Remote control method, device, system, equipment and product for power converter

Abstract

The invention discloses a remote control method, device, system, equipment and product for a power converter, and relates to the technical field of power control. The method is executed by control equipment in a remote control system of the power converter, and the control parameters of the power converter are optimized based on an optimization algorithm by applying current sampling values of a plurality of electrical parameters from an electrical parameter acquisition circuit and a pre-trained multi-dimensional characteristic data and power factor mapping model in real time. The search result is transmitted to the control signal generation circuit in real time through the communication circuit, so that the signal generation circuit generates a control signal for the power converter according to the search result and transmits the control signal; therefore, the purpose of remotely controlling the power converter in real time so as to maximize the power factor of the preceding-stage PFC circuit all the time can be achieved, and a calculation module does not need to be configured for the power converter.

Description

Technical Field

[0001] The present invention belongs to the technical field of power supply control, and in particular relates to a method, device, system, equipment and product for remotely controlling a power supply converter. Background Art

[0002] The power supply is the energy source for the active devices in the electronic circuit to work. The performance of the power supply directly affects the performance of the electronic circuit. The power supply can be said to be the "heart" of the electronic system. Usually an electronic system needs to use a variety of power supplies with different voltages (or currents) and different capacities. Designing a power supply for each application requirement will often increase the system size and cost. Therefore, power converters used to provide different power supplies have emerged, which can greatly facilitate the simplification of power supply design.

[0003] In the existing power converter used as a communication power supply, the main circuit is usually composed of a front-stage PFC (Power Factor Correction) circuit and a rear-stage isolated DC-DC (i.e., direct current to direct current) conversion circuit, and a bus capacitor is connected in parallel between the two circuits. However, due to the input voltage jump and / or output load jump in the power converter, the power factor in the front-stage PFC circuit will also jump, which will affect the power supply efficiency of the power converter and is not conducive to energy saving. Therefore, it is necessary to control the power converter in real time so that the power factor of the front-stage PFC circuit is always maximized, thereby improving the power supply efficiency and facilitating energy saving. In addition, if the control algorithm of the power converter is more complex, it will generate a higher demand for computing resources, so that the power converter also needs to be configured with a computing module with a certain computing power, which will increase the hardware cost. Therefore, it is necessary to centrally run the control algorithm of the power converter at a remote end to reduce the hardware cost on the power converter side.

[0004] In summary, how to provide a new solution for remote real-time control of power converters so that the power factor of the front-stage PFC circuit is always maximized, thereby improving power supply efficiency and saving energy while maintaining low cost of the power converter is a topic that technicians in this field urgently need to study. Summary of the invention

[0005] The object of the present invention is to provide a power converter remote control method, device, system, control equipment, computer-readable storage product and computer program product, which are used to remotely control the power converter in real time so that the power factor of the front-stage PFC circuit is always maximized, thereby improving the power supply efficiency and facilitating energy saving, while maintaining the low cost of the power converter.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions: In a first aspect, a power converter remote control method is provided, which is executed by a control device in a power converter remote control system, wherein the power converter remote control system also includes a power converter, an electrical parameter acquisition circuit, a communication circuit and a control signal generation circuit, and the power converter includes a front-stage active PFC circuit, a bus capacitor and a rear-stage DC-DC conversion circuit, the anode of the bus capacitor is respectively electrically connected to the positive output terminal of the front-stage active PFC circuit and the positive input terminal of the rear-stage DC-DC conversion circuit, and the cathode of the bus capacitor is respectively electrically connected to the front-stage active PF The negative output terminal of the C circuit and the negative input terminal of the post-stage DC-DC conversion circuit, the electrical parameter acquisition circuit is electrically connected to the power converter and is used to collect the electrical parameter sampling values ​​of the power converter in real time and at multiple different positions, the output terminal of the electrical parameter acquisition circuit is communicatively connected to the input terminal of the communication circuit, the output terminal of the communication circuit is communicatively connected to the input terminal of the control signal generation circuit, the output terminal of the control signal generation circuit is communicatively connected to the controlled terminal of the pre-stage active PFC circuit and / or the post-stage DC-DC conversion circuit, and the communication circuit is also communicatively connected to the control device; The power converter remote control method comprises: Acquiring multiple current sampling values ​​of electrical parameters from the electrical parameter acquisition circuit in real time through the communication circuit; Applying the current sampling values ​​of the multiple electrical parameters and the pre-trained multi-dimensional feature data and power factor mapping model in real time, optimizing the control parameters of the power converter based on the optimization algorithm, and obtaining the control parameters and the current optimal search result for maximizing the power factor of the front-stage active PFC circuit, wherein the multi-dimensional feature data and power factor mapping model is used to output a power factor value having a mapping relationship with the multi-dimensional feature data including the electrical parameter sampling values ​​at the multiple different positions and the control parameter values ​​corresponding to the control parameters; The current optimization search result is transmitted to the control signal generating circuit in real time through the communication circuit, so that the control signal generating circuit generates a control signal for the front-stage active PFC circuit and / or the rear-stage DC-DC conversion circuit according to the current optimization search result, and transmits the control signal to the front-stage active PFC circuit and / or the rear-stage DC-DC conversion circuit.

[0007] Based on the above invention content, a new solution for remote real-time control of a power converter based on an optimization algorithm and a multi-dimensional feature data and a power factor mapping model is provided, that is, it is executed by a control device in a remote control system of a power converter, and multiple current sampling values ​​of electrical parameters from an electrical parameter acquisition circuit and pre-trained multi-dimensional feature data and a power factor mapping model are applied in real time, and the control parameters of the power converter are optimized based on the optimization algorithm to obtain the control parameters and the current optimal search result for maximizing the power factor of a front-stage active PFC circuit, and then the search result is transmitted to a control signal generating circuit in real time through a communication circuit, so that the signal generating circuit generates a control signal for the power converter according to the search result and transmits it, so that the purpose of remote real-time control of the power converter to always maximize the power factor of the front-stage PFC circuit can be achieved, and there is no need to configure a calculation module for the power converter, thereby improving the power supply efficiency and facilitating energy saving, and maintaining the power converter at a low cost, which is convenient for practical application and promotion.

