Vehicle control method, device, equipment and medium
By using neural networks and chaotic differential evolution models in new energy vehicles for fault diagnosis and control instructions optimization, the problem of insufficient professional control and fault diagnosis capabilities of the control system is solved, and the safety and reliability of the car is improved.
Patent Information
- Application Number
- CN202411022420.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-29
- Publication Date
- 2024-11-22
AI Technical Summary
The control system of new energy vehicles lacks professional control and efficient cooperation, resulting in lagging control capabilities and incomplete fault diagnosis, affecting the safety and reliability of the car.
By obtaining vehicle driving information, using preset neural network models for fault diagnosis, combining the improved RBF neural network and chaotic differential evolution model, we identify fault types and generate control instructions, optimize vehicle status, and realize intelligent fault diagnosis and control.
The control capability and fault diagnosis performance of the multi-domain integrated control system of new energy vehicles have been improved to ensure safe and efficient driving.
Smart Images

Figure CN118991805A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of automobile control technology, and in particular to a vehicle control method, device, equipment and medium. Background Art
[0002] As an important development direction of the future automobile industry, new energy vehicles use unconventional vehicle fuels or electricity as power sources, and integrate advanced technologies for vehicle power control and drive, including hybrid electric vehicles, pure electric vehicles, fuel cell electric vehicles, etc. These vehicles optimize performance, improve energy efficiency and reduce emissions by integrating advanced electronic control units.
[0003] However, the control systems of new energy vehicles mainly include decentralized and centralized architectures. By integrating sensor data processing, vehicle dynamics calculations, and actuator control modules, it aims to solve the problems of high cost and heavy weight of decentralized architectures and low safety of centralized architectures. Most vehicle control technologies fail to fully divide the control system into professional fields, such as sensor domain, calculation domain, execution domain, and control domain, which limits the specialized control and efficient collaboration of the system. Existing systems generally lack advanced algorithm support, resulting in lagging control capabilities, poor operability, and low efficiency, especially when processing real-time vehicle data and fault information. During vehicle operation, the processing capacity for fault data information is limited, the fault diagnosis mechanism is imperfect, and it is difficult to detect and locate faults in a timely and accurate manner, affecting the safety and reliability of the vehicle.
[0004] Therefore, it is an urgent need to develop a multi-domain integrated control system for new energy vehicles that can overcome these defects and achieve higher efficiency, intelligence, and strong fault diagnosis capabilities. Summary of the invention
[0005] The main purpose of the present invention is to provide a vehicle control system, method, device and medium, aiming to solve the problem of how to improve the control capability and fault diagnosis performance of the multi-domain integrated control system of new energy vehicles.
[0006] To achieve the above object, the present invention provides a vehicle control method, characterized in that the method comprises:
[0007] Obtain vehicle driving information;
[0008] Performing fault diagnosis on the vehicle driving information by using a preset neural network model to obtain fault information;
[0009] Performing a test using a preset test method according to the fault information to obtain a diagnosis result;
[0010] Optimizing the vehicle state according to the diagnosis result and generating control instructions;
[0011] The vehicle is controlled according to the control instruction.
[0012] In one embodiment, the step of performing fault diagnosis on the vehicle driving information by using a preset neural network model to obtain fault information includes:
[0013] The vehicle driving information is identified by a preset neural network model to obtain a classification result;
[0014] The vehicle fault type is determined according to the classification result to obtain fault information.
[0015] In one embodiment, the step of performing data information recognition on the vehicle driving information through a preset neural network model to obtain a classification result includes:
[0016] Preprocessing the vehicle driving information to obtain processed vehicle driving information;
[0017] Acquiring key features from the processed vehicle travel information;
[0018] The key features are input into the preset neural network model to perform data information recognition to obtain classification results.
[0019] In one embodiment, the step of preprocessing the vehicle driving information to obtain processed vehicle driving information includes:
[0020] Encode the input vehicle driving information to obtain encoded information;
[0021] Fusing the encoded information to obtain fused information;
[0022] The fused information is filtered to obtain processed vehicle driving information.
