Mechanism-data fusion driven bidirectional wireless charger control method and system

Abstract

The application belongs to the field of new energy vehicles, and provides a mechanism-data fusion driving bidirectional wireless charger control method and system, which comprises mathematical modeling based on a bidirectional wireless charger topology to obtain an equivalent topology model of the bidirectional wireless charger; taking system demand power as input, predicting based on the equivalent topology model of the bidirectional wireless charger, and constructing a control strategy based on the topology model of the bidirectional wireless charger; obtaining actual demand power of the system, and obtaining a control amount prediction value of the bidirectional wireless charger according to the control strategy based on the topology model of the bidirectional wireless charger; the application combines a topology model based on circuit principle and a neural network algorithm under data driving to solve the problems of poor prediction accuracy of a traditional topology model and high control difficulty of a single neural network method.

Description

Technical Field

[0001] This invention belongs to the field of new energy vehicle technology, specifically relating to a mechanism-data fusion-driven bidirectional wireless charger control method and system. Background Technology

[0002] The statements in this section are merely background information related to the present invention and do not necessarily constitute prior art.

[0003] With the increasing number of traditional gasoline-powered vehicles on the road, energy shortages and environmental protection issues have received growing attention. Vigorously developing new energy vehicles has become an effective way to address energy conservation and environmental protection in the automotive industry, and also a powerful measure to achieve national ecological civilization construction. However, the current traditional wired charging method for electric vehicles offers a poor charging experience and poses safety hazards during the charging process, hindering the further promotion and development of electric vehicles.

[0004] In recent years, wireless power transfer technology has been increasingly widely used in electric vehicles. Compared with traditional wired charging, wireless charging technology can not only effectively solve charging safety issues, but also be combined with technologies such as automatic parking, intelligent recognition, and V2G to achieve automated, intelligent, and convenient electric vehicle charging. However, for bidirectional wireless charging, existing control methods suffer from poor prediction accuracy using traditional topology models and high control difficulty using single neural network methods. This results in the inability to accurately control bidirectional wireless chargers and achieve rapid and accurate charging power response during wired charging. Summary of the Invention

[0005] To address the aforementioned issues, this invention proposes a mechanism-data fusion-driven bidirectional wireless charger control method and system. This invention aims to combine a circuit-based topology model with a data-driven neural network algorithm to solve the problems of poor prediction accuracy of traditional topology models and high control difficulty of single neural network methods, thereby enabling rapid and accurate response of charging power during the wireless charging process.

[0006] According to some embodiments, the first solution of the present invention provides a mechanism-data fusion driven bidirectional wireless charger control method, which adopts the following technical solution:

[0007] A mechanism-data fusion-driven bidirectional wireless charger control method includes:

[0008] Mathematical modeling of the bidirectional wireless charger topology is performed to obtain the equivalent topology model of the bidirectional wireless charger.

[0009] Using the system power demand as input, prediction is performed based on the equivalent topology model of the bidirectional wireless charger, and a control strategy based on the topology model of the bidirectional wireless charger is constructed.

[0010] The actual power demand of the system is obtained, and the predicted control values ​​of the bidirectional wireless charger are obtained according to the control strategy based on the bidirectional wireless charger topology model.

[0011] Furthermore, the method also includes:

[0012] Based on the control strategy of the bidirectional wireless charger topology model, experimental tests were conducted to test the power required by the same system and to detect the difference between the theoretical and actual values ​​of the control quantity.

[0013] Based on the difference between the theoretical and actual values ​​of the control quantity, a neural network model is trained to obtain a well-trained bidirectional wireless charger control quantity correction model.

[0014] The control quantity of the bidirectional wireless charger is corrected based on the trained bidirectional wireless charger control quantity correction model.

[0015] Furthermore, the control strategy based on the bidirectional wireless charger topology model was experimentally tested for the same system power requirements, and the difference between the theoretical and actual control values ​​was detected. Specifically:

[0016] A control strategy based on the topology model of a bidirectional wireless charger is used to control the physical bidirectional wireless charger.

[0017] The bidirectional wireless charger was tested using a load simulator, the system power requirements were set, and the actual system response value was detected.

[0018] Calculate the theoretical response value based on the given power demand, and then compare and analyze the differences between the theoretical response value and the actual response value.

[0019] Furthermore, the process of training a neural network model based on the difference between the theoretical and actual values ​​of the control quantity to obtain a trained bidirectional wireless charger control quantity correction model includes:

[0020] Based on the actual and theoretical response values ​​of the system obtained from the experiment

[0021] The actual system response value is used as input, and the theoretical response value is used as output.