[0008] In a possible design, the electrical parameter acquisition circuit includes a front-stage input voltage acquisition subcircuit, a bus capacitor voltage acquisition subcircuit, a rear-stage output voltage acquisition subcircuit and / or a rear-stage output current acquisition subcircuit, wherein the front-stage input voltage acquisition subcircuit is electrically connected to the input end of the front-stage active PFC circuit and is used to collect the front-stage input voltage sampling value of the front-stage active PFC circuit in real time, the bus capacitor voltage acquisition subcircuit is electrically connected to the anode of the bus capacitor and is used to collect the capacitor voltage sampling value of the bus capacitor in real time, the rear-stage output voltage acquisition subcircuit is electrically connected to the output end of the rear-stage DC-DC conversion circuit and is used to collect the rear-stage output voltage sampling value of the rear-stage DC-DC conversion circuit in real time, and the rear-stage output current acquisition subcircuit is electrically connected to the output end of the rear-stage DC-DC conversion circuit and is used to collect the rear-stage output current sampling value of the rear-stage DC-DC conversion circuit in real time.

[0009] In a possible design, the multi-dimensional feature data and the power factor mapping model are pre-trained according to the following steps: The sample data is obtained in the following manner: a plurality of electrical parameter historical sampling values ​​from the electrical parameter acquisition circuit and a control parameter historical value that is contemporaneous with the plurality of electrical parameter historical sampling values ​​and is used to generate a control signal for the front-stage active PFC circuit and / or the rear-stage DC-DC conversion circuit are used as model input items, and a power factor historical value that is contemporaneous with the plurality of electrical parameter historical sampling values ​​and is measured for the front-stage active PFC circuit is used as a model output item, and then the model input item and the model output item are used as a sample data; All the sample data are applied to perform model training and verification on a machine learning model based on an artificial intelligence algorithm to obtain a verified multidimensional feature data and a power factor mapping model, wherein the multidimensional feature data and the power factor mapping model are used to output a power factor value having a mapping relationship with the multidimensional feature data including the electrical parameter sampling values ​​at the multiple different positions and the control parameter values ​​corresponding to the control parameters.

[0010] In one possible design, the control parameters include a first control parameter for controlling the constant voltage output of the front-stage active PFC circuit, a second control parameter for controlling the phase of the input voltage and current in the front-stage active PFC circuit, a third control parameter for controlling the switching speed of the switch tube in the rear-stage DC-DC conversion circuit, a fourth control parameter for controlling the switching pulse width of the switch tube in the rear-stage DC-DC conversion circuit and / or a fifth control parameter for controlling the switching pulse phase shift angle of different switch tubes in the rear-stage DC-DC conversion circuit.

[0011] In a possible design, the current sampled values ​​of the multiple electrical parameters and the pre-trained multi-dimensional feature data and power factor mapping model are applied in real time, and the control parameters of the power converter are optimized based on an optimization algorithm to obtain the control parameters and the current optimal search result for maximizing the power factor of the front-stage active PFC circuit, including the following steps S201-S212: S201. Initialize the particle swarm optimization algorithm and include the population size , maximum number of iterations , Self-learning factor and the global learning factor The algorithm parameters are used, and the initial position of each particle in the particle population is randomly generated, and then step S202 is performed, wherein the initial position of each particle is randomly generated based on the following formula:

[0012] In the formula, represents a positive integer, Indicates less than or equal to A positive integer, represents the number of dimensions of a parameter vector to be optimized, wherein the parameter vector to be optimized includes control parameters of the power converter to be optimized, represents the first The particle is the first particle in the parameter vector to be optimized The initial position in the dimension, Indicated in the The upper limit of the parameter search space in dimensions, Indicated in the The lower bound of the parameter search space in dimensions, Represents a purely decimal random generator function; S202. For each particle, the current sampling values ​​of the multiple electrical parameters and the corresponding initial positions are imported into the pre-trained multi-dimensional feature data and power factor mapping model, and the corresponding power factor initial value is output, and the power factor initial value is used as the corresponding fitness , then executing step S203, wherein the multidimensional feature data and power factor mapping model is used to output a power factor value having a mapping relationship with the multidimensional feature data including the electrical parameter sampling values ​​at the plurality of different positions and the control parameter value corresponding to the control parameter; S203. Determine whether the maximum value among the fitness of each particle is greater than or equal to a preset threshold value. If so, use the initial position corresponding to the maximum value as the control parameter and the current optimization search result for maximizing the power factor of the front-stage active PFC circuit. Otherwise, execute step S204; S204. Take the initial position of a particle with the maximum fitness as the initial global optimal position , remember the The position of the particle in the iteration process and corresponding to the maximum fitness is the The local optimal position reached by particles , and the position of the particle population in the iteration process corresponding to the maximum fitness is recorded as the global optimal position reached by the particle population , and remember the The moving speed of a particle is , and finally initialize the local optimal position , and initialize the moving speed is zero, and the particle movement inertia coefficient range is also set to [ ], and initialize the period of periodic reduction of the inertia coefficient A randomly selected value within the range of the particle movement inertia coefficient is set, and the particle movement inertia coefficient is also initialized to a value greater than zero during the iteration process, and the current number of iterations is also initialized. is 0, then execute step S205; S205. Update the particle movement inertia coefficient of each particle, and then execute step S206, wherein the update formula of the particle movement inertia coefficient is as follows:

[0013] In the formula, Indicated in After the iteration, the The particle in the The inertia coefficient of particle movement in dimensions, Indicated in iterations ago and the The particle in the The inertia coefficient of particle movement in dimensions, Represents the number of previous iterations For the cycle The result of the remainder operation, and if If it is less than 0, a new value is randomly selected within the range of the particle's moving inertia coefficient as the new period. , and recalculate ,until Not less than 0; S206. Update the moving speed of each particle, and then execute step S207, wherein the updating formula of the moving speed is as follows:

[0014] In the formula, Indicated in After the iteration, the The particle in the The speed of movement in one dimension, Indicated in iterations ago and the The particle in the The speed of movement in one dimension, represents the first random number uniformly distributed in (0,1), Indicates in front During the iteration, The particle in the The local optimal position reached in dimensions, Indicated in iterations ago and the The particle in the The position in the dimension, represents the second random number uniformly distributed in (0,1), Indicates in front In the first iteration, the particle population The global optimal position achieved in dimensions; S207. Update the position of each particle, and then execute step S208, wherein the update formula of the position is as follows:

[0015] In the formula, Indicated in After the iteration, the The particle in the Position in one dimension; S208. For each particle, the current sampling values ​​of the multiple electrical parameters and the corresponding positions are imported into the multidimensional feature data and power factor mapping model, and the corresponding new power factor value is output, and the new power factor value is used as the corresponding fitness , then execute step S209; S209. Determine whether the maximum value among the current fitness of each particle is greater than or equal to the preset threshold value. If so, use the position corresponding to the maximum value as the control parameter and the current optimization search result for maximizing the power factor of the front-stage active PFC circuit. Otherwise, execute step S210; S210. Determine the local optimal position Is the corresponding fitness less than the The current fitness of the particle, if so, the local optimal position Updated to the The current position of the particle, then execute step S211, otherwise directly execute step S211; S211. Determine the global optimal position Is the corresponding fitness less than the maximum value among the current fitness of each particle? If so, the global optimal position Update to the current position of any particle with the maximum value, and then execute step S212, otherwise directly execute step S212; S212. Make the current number of iterations Add 1 to the current number of iterations. Whether the maximum number of iterations has been reached If so, the position corresponding to the global optimal fitness is used as the control parameter and the current optimal search result for maximizing the power factor of the pre-stage active PFC circuit, otherwise, the process returns to step S205, wherein the global optimal fitness refers to the position corresponding to the global optimal position The corresponding fitness.

[0016] In a second aspect, a power converter remote control device is provided, which is suitable for being arranged in a control device of a power converter remote control system, wherein the power converter remote control system also includes a power converter, an electrical parameter acquisition circuit, a communication circuit and a control signal generation circuit, and the power converter includes a front-stage active PFC circuit, a bus capacitor and a rear-stage DC-DC conversion circuit, the anode of the bus capacitor is respectively electrically connected to the positive output terminal of the front-stage active PFC circuit and the positive input terminal of the rear-stage DC-DC conversion circuit, and the cathode of the bus capacitor is respectively electrically connected to the front-stage active PF The negative output terminal of the C circuit and the negative input terminal of the post-stage DC-DC conversion circuit, the electrical parameter acquisition circuit is electrically connected to the power converter and is used to collect the electrical parameter sampling values ​​of the power converter in real time and at multiple different positions, the output terminal of the electrical parameter acquisition circuit is communicatively connected to the input terminal of the communication circuit, the output terminal of the communication circuit is communicatively connected to the input terminal of the control signal generation circuit, the output terminal of the control signal generation circuit is communicatively connected to the controlled terminal of the pre-stage active PFC circuit and / or the post-stage DC-DC conversion circuit, and the communication circuit is also wirelessly connected to the control device; The power converter remote control device comprises a sampling data acquisition unit, a control parameter optimization unit and an optimization result transmission unit which are sequentially communicatively connected; The sampling data acquisition unit is used to acquire multiple current sampling values ​​of electrical parameters from the electrical parameter acquisition circuit in real time through the communication circuit; The control parameter optimization unit is used to apply the current sampling values ​​of the multiple electrical parameters and the pre-trained multi-dimensional feature data and power factor mapping model in real time, optimize the control parameters of the power converter based on the optimization algorithm, and obtain the control parameters and the current optimal search result for maximizing the power factor of the front-stage active PFC circuit, wherein the multi-dimensional feature data and power factor mapping model is used to output a power factor value having a mapping relationship with the multi-dimensional feature data including the electrical parameter sampling values ​​at the multiple different positions and the control parameter values ​​corresponding to the control parameters; The optimization result transmission unit is used to transmit the current optimization search result to the control signal generation circuit in real time through the communication circuit, so that the control signal generation circuit generates a control signal for the front-stage active PFC circuit and / or the rear-stage DC-DC conversion circuit according to the current optimization search result, and transmits the control signal to the front-stage active PFC circuit and / or the rear-stage DC-DC conversion circuit.

[0017] In a third aspect, the present invention provides a remote control system for a power converter, comprising a control device, a power converter, an electrical parameter acquisition circuit, a communication circuit and a control signal generating circuit, wherein the power converter comprises a front-stage active PFC circuit, a bus capacitor and a rear-stage DC-DC conversion circuit, the anode of the bus capacitor is electrically connected to the positive output end of the front-stage active PFC circuit and the positive input end of the rear-stage DC-DC conversion circuit, respectively, the cathode of the bus capacitor is electrically connected to the negative output end of the front-stage active PFC circuit and the negative input end of the rear-stage DC-DC conversion circuit, respectively, the electrical parameter acquisition circuit is electrically connected to the power converter and is used to collect electrical parameter sampling values ​​of the power converter at multiple different positions in real time, the output end of the electrical parameter acquisition circuit is communicatively connected to the input end of the communication circuit, the output end of the communication circuit is communicatively connected to the input end of the control signal generating circuit, the output end of the control signal generating circuit is communicatively connected to the controlled end of the front-stage active PFC circuit and / or the rear-stage DC-DC conversion circuit, and the communication circuit is also wirelessly connected to the control device; The control device is used to execute the power converter remote control method as described in the first aspect or any possible design of the first aspect.

[0018] In a fourth aspect, the present invention provides a control device, comprising a storage module, a processing module and a transceiver module which are communicatively connected in sequence, wherein the storage module is used to store a computer program, the transceiver module is used to send and receive messages, and the processing module is used to read the computer program to execute the remote control method of the power converter as described in the first aspect or any possible design of the first aspect.

[0019] In a fifth aspect, the present invention provides a computer-readable storage product having instructions stored thereon, which, when executed on a computer, executes the power converter remote control method as described in the first aspect or any possible design of the first aspect.