[0023] In one embodiment, before the step of performing fault diagnosis on the vehicle driving information by using a preset neural network model to obtain fault information, the step includes:
[0024] Construct an initial chaotic differential evolution model and define the scaling factor, crossover factor and preset number of iterations;
[0025] Get the initial population;
[0026] calculating the fitness of the population;
[0027] Performing a mutation operation on the fitness of different populations based on the scaling factor, and performing a crossover calculation based on the crossover factor to obtain calculated fitness;
[0028] The calculated fitness is compared, and when the calculated fitness is greater than a preset value or reaches a preset number of iterations, the initial chaotic differential evolution model is output, and the initial chaotic differential evolution model is integrated into a preset neural network model.
[0029] In one embodiment, before the step of performing a test according to the fault information by a preset test method to obtain a diagnosis result, the step includes:
[0030] Get sample fault information;
[0031] Marking the sample fault information to divide it into first sample fault information and second sample fault information;
[0032] A preset test matrix is constructed according to the first sample fault information.
[0033] In one embodiment, the step of performing a test according to the fault information by a preset test method to obtain a diagnosis result includes:
[0034] Inputting the fault information into the preset test matrix to construct a set of equations;
[0035] Solving the system of equations to obtain a solution result;
[0036] A test is performed according to the solution result using a preset test method to obtain a diagnosis result.
[0037] In addition, to achieve the above-mentioned purpose, the present application also proposes a vehicle control device, the vehicle control device comprising:
[0038] An acquisition module, used to acquire vehicle driving information;
[0039] A diagnosis module, used to perform fault diagnosis on the vehicle driving information through a preset neural network model to obtain fault information;
[0040] The diagnostic module is further used to perform a test according to the fault information by a preset test method to obtain a diagnostic result;
[0041] An instruction generation module, used to optimize the vehicle state according to the diagnosis result and generate control instructions;
[0042] The control module is used to control the vehicle according to the control instruction.
[0043] In addition, to achieve the above-mentioned purpose, the present invention also provides a vehicle control device, which includes: a memory, a processor, and a vehicle control program stored in the memory and executable on the processor, wherein the vehicle control program is configured to implement the steps of any one of the vehicle control methods described.
[0044] In addition, to achieve the above-mentioned purpose, the present invention also provides a medium, on which a vehicle control program is stored, and when the vehicle control program is executed by a processor, the steps of any one of the vehicle control methods are implemented.
[0045] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of the vehicle control method described above are implemented.
[0046] The present invention obtains vehicle driving information, performs fault diagnosis on the vehicle driving information through a preset neural network model, obtains fault information, performs testing through a preset test method according to the fault information, obtains a diagnosis result, optimizes the vehicle state according to the diagnosis result, generates a control instruction, and controls the vehicle according to the control instruction. By collecting vehicle conditions in real time, intelligently diagnosing faults and generating control instructions to control the vehicle, the control capability and fault diagnosis performance of the multi-domain integrated control system of new energy vehicles are improved, ensuring safe and efficient driving. BRIEF DESCRIPTION OF THE DRAWINGS
[0047] Figure 1 A schematic flow chart of a first embodiment of a vehicle control method of the present invention;
[0048] Figure 2 This is a structural block diagram of a new energy vehicle multi-domain integrated control system according to a first embodiment of a vehicle control method of the present invention;
[0049] Figure 3 A schematic flow chart of a second embodiment of a vehicle control method of the present invention;
[0050] Figure 4 A schematic flow chart of a third embodiment of a vehicle control method of the present invention;
[0051] Figure 5 This is a schematic diagram of the module structure of the vehicle control device according to an embodiment of the present application;
[0052] Figure 6 Schematic diagram of the device structure of the hardware operating environment involved in the vehicle control method in the embodiment of the present application. DETAILED DESCRIPTION
[0053] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.
[0054] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.
