Power supply control method, device, equipment and medium

Abstract

The invention relates to the field of power supply systems, particularly provides a power supply control method, device and equipment and a medium, and aims to solve the problem that a complex power supply system is difficult to effectively control in the prior art. In order to achieve the purpose, the method comprises the steps of obtaining power state information; inputting the power supply state information into a preset multi-agent model to obtain power supply control information; and performing control processing on the power supply system according to the power supply control information.

Description

Technical Field

[0001] This application relates to the field of power systems, specifically providing a power control method, device, equipment, and medium. Background Technology

[0002] Missiles play a crucial role in modern warfare, their superior long-range precision strike capabilities making them key to gaining the initiative on the battlefield. With the continuous advancement of aviation and aerospace technology, the reliability requirements for missiles are also gradually increasing. A missile consists of multiple subsystems, including a warhead, propulsion system, guidance and control system, and power supply. Among these subsystems, the power supply system is considered the "heart" of the missile, ensuring the normal operation of all other subsystems.

[0003] In existing technologies, the control strategy for missile-borne power systems is manually formulated based on a large amount of prior knowledge. This approach is only suitable for power systems with simple structures. As the structure of power systems becomes increasingly complex, it becomes difficult to obtain a control strategy based on prior knowledge. This leads to the technical problem that the control strategy obtained through prior knowledge cannot effectively control the power system.

[0004] Accordingly, there is a need in the field for a new power control scheme to solve the above problems. Summary of the Invention

[0005] In order to overcome the above-mentioned deficiencies, this application is made to provide a solution or at least a partial solution to the technical problem that control strategies obtained through prior knowledge cannot effectively control power supply systems in the prior art.

[0006] In a first aspect, this application provides a power control method, comprising:

[0007] Obtain power status information;

[0008] The power status information is input into a preset multi-agent model to obtain power control information;

[0009] Based on the power control information, the power system is controlled and processed.

[0010] The acquisition of the preset multi-agent model includes:

[0011] Obtain the current power status information;

[0012] The current power status information is divided to obtain power status grouped data;

[0013] The power state grouping data is input into the corresponding intelligent agents to obtain action sets;

[0014] Based on the set of actions, the power state information for the next moment is obtained;

[0015] Based on the power state information at the next moment and the current power state information, the fault state, bus voltage state, energy state, battery pack state, and switch state are obtained.

[0016] The reward value is obtained based on the fault status, the bus voltage status, the energy status, the battery pack status, and the switch status;

[0017] The parameters of the agent are updated based on the reward value;

[0018] After determining that the training rounds have reached the preset number of rounds, the parameters of the current multiple agents are stored and processed to obtain the preset multi-agent model.

[0019] In one technical solution of the aforementioned power control method, the step of dividing the current power state information to obtain power state grouping data includes:

[0020] The power status information is divided according to the data source to obtain a battery pack data group and other data groups;

[0021] The other data groups are divided into piezoelectric power supply data group, power distribution data group and cable data group;

[0022] The battery pack data group, the piezoelectric power supply data group, the power distribution data group, and the cable data group are combined and processed to obtain power status grouped data.

[0023] In one technical solution of the aforementioned power control method, obtaining the power state information at the next moment based on the action set includes:

[0024] The state of charge of the battery cells in the battery pack is obtained based on the state of charge of the battery cells in the battery pack at the previous moment, the switching duration, the battery capacity, and the current of the battery pack.

[0025] The battery voltage is obtained based on the battery current, battery open-circuit voltage, battery resistance, first voltage, and second voltage; wherein the first voltage and the second voltage satisfy a preset relationship.

[0026] In one technical solution of the above-mentioned power control method, obtaining the current of the battery pack includes:

[0027] The current of the battery pack is obtained based on the power supply status, bus voltage, load power, and piezoelectric power supply power.

[0028] In one technical solution of the aforementioned power control method, obtaining the reward value based on the fault state, bus voltage state, energy state, battery pack state, and switch state includes:

[0029] Based on the fault state, bus voltage state, energy state, battery pack state, and switch state, a first coefficient, a second coefficient, a third coefficient, a fourth coefficient, and a fifth coefficient are obtained, corresponding to the fault state, the bus voltage state, the energy state, the battery pack state, and the switch state, respectively.

