Electrodynamic force determination method and device, electronic equipment and storage medium

Abstract

The invention discloses an electrodynamic force determination method and apparatus, an electronic device and a storage medium. The method comprises the steps of obtaining first parameter information of a first switch in a first state; inputting the current density of the first switch, the magnetic induction intensity of the first switch, the conductivity of a movable blade of the first switch, the electric field intensity of the first switch and the volume of the first switch into a first target model to obtain a first ampere force of the first switch, inputting the magnetic conductivity of the movable blade of the first switch, the magnetic induction intensity of the first switch, the contact area of the movable blade of the first switch and the static contact, the density of the movable blade of the first switch, the current density of the first switch and the electric field intensity of the first switch into a second target model to obtain a first Holm force of the first switch, and determining a first electrodynamic force of the first switch according to the first ampere force and the first Holm force. Through the first target model and the second target model, the size of the first electrodynamic force can be finally, quickly and accurately obtained in real time.

Description

Technical Field

[0001] The present invention relates to the technical field of power electronics and electromagnetic field modeling, and in particular to a method and device for determining electric force, an electronic device, and a storage medium. Background Art

[0002] In the fields of power electronics and electromagnetic field modeling, accurately obtaining relevant force parameters, such as electrodynamic forces, that characterize the health of switches is of great importance. Traditional methods for determining electrodynamic forces in switches typically rely on empirical formulas and manual calculations. However, these methods have numerous limitations and drawbacks, including low computational accuracy, high complexity, and the inability to capture dynamic data in real time. Summary of the Invention

[0003] The present invention provides a method and device for determining the electromotive force of a switch, an electronic device and a storage medium to solve the problem of low accuracy and high complexity in calculating the electromotive force of a switch.

[0004] According to a first aspect of the present invention, a method for determining the electric force of a switch is provided, wherein the switch includes a movable blade and at least one stationary contact, and the method for determining the electric force of the switch includes:

[0005] acquiring first parameter information of the first switch in the first state, where the first parameter information of the first switch in the first state includes: magnetic induction intensity of the first switch, electric field intensity of the first switch, volume of the first switch, current density of the first switch, electrical conductivity of a movable blade of the first switch, magnetic permeability of the movable blade of the first switch, density of the movable blade of the first switch, and contact area between the movable blade and a static contact of the first switch;

[0006] Inputting the current density of the first switch, the magnetic induction intensity of the first switch, the conductivity of the movable blade of the first switch, the electric field intensity of the first switch, and the volume of the first switch into a first target model to obtain a first Ampere force of the first switch;

[0007] inputting the magnetic permeability of the movable blade of the first switch, the magnetic induction intensity of the first switch, the contact area between the movable blade and the static contact of the first switch, the density of the movable blades of the first switch, the current density of the first switch, and the electric field intensity of the first switch into a second target model to obtain a first Holm force of the first switch;

[0008] A first electromotive force of the first switch is determined according to the first Ampere force and the first Holm force.

[0009] Optionally, determining the first electromotive force of the first switch according to the first Ampere force and the first Holm force includes:

[0010] The sum of a product of the first Ampere force multiplied by a first weight and a product of the first Holm force multiplied by a second weight is determined as the first electromotive force of the first switch.

[0011] Optionally, before obtaining the first parameter information of the first switch in the first state, the method further includes: obtaining a set of second parameter information for each of the c second switches in each of the m second states, and an actual Ampere force and an actual Holm force corresponding to each set of second parameter information; the second parameter information of the second switch in the second state includes: magnetic induction intensity of the second switch, electric field intensity of the second switch, volume of the second switch, current density of the second switch, electrical conductivity of the movable blade of the second switch, magnetic permeability of the movable blade of the second switch, density of the movable blade of the second switch, and contact area between the movable blade and the static contact of the second switch; m, a, and c are all integers greater than or equal to 1;

[0012] The current density of the second switch, the magnetic induction intensity of the second switch, the conductivity of the movable blade of the second switch, the electric field intensity of the second switch, the volume of the second switch and the corresponding actual Ampere force are used as a first training data set;

[0013] using the magnetic permeability of the movable blade of the second switch, the magnetic induction intensity of the second switch, the contact area between the movable blade and the static contact of the second switch, the density of the movable blades of the second switch, the current density of the second switch, the electric field intensity of the second switch, and the actual Holm force as a second training data set;

[0014] Inputting c·m·a first training data sets into the first initial model, and sequentially obtaining c·m·a first initial Ampere forces; inputting c·m·a second training data sets into the second initial model, and sequentially obtaining c·m·a first initial Holm forces;

[0015] The first weight is adjusted according to the first initial Ampere force and the actual Ampere force; and the second weight is adjusted according to the first initial Holm force and the actual Holm force.

[0016] Optionally, adjusting the first weight according to the first initial Ampere force and the actual Ampere force includes:

[0017] Using a ratio of the p-th actual Ampere force to the p-th first training data set input into the first initial model to obtain the first initial Ampere force as a first weight corresponding to the first initial model during the p-th training, and determining a first loss function value corresponding to the first weight during the p-th training; p is an integer greater than or equal to 1 and less than or equal to c·m·a;

[0018] Inputting the second parameter information into the first policy network to obtain a first probability distribution, where the first probability distribution is used to represent an adjustment direction of the model parameters of the first initial model;

[0019] Inputting the second parameter information into a first value network to obtain a first value, where the first value is used to identify an adjustment value of the first strategy network;

[0020] The adjusting the second weight according to the first initial Holm force and the actual Holm force includes:

[0021] Using a ratio of the p-th actual Holm force to the p-th second training data set input into the second initial model to obtain the first initial Holm force as a second weight corresponding to the second initial model during the p-th training, and determining a second loss function value corresponding to the second weight during the p-th training;

[0022] Inputting the second parameter information into a second policy network to obtain a second probability distribution, where the second probability distribution is used to represent an adjustment direction of the model parameters of the second initial model;

[0023] The second parameter information is input into a second value network to obtain a second value, where the second value is used to identify an adjustment value of the second strategy network.

[0024] Optionally, the first parameter information of the first switch in the first state includes the electric field strength of the first switch;

[0025] The acquiring of first parameter information of the first switch in the first state includes:

[0026] Acquiring an electric field distribution image of the first switch in a first state;

[0027] The electric field strength at the center of the movable blade of the first switch is determined according to the electric field distribution image, and the electric field strength at the center of the movable blade of the first switch is used as the electric field strength of the first switch.