[0055] The main solution of the embodiment of the present application is: by acquiring vehicle driving information, diagnosing the fault of the vehicle driving information through a preset neural network model to obtain fault information, testing according to the fault information through a preset test method to obtain a diagnosis result, optimizing the vehicle state according to the diagnosis result, generating control instructions, and controlling the vehicle according to the control instructions.
[0056] Based on this, the embodiment of the present application provides a vehicle control method, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the vehicle control method of the present application.
[0057] The method is applied to the multi-domain integrated control system of new energy vehicles. Figure 2 The structural block diagram of the multi-domain integrated control system of new energy vehicles includes:
[0058] The central control module 10 is used to control and manage the entire vehicle system, coordinate the work of each part and the processing of data, and monitor the system, and maintain safety and performance;
[0059] Communication module 20, used for transmitting and integrating information from various parts and ensuring the secure transmission and sharing of various information;
[0060] The sensor group 30 is used to collect data information during the operation of the new energy vehicle, to collect information from various parts of the system, and to convert it into control instructions;
[0061] The controller 40 is responsible for receiving sensor data, storing and managing data, and performing data processing and control decision-making;
[0062] A fault diagnosis module 50 is used to diagnose the running state of the vehicle during driving, and to diagnose overvoltage, undervoltage, overtemperature, undertemperature, overcurrent and undercurrent during the running state of the vehicle; wherein the fault diagnosis module realizes the diagnosis of the vehicle driving process through the Malek test model;
[0063] The central control system 10 is respectively connected to the communication module 20 , the sensor group 30 , the controller 40 and the fault diagnosis module 50 .
[0064] Further, the sensor group 30 includes at least a torque sensor, an integrated sensor, a cam sensor, a crankshaft sensor and a motor temperature control sensor. In a specific embodiment, different information can be detected and calculated by different sensors to improve data information sensing capability.
[0065] Furthermore, the communication module 20 includes an in-vehicle network module and a wireless network module. The in-vehicle network module controls the in-vehicle sensor through the actuator operation, and the wireless network module includes a transmitting module, a receiving module, a GPRS module and a memory connected to the single-chip computer. The in-vehicle network module includes a bus, an actuator and an in-vehicle sensor; wherein the transmitting module includes a CC2541 wireless radio frequency chip, a transmitting circuit and a signal conversion module, the transmitting module transmits the digital electrical signal of the driving system, the signal conversion module converts the digital electrical signal into an analog signal through a digital-to-analog converter, and the CC2541 wireless radio frequency chip controls the analog signal to transmit the analog signal through the transmitting circuit; the receiving module includes a signal gain module, a receiving circuit, a signal processor and a signal conversion module, the receiving module receives the signal, the gain module amplifies the signal coefficient of the received signal through the antenna, the signal conversion module converts the analog signal into a digital signal through an analog-to-digital converter, and the signal processor analyzes and processes the digital signal.
[0066] Furthermore, the fault diagnosis module 50 includes an improved RBF neural network algorithm model, which is used to identify vehicle driving information, wherein the improved RBF neural network algorithm model integrated setting includes an RCE algorithm model and a KNN algorithm model. In this embodiment, an improved RBF neural network is introduced, and the multiplication operation of the difference value between the external data and the sample prototype vector of the RBF neural network algorithm model structure is changed to an addition operation to reduce the amount of network operation, and the RBF neural network superimposes the difference between the external data and the prototype sample; the RCE algorithm calculates the Manhattan distance in the middle layer; the KNN algorithm relies on the adjacent samples around the data point to classify; and the minimum mean square error algorithm is used to adjust the weight.
[0067] The principle of multi-domain integrated control system is to integrate systems from different fields in order to achieve the control requirements of different fields. Through testing and integration, a system with good performance can be designed, controlled and managed.
[0068] In this embodiment, the vehicle control method includes steps S10 to S50:
[0069] Step S10, obtaining vehicle driving information.
