-time speed of the vehicle is adjusted according to the vehicle speed adjustment amount output by the target PID controller until the real-time speed reaches the target vehicle speed.

2. The vehicle control method according to claim 1, characterized in that, Determine multiple initialization parameter sets for the backpropagation BP neural network in the vehicle speed control system, including: Determine the value range of each parameter of the BP neural network; Using each of the aforementioned value ranges as a search space, multiple initialization parameter groups are obtained by randomly initializing within each of the aforementioned search spaces.

3. The vehicle control method according to claim 2, characterized in that, The optimized parameter set of the BP neural network is determined from each of the initialization parameter sets using a global optimization algorithm, including: The actual vehicle speed is determined based on the vehicle speed adjustment amount output by the PID controller, which is determined by the initialization BP neural network corresponding to each initialization parameter group. The vehicle speed steady-state error corresponding to each initialization parameter group is determined based on the vehicle's target speed and the actual vehicle speed. The initial parameter set corresponding to the minimum vehicle speed steady-state error is taken as the current optimal parameter set; By updating each parameter in each of the initialization parameter groups, the next parameter group corresponding to each initialization parameter group is obtained. Each of the next parameter groups is used as the initialization parameter group. The process returns to determine the actual vehicle speed based on the vehicle speed adjustment amount output by the PID controller determined by the initialization BP neural network corresponding to each initialization parameter group, until the update condition is met. The current optimal parameter set when the update condition is met is determined as the optimized parameter set of the BP neural network.

4. The vehicle control method according to claim 3, characterized in that, When obtaining the next parameter group corresponding to each initialization parameter group by updating each parameter in each initialization parameter group, the method further includes: If the updated value of any of the initialization parameters exceeds the value range corresponding to the parameter, a replacement value for the parameter is randomly generated with reference to the value range of the parameter, and the updated value is replaced based on the replacement value.

5. The vehicle control method according to claim 1, characterized in that, The target PID controller is obtained by updating the control parameters of the optimized PID controller according to the target BP neural network, including: The target vehicle speed, the actual vehicle speed, and the speed error between the target vehicle speed and the actual vehicle speed are input into the target BP neural network so that the target BP neural network outputs target parameters. The target PID controller is obtained by updating the control parameters of the optimized PID controller using the target parameters.

6. The vehicle control method according to claim 1, characterized in that, The parameters included in the parameter set of the BP neural network are the number of hidden layer nodes, learning rate, minimum error of the training objective, and initial weight change.

7. The vehicle control method according to claim 1, characterized in that, Adjusting the real-time speed of the vehicle according to the vehicle speed adjustment amount output by the target PID controller includes: The vehicle speed adjustment amount output by the target PID controller is sent to the vehicle control system so that the vehicle control system adjusts the real-time speed of the vehicle.

8. A vehicle control device, characterized in that, include: The execution module is used to determine multiple initialization parameter sets of the backpropagation BP neural network in the vehicle speed control system, and to determine the optimized parameter set of the BP neural network in each of the initialization parameter sets through a global optimization algorithm. The vehicle speed control system consisting of the optimized BP neural network corresponding to the optimized parameter set and the proportional-integral-derivative PID controller determined based on the optimized BP neural network has the smallest vehicle speed error. The input information of the BP neural network includes the vehicle speed error between the target vehicle speed and the actual vehicle speed, and the output information includes the control parameters of the PID controller. The determination module is used to determine the vehicle speed error based on the target vehicle speed and the actual vehicle speed determined by the speed adjustment amount output by the optimized PID controller, wherein the optimized PID controller is obtained by updating the control parameters of the PID controller by the optimized BP neural network; The update module is used to update the optimized parameter set of the optimized BP neural network by backpropagating the vehicle speed error until the iteration condition is met, and the target BP neural network is obtained. The control module is used to update the control parameters of the optimized PID controller according to the target BP neural network to obtain the target PID controller, and adjust the real-time speed of the vehicle according to the vehicle speed adjustment amount output by the target PID controller until the real-time speed reaches the target vehicle speed.

9. A vehicle, characterized in that, The vehicles include: At least one processor; and a memory communicatively connected to said at least one processor; The memory stores a computer program that can be executed by the at least one processor, which is then executed by the at least one processor to enable the at least one processor to perform the vehicle control method as described in any one of claims 1-7.

10. A storage medium containing computer-executable instructions, characterized in that, The computer-executable instructions, when executed by a computer processor, are used to perform the vehicle control method as described in any one of claims 1-7.

Images