[0030] The reward value is obtained based on the fault status, the bus voltage status, the energy status, the battery pack status, the switch status, the first coefficient, the second coefficient, the third coefficient, the fourth coefficient, and the fifth coefficient.

[0031] In one technical solution of the aforementioned power control method, obtaining the fault state, bus voltage state, energy state, battery pack state, and switch state based on the power state information at the next moment and the current power state information includes:

[0032] The fault status is obtained based on the fault status of the piezoelectric power supply, the fault status of the reconfigurable battery pack, and the fault status of the power distribution section.

[0033] The bus voltage state is obtained based on the bus voltage at both ends of the battery pack and the bus voltage at both ends of the battery pack at the next moment.

[0034] The energy state is obtained based on the load power, piezoelectric power supply power, and battery pack power.

[0035] The battery pack state is obtained based on the state of charge of the battery cells and the average state of charge of the reconfigurable battery pack.

[0036] The switch state is obtained based on the current state of the switch and the state at the next moment.

[0037] In one technical solution of the aforementioned power control method, the power status information includes:

[0038] Piezoelectric power supply failure, battery cell failure, power distribution failure, load failure, battery cell state of charge, piezoelectric power supply power, and battery cell bus voltage.

[0039] Secondly, this application provides a power control device, comprising:

[0040] The acquisition module is used to acquire power status information;

[0041] The analysis module is used to input the power status information into a preset multi-agent model to obtain power control information;

[0042] The control module is used to control the power system according to the power control information.

[0043] The acquisition of the preset multi-agent model includes:

[0044] Obtain the current power status information;

[0045] The current power status information is divided to obtain power status grouped data;

[0046] The power state grouping data is input into the corresponding intelligent agents to obtain action sets;

[0047] Based on the set of actions, the power state information for the next moment is obtained;

[0048] Based on the power state information at the next moment and the current power state information, the fault state, bus voltage state, energy state, battery pack state, and switch state are obtained.

[0049] The reward value is obtained based on the fault status, the bus voltage status, the energy status, the battery pack status, and the switch status;

[0050] The parameters of the agent are updated based on the reward value;

[0051] After determining that the training rounds have reached the preset number of rounds, the parameters of the current multiple agents are stored and processed to obtain the preset multi-agent model.

[0052] Thirdly, this application provides a power control device, including a processor and a storage device, the storage device being adapted to store a plurality of program codes, the program codes being adapted to be loaded and run by the processor to perform the method described in any one of the first aspects.

[0053] Fourthly, this application provides a computer-readable storage medium storing a plurality of program codes adapted to be loaded and run by a processor to perform the method described in any one of the first aspects.

[0054] This application provides a power control method, apparatus, device, and medium. The method specifically comprises: acquiring power status information; inputting the power status information into a preset multi-agent model to obtain power control information; and performing control processing on the power system according to the power control information to achieve efficient control of the missile-borne circuit system. Attached Figure Description

[0055] The disclosure of this application will become more readily understood with reference to the accompanying drawings. It will be readily understood by those skilled in the art that these drawings are for illustrative purposes only and are not intended to limit the scope of protection of this application. Furthermore, similar numbers in the drawings are used to denote similar components, wherein:

[0056] Figure 1 This is a schematic diagram of the structure of a power control system according to a first embodiment of the present application.

[0057] Figure 2 This is a flowchart illustrating a power control method according to an embodiment of this application.

[0058] Figure 3 This is a flowchart illustrating a second embodiment of a power control method provided in this application.

[0059] Figure 4 This is a flowchart illustrating a third embodiment of a power control method provided in this application.

[0060] Figure 5 This is a flowchart illustrating a fourth embodiment of a power control method provided in this application.

[0061] Figure 6 This is a flowchart illustrating a fifth embodiment of a power control method provided in this application.

[0062] Figure 7 This is a flowchart illustrating a sixth embodiment of a power control method provided in this application.

[0063] Figure 8 This is a flowchart illustrating a seventh embodiment of a power control method provided in this application.

[0064] Figure 9 This is a schematic diagram of the structure of a power control device provided in an embodiment of this application;

[0065] Figure 10 This is a schematic diagram of the structure of a power control device provided in an embodiment of this application.