[0070] It should be noted that obtaining vehicle driving information involves real-time monitoring and data analysis of various parameters of the vehicle during driving. This information not only includes basic vehicle speed, fuel consumption, engine speed, etc., but also covers more complex data, such as battery power, motor temperature, brake system status, vehicle position, acceleration, inclination, etc. Through the real-time acquisition and analysis of this driving information, the control system can evaluate the health of the vehicle, predict potential failures and performance degradation, and take measures to intervene in advance. For example, if the system detects that the battery power is too low, it can automatically adjust the energy recovery strategy to optimize the battery efficiency; if it detects that the motor temperature is abnormally high, the system can reduce the motor load or start the cooling system in time to prevent damage caused by overheating.
[0071] In addition, driving information can also be used to optimize the dynamic performance of the vehicle. By analyzing data such as acceleration and inclination, the control system can adjust the stiffness and damping of the suspension system in real time to improve the vehicle's handling stability and ride comfort. At the same time, this information can also be used to build vehicle usage patterns and driving behavior analysis, providing data support for vehicle personalized settings and intelligent driving.
[0072] Step S20, performing fault diagnosis on the vehicle driving information through a preset neural network model to obtain fault information.
[0073] It should be noted that, in this embodiment, an improved RBF neural network is introduced as a preset neural network, wherein the integrated setting of the improved RBF neural network algorithm model includes an RCE algorithm model and a KNN algorithm model, and the multiplication operation of the external data of the RBF neural network algorithm model structure and the sample prototype vector difference value is changed to an addition operation to reduce the amount of network calculation, the RBF neural network superimposes the difference between the external data and the prototype sample, the RCE algorithm model calculates the Manhattan distance in the middle layer, and the KNN algorithm model relies on the neighboring samples around the data point for category classification, and the minimum mean square error algorithm is used to adjust the weights.
[0074] Furthermore, before the KNN algorithm model works, an initial chaotic differential evolution model is constructed, and the scaling factor, crossover factor and preset number of iterations are defined, and then the initialization population is obtained. The scaling factor is defined as F, the crossover factor is defined as CR, and the maximum number of iterations is defined as G. max , the number of global searches is K, and the initial population is randomly generated. Each individual in the population represents a potential solution, which is characterized by various parameters of vehicle driving information. Assuming that the population size is set to N, the formula for initializing the population number is:
[0075] x ij (0) = x max,j +rand(1)×(x max,j-x min,j )
[0076] Among them, x max,j is the maximum value of the parameter, x min,j is the minimum value of the parameter, i is a number between 1 and N, j is a scalar value of a different parameter, and rand(1) is a random number between 0 and 1.
[0077] Furthermore, the fitness of the population is calculated, and a fitness function is designed to evaluate the performance of each individual. The fitness function should be able to reflect the adaptability of the individual to the fault diagnosis task. Specifically, the calculation formula is:
[0078] F best =f(X best )
[0079] In different data parameters of vehicle driving data, different data information can be searched through indexes:
[0080] index(X best )=i
[0081] Furthermore, the fitness of different populations is mutated based on the scaling factor, and crossover calculation is performed based on the crossover factor to obtain the calculated fitness. The individuals in the population are mutated according to the scaling factor. The mutation operation is performed by adding a small, randomly determined change to the characteristics of the individual, simulating the random mutation in chaos theory. The specific formula is:
[0082] V i (t+1)=x r1 (t)+F×(x r2 (t)-x 3 (t))
[0083] Among them, r 1 ,r 2 ,r 3 is the amount of data for different parameters, x r1 (t) represents different data volumes. Then, the crossover factor is used to perform a crossover operation in the population to generate new offspring. The crossover operation simulates the gene recombination in the genetic algorithm. The specific calculation function is:
[0084]
[0085] Further, the calculated fitness is compared. When the calculated fitness is greater than a preset value or reaches a preset number of iterations, the initial chaotic differential evolution model is output, and the initial chaotic differential evolution model is merged into the preset neural network model. Specifically, the fitness of the population after mutation and crossover operations is calculated again, and then the new fitness is compared with the preset value, or it is checked whether the preset number of iterations has been reached. In this embodiment, the fitness is 10. If the condition is not reached, the iteration continues. The obtained optimal individual (i.e., the chaotic differential evolution model) is combined with the improved RBF neural network model, and the parameters of the chaotic differential evolution model are used as the input features or weights of the neural network. After the parameters of the chaotic differential evolution model are merged, the improved RBF neural network model is trained.