[0028] Optionally, the first parameter information of the first switch in the first state includes a current density of the first switch;

[0029] The acquiring first parameter information of the first switch in the first state includes:

[0030] obtaining current values ​​of the first switch at different times respectively;

[0031] generating an initial current waveform function according to current values ​​of the first switch at different times;

[0032] generating a predicted current waveform function based on an ensemble learning algorithm and the initial current waveform function;

[0033] A maximum value of the predicted current is determined according to the predicted current waveform function, and a current density of the first switch is determined according to the maximum value of the predicted current.

[0034] Optionally, the first parameter information of the first switch in the first state includes the density of the movable blade of the first switch, the electrical conductivity of the movable blade of the first switch, and the magnetic permeability of the movable blade of the first switch;

[0035] The acquiring first parameter information of the first switch in the first state includes:

[0036] Based on the material of the movable blade of the first switch and a preset correspondence, the density of the movable blade of the first switch, the electrical conductivity of the movable blade of the first switch, and the magnetic permeability of the movable blade of the first switch are determined; wherein the preset correspondence is a correspondence between material and density, electrical conductivity, and magnetic permeability.

[0037] According to a second aspect of the present invention, there is provided a device for determining the electric force of a switch, the switch comprising a movable blade and at least one stationary contact, the device for determining the electric force of the switch comprising:

[0038] a parameter information acquisition module, configured to acquire first parameter information of the first switch in a first state, the first parameter information of the first switch in the first state including: magnetic induction intensity of the first switch, electric field intensity of the first switch, volume of the first switch, current density of the first switch, conductivity of a movable blade of the first switch, magnetic permeability of the movable blade of the first switch, density of the movable blade of the first switch, and contact area between the movable blade and the static contact of the first switch; a first Ampere force generation module, configured to input the current density of the first switch, magnetic induction intensity of the first switch, conductivity of the movable blade of the first switch, electric field intensity of the first switch, and volume of the first switch into a first target model to obtain a first Ampere force of the first switch;

[0039] a first Holm force generating module, configured to input the magnetic permeability of the movable blade of the first switch, the magnetic induction intensity of the first switch, the contact area between the movable blade and the static contact of the first switch, the density of the movable blades of the first switch, the current density of the first switch, and the electric field intensity of the first switch into a second target model to obtain a first Holm force of the first switch;

[0040] An electromotive force generating module is configured to determine a first electromotive force of the first switch according to the first Ampere force and the first Holm force.

[0041] According to a third aspect of the present invention, there is provided an electronic device, comprising:

[0042] at least one processor; and

[0043] a memory communicatively connected to the at least one processor; wherein,

[0044] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to perform the method for determining the electric force of the switch described in any one of the first aspects.

[0045] According to a fourth aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for determining the electromotive force of the switch according to the first aspect when executed.

[0046] The technical solution of the embodiment of the present invention is that after obtaining the first parameter information of the first switch in the first state, the part of the first parameter information related to the Ampere force in the first parameter information is input into the trained first target model to obtain the first Ampere force, and the part of the first parameter information related to the Holm force in the first parameter information is input into the trained second target model to obtain the first Holm force, and then the first electric force is obtained based on the first Ampere force and the first Holm force. Because the first target model and the second target model have been trained in the early stage, the output values ​​of the model are the first Ampere force and the first Holm force, and the first Ampere force and the first Holm force of the first switch can be accurately obtained, and then the first electric force can be obtained. Through the first target model and the second target model, the magnitude of the first electric force of the first switch can be finally obtained in real time, quickly and accurately, solving the problems of low calculation accuracy and high complexity of traditional methods.

[0047] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0049] Figure 1 A flow chart of a method for determining the electromotive force of a switch provided in an embodiment of the present invention;

[0050] Figure 2A flow chart of another method for determining the electromotive force of a switch provided by an embodiment of the present invention;

[0051] Figure 3 A comparison diagram of an actual current waveform and a predicted current waveform provided by an embodiment of the present invention;

[0052] Figure 4 A flow chart of another method for determining the electromotive force of a switch provided by an embodiment of the present invention;

[0053] Figure 5 A network architecture diagram of reinforcement learning provided by an embodiment of the present invention;

[0054] Figure 6 A schematic structural diagram of an electric force determination device provided by an embodiment of the present invention;

[0055] Figure 7 A schematic structural diagram of an electronic device for implementing the method for determining electric force according to an embodiment of the present invention. DETAILED DESCRIPTION

[0056] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0057] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0058] Figure 1 This is a flow chart of a method for determining the electromotive force of a switch provided by an embodiment of the present invention. This embodiment is applicable to situations where the health of a switch is determined by the magnitude of the electromotive force of the switch. The switch includes a moving blade and at least one static contact. The switch can be a three-position switch or a load switch, such as Figure 1 As shown, the method includes:

[0059] S110: Acquire first parameter information of the first switch in the first state.

[0060] The first state of the first switch can be understood as the state of the first switch at the current moment. The first state of the first switch includes a state in which the movable blade of the first switch is not in contact with any of the static contacts of the first switch or a state in which the movable blade of the first switch is in contact with any of the static contacts of the first switch.

[0061] Exemplarily, the switch includes a moving blade and two static contacts, and the two static contacts are an upper static contact and a grounding knife. The first switch is a switch including any one of the moving blade and the static contact, the health status of which needs to be determined based on the electric force, that is, any switch to be detected electric force. The first state of the first switch includes two closed states and one open state, wherein in the open state, the moving blade of the first switch and any static contact of the first switch are not in contact. The two closed states further include a first closed state and a second closed state, wherein in the first closed state, the moving blade of the first switch is in contact with the upper static contact of the first switch, and in the second closed state, the moving blade of the first switch is in contact with the grounding knife of the first switch. In different closed states, the current flowing through the first switch is different. In different first states of the first switch, the specific numerical value of at least part of the first parameter information corresponding to it is different.

[0062] The first parameter information of the first switch in the first state includes: the magnetic induction intensity of the first switch, the electric field intensity of the first switch, the volume of the first switch, the current density of the first switch, the electrical conductivity of the moving blade of the first switch, the magnetic permeability of the moving blade of the first switch, the density of the moving blade of the first switch, and the contact area between the moving blade and the static contact of the first switch.