[0066] List of reference numerals :

[0067] 11: Data analysis device; 12: Data acquisition device; 13: Power control device; 14: Power system; 21: Acquisition module; 22: Analysis module; 23: Control module; 31: Processor; 32: Memory. Detailed Implementation

[0068] Some embodiments of this application are described below with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of this application and are not intended to limit the scope of protection of this application.

[0069] In the description of this application, "module" and "processor" can include hardware, software, or a combination of both. A module can include hardware circuitry, various suitable sensors, communication ports, memory, and can also include software components, such as program code, or a combination of software and hardware. A processor can be a central processing unit, microprocessor, image processor, digital signal processor, or any other suitable processor. The processor has data and / or signal processing capabilities. The processor can be implemented in software, in hardware, or a combination of both. Non-transitory computer-readable storage media includes any suitable medium capable of storing program code, such as magnetic disks, hard disks, optical disks, flash memory, read-only memory, random access memory, etc. The term "A and / or B" means all possible combinations of A and B, such as only A, only B, or A and B. The terms "at least one A or B" or "at least one of A and B" have a similar meaning to "A and / or B" and can include only A, only B, or A and B. The singular terms "a" or "this" can also include plural forms.

[0070] As missile-borne power systems become increasingly complex, control strategies derived from prior knowledge are insufficient to control the power supply of these systems, leading to the technical problem that existing technologies cannot effectively control complex power systems.

[0071] Based on this, in order to solve the above-mentioned technical problems, the technical concept of this application is to provide a new power control method to achieve efficient control of the missile-borne power system.

[0072] Figure 1 This is a schematic diagram of the structure of a power control system according to an embodiment of this application. Figure 1 As shown, the power control system includes: a data analysis device 11, a data acquisition device 12, a power control device 13, and a power system 14. The data acquisition device 12 collects power status information and sends the power status information to the data analysis device 11. The data analysis device 11 inputs the power status information into a preset multi-agent model in the data analysis device 11 to obtain power control information. The data analysis device 11 sends the power control information to the power control device 13. After receiving the power control information, the power control device 13 performs control processing on the power system 14.

[0073] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0074] Figure 2 This is a schematic flowchart of an embodiment of a power control method provided in this application. Figure 2 As shown, specifically, the method includes:

[0075] Step S201: Obtain power status information.

[0076] In this embodiment, the power status information includes piezoelectric power supply faults, battery cell faults, power distribution power supply faults, load faults, battery cell state of charge, piezoelectric power supply power, and battery cell bus voltage.

[0077] In this embodiment, the power system includes multiple reconfigurable battery cells, a piezoelectric power supply, a power distribution supply, a load, a switch, and cables. The states of the multiple reconfigurable battery cells include battery cell faults, battery cell state of charge, and battery cell bus voltage. The states of the piezoelectric power supply include piezoelectric power supply faults and piezoelectric power supply power. The states of the power distribution supply include power distribution supply faults, and the states of the load include load faults.

[0078] Step S202: Input the power status information into the preset multi-agent model to obtain power control information.

[0079] In this embodiment, the current power status information is input into the corresponding agents in the preset multi-agent model. Each agent obtains its own power control information based on its corresponding power status information. Then, the power control information of each agent is analyzed and processed to obtain the power control information.

[0080] Step S203: Perform control processing on the power system according to the power control information.

[0081] In this embodiment, the power control information is the on / off state of each switch in the power system.

[0082] In this embodiment, for example, 1 indicates that the switch is on and 0 indicates that the switch is off. Then the power control information is {id1:1; id2:0; id3:1}, where id1, id2, and id3 represent the switch numbers.

[0083] In this embodiment, power state information is acquired; the power state information is input into a preset multi-agent model to obtain power control information; and the power system is controlled according to the power control information. Compared with the prior art, where the control strategy obtained through prior knowledge cannot effectively control the power system, this application acquires the power state information of the power system and inputs it into a preset multi-agent model to obtain power control information, so that the power system can control the power according to the power control information to achieve efficient control of the power.

[0084] Figure 3 This is a flowchart illustrating a second embodiment of a power control method provided in this application. Based on the above embodiments, as follows... Figure 3 As shown, specifically, obtaining the preset multi-agent model in step S202 includes:

[0085] Step S301: Obtain the current power status information.

[0086] In this embodiment, each part of the power system sends the currently collected status information to the cloud server.