[0086] Step S30, performing a test using a preset test method according to the fault information to obtain a diagnosis result.
[0087] It should be noted that a preset test method is used for more in-depth diagnosis. For example, the Malek test method is a technology widely used in fault diagnosis of new energy vehicle drive control systems. It checks the vehicle drive control signal through two different test methods, and finally obtains the Malek test model through two test results. The model is represented in the form of a matrix W, and each element in the matrix reflects the state of the signal under a specific test (normal, undetected or faulty). Based on the Malek test results, a set of equations is constructed to represent the relationship between the state of each control signal and the detection signal. Each equation in the set of equations is a diagnostic condition for a signal, and these equations are combined to form a constraint system for parsing the true state of the signal. The above set of equations is solved by mathematical methods to obtain the state judgment of each control signal, that is, which signals are in normal working state and which have faults or abnormalities.
[0088] Step S40, optimizing the vehicle state according to the diagnosis result and generating a control instruction.
[0089] It should be noted that, based on the diagnosis results, the abnormal vehicle status is corrected or optimized to ensure that the vehicle's current operating condition returns to normal and reduce potential risks caused by control errors.
[0090] Step S50, controlling the vehicle according to the control instruction.
[0091] It should be noted that the generated control instructions are sent to the corresponding actuators, such as the motor controller, battery management system, etc., to perform specific operations. For example, if the control instruction indicates to increase the motor output power, the motor controller will adjust the motor speed and torque accordingly.
[0092] This embodiment obtains vehicle driving information, performs fault diagnosis on the vehicle driving information through a preset neural network model, obtains fault information, performs testing through a preset test method according to the fault information, obtains a diagnosis result, optimizes the vehicle state according to the diagnosis result, generates a control instruction, and controls the vehicle according to the control instruction. By collecting vehicle conditions in real time, intelligently diagnosing faults and generating control instructions to control the vehicle, the control capability and fault diagnosis performance of the multi-domain integrated control system of new energy vehicles are improved, ensuring safe and efficient driving.
[0093] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can refer to the above introduction, and will not be repeated later. Figure 3 The vehicle control method step S20 further includes steps S201 to S202:
[0094] Step S201: The vehicle driving information is identified through a preset neural network model to obtain a classification result.
[0095] It should be understood that the improved RBF neural network model includes the RCE algorithm model and the KNN algorithm model. The RCE algorithm model calculates the Manhattan distance in the middle layer, while the KNN algorithm model uses the adjacent samples around the data point to classify the data. The data information recognition is mainly based on the KNN algorithm model. The KNN algorithm uses a knowledge graph composed of multiple decision nodes and output nodes. The decision node represents the category of the sample, and the output node represents the node label obtained by the sample in the knowledge graph.
[0096] Furthermore, the vehicle driving information is preprocessed to obtain processed vehicle driving information. Specifically, the input vehicle driving information is first encoded to obtain encoded information, and then the encoded information is fused to obtain fused information. Finally, the fused information is filtered to obtain processed vehicle driving information.
[0097] Furthermore, key features are obtained from the processed vehicle driving information. Features closely related to the vehicle state are selected from the processed vehicle driving information. These features may include but are not limited to vehicle speed, battery voltage, motor temperature, accelerator pedal position, brake pedal position, steering angle, etc. These features can reflect the operating state of the vehicle under different working conditions, and then the frequency domain features are extracted by normalizing the features and performing Fourier transform, and then feature dimensionality reduction is performed using methods such as principal component analysis (PCA) or autoencoder to obtain key features and reduce computational complexity.