[0063] S120: Inputting the current density of the first switch, the magnetic induction intensity of the first switch, the conductivity of the movable blade of the first switch, the electric field intensity of the first switch, and the volume of the first switch into the first target model to obtain a first Ampere force of the first switch.

[0064] The first Ampere force is the force exerted on the energized first switch in the magnetic field. When current flows through the first switch, the current generates a magnetic field, causing the first switch to be in the magnetic field.

[0065] The current density of the first switch, the magnetic induction intensity of the first switch, the conductivity of the first switch's moving blade, the electric field strength of the first switch, and the volume of the first switch are all related to the magnitude of the Ampere force of the first switch. The first target model is a pre-trained model. The current density of the first switch, the magnetic induction intensity of the first switch, the conductivity of the first switch's moving blade, the electric field strength of the first switch, and the volume of the first switch are input into the first target model. The output value of the first target model is the first Ampere force of the first switch.

[0066] S130: Input the magnetic permeability of the movable blade of the first switch, the magnetic induction intensity of the first switch, the contact area between the movable blade and the static contact of the first switch, the density of the movable blades of the first switch, the current density of the first switch, and the electric field intensity of the first switch into the second target model to obtain the first Holm force of the first switch.

[0067] Because the contact surface between the movable blade and the stationary contact is uneven, when current flows through the uneven contact surface, the current contracts near the contact surface, generating a contracting electrodynamic repulsive force between the movable blade and the stationary contact, known as the Holm force. Therefore, when current flows through the first switch, a first Holm force is generated when the first switch is in the first state.

[0068] The magnetic permeability of the first switch's movable blade, the magnetic flux density of the first switch, the contact area between the movable blade and the stationary contact, the density of the movable blades, the current density of the first switch, and the electric field strength of the first switch are all related to the Holm's force of the first switch. The second target model is a pre-trained model. The magnetic permeability of the second switch's movable blade, the magnetic flux density of the first switch, the contact area between the movable blade and the stationary contact, the density of the movable blades, the current density of the first switch, and the electric field strength of the first switch are input into the second target model. The output of the second target model is the first Holm's force of the first switch.

[0069] S140: Determine a first electromotive force of the first switch according to the first Ampere force and the first Holm force.

[0070] The first electromotive force is related to both the first Ampere force and the first Holm force, and is a comprehensive representation of the first Ampere force and the first Holm force. The health of the first switch in the first state is determined based on the magnitude of the first electromotive force.

[0071] The technical solution of the embodiment of the present invention is that after obtaining the first parameter information of the first switch in the first state, the part of the first parameter information related to the Ampere force in the first parameter information is input into the trained first target model to obtain the first Ampere force, and the part of the first parameter information related to the Holm force in the first parameter information is input into the trained second target model to obtain the first Holm force, and then the first electric force is obtained based on the first Ampere force and the first Holm force. Because the first target model and the second target model have been trained in the early stage, the output values ​​of the model are the first Ampere force and the first Holm force, and the first Ampere force and the first Holm force of the first switch can be accurately obtained, and then the first electric force can be obtained. Through the first target model and the second target model, the magnitude of the first electric force of the first switch can be finally obtained in real time, quickly and accurately, solving the problems of low calculation accuracy and high complexity of traditional methods.

[0072] Figure 2 A flowchart of another method for determining the electromotive force of a switch provided by an embodiment of the present invention, Figure 2 For Figure 1 For further refinement of S110, refer to Figure 2 , the method comprising:

[0073] S111: Acquire an electric field distribution image of the first switch in a first state; wherein the first parameter information of the first switch in the first state includes the electric field intensity of the first switch.

[0074] A spatial electromagnetic field visualizer was used to capture the electric field distribution image of the first switch in its first state. In the electric field distribution image, different positions of the first switch, such as the moving blade and the static contact, exhibit different electric field intensities, resulting in different colors at different positions of the first switch. In the electric field distribution image, the colors correspond to the magnitude of the electric field intensities.

[0075] S121: Determine the electric field strength at the center of the movable blade of the first switch according to the electric field distribution image, and use the electric field strength at the center of the movable blade of the first switch as the electric field strength of the first switch.

[0076] The color of the center position of the moving blade is obtained from the electric field distribution image, and then the magnitude of the electric field strength at the center position of the moving blade of the first switch is determined through the correspondence between color and electric field strength. The electric field strength of the first switch is represented by the electric field strength at the center position of the moving blade of the first switch, and then the electric field strength of the first switch is obtained.

[0077] S131: Obtain current values ​​of the first switch at different times respectively.

[0078] Under the condition that the current of the first switch meets the rated peak withstand current and the rated short-circuit withstand current, the magnitude of the current in the first switch is obtained through the current transformer at different times, thereby obtaining the current value of the first switch at different times.

[0079] S141: Generate an initial current waveform function according to the current value of the first switch at different times.

[0080] The current values ​​of the first switch obtained at different times are fitted to obtain the initial current waveform function , specifically:

[0081] ;in, Represents the maximum value of the actual current, represents the angular frequency of the actual current, Represents the initial phase angle of the actual current.

[0082] S151: Generate a predicted current waveform function based on the ensemble learning algorithm and the initial current waveform function.

[0083] The ensemble learning algorithm is used to integrate and analyze the initial current waveform function to predict the current change trend:

[0084] ;

[0085] in, Represents the prediction function, represents the weight of the fth weak learner in the ensemble learning model, represents the prediction result of the fth weak learner, and F represents the number of weak learners. By weighted averaging the prediction results of multiple weak learners, the accuracy and stability of the overall prediction can be improved.

[0086] Predicted current waveform function satisfy:

[0087] ;in, represents the maximum value of the predicted current, represents the angular frequency of the predicted current, Represents the initial phase angle of the predicted current.

[0088] Figure 3 A comparison diagram of an actual current waveform and a predicted current waveform provided by an embodiment of the present invention, Figure 3The horizontal axis represents time in seconds, and the vertical axis represents current in amperes. As can be seen from the figure, the actual current waveform (blue curve) fluctuates at different time points, reflecting the current changes under different load and short-circuit conditions. The predicted current waveform (orange curve) smoothes these fluctuations using a sliding average method, better illustrating the current trend.