[0020] In a sixth aspect, the present invention provides a computer program product, comprising a computer program or instructions, which, when executed by a computer, implement the remote control method for a power converter as described in the first aspect or any possible design of the first aspect.

[0021] Beneficial effects of the above scheme: (1) The present invention creatively provides a new scheme for remote real-time control of a power converter based on an optimization algorithm and a multi-dimensional feature data and power factor mapping model, that is, the control device in the remote control system of the power converter executes and applies in real time the current sampled values ​​of multiple electrical parameters from the electrical parameter acquisition circuit and the pre-trained multi-dimensional feature data and power factor mapping model, optimizes the control parameters of the power converter based on the optimization algorithm, obtains the current optimal search result of the control parameters for maximizing the power factor of the front-stage active PFC circuit, and then transmits the search result to the control signal generating circuit in real time through the communication circuit, so that the signal generating circuit generates and transmits the control signal for the power converter according to the search result, thereby achieving the purpose of remote real-time control of the power converter to maximize the power factor of the front-stage PFC circuit, and eliminating the need to configure a computing module for the power converter, thereby improving the power supply efficiency and facilitating energy saving, while maintaining the low cost of the power converter, and facilitating practical application and promotion. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. 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 paying creative work.

[0023] Figure 1 A flowchart of a remote control method for a power converter provided in an embodiment of the present application.

[0024] Figure 2 A schematic diagram of the structure of a remote control device for a power converter provided in an embodiment of the present application.

[0025] Figure 3 A schematic diagram of the structure of a remote control system for a power converter provided in an embodiment of the present application.

[0026] Figure 4 A schematic diagram of the structure of a control device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0027] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the present invention will be briefly introduced below in combination with the drawings and the description of the embodiments or the prior art. Obviously, the following description of the structure of the drawings is only some embodiments of the present invention. For ordinary technicians in this field, other embodiments can be obtained based on these embodiments without creative work. It should be noted that the description of these embodiments is used to help understand the present invention, but does not constitute a limitation of the present invention.

[0028] It should be understood that although the terms first and second, etc. may be used herein to describe various objects, these objects should not be limited by these terms. These terms are only used to distinguish one object from another object. For example, a first object can be referred to as a second object, and similarly, a second object can be referred to as a first object without departing from the scope of the exemplary embodiments of the present invention.

[0029] It should be understood that the term "and / or" that may appear in this document is merely a description of the association relationship between associated objects, indicating that there may be three relationships. For example, A and / or B can indicate three situations: A exists alone, B exists alone, or A and B exist at the same time. For another example, A, B and / or C can indicate the existence of any one of A, B and C or any combination of them. The term " / and" that may appear in this document describes another type of association object relationship, indicating that there may be two relationships. For example, A / and B can indicate two situations: A exists alone or A and B exist at the same time. In addition, the character " / " that may appear in this document generally indicates that the previous and next associated objects are in an "or" relationship.

[0030] Example like Figure 1 and Figure 3 As shown, the power converter remote control method provided in the first aspect of this embodiment can be, but is not limited to, executed by a control device having certain computing resources and in a power converter remote control system, wherein the power converter remote control system further includes, but is not limited to, a power converter, an electrical parameter acquisition circuit, a communication circuit, and a control signal generation circuit, etc. The power converter includes, but is not limited to, a front-stage active PFC circuit, a bus capacitor, and a rear-stage DC-DC conversion circuit, etc. The anode of the bus capacitor is electrically connected to the positive output terminal of the front-stage active PFC circuit and the positive input terminal of the rear-stage DC-DC conversion circuit, respectively, and the bus capacitor is electrically connected to the positive output terminal of the front-stage active PFC circuit and the positive input terminal of the rear-stage DC-DC conversion circuit, respectively. The cathode is electrically connected to the negative output terminal of the front-stage active PFC circuit and the negative input terminal of the rear-stage DC-DC conversion circuit respectively; the electrical parameter acquisition circuit is electrically connected to the power converter and is used to acquire electrical parameter sampling values ​​of the power converter in real time at multiple different positions; the output terminal of the electrical parameter acquisition circuit is communicatively connected to the input terminal of the communication circuit; the output terminal of the communication circuit is communicatively connected to the input terminal of the control signal generation circuit; the output terminal of the control signal generation circuit is communicatively connected to the controlled terminal of the front-stage active PFC circuit and / or the rear-stage DC-DC conversion circuit; and the communication circuit is also communicatively connected to the control device.

[0031] like Figure 3As shown, the combined circuit structure of the aforementioned front-stage active PFC circuit, bus capacitor and rear-stage DC-DC conversion circuit is a conventional circuit structure of an existing power converter, wherein the front-stage active PFC circuit is an existing circuit and has the following two control objectives: (1) output constant voltage; (2) input voltage and current in phase; the bus capacitor can be implemented by an electrolytic capacitor with a certain capacity; the rear-stage DC-DC conversion circuit is also an existing circuit and can achieve different power outputs by turning on and off the internal switch tube, that is, there are at least the following three control objects: (1) the switching speed of the switch tube in the rear-stage DC-DC conversion circuit (i.e., the switching frequency), (2) the switching pulse width of the switch tube in the rear-stage DC-DC conversion circuit (i.e., the duty cycle of the pulse signal generated by the switching action), and (3) the switching pulse phase shift angle of different switch tubes in the rear-stage DC-DC conversion circuit (i.e., the phase shift angle of different pulse signals).