[0022] A training set and a test set are established using a sampling method. A neural network model is then built using the training set and the test set, and the neural network model is trained.

[0023] A well-trained bidirectional wireless charger control quantity correction model is obtained.

[0024] Furthermore, the mathematical modeling based on the bidirectional wireless charger topology to obtain an equivalent topological model of the bidirectional wireless charger includes:

[0025] Based on a given bidirectional wireless charger topology, establish a mathematical description of all electrical components within the topology;

[0026] It takes the power demand at the load end as input and the voltage, current and power at the supply end as output;

[0027] An equivalent topological model of a bidirectional wireless charger is established using Kirchhoff's voltage law and current law.

[0028] Furthermore, the control strategy based on the bidirectional wireless charger topology model is specifically as follows:

[0029] This is a control method that takes the power required by the system as input, makes predictions based on the equivalent topology model of the bidirectional wireless charger, and outputs the predicted control quantity of the bidirectional wireless charger.

[0030] Furthermore, the predicted control quantity includes predicted voltage control quantity and predicted current control quantity.

[0031] According to some embodiments, the second aspect of the present invention provides a mechanism-data fusion driven bidirectional wireless charger control system, which adopts the following technical solution:

[0032] A mechanism-data fusion-driven bidirectional wireless charger control system includes:

[0033] The topology model building module is configured to perform mathematical modeling based on the bidirectional wireless charger topology to obtain an equivalent topology model of the bidirectional wireless charger.

[0034] A control strategy module is configured to take the system demand power as input, make predictions based on the equivalent topology model of the bidirectional wireless charger, and construct a control strategy based on the topology model of the bidirectional wireless charger.

[0035] The control prediction module is configured to obtain the actual power demand of the system and, based on the control strategy of the bidirectional wireless charger topology model, obtain the predicted control quantity of the bidirectional wireless charger.

[0036] According to some embodiments, a third aspect of the present invention provides a computer-readable storage medium.

[0037] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the mechanism-data fusion-driven bidirectional wireless charger control method as described in the first aspect above.

[0038] According to some embodiments, a fourth aspect of the present invention provides a computer device.

[0039] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the program, implements the steps of the mechanism-data fusion-driven bidirectional wireless charger control method described in the first aspect above.

[0040] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0041] This invention combines a discretized control model for a bidirectional wireless charger with a data-driven neural network algorithm. Through model predictive control, the discretized control model predicts the charger output based on a given power demand. The predicted value is then corrected through experiments. Based on the charger output predicted by the control model and with the correction value from the neural network algorithm as a reference, precise control of the bidirectional wireless charger is achieved. Attached Figure Description

[0042] The accompanying drawings, which form part of this invention, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an improper limitation of the invention.

[0043] Figure 1 This is a flowchart of the mechanism-data fusion-driven bidirectional wireless charger control method described in an embodiment of the present invention. Detailed Implementation

[0044] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0045] It should be noted that the following detailed description is illustrative and intended to provide further explanation of the invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0046] It should be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of exemplary embodiments according to the invention. As used herein, the singular form is intended to include the plural form as well, unless the context clearly indicates otherwise. Furthermore, it should be understood that when the terms "comprising" and / or "including" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.

[0047] Where there is no conflict, the embodiments and features in the embodiments of the present invention can be combined with each other.

[0048] Example 1

[0049] like Figure 1As shown, this embodiment provides a mechanism-data fusion-driven bidirectional wireless charger control method. This embodiment uses the application of this method to a server as an example for illustration. It is understood that this method can also be applied to terminals, and can also be applied to systems including terminals, servers, and other components, and is implemented through interaction between the terminal and the server. The server can be an independent physical server, a server cluster composed of multiple physical servers, or a distributed system. It can also be a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network servers, cloud communication, middleware services, domain name services, CDN security services, and big data and artificial intelligence platforms. The terminal can be a smartphone, tablet, laptop, desktop computer, smart speaker, smartwatch, etc., but is not limited to these. The terminal and server can be directly or indirectly connected via wired or wireless communication, which is not limited herein. In this embodiment, the method includes the following steps:

[0050] Step S1: Perform mathematical modeling based on the bidirectional wireless charger topology to obtain the equivalent topology model of the bidirectional wireless charger;

[0051] The mathematical modeling based on the bidirectional wireless charger topology yields an equivalent topology model of the bidirectional wireless charger, including:

[0052] Step S1.1: Based on the given bidirectional wireless charger topology, establish a mathematical description of all electrical components within the topology;

[0053] Step S1.2: Take the power demand at the load end as the input, and the voltage, current and power at the supply end as the output;

[0054] Step S1.3: Establish an equivalent topology model of the bidirectional wireless charger using Kirchhoff's voltage law and current law.