[0089] Specifically, the orange curve in the figure closely follows the overall trend of the blue curve, demonstrating that the ensemble learning algorithm, integrating and analyzing sensor data, can accurately predict current trends. This trend prediction helps better understand the dynamic behavior of current, providing strong support for load switch optimization and fault diagnosis. Comparing the actual and predicted waveforms demonstrates the effectiveness of the ensemble learning algorithm in capturing overall trends while also identifying noise and short-term fluctuations in the waveforms. By weighted averaging the predictions of multiple weak learners, the accuracy and stability of the overall prediction are improved, compensating for the insensitivity of traditional methods to changes in complex electromagnetic environments.

[0090] S161: Determine a maximum value of the predicted current according to the predicted current waveform function, and determine a current density of the first switch according to the maximum value of the predicted current.

[0091] After obtaining the predicted current waveform function, the maximum value of the predicted current can be obtained , the ratio of the maximum value of the predicted current to the cross-sectional area of ​​the first switch in a direction perpendicular to the actual current direction is taken as the current density of the first switch.

[0092] S171: Based on the material of the movable blade of the first switch and a preset correspondence, determine the density of the movable blade of the first switch, the electrical conductivity of the movable blade of the first switch, and the magnetic permeability of the movable blade of the first switch; wherein the preset correspondence is the correspondence between the material and the density, electrical conductivity, and magnetic permeability.

[0093] The BERT model is used to process literature and databases related to material properties to automatically extract and summarize the material's electrical conductivity, magnetic permeability, and density properties. The preset correspondence can be a preset correspondence table. Table 1 shows the electrical conductivity, magnetic permeability, and density data for several materials extracted from literature and databases using the BERT model in this embodiment.

[0094] Table 1: Correspondence between different switch materials and conductivity, magnetic permeability and density

[0095]

[0096] As shown in the table above, silver has the highest electrical conductivity, at 6.30 × 10^7 S / m, making it suitable for high-performance electrical applications. Copper has a conductivity of 5.96 × 10^7 S / m and is widely used in wire and cable. Aluminum has a conductivity of 3.77 × 10^7 S / m and the lowest density, at 2.70 g / cm³, making it suitable for lightweight applications. Gold, while having a slightly lower conductivity of 4.10 × 10^7 S / m, is often used in high-end electronic devices due to its corrosion resistance. Iron has a conductivity of 1.0 × 10^7 S / m but the highest magnetic permeability, at 6.3 × 10^-3 H / m, making it suitable for use as a magnetic material. The properties of each material provide a scientific basis for selecting the optimal material for different applications.

[0097] After the material of the movable blade of the first switch is determined, the density, magnetic permeability and electrical conductivity of the corresponding movable blade are determined by looking up a table.

[0098] In one optional method, to obtain the contact area between the first switch and any stationary contact, a contact liquid is applied to the movable blade of the first switch. The first switch is closed for a predetermined period of time and then opened. The area of ​​the contact liquid remaining on the movable blade of the first switch is then measured as the contact area between the movable blade and the stationary contact of the first switch. When the movable blade of the first switch is not in contact with any stationary contact, the contact area between the movable blade and the stationary contact of the first switch is considered to be zero.

[0099] Optionally, the magnetic induction intensity B of the first switch is obtained by the formula:

[0100] ;in, is the magnetic permeability of the movable blade of the first switch, I is the effective value of the current flowing in the first switch, and k is the length of the first switch in a direction perpendicular to the current direction.

[0101] Optionally, before inputting the first parameter information of the first switch in the first state into the first target model and the second target model, each first parameter information may be normalized. Normalization refers to converting data of different dimensions into the same dimension so that they have the same metric standard.

[0102] Optionally, the volume of the first switch is the volume of the entire structure consisting of the movable blade and all static contacts of the first switch. The volume of the first switch is determined before the switch leaves the factory, and the volume of the first switch at the time of leaving the factory can be directly obtained later.

[0103] S181: Inputting the current density of the first switch, the magnetic induction intensity of the first switch, the conductivity of the movable blade of the first switch, the electric field intensity of the first switch, and the volume of the first switch into the first target model to obtain a first Ampere force of the first switch.

[0104] S191: Input the magnetic permeability of the movable blade of the first switch, the magnetic induction intensity of the first switch, the contact area between the movable blade and the static contact of the first switch, the density of the movable blade of the first switch, the current density of the first switch, and the electric field intensity of the first switch into the second target model to obtain the first Holm force of the first switch.

[0105] S201: Determine a first electromotive force of a first switch according to a first Ampere force and a first Holm force.

[0106] Figure 4 A flowchart of another method for determining the electromotive force of a switch provided by an embodiment of the present invention, referring to Figure 4 , the method comprising:

[0107] S112: Obtain a set of second parameter information for each of the c second switches in each of the m second states, and the actual Ampere force and actual Holm force corresponding to each set of second parameter information, where m, a, and c are all integers greater than or equal to 1.

[0108] Among them, the second parameter information of the second switch in the second state includes: the magnetic induction intensity of the second switch, the electric field strength of the second switch, the volume of the second switch, the current density of the second switch, the conductivity of the moving blade of the second switch, the magnetic permeability of the moving blade of the second switch, the density of the moving blade of the second switch, and the contact area between the moving blade of the second switch and the static contact.

[0109] According to the calculation formula of Ampere force and the calculation formula of Holm force, the parameter information related to Ampere force and the parameter information related to Holm force can be determined, specifically:

[0110] ;

[0111] ;

[0112] in, The computational model representing the Ampere force, The computational model representing the Holm force, Represents the current density of the switch, B represents the magnetic induction intensity of the switch, σ represents the conductivity of the moving blade, and E represents the electric field intensity of the switch. represents the vacuum dielectric constant, V represents the volume of the switch, and H represents the magnetic field strength of the switch. represents the curl of the magnetic field, A represents the contact area between the moving blade and the static contact, and ρ represents the density of the moving blade. , represents the magnetic permeability of the moving blade, where .

[0113] The second switch is any switch with the same structure as the first switch, that is, any switch comprising a movable blade and a stationary contact. The c second switches can all be from the same batch as the first switch, ensuring that the performance of the second switches is similar to that of the first switch, thereby improving the accuracy of training the first and second initial models based on the second parameter information obtained from the second switches. Alternatively, the c second switches may include the first switch, which is not specifically limited in this embodiment.