[0098] Furthermore, the key features are input into the preset neural network model for data information recognition to obtain the classification results. In the KNN algorithm, each feature needs to compare its knowledge node with a trained knowledge graph to determine whether the feature belongs to a certain category. The obtained key features are input into the improved RBF neural network model, and the classification results are output.
[0099] Step S202: Determine the vehicle fault type according to the classification result and obtain fault information.
[0100] It should be understood that the processed vehicle driving information is identified by the improved RBF neural network algorithm model to obtain classification results. These results are usually given in numerical form, representing the possibility of different fault types. Based on the classification results, the system can identify the specific fault types that the vehicle may encounter. For example, overvoltage, undervoltage, high or low temperature, overcurrent or undercurrent, etc. For each identified fault type, the system will collect relevant fault information. This information may include the time when the fault occurred, the duration, the affected system components, etc.
[0101] In this embodiment, the vehicle driving information is subjected to data information recognition through a preset neural network model to obtain a classification result, the vehicle fault type is determined based on the classification result, the fault information is obtained, the vehicle driving data is recognized through the neural network model, and the fault type is accurately determined.
[0102] Based on the first embodiment of the present application, in the third embodiment of the present application, the same or similar contents as those in the first embodiment can be referred to the above description, and will not be described in detail later. Figure 4 The vehicle control method step S30 further includes steps S301 to S303:
[0103] Step S301: input the fault information into a preset test matrix to construct a set of equations.
[0104] It should be noted that before constructing the equation group, a preset test matrix is first obtained. Sample fault information is obtained, and it is marked according to the sample fault information, and divided into first sample fault information and second sample fault information. The first sample fault information is a detected signal. When the detected fault information is that there is a fault, the fault information at this time is marked as -1, and when the detected fault information is that there is no fault, the fault information at this time is marked as +1. The second sample fault information refers to the fault information that has not been detected, which is marked as 0, and then a preset test matrix is constructed according to the first sample fault information. Specifically, the preset test matrix W is:
[0105] W=(w ij ) n×n ,w ij ∈{±1,0}
[0106] Among them, i and j represent the types of fault information.
[0107] Then, the system of equations is constructed according to W. The specific system of equations is expressed as:
[0108]
[0109] where u i and u j is the corresponding fault information, u i =1 is normal, u i =-1 means there is a fault.
[0110] Step S302: Solve the system of equations to obtain a solution result.
[0111] It should be understood that in order to solve the above system of equations, mathematical solution methods can be used, such as Gaussian elimination, LU decomposition, iteration method, etc. in linear algebra. These methods can help us find a solution set that satisfies all equations, that is, the state of each control signal, set initial conditions, such as the initial value of the unknown number or the coefficient matrix of the system of equations, gradually approach the optimal solution through repeated iterations, check whether the solution meets the convergence conditions after each iteration, and output the final solution as the solution result when the convergence conditions are met.
[0112] Step S303: Perform a test using a preset test method according to the solution result to obtain a diagnosis result.
[0113] Specifically, the solution provides the status judgment of each control signal, that is, which signals are in normal working state and which are faulty or abnormal. Based on the solution results of the Malek test method, the system can quickly identify the faulty vehicle components and generate control signals in time to take corresponding corrective measures to ensure the safe and stable operation of the vehicle.
[0114] In this embodiment, fault information is input into a preset test matrix, a set of equations is constructed, the set of equations is solved to obtain a solution result, and a preset test method is used to test according to the solution result to obtain a diagnostic result, thereby improving driving safety.
[0115] This application also provides a vehicle control device, please refer to Figure 5 , the device comprises:
[0116] The acquisition module 10 is used to acquire vehicle driving information.
[0117] The diagnosis module 20 is used to perform fault diagnosis on the vehicle driving information through a preset neural network model to obtain fault information.
[0118] The diagnosis module 20 is further used to perform a test using a preset test method according to the fault information to obtain a diagnosis result.
[0119] An instruction generation module 30, for optimizing the vehicle state according to the diagnosis result and generating a control instruction;
[0120] The control module 40 is used to control the vehicle according to the control instruction.