[0087] Step S302: Divide the current power status information to obtain power status group data.

[0088] In this embodiment, the current power status information is divided according to data categories to obtain power status grouped data.

[0089] In this embodiment, for example, the battery category status data in the current power status information is divided into groups to obtain battery group data.

[0090] Step S303: Input the power state grouping data into the corresponding intelligent agents to obtain the action set.

[0091] In this embodiment, the power state grouping data is input to the corresponding intelligent agents respectively. Each intelligent agent obtains a corresponding action based on the corresponding state data. The actions obtained by each intelligent agent are combined to obtain an action set.

[0092] In this embodiment, each of the multiple reconfigurable battery cells, piezoelectric power supply, power distribution power supply, and cable corresponds to an intelligent agent. The multiple intelligent agents corresponding to the multiple reconfigurable battery cells employ a centralized training and distributed execution approach. The multiple intelligent agents corresponding to the piezoelectric power supply, power distribution power supply, and cable employ a distributed training and distributed execution approach.

[0093] Step S304: Obtain the power state information for the next moment based on the action set.

[0094] In this embodiment, each agent obtains a different action based on its own state data. After obtaining the action set, a collaborative decision-making algorithm is used to obtain the optimal action.

[0095] Step S305: Based on the power state information at the next moment and the current power state information, obtain the fault state, bus voltage state, energy state, battery pack state and switch state.

[0096] Step S306: Obtain the reward value based on the fault status, bus voltage status, energy status, battery pack status, and switch status.

[0097] In this embodiment, a reward function is preset. By evaluating the fault state, bus voltage state, energy state, battery pack state, and switch state, a corresponding reward or penalty is obtained. Then, the reward or penalty is substituted into the reward function to obtain the reward value.

[0098] Step S307: Update the agent's parameters based on the reward value.

[0099] Step S308: Determine whether the training rounds have reached the preset number of rounds. If yes, proceed to step S309; ​​otherwise, proceed to step S301.

[0100] Step S309: Store and process the parameters of the current multiple agents to obtain a preset multi-agent model.

[0101] In this embodiment, steps S301 to S307 constitute a training round. When the preset training round is reached, training is stopped, and the parameters of the current multiple agents are stored and processed to obtain a preset multi-agent model.

[0102] In this embodiment, the current power state information is acquired; the current power state information is divided to obtain power state group data; the power state group data is input to the corresponding agents to obtain action sets; based on the action sets, the power state information at the next moment is obtained; based on the power state information at the next moment and the current power state information, the fault state, bus voltage state, energy state, battery pack state, and switch state are obtained; based on the fault state, bus voltage state, energy state, battery pack state, and switch state, a reward value is obtained; based on the reward value, the parameters of the agents are updated; after determining that the training rounds have reached a preset number of rounds, the parameters of the current multiple agents are stored to obtain a preset multi-agent model.

[0103] Figure 4 This is a flowchart illustrating a third embodiment of a power control method provided in this application. Based on the above embodiments, as follows... Figure 4 As shown, one specific implementation of step S302 includes:

[0104] Step S401: Divide the power status information according to the data source to obtain the battery pack data group and other data groups.

[0105] In this embodiment, the power status information includes data from each module in the power system. The power status information is divided according to the module identifier of the data to obtain battery pack data and other data groups.

[0106] In this embodiment, since there is a lot of data from the battery pack, the data from the battery pack is first divided from the battery status information, and then the data from other data groups is divided from the power status information.

[0107] In this embodiment, each data point in the power status information consists of data and a module identifier.

[0108] Step S402: Divide the other data groups to obtain piezoelectric power supply data group, power distribution data group and cable data group.

[0109] In this embodiment, other data are divided according to the module identifier to obtain piezoelectric power supply data group, power distribution data group and cable data group.

[0110] Step S403: Combine the battery pack data group, piezoelectric power supply data group, power distribution data group and cable data group to obtain power status grouped data.

[0111] In this embodiment, the battery pack data group, piezoelectric power supply data group, power distribution data group, and cable data group are combined to obtain power status grouped data.

[0112] In this embodiment, the power status information is divided according to the data source to obtain a battery pack data group and other data groups; the other data groups are further divided to obtain a piezoelectric power supply data group, a power distribution data group, and a cable data group; the battery pack data group, the piezoelectric power supply data group, the power distribution data group, and the cable data group are combined to obtain power status grouped data, thereby realizing the division of power status information.