[0114] The second state includes a state where the movable blade of the second switch is not in contact with any of the second switch's stationary contacts, and a state where the movable blade of the second switch is in contact with each of the second switch's stationary contacts. The second state of the second switch includes two closed states and one open state. In the open state, the movable blade of the second switch is not in contact with any of the second switch's stationary contacts. The two closed states further include a third closed state and a fourth closed state. In the third closed state, the movable blade of the second switch is in contact with the upper stationary contact of the second switch, and in the fourth closed state, the movable blade of the second switch is in contact with the grounding contact of the second switch. Different currents flow through the second switch in different closed states. The specific values ​​of at least part of the second parameter information corresponding to the second switch vary in different second states. Optionally, if m is equal to 3, a set of second parameter information is obtained for each second switch in each of the three second states. The three states are: a state where the movable blade of the second switch is not in contact with any of the second switch's stationary contacts, a state where the movable blade of the second switch is in contact with the upper stationary contact of the second switch, and a state where the movable blade of the second switch is in contact with the grounding contact of the second switch. Each second switch changes the magnitude of the current input into the second switch in each state by changing the current source of the second switch, thereby obtaining a set of second parameter information.

[0115] In an optional embodiment, the materials of the movable blades of each of the c second switches are different. Optionally, c=5, and multiple sets of second parameter information are obtained for each second state of the five second switches. The movable blades of the five second switches are made of different materials, and the materials of the movable blades of the five second switches can be copper, iron, aluminum, silver, and gold, respectively. At least three sets of second parameter information are obtained for each second state of each second switch. Specifically, for the same second switch, the current source providing current to the second switch is changed, and the second parameter information of the second switch for each current source is obtained. Specifically, for the same second switch, different current sources corresponding to the second switches have different electric field strengths, different magnetic induction intensities, and different current densities. The contact area between the movable blade and the static contact of the second switch is the same, the density of the movable blades of the second switch is the same, the electrical conductivity of the movable blades of the second switch is the same, and the magnetic permeability of the movable blades of the second switch is the same. In the same second state, when the materials of the movable blades of different second switches are different, the density of the movable blades of the second switches is different, the electrical conductivity of the movable blades of the second switches is different, the magnetic permeability of the movable blades of the second switches is different, and the contact area between the movable blades of the second switches and the static contact is different.

[0116] Among them, the method for obtaining the magnetic induction intensity of the second switch is the same as the method for obtaining the magnetic induction intensity of the first switch, the method for obtaining the electric field intensity of the second switch is the same as the method for obtaining the electric field intensity of the first switch recorded in S111-S121, the method for obtaining the volume of the second switch is the same as the method for obtaining the volume of the first switch, the current density of the second switch is the same as the method for obtaining the current density of the first switch recorded in S131-161, the conductivity of the moving blade of the second switch, the magnetic permeability of the moving blade of the second switch, and the density of the moving blade of the second switch are the same as the conductivity, magnetic permeability, and density of the moving blade of the first switch recorded in S171, and the contact area between the moving blade of the second switch and the static contact is the same as the contact area between the moving blade and the static contact of the first switch recorded above, and they are not repeated here.

[0117] The actual Ampere force and the actual Holm force are real data directly obtained from experiments or measurements. Optionally, the Ampere force of the second switch can be measured using a high-precision instrument such as a strain sensor or an electromagnetic field sensor to serve as the actual Ampere force of the second switch, and the Holm force of the second switch can be measured to serve as the actual Holm force of the second switch.

[0118] In this embodiment, a group of second parameter information is obtained for each second switch in each of the three second states to ensure that the second parameter information of the second switch under different working conditions is covered, so as to provide sufficient data for subsequent model training and ensure the accuracy of model training.

[0119] Optionally, each set of second parameter information of each second switch in each second state obtained above, and the actual Ampere force and actual Holm force corresponding to the set of parameter information are stored as a data group, and then a data table can be obtained. Each row in the data table can be a data group, and different columns represent different second parameter information, actual Ampere force and actual Holm force.

[0120] Optionally, before S122 and S132, the following is also included:

[0121] After obtaining multiple sets of second parameter information for each second switch in each second state, the data in each acquired data set is normalized to ensure data consistency and comparability. Normalization refers to converting data of different dimensions to the same dimension so that they have the same metric. Each normalized data set is then tested for outliers using the interquartile range method, and data sets containing outliers are removed from the data table.

[0122] The data set in the data table is cleaned to remove error values ​​and outliers. Error values ​​refer to obvious errors in the data, such as negative conductivity values ​​or values ​​outside the reasonable range. In this embodiment, the outlier detection method uses a statistical method such as the interquartile range method to detect outliers L in the data. Specifically:

[0123]

[0124] ;

[0125] Among them, Q1 is the first quartile, Q3 is the third quartile, and IQR is the interquartile range. is the second parameter information after normalization, the actual Ampere force or the actual Holm force.

[0126] S122: The current density of the second switch, the magnetic induction intensity of the second switch, the conductivity of the movable blade of the second switch, the electric field intensity of the second switch, the volume of the second switch, and the corresponding actual Ampere force are used as a first training data set.

[0127] The current density of the second switch, the magnetic induction intensity of the second switch, the conductivity of the moving blade of the second switch, the electric field intensity of the second switch, the volume of the second switch and the corresponding actual Ampere force in each set of second parameter information of each second switch in each second state constitute a first training data set.

[0128] S132: The magnetic permeability of the movable blade of the second switch, the magnetic induction intensity of the second switch, the contact area between the movable blade of the second switch and the static contact, the density of the movable blade of the second switch, the current density of the second switch, the electric field intensity of the second switch, and the actual Holm force are used as a second training data set.

[0129] The magnetic permeability of the moving blade of the second switch, the magnetic induction intensity of the second switch, the contact area between the moving blade and the static contact of the second switch, the density of the moving blade of the second switch, the current density of the second switch, the electric field intensity of the second switch and the actual Holm force in each set of second parameter information of each second switch in each second state constitute a second training data set.

[0130] S142: Input c·m·a first training data sets into the first initial model to obtain c·m·a first initial Ampere forces in sequence; input c·m·a second training data sets into the second initial model to obtain c·m·a first initial Holm forces in sequence.

[0131] After each first training data set is input into the first initial model, the first initial model generates an output value, which is the first initial Ampere force. That is, by inputting c·m·a first training data sets into the first initial model, c·m·a first initial Ampere forces are obtained in sequence. After each second training data set is input into the second initial model, the second initial model generates an output value, which is the first initial Holm force. That is, by inputting c·m·a second training data sets into the second initial model, c·m·a first initial Holm forces are obtained in sequence.