[0032] like Figure 3 As shown, specifically, the electrical parameter acquisition circuit includes but is not limited to a front-stage input voltage acquisition subcircuit, a bus capacitor voltage acquisition subcircuit, a rear-stage output voltage acquisition subcircuit and / or a rear-stage output current acquisition subcircuit, etc., wherein the front-stage input voltage acquisition subcircuit is electrically connected to the input end of the front-stage active PFC circuit and is used to collect the front-stage input voltage sampling value of the front-stage active PFC circuit in real time, the bus capacitor voltage acquisition subcircuit is electrically connected to the anode of the bus capacitor and is used to collect the capacitor voltage sampling value of the bus capacitor in real time, the rear-stage output voltage acquisition subcircuit is electrically connected to the output end of the rear-stage DC-DC conversion circuit and is used to collect the rear-stage output voltage sampling value of the rear-stage DC-DC conversion circuit in real time, and the rear-stage output current acquisition subcircuit is electrically connected to the output end of the rear-stage DC-DC conversion circuit and is used to collect the rear-stage output current sampling value of the rear-stage DC-DC conversion circuit in real time. The aforementioned front-stage input voltage acquisition subcircuit, bus capacitor voltage acquisition subcircuit, rear-stage output voltage acquisition subcircuit and rear-stage output current acquisition subcircuit can all be conventionally implemented using existing circuits; for example, since the input power of the front-stage active PFC circuit is AC power, the front-stage input voltage acquisition subcircuit can be conventionally composed of a voltage transformer and related auxiliary components, and the bus capacitor voltage acquisition subcircuit and the rear-stage output voltage acquisition subcircuit can be conventionally implemented using differential sampling circuits based on operational amplifiers, etc. In addition, the electrical parameter sampling value is specifically the front-stage input voltage sampling value, the capacitor voltage sampling value, the rear-stage output voltage sampling value or the rear-stage output current sampling value, etc.

[0033] The communication circuit is used to achieve the purpose of remote communication between the control device and the electrical parameter acquisition circuit and the control signal generation circuit. It can adopt a wired communication circuit based on RS485 communication mode, or a wireless communication circuit based on WiFi or LoRa (Long Range Radio) communication mode. The control signal generation circuit is used to generate a control signal for the front-stage active PFC circuit and / or the rear-stage DC-DC conversion circuit according to the control parameters of the power converter from the control device, and transmit the control signal to the front-stage active PFC circuit and / or the rear-stage DC-DC conversion circuit, thereby completing the remote control of the power converter. Specifically, the control parameters include but are not limited to a first control parameter for controlling the constant voltage output of the front-stage active PFC circuit, a second control parameter for controlling the same phase of the input voltage and current in the front-stage active PFC circuit, a third control parameter for controlling the switching speed of the switch tube in the rear-stage DC-DC conversion circuit, a fourth control parameter for controlling the switching pulse width of the switch tube in the rear-stage DC-DC conversion circuit, and / or a fifth control parameter for controlling the switching pulse phase shift angle of different switch tubes in the rear-stage DC-DC conversion circuit, etc. In addition, the control signal generating circuit can be conventionally implemented using an existing signal generating circuit.

[0034] like Figure 1 As shown, the power converter remote control method includes but is not limited to the following steps S1 to S3.

[0035] S1. Acquire multiple current sampling values ​​of electrical parameters from the electrical parameter acquisition circuit in real time through the communication circuit.

[0036] In step S1, the multiple current sampling values ​​of electrical parameters specifically include but are not limited to the currently collected front-stage input voltage sampling value, the capacitor voltage sampling value, the rear-stage output voltage sampling value and / or the rear-stage output current sampling value.

[0037] S2. Apply the current sampling values ​​of the multiple electrical parameters and the pre-trained multi-dimensional feature data and power factor mapping model in real time, optimize the control parameters of the power converter based on the optimization algorithm, and obtain the control parameters and the current optimal search result for maximizing the power factor of the front-stage active PFC circuit, wherein the multi-dimensional feature data and power factor mapping model is used to output a power factor value having a mapping relationship with the multi-dimensional feature data including the electrical parameter sampling values ​​at the multiple different positions and the control parameter values ​​corresponding to the control parameters.

[0038] In the step S2, the aforementioned multidimensional feature data including the electrical parameter sampling values ​​at the multiple different positions and the control parameter value is the model input item data of the multidimensional feature data and the power factor mapping model, and the power factor value is the model output item data of the multidimensional feature data and the power factor mapping model. The multidimensional feature data and the power factor mapping model is used to reflect the mapping relationship between the electrical parameter sampling values ​​at the multiple different positions and the control parameter value and the power factor value and conforms to the law of nature, which is specifically but not limited to being pre-trained according to the following steps S101 to S102.

[0039] S101. Obtain sample data in the following manner: use a plurality of electrical parameter historical sampling values ​​from the electrical parameter acquisition circuit and a control parameter historical value that is contemporaneous with the plurality of electrical parameter historical sampling values ​​and is used to generate a control signal for the front-stage active PFC circuit and / or the rear-stage DC-DC conversion circuit as model input items, and use a power factor historical value that is contemporaneous with the plurality of electrical parameter historical sampling values ​​and is measured for the front-stage active PFC circuit as a model output item, and then use the model input item and the model output item as a sample data.

[0040] In the step S101, for example, the historical sampling values ​​of the front-stage input voltage, the historical sampling values ​​of the capacitor voltage, the historical sampling values ​​of the rear-stage output voltage and / or the historical sampling values ​​of the rear-stage output current, etc., collected at 10:00, and the historical values ​​of the control parameters used to generate the control signal for the front-stage active PFC circuit and / or the rear-stage DC-DC conversion circuit at 10:00 can be used as the model input items, and the historical value of the power factor measured at 10:00 for the front-stage active PFC circuit can be used as the model output item, thereby obtaining a sample data.

[0041] S102. Apply all the sample data to perform model training and verification on the machine learning model based on the artificial intelligence algorithm, and obtain the verified multidimensional feature data and power factor mapping model, wherein the multidimensional feature data and power factor mapping model is used to output a power factor value having a mapping relationship with the multidimensional feature data including the electrical parameter sampling values ​​at the multiple different positions and the control parameter values ​​corresponding to the control parameters.