[0113] Figure 5 This is a flowchart illustrating a fourth embodiment of a power control method provided in this application. Based on the above embodiments, as follows... Figure 5 As shown, one specific implementation of step S304 includes:

[0114] Step S501: Based on the state of charge of the battery cells in the battery pack at the previous moment, the switching duration, the battery capacity, and the current of the battery pack, obtain the state of charge of the battery cells in the battery pack.

[0115] In this embodiment, according to formula 1:

[0116]

[0117] Obtain the state of charge (SOC) of the battery cells in the battery pack. bij Among them, SOC bij_pre Let dt be the state of charge of the j-th battery cell in the i-th battery pack at the previous moment, dt be the switching duration, C be the battery capacity, and I be the state of charge. bij Let be the current of the battery pack, and k be a constant.

[0118] In this embodiment, for example, the value of k is 3600.

[0119] In this embodiment, the range of the state of charge is greater than or equal to 0 and less than or equal to 1.

[0120] Step S502: Obtain the battery voltage based on the battery current, battery open-circuit voltage, battery resistance, first voltage, and second voltage.

[0121] In this embodiment, according to formula 2:

[0122] U bij =U OC -I bij R0-U1-U2 (2)

[0123] Obtain the battery voltage U bij Among them, U OC I represents the battery open-circuit voltage. bij R0 represents the battery current, R0 represents the battery resistance, U1 represents the first voltage, and U2 represents the second voltage.

[0124] In this embodiment, for example, the first voltage and the second voltage are the voltages of two RC links, respectively.

[0125] In this embodiment, the first voltage and the second voltage satisfy a preset relationship.

[0126] According to formulas 3 and 4:

[0127]

[0128] The preset relationship is obtained. Among them, R1 and R2 are the resistance values ​​of the two RC links, and C1 and C2 are the capacitance values ​​of the two RC links.

[0129] In this embodiment, the state of charge of the battery cells in the battery pack is obtained based on the state of charge of the battery cells in the battery pack at the previous moment, the switching duration, the battery capacity, and the current of the battery pack; the battery voltage is obtained based on the battery current, the battery open-circuit voltage, the battery resistance, the first voltage, and the second voltage.

[0130] Figure 6 This is a flowchart illustrating a fifth embodiment of a power control method provided in this application. Based on the above embodiments, as follows... Figure 6 As shown, specifically, obtaining the battery pack current in step S501 includes:

[0131] Step S601: Obtain the current of the battery pack based on the current, the state of operation, the bus voltage, the load power, and the piezoelectric power supply power.

[0132] In this embodiment, according to formula 5:

[0133]

[0134] Obtain the current I of the battery pack bij Among them, a bij P represents the operational status of the j-th battery cell in the i-th battery pack. load P represents the power of the load. pe The n represents the total power of the piezoelectric power supply, m represents the number of battery packs operating normally, and n represents the total power of the piezoelectric power supply. i V represents the number of battery cells in the i-th battery pack. bus This indicates the bus voltage at both ends of the battery pack.

[0135] In this embodiment, the current of the battery pack is obtained based on the current, the activation status, the bus voltage, the load power, and the piezoelectric power supply power.

[0136] Figure 7 This is a flowchart illustrating a sixth embodiment of a power control method provided in this application. Based on the above embodiments, as follows... Figure 7 As shown, one specific implementation of step S306 includes:

[0137] Step S701: Based on the fault state, bus voltage state, energy state, battery pack state, and switch state, obtain the first coefficient, second coefficient, third coefficient, fourth coefficient, and fifth coefficient corresponding to the fault state, bus voltage state, energy state, battery pack state, and switch state, respectively.

[0138] In this embodiment, the importance of fault state, bus voltage state, energy state, battery pack state, and switch state is evaluated to obtain importance coefficients corresponding to the fault state, bus voltage state, energy state, battery pack state, and switch state.

[0139] Step S702: Obtain the reward value based on the fault status, bus voltage status, energy status, battery pack status, switch status, first coefficient, second coefficient, third coefficient, fourth coefficient, and fifth coefficient.