[0132] S152: For each first initial Ampere force, after obtaining a first initial Ampere force, adjust the first weight according to the first initial Ampere force and the actual Ampere force corresponding to the first initial Ampere force; for each first initial Holm force, after obtaining a first initial Holm force, adjust the second weight according to the first initial Holm force and the actual Holm force corresponding to the first initial Holm force.

[0133] The actual Ampere force corresponding to the first initial Ampere force is the actual Ampere force in the first training data set corresponding to the first initial Ampere force, and the actual Holm force corresponding to the first initial Holm force is the actual Holm force in the second training data set corresponding to the first initial Holm force. The first electromotive force is the weighted sum of the first Ampere force and the first Holm force, that is, the sum of the product of the first Ampere force multiplied by the first weight and the product of the first Holm force multiplied by the second weight is determined as the first electromotive force of the first switch. Therefore, during the model training process, the size of the first weight is continuously adjusted to make the first initial Ampere force closer to the actual Ampere force, and the size of the second weight is adjusted to make the first initial Holm force closer to the size of the actual Holm force.

[0134] Adjusting the first weight according to the first initial Ampere force and the actual Ampere force can be before adjusting the second weight according to the first initial Holm force and the actual Holm force, or it can be after adjusting the second weight according to the first initial Holm force and the actual Holm force. There is no limit on the order of the two.

[0135] S162: Obtain first parameter information of the first switch in the first state.

[0136] S172: Inputting the current density of the first switch, the magnetic induction intensity of the first switch, the conductivity of the movable blade of the first switch, the electric field intensity of the first switch, and the volume of the first switch into the first target model to obtain a first Ampere force of the first switch.

[0137] S182: The magnetic permeability of the movable blade of the first switch, the magnetic induction intensity of the first switch, the contact area between the movable blade and the static contact of the first switch, the density of the movable blade of the first switch, the current density of the first switch, and the electric field intensity of the first switch are input into the second target model to obtain the first Holm force of the first switch.

[0138] S192: Determine the sum of the product of the first Ampere force multiplied by the first weight and the product of the first Holm force multiplied by the second weight as the first electromotive force of the first switch.

[0139] Optionally, adjusting the first weight according to the first initial Ampere force and the actual Ampere force includes:

[0140] 1) A ratio of the p-th actual Ampere force to the first initial Ampere force obtained by inputting the p-th first training data set into the first initial model is used as a first weight corresponding to the first initial model during the p-th training, and a first loss function value corresponding to the first weight during the p-th training is determined; p is an integer greater than or equal to 1 and less than or equal to c·m·a.

[0141] The P-th training data set is input into the first initial model. The output of the model is the first initial Ampere force obtained during the P-th training. The ratio of the p-th actual Ampere force to the first initial Ampere force obtained during the P-th training is used as the first weight corresponding to the first initial model during the p-th training.

[0142] The loss function is defined during model training. The value of the loss function of the first initial model during the Pth training is the first loss function value. The specific calculation process of the first loss function value is described later.

[0143] 2) Inputting the second parameter information into the first policy network to obtain a first probability distribution, where the first probability distribution is used to represent the adjustment direction of the model parameters of the first initial model.

[0144] Figure 5A network architecture diagram of reinforcement learning provided by an embodiment of the present invention, refer to Figure 5 In this phase, a reinforcement learning network is used to dynamically optimize the model parameters. Through continuous trial and error and feedback from the reinforcement learning algorithm, the model parameters are adjusted to minimize the prediction error and ensure that the model maintains high accuracy under different conditions.

[0145] First, initialize the reinforcement learning environment, use the Ampere force and Holm force computational models as the reinforcement learning environment, and define the state, action, and reward functions. The reinforcement learning environment is where the model parameters interact and learn.

[0146] The status includes the model parameter settings and prediction errors of the first initial model:

[0147] ;

[0148] in, is the i-th model parameter, is the current prediction error. The current prediction error represents the deviation between the first initial Ampere force and the actual Ampere force. The state formula describes the current state of the first initial model. It serves as input in reinforcement learning and provides a basis for subsequent action selection and strategy optimization.

[0149] Actions consist of adjusting the magnitude and direction of model parameters:

[0150] ;

[0151] in, is the adjustment amount for the i-th model parameter.

[0152] The reward function gives rewards or penalties based on the size of the prediction error. The smaller the error, the greater the reward:

[0153]

[0154] in, is the current prediction error. The smaller the error, the better the model performance and the greater the reward. The weight parameter of the penalty term is used to balance the relationship between error reduction and model parameter adjustment. A too large value may suppress the adjustment effect, while a too small value may cause the first initial model to be over-adjusted. is the adjustment to the i-th model parameter. Excessive adjustments can lead to model instability, so large parameter changes need to be penalized. The reward function is the core of reinforcement learning, used to evaluate the effectiveness of a model parameter adjustment (action). A larger reward value indicates a more effective action.

[0155] Then, a complex multi-layer deep reinforcement learning network is used to optimize the parameters of the first policy network and the first value network through multi-task learning and adaptive gradient adjustment. The first policy network outputs an action vector for adjusting the model parameters:

[0156] ;

[0157] Among them, s is the current state, is the first probability distribution output by the first policy network, is the weight of the first policy network, is the bias term of the first policy network, ReLU: activation function, used to introduce nonlinear characteristics, softmax: normalization function, converting the network output into probability distribution.

[0158] 3) inputting the second parameter information into the first value network to obtain a first value, where the first value is used to identify the adjusted value of the first strategy network;

[0159] The first value network estimates the value of the current state and is used to guide the optimization of the first policy network:

[0160]

[0161] in, is the first value output by the first value network, is the weight of the first value network, is the bias term of the first value network.

[0162] The strategy update combines the first strategy network and the first value network, and is optimized through multi-task learning and adaptive gradient adjustment, where the loss function satisfies:

[0163] ;

[0164] In addition, an adaptive gradient adjustment mechanism is introduced to improve optimization efficiency:

[0165] ;

[0166] ;

[0167] in, is the mean square error of the first value network, is the log-probability weighted value network error of the policy network, is the learning rate, is the sum of squared gradients of the policy network, is the cumulative sum of the squared gradients of the value network, ϵ is a small constant to prevent division by zero, is the loss function. is the reward value, is the first value of the current state and the next state, is a discount factor that weighs the relationship between current rewards and future rewards. The loss function consists of two parts:

[0168] The optimization goal of the first value network is to ensure that the estimation of the first value is accurate;

[0169] : The optimization goal of the first policy network is to encourage the selection of actions that maximize the value difference.