[0042] In step S102, the artificial intelligence algorithm is a core artificial intelligence algorithm that specifically studies how computers simulate or implement human learning behavior to acquire new knowledge or skills, reorganize existing knowledge structures to continuously improve their own performance, and is the fundamental way to make computers intelligent; specifically, the artificial intelligence algorithm preferably, but not limited to, adopts a machine learning algorithm based on support vector machine, K nearest neighbor method, stochastic gradient descent method, multi-layer perceptron, decision tree, back propagation neural network or radial basis function network, etc., so as to quickly and accurately find the rules in the data. Based on a certain amount of sample data, the conventional calibration verification modeling method (the specific process includes the calibration process and the verification process of the model, that is, first by comparing the model simulation results with the measured data, and then adjusting the model parameters according to the comparison results, so that the simulation results are consistent with the actual process) can be used to train and obtain the verified multidimensional feature data and power factor mapping model. In addition, in the calibration verification modeling process of the multidimensional feature data and power factor mapping model, the model parameters can be tuned by a tree-structured Bayesian optimization algorithm.

[0043] In the step S2, specifically, the optimization algorithm may be, but is not limited to, a GreyWolf Algorithm, a Particle Swarm Optimization Algorithm, a Bat Algorithm, an Aquila Optimizer, or a Bald eagle search optimization algorithm, etc., wherein the Particle Swarm Optimization (PSO) is a heuristic optimization algorithm that simulates the information sharing and collaboration mechanism in the foraging behavior of a flock of birds, and seeks the optimal solution to the problem through interaction between individuals. In order to balance the capabilities of local optimum and global optimum in parameter optimization, improve the efficiency of optimizing parameter search while ensuring overall reliability, preferably, the current sampled values ​​of the multiple electrical parameters are applied in real time, and the pre-trained multi-dimensional feature data and power factor mapping model are completed, and the control parameters of the power converter are optimized based on the optimization algorithm, and the control parameters are obtained and the current optimal search results for maximizing the power factor of the pre-stage active PFC circuit are obtained, including but not limited to the following steps S201 to S212.

[0044] S201. Initialize the particle swarm optimization algorithm and include the population size , maximum number of iterations , Self-learning factor and the global learning factor The algorithm parameters are used, and the initial position of each particle in the particle population is randomly generated, and then step S202 is performed, wherein the initial position of each particle is randomly generated based on the following formula:

[0045] In the formula, represents a positive integer, Indicates less than or equal to A positive integer, represents the number of dimensions of a parameter vector to be optimized, wherein the parameter vector to be optimized includes control parameters of the power converter to be optimized, represents the first The particle is the first particle in the parameter vector to be optimized The initial position in the dimension, Indicated in the The upper limit of the parameter search space in dimensions, Indicated in the The lower bound of the parameter search space in dimensions, Represents a purely decimal random generator.

[0046] S202. For each particle, the current sampling values ​​of the multiple electrical parameters and the corresponding initial positions are imported into the pre-trained multi-dimensional feature data and power factor mapping model, and the corresponding power factor initial value is output, and the power factor initial value is used as the corresponding fitness , and then execute step S203, wherein the multidimensional feature data and power factor mapping model is used to output a power factor value having a mapping relationship with the multidimensional feature data including the electrical parameter sampling values ​​at the multiple different positions and the control parameter value corresponding to the control parameter.

[0047] In step S202, since the initial position is a specific control parameter value corresponding to the control parameter, it can be imported into the multi-dimensional feature data and power factor mapping model together with the current sampled values ​​of the multiple electrical parameters as model input data to obtain the corresponding power factor initial value. Since the optimization goal is to maximize the power factor of the pre-stage active PFC circuit, the power factor initial value can be directly used as the fitness .

[0048] S203. Determine whether the maximum value among the fitness of each particle is greater than or equal to a preset threshold value. If so, use the initial position corresponding to the maximum value as the control parameter and the current optimization search result for maximizing the power factor of the front-stage active PFC circuit. Otherwise, execute step S204.

[0049] In step S203, the preset threshold is the power factor optimization target value of the pre-stage active PFC circuit, for example, preset to 99%. When it is determined that the maximum value among the fitness of each particle is greater than or equal to the preset threshold, it indicates that the power factor optimization target of the pre-stage active PFC circuit has been achieved, so the subsequent steps S204 to S212 may no longer be executed. In addition, in order to continuously explore the optimal control parameters, the preset threshold can also be preset to a value of 100% or above.

[0050] S204. Take the initial position of a particle with the maximum fitness as the initial global optimal position , remember the The position of the particle in the iteration process and corresponding to the maximum fitness is the The local optimal position reached by particles , and the position of the particle population in the iteration process corresponding to the maximum fitness is recorded as the global optimal position reached by the particle population , and remember the The moving speed of a particle is , and finally initialize the local optimal position , and initialize the moving speed is zero, and the particle movement inertia coefficient range is also set to [ ], and initialize the period of periodic reduction of the inertia coefficient A randomly selected value within the range of the particle movement inertia coefficient is set, and the particle movement inertia coefficient is also initialized to a value greater than zero during the iteration process, and the current number of iterations is also initialized. is 0, and then execute step S205.

[0051] S205. Update the particle movement inertia coefficient of each particle, and then execute step S206, wherein the update formula of the particle movement inertia coefficient is as follows:

[0052] In the formula, Indicated in After the iterations, the The particle in the The inertia coefficient of particle movement in dimensions, Indicated in iterations ago and the The particle in the The inertia coefficient of particle movement in dimensions, Represents the number of previous iterations For the cycle The result of the remainder operation, and if If it is less than 0, a new value is randomly selected within the range of the particle's moving inertia coefficient as the new period. , and recalculate ,until Not less than 0.

[0053] S206. Update the moving speed of each particle, and then execute step S207, wherein the updating formula of the moving speed is as follows:

[0054] In the formula, Indicated in After the iterations, the The particle in the The speed of movement in one dimension, Indicated in iterations ago and the The particle in the The speed of movement in one dimension, represents the first random number uniformly distributed in (0,1), Indicates in front During the iteration, The particle in the The local optimal position reached in dimensions, Indicated in iterations ago and the The particle in the The position in the dimension, represents the second random number uniformly distributed in (0,1), Indicates in front In the first iteration, the particle population The global optimal position achieved in all dimensions.

[0055] S207. Update the position of each particle, and then execute step S208, wherein the update formula of the position is as follows:

[0056] In the formula, Indicated in After the iterations, the The particle in the Position in one dimension.