[0055] Step S2: Using the system power demand as input, predict based on the equivalent topology model of the bidirectional wireless charger, and construct a control strategy based on the topology model of the bidirectional wireless charger.

[0056] Step S3: Obtain the actual power demand of the system, and according to the control strategy based on the bidirectional wireless charger topology model, obtain the predicted control quantity of the bidirectional wireless charger.

[0057] Specifically, the method also includes:

[0058] Based on the control strategy of the bidirectional wireless charger topology model, experimental tests were conducted to test the power required by the same system and to detect the difference between the theoretical and actual values ​​of the control quantity.

[0059] Based on the difference between the theoretical and actual values ​​of the control quantity, a neural network model is trained to obtain a well-trained bidirectional wireless charger control quantity correction model.

[0060] The control quantity of the bidirectional wireless charger is corrected based on the trained bidirectional wireless charger control quantity correction model.

[0061] The control strategy based on the bidirectional wireless charger topology model was tested experimentally for the same system power requirements, and the difference between the theoretical and actual control values ​​was detected. Specifically:

[0062] A control strategy based on the topology model of a bidirectional wireless charger is used to control the physical bidirectional wireless charger.

[0063] The bidirectional wireless charger was tested using a load simulator, the system power requirements were set, and the actual system response value was detected.

[0064] Calculate the theoretical response value based on the given power demand, and then compare and analyze the differences between the theoretical response value and the actual response value.

[0065] The process involves training a neural network model based on the difference between the theoretical and actual values ​​of the control quantity, resulting in a well-trained bidirectional wireless charger control quantity correction model. This model includes:

[0066] Based on the actual and theoretical response values ​​of the system obtained from the experiment

[0067] The actual system response value is used as input, and the theoretical response value is used as output.

[0068] A training set and a test set are established using a sampling method. A neural network model is then built using the training set and the test set, and the neural network model is trained.

[0069] A well-trained bidirectional wireless charger control quantity correction model is obtained.

[0070] The control strategy based on the bidirectional wireless charger topology model is as follows:

[0071] This is a control method that takes the power required by the system as input, makes predictions based on the equivalent topology model of the bidirectional wireless charger, and outputs the predicted control quantity of the bidirectional wireless charger.

[0072] The predicted control values ​​include predicted voltage control values ​​and predicted current control values.

[0073] like Figure 1 As shown, the method described in this embodiment includes:

[0074] First, the topology of the bidirectional wireless charger is mathematically modeled and converted into state-space equations using a discretization method.

[0075] Secondly, a control strategy based on a bidirectional wireless charger model is constructed, and the current / voltage control quantities are predicted based on the model according to the required power.

[0076] Next, experimental tests were conducted to examine the difference between the control quantity predicted by the model and the expected value for a given power demand.

[0077] Finally, a neural network model is established to correct the control quantities predicted by the model, thereby achieving precise control of the bidirectional wireless charger.

[0078] The bidirectional wireless charger topology mathematical modeling described in this embodiment refers to establishing mathematical descriptions of components such as capacitors, inductors, resistors, and transformers within a given bidirectional wireless charger topology. An equivalent topology model of the bidirectional wireless charger is established using Kirchhoff's voltage law, Kirchhoff's current law, and other methods. The model takes the power demand at the load end as input and the voltage, current, power, and other parameters at the supply end as outputs.

[0079] The discretization-based transformation of state-space equations described in this embodiment refers to discretizing the bidirectional wireless charger topology model constructed in the time domain using methods such as S-transform and Z-transform, and converting it into state-space equations in the frequency domain.

[0080] The transformed equations include the system state variables at the current moment, the system state variables at the next moment, the system input at the current moment, the system state transition matrix, the system control transition matrix, and the system observation equations.

[0081] The control strategy based on the bidirectional wireless charger model described in this embodiment refers to a control method that takes the power demanded by the system as input, combines the prediction of the bidirectional wireless charger model, and outputs the predicted values ​​of current / voltage control quantities. By establishing the system control objective, an evaluation function is formed, and the optimal value of the evaluation function and its corresponding predicted values ​​of system current / voltage control quantities are solved through the optimization control method.