[0140] In this embodiment, according to formula 6:

[0141] R=k1*R1+k2*R2+k3*R3+k4*R4+k5*R5 (6)

[0142] The reward value R is obtained. Among them, R1 is the fault state, R2 is the bus voltage state, R3 is the energy state, R4 is the battery pack state, R5 is the switch state, k1 is the first coefficient, k2 is the second coefficient, k3 is the third coefficient, k4 is the fourth coefficient, and k5 is the fifth coefficient.

[0143] According to formulas 7 to 11:

[0144] R1=-(F pe +F b1 +F b2 +F b3 +F pd (7)

[0145] R2=-|V bus_next -V bus | (8)

[0146] R3 = -|P pe +P load +P b | (9)

[0147]

[0148] We obtain R1, R2, R3, R4, and R5. Among them, F... pe F is a fault in the piezoelectric power supply. b1 F b2 F b3 These represent the faults of the three reconfigurable battery packs, F pd For a fault in the power distribution section, V bus_next This represents the bus voltage value at the next moment, V. bus P represents the current bus voltage value. pe P represents the power of the piezoelectric power supply. load P is the power of the load. b Battery malfunction, SoC mean It is the average SOC of the reconfigurable battery pack, A m_next Let A be the operating state of the m-th switch at the next moment. m This represents the current operating state of the m-th switch.

[0149] In this embodiment, the reward function can minimize the number of faults, achieve the most stable bus voltage, optimize energy dispatch, balance battery pack capacity, and reduce the number of switching operations.

[0150] In this embodiment, based on the fault state, bus voltage state, energy state, battery pack state, and switch state, a first coefficient, a second coefficient, a third coefficient, a fourth coefficient, and a fifth coefficient are obtained, corresponding to the fault state, bus voltage state, energy state, battery pack state, and switch state, respectively. Based on the fault state, bus voltage state, energy state, battery pack state, switch state, and the first, second, third, fourth, and fifth coefficients, a reward value is obtained. The quality of the current action can be judged based on the reward value, thereby improving the robustness of model training.

[0151] Figure 8 This is a flowchart illustrating a seventh embodiment of a power control method provided in this application. Based on the above embodiments, as follows... Figure 8 As shown, one specific implementation of step S305 includes:

[0152] Step S801: Obtain the fault status based on the fault status of the piezoelectric power supply, the fault status of the reconfigurable battery pack, and the fault status of the power distribution section.

[0153] In this embodiment, the fault states of the piezoelectric power supply, the reconfigurable battery pack, and the power distribution section are combined to obtain the fault state.

[0154] Step S802: Obtain the bus voltage state based on the bus voltage at both ends of the battery pack and the bus voltage at both ends of the battery pack at the next moment.

[0155] In this embodiment, the difference between the bus voltage at both ends of the battery pack and the bus voltage at both ends of the battery pack at the next moment is used to obtain the bus voltage state.

[0156] Step S803: Obtain the state of energy based on the load power, piezoelectric power supply power, and battery pack power.

[0157] In this embodiment, the load power, piezoelectric power supply power, and battery pack power are summed to obtain the state of energy.

[0158] Step S804: Obtain the battery pack state based on the state of charge of the battery cells and the average state of charge of the reconfigurable battery pack.

[0159] In this embodiment, the battery pack state is obtained by subtracting the state of charge of the battery cell from the average state of charge of the reconfigurable battery pack.

[0160] Step S805: Obtain the switch state based on the current state of the switch and the state at the next moment.

[0161] In this embodiment, the switch state is obtained by subtracting the current state of the switch from its state at the next moment.

[0162] In this embodiment, the fault state is obtained based on the fault state of the piezoelectric power supply, the fault state of the reconfigurable battery pack, and the fault state of the power distribution section; the bus voltage state is obtained based on the bus voltage at both ends of the battery pack and the bus voltage at both ends of the battery pack at the next moment; the energy state is obtained based on the load power, the piezoelectric power supply power, and the battery pack power; the battery pack state is obtained based on the state of charge of the battery cells and the average state of charge of the reconfigurable battery pack; and the switch state is obtained based on the current state of the switch and the state at the next moment.

[0163] It should be noted that although the steps in the above embodiments are described in a specific order, those skilled in the art will understand that in order to achieve the effect of this application, different steps do not necessarily have to be executed in such an order. They can be executed simultaneously (in parallel) or in other orders, and these variations are all within the scope of protection of this application.