[0057] S208. For each particle, the current sampling values ​​of the multiple electrical parameters and the corresponding positions are imported into the multi-dimensional feature data and power factor mapping model, and the corresponding new power factor value is output, and the new power factor value is used as the corresponding fitness , then execute step S209.

[0058] S209. Determine whether the maximum value among the current fitness of each particle is greater than or equal to the preset threshold value. If so, use the position corresponding to the maximum value as the control parameter and the current optimization search result for maximizing the power factor of the front-stage active PFC circuit. Otherwise, execute step S210.

[0059] S210. Determine the local optimal position Is the corresponding fitness less than the The current fitness of the particle, if so, the local optimal position Updated to the The current position of the particle is determined, and then step S211 is executed; otherwise, step S211 is executed directly.

[0060] S211. Determine the global optimal position Is the corresponding fitness less than the maximum value among the current fitness of each particle? If so, the global optimal position Update to the current position of any particle having the maximum value, and then execute step S212; otherwise, directly execute step S212.

[0061] S212. Make the current number of iterations Add 1 to the current number of iterations. Whether the maximum number of iterations has been reached If so, the position corresponding to the global optimal fitness is used as the control parameter and the current optimal search result for maximizing the power factor of the pre-stage active PFC circuit, otherwise, the process returns to step S205, wherein the global optimal fitness refers to the position corresponding to the global optimal position The corresponding fitness.

[0062] In the step S212, the position corresponding to the global optimal fitness is used as the control parameter and the current optimal search result for maximizing the power factor of the pre-stage active PFC circuit, indicating that the power factor of the pre-stage active PFC circuit is maximized at this time, and further optimization can be stopped. In addition, based on the above steps S201 to S212, the control parameter optimization can be performed using an improved particle swarm optimization algorithm, and a dynamic adjustment item of the inertia coefficient is added to the particle swarm algorithm, which balances the local optimal and global optimal capabilities in parameter optimization, improves the optimization parameter search efficiency, and ensures overall reliability.

[0063] S3. The current optimization search result is transmitted to the control signal generating circuit in real time through the communication circuit, so that the control signal generating circuit generates a control signal for the front-stage active PFC circuit and / or the rear-stage DC-DC conversion circuit according to the current optimization search result, and transmits the control signal to the front-stage active PFC circuit and / or the rear-stage DC-DC conversion circuit.

[0064] In step S3, the current optimization search result includes the optimized parameter value of the control parameter, so when the control signal is transmitted to the front-stage active PFC circuit and / or the rear-stage DC-DC conversion circuit, the purpose of remotely controlling the power converter in real time to always maximize the power factor of the front-stage PFC circuit can be achieved.

[0065] Therefore, based on the power converter remote control method described in the aforementioned steps S1 to S3, a new scheme for remote real-time control of the power converter based on the optimization algorithm and the multi-dimensional feature data and the power factor mapping model is provided, that is, it is executed by the control device in the power converter remote control system, and the current sampling values ​​of multiple electrical parameters from the electrical parameter acquisition circuit and the pre-trained multi-dimensional feature data and the power factor mapping model are applied in real time, and the control parameters of the power converter are optimized based on the optimization algorithm to obtain the control parameters and the current optimal search result for maximizing the power factor of the front-stage active PFC circuit, and then the search result is transmitted to the control signal generating circuit in real time through the communication circuit, so that the signal generating circuit generates and transmits the control signal for the power converter according to the search result, so that the purpose of remote real-time control of the power converter to always maximize the power factor of the front-stage PFC circuit can be achieved, and there is no need to configure a calculation module for the power converter, thereby improving the power supply efficiency and facilitating energy saving, and maintaining the low cost of the power converter, which is convenient for practical application and promotion.

[0066] like Figure 2As shown, the second aspect of this embodiment provides a virtual device for implementing the remote control method of the power converter described in the first aspect, which is suitable for being arranged in a control device of a power converter remote control system, wherein the power converter remote control system also includes a power converter, an electrical parameter acquisition circuit, a communication circuit and a control signal generation circuit, the power converter includes a front-stage active PFC circuit, a bus capacitor and a rear-stage DC-DC conversion circuit, the anode of the bus capacitor is electrically connected to the positive output end of the front-stage active PFC circuit and the positive input end of the rear-stage DC-DC conversion circuit, and the cathode of the bus capacitor is electrically connected to the positive output end of the front-stage active PFC circuit and the positive input end of the rear-stage DC-DC conversion circuit, respectively. The negative output terminal of the front-stage active PFC circuit and the negative input terminal of the rear-stage DC-DC conversion circuit are connected, the electrical parameter acquisition circuit is electrically connected to the power converter and is used to collect the electrical parameter sampling values ​​of the power converter in real time and at multiple different positions, the output terminal of the electrical parameter acquisition circuit is communicatively connected to the input terminal of the communication circuit, the output terminal of the communication circuit is communicatively connected to the input terminal of the control signal generation circuit, the output terminal of the control signal generation circuit is communicatively connected to the controlled terminal of the front-stage active PFC circuit and / or the rear-stage DC-DC conversion circuit, and the communication circuit is also wirelessly connected to the control device; The virtual device includes a sampling data acquisition unit, a control parameter optimization unit and an optimization result transmission unit which are sequentially communicatively connected; The sampling data acquisition unit is used to acquire multiple current sampling values ​​of electrical parameters from the electrical parameter acquisition circuit in real time through the communication circuit; The control parameter optimization unit is used to apply the current sampling values ​​of the multiple electrical parameters and the pre-trained multi-dimensional feature data and power factor mapping model in real time, optimize the control parameters of the power converter based on the optimization algorithm, and obtain the control parameters and the current optimal search result for maximizing the power factor of the front-stage active PFC circuit, wherein the multi-dimensional feature data and power factor mapping model is used to output a power factor value having a mapping relationship with the multi-dimensional feature data including the electrical parameter sampling values ​​at the multiple different positions and the control parameter values ​​corresponding to the control parameters; The optimization result transmission unit is used to transmit the current optimization search result to the control signal generation circuit in real time through the communication circuit, so that the control signal generation circuit generates a control signal for the front-stage active PFC circuit and / or the rear-stage DC-DC conversion circuit according to the current optimization search result, and transmits the control signal to the front-stage active PFC circuit and / or the rear-stage DC-DC conversion circuit.