[0082] Using the power required by the system as input, predictions are made based on the equivalent topology model of the bidirectional wireless charger to obtain the predicted control quantity of the bidirectional wireless charger.

[0083] Establish system control objectives and formulate evaluation functions;

[0084] The optimal value of the evaluation function and its corresponding predicted control quantity of the bidirectional wireless charger are obtained by using the optimal control method.

[0085] The evaluation function refers to the predicted control quantity of the bidirectional wireless charger that is optimal under the premise of meeting the system's control objectives.

[0086] Specifically, the control strategies described in this embodiment may include PID control, model predictive control, sliding mode control, neural network control, fuzzy control, etc.

[0087] The experimental testing described in this embodiment, which detects the difference between the control quantity predicted by the model and the expected value for a given power demand, refers to converting the control strategy code into an executable file for an embedded system based on a physical bidirectional wireless charger. The embedded system is then used to control the bidirectional wireless charger, and the charger is tested using devices such as a load simulator. By setting the power demand, the actual current and voltage signals of the system response are detected. The theoretical value of the response is calculated based on the given power demand, and then compared with the actual response value to analyze the difference.

[0088] The method described in this embodiment for correcting the control quantity predicted by the model using a neural network model refers to establishing a training set and a test set by sampling partitioning the actual system response value and the theoretical response value obtained from the experiment, with the actual system response value as input and the theoretical response value as output, and then establishing and training the neural network model using the training set and the test set.

[0089] The neural network models described in this embodiment include various neural network prediction models such as BP neural network model, RBF neural network model, recurrent neural network model, and LSTM neural network model.

[0090] The bidirectional wireless charger control method proposed in this embodiment combines a charger model and a neural network model. Based on the model prediction, the neural network model is used for correction to improve the tracking ability of the expected response and achieve precise control of the bidirectional wireless charger.

[0091] Example 2

[0092] This embodiment provides a mechanism-data fusion-driven bidirectional wireless charger control system, including:

[0093] The topology model building module is configured to perform mathematical modeling based on the bidirectional wireless charger topology to obtain an equivalent topology model of the bidirectional wireless charger.

[0094] A control strategy module is configured to take the system demand power as input, make predictions based on the equivalent topology model of the bidirectional wireless charger, and construct a control strategy based on the topology model of the bidirectional wireless charger.

[0095] The control prediction module is configured to obtain the actual power demand of the system and, based on the control strategy of the bidirectional wireless charger topology model, obtain the predicted control quantity of the bidirectional wireless charger.

[0096] The examples and application scenarios implemented by the above modules and corresponding steps are the same, but are not limited to the content disclosed in Embodiment 1 above. It should be noted that the above modules, as part of the system, can be executed in a computer system such as a set of computer-executable instructions.

[0097] The descriptions of each embodiment in the above embodiments have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0098] The proposed system can be implemented in other ways. For example, the system embodiments described above are merely illustrative, and the division of modules described above is only a logical functional division. In actual implementation, there may be other division methods. For example, multiple modules may be combined or integrated into another system, or some features may be ignored or not executed.

[0099] Example 3

[0100] This embodiment provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps in the mechanism-data fusion-driven bidirectional wireless charger control method described in Embodiment 1 above.

[0101] Example 4

[0102] This embodiment provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the steps in the mechanism-data fusion-driven bidirectional wireless charger control method described in Embodiment 1 above.

[0103] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of hardware embodiments, software embodiments, or embodiments combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage and optical storage) containing computer-usable program code.

[0104] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0105] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0106] These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable apparatus for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0107] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc.

[0108] While the specific embodiments of the present invention have been described above in conjunction with the accompanying drawings, this is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art without creative effort based on the technical solutions of the present invention are still within the scope of protection of the present invention.