[0164] Furthermore, this application also provides a power control device.

[0165] Figure 9 This is a schematic diagram of the structure of a power control device provided in an embodiment of this application. Figure 9 As shown, the power control device in this embodiment mainly includes an acquisition module 21, an analysis module 22, and a control module 23. In some embodiments, one or more of the acquisition module 21, analysis module 22, and control module 23 can be combined into a single module. In some embodiments, the acquisition module 21 can be configured to acquire power status information. The analysis module 22 can be configured to input the power status information into a preset multi-agent model to obtain power control information. The control module 23 can be configured to perform control processing on the power system according to the power control information. The process of obtaining a preset multi-agent model includes: acquiring the current power state information; dividing the current power state information into power state group data; inputting the power state group data into the corresponding agents to obtain action sets; obtaining the power state information at the next moment based on the action sets; obtaining the fault state, bus voltage state, energy state, battery pack state, and switch state based on the power state information at the next moment and the current power state information; obtaining the reward value based on the fault state, bus voltage state, energy state, battery pack state, and switch state; updating the parameters of the agents based on the reward value; and storing the parameters of the current multiple agents after determining that the training rounds have reached a preset number of rounds to obtain the preset multi-agent model.

[0166] The aforementioned power control device is used to perform Figure 2 and Figure 3The power control method embodiments shown are similar in technical principle, the technical problems they solve, and the technical effects they produce. Those skilled in the art can clearly understand that, for the sake of convenience and brevity, the specific working process and related descriptions of the power control device can be found in the embodiments of the power control method, and will not be repeated here.

[0167] Those skilled in the art will understand that all or part of the processes in the method of the above-described embodiment can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable file, or some intermediate form. The computer-readable storage medium can include any entity or device capable of carrying the computer program code, a medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory, a random access memory, an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc. It should be noted that the content included in the computer-readable storage medium can be appropriately added or removed according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable storage medium does not include electrical carrier signals and telecommunication signals.

[0168] Furthermore, this application also provides a power control device.

[0169] Figure 10 This is a schematic diagram of a power control device provided in an embodiment of this application. Figure 10 As shown. In one embodiment of a power control device according to this application, the power control device includes a processor 31 and a memory 32. The memory 32 can be configured to store a program for executing the power control method of the above-described method embodiments, and the processor 31 can be configured to execute the program in the memory. The program includes, but is not limited to, a program for executing the power control method of the above-described method embodiments. For ease of explanation, only the parts related to the embodiments of this application are shown. For specific technical details not disclosed, please refer to the method section of the embodiments of this application. The power control device can be a control device device comprising various electronic devices.

[0170] Furthermore, this application also provides a computer-readable storage medium. In one embodiment of the computer-readable storage medium according to this application, the computer-readable storage medium can be configured to store a program that performs the power control method of the above-described method embodiments. This program can be loaded and run by a processor to implement the above-described power control method. For ease of explanation, only the parts related to the embodiments of this application are shown; for specific technical details not disclosed, please refer to the method section of the embodiments of this application. The computer-readable storage medium can be a storage device comprising various electronic devices. Optionally, in the embodiments of this application, the computer-readable storage medium is a non-transitory computer-readable storage medium.

[0171] Furthermore, it should be understood that since the various modules are only provided to illustrate the functional units of the device described in this application, the physical devices corresponding to these modules may be the processor itself, or a part of the processor's software, hardware, or a combination of both. Therefore, the number of modules shown in the figures is merely illustrative.

[0172] Those skilled in the art will understand that the various modules in the device can be adaptively split or combined. Such splitting or combining of specific modules will not cause the technical solution to deviate from the principles of this application; therefore, the technical solutions after splitting or combining will fall within the protection scope of this application.

[0173] The technical solutions of this application have been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of this application is obviously not limited to these specific embodiments. Without departing from the principles of this application, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of this application.