[0121] The vehicle control device provided by the present application adopts the vehicle control method in the above embodiment, which can solve the technical problem of how to improve the control capability and fault diagnosis performance of the multi-domain integrated control system of new energy vehicles. Compared with the prior art, the beneficial effects of the vehicle control device provided by the present application are the same as the beneficial effects of the vehicle control method provided by the above embodiment, and the other technical features in the vehicle control device are the same as the features disclosed in the above embodiment method, which will not be repeated here.
[0122] In one embodiment, the diagnosis module 20 is further used to perform data information recognition on the vehicle driving information through a preset neural network model to obtain a classification result; determine the vehicle fault type according to the classification result to obtain fault information.
[0123] In one embodiment, the diagnostic module 20 is also used to pre-process the vehicle driving information to obtain processed vehicle driving information; obtain key features from the processed vehicle driving information; input the key features into a preset neural network model to perform data information recognition to obtain classification results.
[0124] In one embodiment, the diagnostic module 20 is further used to encode the input vehicle driving information to obtain encoded information; fuse the encoded information to obtain fused information; and filter the fused information to obtain processed vehicle driving information.
[0125] In one embodiment, the diagnostic module 20 is also used to construct an initial chaotic differential evolution model, and define a scaling factor, a crossover factor and a preset number of iterations; obtain an initialized population; calculate the fitness of the population; perform a mutation operation on the fitness of different populations based on the scaling factor, and perform a crossover calculation based on the crossover factor to obtain the calculated fitness; compare the calculated fitness, and when the calculated fitness is greater than a preset value or reaches a preset number of iterations, output the initial chaotic differential evolution model, and merge the initial chaotic differential evolution model into the preset neural network model.
[0126] In one embodiment, the diagnosis module 20 is further used to obtain sample fault information; mark the sample fault information and divide it into first sample fault information and second sample fault information; and construct a preset test matrix according to the first sample fault information.
[0127] In one embodiment, the diagnostic module 20 is further used to input fault information into a preset test matrix to construct a set of equations; solve the set of equations to obtain a solution result; and perform a test using a preset test method according to the solution result to obtain a diagnostic result.
[0128] The present application provides a vehicle control device, which includes: at least one processor; and a memory that is communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the vehicle control method in the above-mentioned embodiment one.
[0129] Reference below Figure 6 , which shows a schematic diagram of the structure of a vehicle control device suitable for implementing an embodiment of the present application. The vehicle control device in the embodiment of the present application may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 6 The vehicle control device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.
[0130] like Figure 6As shown, the vehicle control device may include a processing device 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the vehicle control device are also stored. The processing device 1001, ROM1002, and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the vehicle control device to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows a vehicle control device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or have alternatively.
[0131] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.
[0132] The vehicle control device provided by the present application adopts the vehicle control method in the above embodiment, which can solve the technical problem of how to improve the control capability and fault diagnosis performance of the multi-domain integrated control system of new energy vehicles. Compared with the prior art, the beneficial effects of the vehicle control device provided by the present application are the same as the beneficial effects of the vehicle control method provided by the above embodiment, and the other technical features in the vehicle control device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.
[0133] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.
[0134] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.
[0135] The present application provides a computer-readable medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the vehicle control method in the above-mentioned embodiment.
[0136] The computer-readable medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.
[0137] The computer-readable medium may be included in the vehicle control device; or may exist independently without being assembled into the vehicle control device.
[0138] The computer-readable medium carries one or more programs. When the one or more programs are executed by the vehicle control device, the vehicle control device can write computer program codes for performing the operations of the present application in one or more programming languages or a combination thereof. The programming languages include object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "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 an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).
[0139] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.
[0140] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.
[0141] The readable medium provided in this application is a computer-readable medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned vehicle control method, and can solve the technical problem of how to improve the control capability and fault diagnosis performance of the multi-domain integrated control system of new energy vehicles. Compared with the prior art, the beneficial effects of the computer-readable medium provided in this application are the same as the beneficial effects of the vehicle control method provided in the above-mentioned embodiment, and will not be repeated here.