Claims

1. A mechanism-data fusion-driven bidirectional wireless charger control method, characterized in that, include: Mathematical modeling of the bidirectional wireless charger topology is performed to obtain an equivalent topological model of the bidirectional wireless charger, which is then converted into a state-space equation through a discretization method. Using the system power demand as input, prediction is made based on the equivalent topology model of the bidirectional wireless charger, and a control strategy based on the bidirectional wireless charger topology model is constructed; using the voltage, current and power of the supply side as output; and establishing the equivalent topology model of the bidirectional wireless charger through Kirchhoff's voltage law and Kirchhoff's current law. The actual power demand of the system is obtained, and the predicted control quantity of the bidirectional wireless charger is obtained according to the control strategy based on the bidirectional wireless charger topology model. Experimental tests are carried out based on the control strategy of the bidirectional wireless charger topology model for the same system power demand to detect the difference between the theoretical value and the actual value of the control quantity. Based on the relationship between the difference between the theoretical value and the actual value of the control quantity, a neural network model is trained to obtain a trained bidirectional wireless charger control quantity correction model, which corrects the control quantity of the bidirectional wireless charger. The process involves training a neural network model based on the difference between the theoretical and actual values ​​of the control quantity, resulting in a well-trained bidirectional wireless charger control quantity correction model. This model includes: Based on the actual and theoretical response values ​​of the system obtained from the experiment The actual system response value is used as input, and the theoretical response value is used as output. A training set and a test set are established using a sampling method. A neural network model is then built using the training set and the test set, and the neural network model is trained. A well-trained bidirectional wireless charger control quantity correction model is obtained; The control strategy based on the bidirectional wireless charger topology model is as follows: This is a control method that takes the power required by the system as input, makes predictions based on the equivalent topology model of the bidirectional wireless charger, and outputs the predicted control quantity of the bidirectional wireless charger.

2. The mechanism-data fusion-driven bidirectional wireless charger control method as described in claim 1, characterized in that, The control strategy based on the bidirectional wireless charger topology model was tested experimentally for the same system power requirements. The difference between the theoretical and actual control values ​​was detected. Specifically: A control strategy based on the topology model of a bidirectional wireless charger is used to control the physical bidirectional wireless charger. The bidirectional wireless charger was tested using a load simulator, the system power requirements were set, and the actual system response value was detected. Calculate the theoretical response value based on the given power demand, and then compare and analyze the differences between the theoretical response value and the actual response value.

3. The mechanism-data fusion-driven bidirectional wireless charger control method as described in claim 1, characterized in that, The mathematical modeling based on the bidirectional wireless charger topology yields an equivalent topology model of the bidirectional wireless charger, including: Based on a given bidirectional wireless charger topology, a mathematical description is established for all electrical components within the topology.

4. The mechanism-data fusion-driven bidirectional wireless charger control method as described in claim 1, characterized in that, The predicted control values ​​include predicted voltage control values ​​and predicted current control values.

5. A mechanism-data fusion-driven bidirectional wireless charger control system, characterized in that, include: The topology model building module is configured to perform mathematical modeling based on the topology of the bidirectional wireless charger, obtain the equivalent topology model of the bidirectional wireless charger, and convert it into state-space equations through discretization. A control strategy module is constructed and configured to take the system demand power as input, predict it based on the equivalent topology model of the bidirectional wireless charger, and construct a control strategy based on the topology model of the bidirectional wireless charger; the voltage, current and power of the supply side are used as outputs; and the equivalent topology model of the bidirectional wireless charger is established through Kirchhoff's voltage law and Kirchhoff's current law. The control prediction module is configured to acquire the actual power demand of the system, obtain the predicted control quantity of the bidirectional wireless charger based on the control strategy of the bidirectional wireless charger topology model, conduct experimental tests based on the control strategy of the bidirectional wireless charger topology model for the same system power demand, and detect the difference between the theoretical value and the actual value of the control quantity; based on the difference between the theoretical value and the actual value of the control quantity, train a neural network model to obtain a trained bidirectional wireless charger control quantity correction model, and correct the control quantity of the bidirectional wireless charger. The process involves training a neural network model based on the difference between the theoretical and actual values ​​of the control quantity, resulting in a well-trained bidirectional wireless charger control quantity correction model. This model includes: Based on the actual and theoretical response values ​​of the system obtained from the experiment The actual system response value is used as input, and the theoretical response value is used as output. A training set and a test set are established using a sampling method. A neural network model is then built using the training set and the test set, and the neural network model is trained. A well-trained bidirectional wireless charger control quantity correction model is obtained; The control strategy based on the bidirectional wireless charger topology model is as follows: This is a control method that takes the power required by the system as input, makes predictions based on the equivalent topology model of the bidirectional wireless charger, and outputs the predicted control quantity of the bidirectional wireless charger.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the steps in the mechanism-data fusion-driven bidirectional wireless charger control method as described in any one of claims 1-4.

7. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps in the mechanism-data fusion-driven bidirectional wireless charger control method as described in any one of claims 1-4.

Images