[0170] Based on the above loss function formula, the first loss function value corresponding to each training run is obtained. When the first initial model meets the training termination condition, the first weight corresponding to the minimum first loss function value obtained in each training run is used as the first weight corresponding to the first target model, and the corresponding first initial model is used as the first target model. Optionally, the training termination condition can be that the number of times the first initial model is trained reaches a preset value.

[0171] Optionally, adjusting the second weight according to the first initial Holm force and the actual Holm force includes:

[0172] 1) The ratio of the first initial Holm force obtained by inputting the P-th actual Holm force and the p-th second training data set into the second initial model is used as the second weight corresponding to the second initial model during the P-th training, and the second loss function value corresponding to the second weight during the P-th training is determined;

[0173] 2) inputting the second parameter information into the second policy network to obtain a second probability distribution, where the second probability distribution is used to represent the adjustment direction of the model parameters of the second initial model;

[0174] 3) Inputting the second parameter information into the second value network to obtain a second value, where the second value is used to identify the adjusted value of the second strategy network.

[0175] The specific working process of each of the above steps is similar to the specific process of adjusting the second weight according to the first initial Ampere force and the actual Ampere force, and will not be repeated here.

[0176] This embodiment dynamically optimizes model parameters using reinforcement learning, providing an intelligent adjustment mechanism for electric power prediction. This addresses the large prediction errors and weak model adaptability inherent in traditional methods due to fixed parameter settings. Through the reinforcement learning network, the model can perceive environmental changes in real time and dynamically adjust the weight of each parameter based on the input state (including model parameters and prediction errors), thereby reducing errors and improving accuracy. Under complex electromagnetic field environments, vibration stresses, and variable material properties, the reinforcement learning mechanism allows the model to adaptively adjust parameter configurations, enabling global exploration of parameter optimization and rapidly converge to the optimal solution, effectively avoiding local optima. Furthermore, the policy network and value network in this embodiment work together, using a reward function to guide the initial model to adjust parameters in a direction that reduces error. Combined with an adaptive learning rate mechanism, this further improves optimization efficiency and stability. This dynamic learning feature enables the target model to maintain high efficiency and accuracy in complex and changing scenarios in practical applications, enabling rapid response and adjustment, particularly in the face of dynamic environmental changes or material property degradation. The use of reinforcement learning training models reduces the tedious manual parameter adjustment process, improves optimization efficiency, and unifies the optimization framework for multi-dimensional features, enabling the solution to coordinate the nonlinear relationships between multiple variables, such as the switch's electromagnetic field strength, the switch's electric field strength, the switch's current density, and the contact area between the moving blade and the static contact, providing strong support for the entire technical solution. This intelligent and dynamic optimization approach not only significantly improves prediction accuracy and robustness, but also expands the practical applicability of the target model in a variety of scenarios, demonstrating extremely high technological innovation and application value.

[0177] The embodiment of the present invention further provides a device for determining electric force. Figure 6 A schematic diagram of a structure of an electric force determination device provided by an embodiment of the present invention, referring to Figure 6 , the device for determining the electromotive force of the switch comprises:

[0178] The parameter information acquisition module 1 is used to obtain first parameter information of the first switch in the first state; the first parameter information of the first switch in the first state includes: the magnetic induction intensity of the first switch, the electric field intensity of the first switch, the volume of the first switch, the current density of the first switch, the electrical conductivity of the movable blade of the first switch, the magnetic permeability of the movable blade of the first switch, the density of the movable blade of the first switch, and the contact area between the movable blade and the static contact of the first switch.

[0179] The first Ampere force generating module 2 is used to input the current density of the first switch, the magnetic induction intensity of the first switch, the conductivity of the movable blade of the first switch, the electric field intensity of the first switch and the volume of the first switch into the first target model to obtain the first Ampere force of the first switch.

[0180] The first Holm force generating module 3 is used to input the magnetic permeability of the movable blade of the first switch, the magnetic induction intensity of the first switch, the contact area between the movable blade and the static contact of the first switch, the density of the movable blade of the first switch, the current density of the first switch and the electric field intensity of the first switch into the second target model to obtain the first Holm force of the first switch.

[0181] The electric force generating module 4 is configured to determine a first electric force of the first switch according to the first Ampere force and the first Holm force.

[0182] The beneficial effects of the electric force determination device are the same as those of the method for determining the electric force of the switch, and will not be described in detail here.

[0183] An embodiment of the present invention further provides an electronic device, Figure 7 A schematic diagram of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0184] like Figure 7 As shown, electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) or random access memory (RAM), communicatively connected to at least one processor 11. The memory stores computer programs executable by the at least one processor. Processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM or loaded from storage unit 18 into the RAM. RAM 13 can also store various programs and data required for the operation of electronic device 10. Processor 11, ROM 12, and RAM 13 are interconnected via bus 14. An input / output (I / O) interface is also connected to bus 14.

[0185] Multiple components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0186] Processor 11 may be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any other suitable processor, controller, microcontroller, etc. Processor 11 executes the various methods and processes described above.

[0187] An embodiment of the present invention further provides a computer-readable storage medium storing computer instructions, which are used to enable a processor to implement the method for determining the electric force of a switch in any of the above embodiments when executed.

[0188] A computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media may include an electrical connection based on 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), 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 foregoing.

[0189] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the present invention can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved. This is not limited herein.

[0190] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. A method for determining the electric force of a switch, the switch comprising a moving blade and at least one stationary contact, characterized in that ,The method for determining the electromotive force of the switch includes: Acquiring first parameter information of the first switch in the first state, the first parameter information of the first switch in the first state including: magnetic induction intensity of the first switch, electric field intensity of the first switch, volume of the first switch, current density of the first switch, conductivity of a moving blade of the first switch, magnetic permeability of the moving blade of the first switch, density of the moving blade of the first switch, and contact area between the moving blade of the first switch and a static contact; Inputting the current density of the first switch, the magnetic induction intensity of the first switch, the conductivity of the movable blade of the first switch, the electric field intensity of the first switch and the volume of the first switch into the first target model to obtain the first Ampere force of the first switch; Inputting the magnetic permeability of the movable blade of the first switch, the magnetic induction intensity of the first switch, the contact area between the movable blade of the first switch and the stationary contact, the density of the movable blades of the first switch, the current density of the first switch and the electric field intensity of the first switch into the second target model to obtain the first Holm force of the first switch; A first electromotive force of the first switch is determined according to the first Ampere force and the first Holm force.