[0142] The present application also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the steps of the vehicle control method as described above are implemented.
[0143] The computer program product provided by this application can solve the technical problem of how to improve the control capability and fault diagnosis performance of the multi-domain integrated control system of new energy vehicles. Compared with the prior art, the beneficial effects of the computer program product provided by this application are the same as the beneficial effects of the vehicle control method provided by the above embodiment, which will not be repeated here.
[0144] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.
Claims
1. A vehicle control method, It is characterized in that The method comprises: Obtain vehicle driving information; Performing fault diagnosis on the vehicle driving information by using a preset neural network model to obtain fault information; Performing a test using a preset test method according to the fault information to obtain a diagnosis result; Optimizing the vehicle state according to the diagnosis result and generating control instructions; The vehicle is controlled according to the control instruction.
2. The method according to claim 1, It is characterized in that The step of performing fault diagnosis on the vehicle driving information by using a preset neural network model to obtain fault information comprises: The vehicle driving information is identified by a preset neural network model to obtain a classification result; The vehicle fault type is determined according to the classification result to obtain fault information.
3. The method according to claim 2, It is characterized in that The step of identifying the vehicle driving information through a preset neural network model to obtain a classification result includes: Preprocessing the vehicle driving information to obtain processed vehicle driving information; Acquiring key features from the processed vehicle travel information; The key features are input into the preset neural network model to perform data information recognition to obtain classification results.
4. The method according to claim 3, It is characterized in that The step of preprocessing the vehicle driving information to obtain processed vehicle driving information includes: Encode the input vehicle driving information to obtain encoded information; Fusing the encoded information to obtain fused information; The fused information is filtered to obtain processed vehicle driving information.
5. The method according to claim 1, It is characterized in that Before the step of performing fault diagnosis on the vehicle driving information by using a preset neural network model to obtain fault information, the method includes: Construct an initial chaotic differential evolution model and define the scaling factor, crossover factor and preset number of iterations; Get the initial population; calculating the fitness of the population; Performing a mutation operation on the fitness of different populations based on the scaling factor, and performing a crossover calculation based on the crossover factor to obtain calculated fitness; The calculated fitness is compared, and when the calculated fitness is greater than a preset value or reaches a preset number of iterations, the initial chaotic differential evolution model is output, and the initial chaotic differential evolution model is integrated into a preset neural network model.
6. The method according to claim 1, It is characterized in that Before the step of performing a test according to the fault information by a preset test method to obtain a diagnosis result, the method includes: Get sample fault information; Marking the sample fault information to divide it into first sample fault information and second sample fault information; A preset test matrix is constructed according to the first sample fault information.
7. The method according to claim 6, It is characterized in that The step of performing a test according to the fault information by a preset test method to obtain a diagnosis result comprises: Inputting the fault information into the preset test matrix to construct a set of equations; Solving the system of equations to obtain a solution result; A test is performed according to the solution result using a preset test method to obtain a diagnosis result.
8. A vehicle control device, It is characterized in that The device comprises: An acquisition module, used to acquire vehicle driving information; A diagnosis module, used to perform fault diagnosis on the vehicle driving information through a preset neural network model to obtain fault information; The diagnostic module is further used to perform a test according to the fault information by a preset test method to obtain a diagnostic result; An instruction generation module, used to optimize the vehicle state according to the diagnosis result and generate control instructions; The control module is used to control the vehicle according to the control instruction.
9. A vehicle control device, It is characterized in that The device comprises: a memory, a processor, and a vehicle control program stored in the memory and executable on the processor, wherein the vehicle control program is configured to implement the steps of the vehicle control method according to any one of claims 1 to 7.
10. A medium, It is characterized in that The medium stores a vehicle control program, and when the vehicle control program is executed by the processor, the steps of the vehicle control method according to any one of claims 1 to 7 are implemented.