Claims

1. A power supply control method, characterized in that, include: Obtain power status information; The power status information is input into a preset multi-agent model to obtain power control information; Based on the power control information, the power system is controlled and processed. The acquisition of the preset multi-agent model includes: Obtain the current power status information; The current power status information is divided to obtain power status grouped data; The power state grouping data is input into the corresponding intelligent agents to obtain action sets; Based on the set of actions, the power state information for the next moment is obtained; Based on the power state information at the next moment and the current power state information, the fault state, bus voltage state, energy state, battery pack state, and switch state are obtained. The reward value is obtained based on the fault status, the bus voltage status, the energy status, the battery pack status, and the switch status; The parameters of the agent are updated based on the reward value; After determining that the training rounds have reached the preset number of rounds, the parameters of the current multiple agents are stored and processed to obtain the preset multi-agent model.

2. The method according to claim 1, characterized in that, The step of dividing the current power state information to obtain power state grouped data includes: The power status information is divided according to the data source to obtain a battery pack data group and other data groups; The other data groups are divided into piezoelectric power supply data group, power distribution data group and cable data group; The battery pack data group, the piezoelectric power supply data group, the power distribution data group, and the cable data group are combined and processed to obtain power status grouped data.

3. The method according to claim 1, characterized in that, The step of obtaining the power state information for the next moment based on the set of actions includes: The state of charge of the battery cells in the battery pack is obtained based on the state of charge of the battery cells in the battery pack at the previous moment, the switching duration, the battery capacity, and the current of the battery pack. The battery voltage is obtained based on the battery current, battery open-circuit voltage, battery resistance, first voltage, and second voltage; wherein the first voltage and the second voltage satisfy a preset relationship.

4. The method according to claim 3, characterized in that, Obtaining the current of the battery pack includes: The current of the battery pack is obtained based on the power supply status, bus voltage, load power, and piezoelectric power supply power.

5. The method according to claim 1, characterized in that, The reward value is obtained based on the fault status, bus voltage status, energy status, battery pack status, and switch status, including: Based on the fault state, bus voltage state, energy state, battery pack state, and switch state, a first coefficient, a second coefficient, a third coefficient, a fourth coefficient, and a fifth coefficient are obtained, corresponding to the fault state, the bus voltage state, the energy state, the battery pack state, and the switch state, respectively. The reward value is obtained based on the fault status, the bus voltage status, the energy status, the battery pack status, the switch status, the first coefficient, the second coefficient, the third coefficient, the fourth coefficient, and the fifth coefficient.

6. The method according to claim 1, characterized in that, The process of obtaining the fault status, bus voltage status, energy status, battery pack status, and switch status based on the power status information at the next moment and the current power status information includes: The fault status is obtained based on the fault status of the piezoelectric power supply, the fault status of the reconfigurable battery pack, and the fault status of the power distribution section. The bus voltage state is obtained based on the bus voltage at both ends of the battery pack and the bus voltage at both ends of the battery pack at the next moment. The energy state is obtained based on the load power, piezoelectric power supply power, and battery pack power. The battery pack state is obtained based on the state of charge of the battery cells and the average state of charge of the reconfigurable battery pack. The switch state is obtained based on the current state of the switch and the state at the next moment.

7. The method according to claim 1, characterized in that, The power status information includes: Piezoelectric power supply failure, battery cell failure, power distribution failure, load failure, battery cell state of charge, piezoelectric power supply power, and battery cell bus voltage.

8. A power control device, characterized in that, include: The acquisition module is used to acquire power status information; The analysis module is used to input the power status information into a preset multi-agent model to obtain power control information; The control module is used to control the power system according to the power control information. The acquisition of the preset multi-agent model includes: Obtain the current power status information; The current power status information is divided to obtain power status grouped data; The power state grouping data is input into the corresponding intelligent agents to obtain action sets; Based on the set of actions, the power state information for the next moment is obtained; Based on the power state information at the next moment and the current power state information, the fault state, bus voltage state, energy state, battery pack state, and switch state are obtained. The reward value is obtained based on the fault status, the bus voltage status, the energy status, the battery pack status, and the switch status; The parameters of the agent are updated based on the reward value; After determining that the training rounds have reached the preset number of rounds, the parameters of the current multiple agents are stored and processed to obtain the preset multi-agent model.

9. A power control device, comprising a processor and a storage device, said storage device being adapted to store multiple lines of program code, characterized in that, The program code is adapted to be loaded and run by the processor to perform the method of any one of claims 1 to 7.

10. A computer-readable storage medium storing a plurality of program codes, characterized in that, The program code is adapted to be loaded and run by a processor to perform the method of any one of claims 1 to 7.

Images