2. The method for determining the electromotive force of a switch according to claim 1, characterized in that: The determining the first electromotive force of the first switch according to the first Ampere force and the first Holm force comprises: The sum of a product of the first Ampere force multiplied by a first weight and a product of the first Holm force multiplied by a second weight is determined as a first electromotive force of the first switch.

3. The method for determining the electromotive force of a switch according to claim 1, characterized in that: Before obtaining the first parameter information of the first switch in the first state, the method further includes: obtaining a group of second parameter information of each second switch in each of the m second states among the c second switches, and an actual Ampere force and an actual Holm force corresponding to each group of second parameter information; the second parameter information of the second switch in the second state includes: the magnetic induction intensity of the second switch, the electric field intensity of the second switch, the volume of the second switch, the current density of the second switch, the conductivity of the moving blade of the second switch, the magnetic permeability of the moving blade of the second switch, the density of the moving blade of the second switch, and the contact area between the moving blade of the second switch and the static contact; m, a and c are all integers greater than or equal to 1; taking the current density of the second switch, the magnetic induction intensity of the second switch, the conductivity of the moving blade of the second switch, the electric field intensity of the second switch, the volume of the second switch and the corresponding actual Ampere force as a first training data set; taking the magnetic permeability of the moving blade of the second switch, the magnetic induction intensity of the second switch, the contact area between the moving blade of the second switch and the static contact, the density of the moving blade of the second switch, the current density of the second switch, the electric field intensity of the second switch and the actual Holm force as the second training data set; Inputting c·m·a first training data sets into the first initial model, and sequentially obtaining c·m·a first initial Ampere forces; inputting c·m·a second training data sets into the second initial model, and sequentially obtaining c·m·a first initial Holm forces; The first weight is adjusted according to the first initial Ampere force and the actual Ampere force; and the second weight is adjusted according to the first initial Holm force and the actual Holm force.

4. The method for determining the electromotive force of a switch according to claim 3, characterized in that: The adjusting the first weight according to the first initial Ampere force and the actual Ampere force includes: The ratio of the p-th actual Ampere force to the first initial Ampere force obtained by inputting the p-th first training data set into the first initial model is used as the first weight corresponding to the first initial model during the p-th training, and the first loss function value corresponding to the first weight during the p-th training is determined; p is an integer greater than or equal to 1 and less than or equal to c·m·a; Inputting the second parameter information into a first policy network to obtain a first probability distribution, where the first probability distribution is used to represent an adjustment direction of a model parameter of the first initial model; Inputting the second parameter information into a first value network to obtain a first value, where the first value is used to identify an adjustment value of the first strategy network; The adjusting the second weight according to the first initial Holm force and the actual Holm force comprises: Using the ratio of the p-th actual Holm force to the first initial Holm force obtained by inputting the p-th second training data set into the second initial model as the second weight corresponding to the second initial model during the p-th training, and determining the second loss function value corresponding to the second weight during the p-th training; Inputting the second parameter information into a second strategy network to obtain a second probability distribution, where the second probability distribution is used to represent an adjustment direction of a model parameter of the second initial model; The second parameter information is input into a second value network to obtain a second value, where the second value is used to identify an adjustment value of the second strategy network.

5. The method for determining the electromotive force of a switch according to any one of claims 1 to 4, characterized in that: The first parameter information of the first switch in the first state includes the electric field strength of the first switch; The obtaining of first parameter information of the first switch in the first state includes: Acquire an electric field distribution image of the first switch in a first state; The electric field strength at the center position of the movable blade of the first switch is determined according to the electric field distribution image, and the electric field strength at the center position of the movable blade of the first switch is used as the electric field strength of the first switch.

6. The method for determining the electromotive force of a switch according to any one of claims 1 to 4, characterized in that: The first parameter information of the first switch in the first state includes a current density of the first switch; The obtaining of first parameter information of the first switch in the first state includes: obtaining current values ​​of the first switch at different times respectively; generating an initial current waveform function according to the current value of the first switch at different times; Generate a predicted current waveform function based on an integrated learning algorithm and the initial current waveform function; A maximum value of the predicted current is determined according to the predicted current waveform function, and a current density of the first switch is determined according to the maximum value of the predicted current.

7. The method for determining the electromotive force of a switch according to any one of claims 1 to 4, characterized in that: The first parameter information of the first switch in the first state includes the density of the movable blade of the first switch, the electrical conductivity of the movable blade of the first switch, and the magnetic permeability of the movable blade of the first switch; The obtaining of first parameter information of the first switch in the first state includes: Based on the material of the moving blade of the first switch and a preset correspondence, the density of the moving blade of the first switch, the electrical conductivity of the moving blade of the first switch and the magnetic permeability of the moving blade of the first switch are determined; wherein the preset correspondence is a correspondence between material and density, electrical conductivity and magnetic permeability.

8. A device for determining the electric force of a switch, the switch comprising a moving blade and at least one stationary contact, characterized in that: The device for determining the electromotive force of the switch comprises: a parameter information acquisition module, configured to acquire first parameter information of the first switch in the first state, wherein the first parameter information of the first switch in the first state includes: magnetic induction intensity of the first switch, electric field intensity of the first switch, volume of the first switch, current density of the first switch, conductivity of a moving blade of the first switch, magnetic permeability of the moving blade of the first switch, density of the moving blade of the first switch, and contact area between the moving blade of the first switch and a static contact; a first Ampere force generating module, configured to input the current density of the first switch, the magnetic induction intensity of the first switch, the conductivity of the moving blade of the first switch, the electric field intensity of the first switch, and the volume of the first switch into a first target model to obtain a first Ampere force of the first switch; a first Holm force generating module, configured to input the magnetic permeability of the movable blade of the first switch, the magnetic induction intensity of the first switch, the contact area between the movable blade of the first switch and the stationary contact, the density of the movable blade of the first switch, the current density of the first switch and the electric field intensity of the first switch into a second target model to obtain a first Holm force of the first switch; The electromotive force generating module is used to determine a first electromotive force of the first switch according to the first Ampere force and the first Holm force.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can perform the method for determining the electromotive force of the switch according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for determining the electromotive force of a switch according to any one of claims 1 to 7 when the instructions are executed.

Images