[0067] The working process, working details and technical effects of the aforementioned device provided in the second aspect of this embodiment can be referred to the remote control method of the power converter described in the first aspect, and will not be described in detail here.

[0068] like Figure 3 As shown, the third aspect of the present embodiment provides a physical system for implementing the remote control method of the power converter described in the first aspect, including a control device, a power converter, an electrical parameter acquisition circuit, a communication circuit and a control signal generation circuit, wherein the power converter includes a front-stage active PFC circuit, a bus capacitor and a rear-stage DC-DC conversion circuit, the anode of the bus capacitor is respectively electrically connected to the positive output terminal of the front-stage active PFC circuit and the positive input terminal of the rear-stage DC-DC conversion circuit, and the cathode of the bus capacitor is respectively electrically connected to the negative input terminal of the front-stage active PFC circuit. The output end of the electrical parameter acquisition circuit is connected to the negative input end of the post-stage DC-DC conversion circuit, the electrical parameter acquisition circuit is electrically connected to the power converter and is used to collect the electrical parameter sampling values ​​of the power converter in real time and at multiple different positions, the output end of the electrical parameter acquisition circuit is communicatively connected to the input end of the communication circuit, the output end of the communication circuit is communicatively connected to the input end of the control signal generation circuit, the output end of the control signal generation circuit is communicatively connected to the controlled end of the pre-stage active PFC circuit and / or the post-stage DC-DC conversion circuit, and the communication circuit is also wirelessly connected to the control device; The control device is used to execute the power converter remote control method as described in the first aspect.

[0069] The working process, working details and technical effects of the aforementioned system provided in the third aspect of this embodiment can be referred to the remote control method of the power converter described in the first aspect, and will not be described in detail here.

[0070] like Figure 4As shown, the fourth aspect of this embodiment provides a control device for executing the remote control method of the power converter as described in the first aspect, including a storage module, a processing module and a transceiver module that are sequentially connected in communication, wherein the storage module is used to store a computer program, the transceiver module is used to send and receive messages, and the processing module is used to read the computer program and execute the remote control method of the power converter as described in the first aspect. For example, the storage module may include, but is not limited to, a random access memory (Random-Access Memory, RAM), a read-only memory (Read-Only Memory, ROM), a flash memory (Flash Memory), a first-in-first-out memory (First Input First Output, FIFO) and / or a first-in-last-out memory (First Input Last Output, FILO), etc.; the processing module may include, but is not limited to, a microprocessor of the STM32F105 series. In addition, the control device may also include, but is not limited to, a power module, a display screen and other necessary components.

[0071] The working process, working details and technical effects of the aforementioned control device provided in the fourth aspect of this embodiment can be referred to the remote control method of the power converter described in the first aspect, and will not be repeated here.

[0072] In a fifth aspect of this embodiment, there is provided a computer-readable storage product storing instructions including the method for remotely controlling a power converter as described in the first aspect, that is, the computer-readable storage product stores instructions, and when the instructions are run on a computer, the method for remotely controlling a power converter as described in the first aspect is executed. The computer-readable storage product refers to a carrier for storing data, which may include, but is not limited to, a computer-readable storage medium such as a floppy disk, an optical disk, a hard disk, a flash memory, a USB flash drive, and / or a memory stick, and the computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.

[0073] The working process, working details and technical effects of the aforementioned computer-readable storage product provided in the fifth aspect of this embodiment can be referred to the remote control method for the power converter described in the first aspect, and will not be repeated here.

[0074] A sixth aspect of this embodiment provides a computer program product, including a computer program or instructions, wherein the computer program or instructions, when executed by a computer, implements the power converter remote control method as described in the first aspect. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.

[0075] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A remote control method for a power converter, characterized in that: Executed by a control device in a remote control system for a power converter, wherein the remote control system for the power converter further comprises a power converter, an electrical parameter acquisition circuit, a communication circuit and a control signal generation circuit, wherein the power converter comprises a front-stage active PFC circuit, a bus capacitor and a rear-stage DC-DC conversion circuit, wherein the anode of the bus capacitor is electrically connected to the positive output terminal of the front-stage active PFC circuit and the positive input terminal of the rear-stage DC-DC conversion circuit, respectively, and the cathode of the bus capacitor is electrically connected to the negative output terminal of the front-stage active PFC circuit and the negative input terminal of the rear-stage DC-DC conversion circuit, respectively, wherein the electrical parameter acquisition circuit is electrically connected to the power converter and is used to collect electrical parameter sampling values ​​of the power converter at multiple different positions in real time, wherein the output terminal of the electrical parameter acquisition circuit is communicatively connected to the input terminal of the communication circuit, wherein the output terminal of the communication circuit is communicatively connected to the input terminal of the control signal generation circuit, wherein the output terminal of the control signal generation circuit is communicatively connected to the controlled terminal of the front-stage active PFC circuit and / or the rear-stage DC-DC conversion circuit, and wherein the communication circuit is also communicatively connected to the control device; The power converter remote control method comprises: Acquiring multiple current sampling values ​​of electrical parameters from the electrical parameter acquisition circuit in real time through the communication circuit; Applying the current sampling values ​​of the multiple electrical parameters and the pre-trained multi-dimensional feature data and power factor mapping model in real time, optimizing the control parameters of the power converter based on the optimization algorithm, and obtaining the control parameters and the current optimal search result for maximizing the power factor of the front-stage active PFC circuit, wherein the multi-dimensional feature data and power factor mapping model is used to output a power factor value having a mapping relationship with the multi-dimensional feature data including the electrical parameter sampling values ​​at the multiple different positions and the control parameter values ​​corresponding to the control parameters; The current optimization search result is transmitted to the control signal generating circuit in real time through the communication circuit, so that the control signal generating circuit generates a control signal for the front-stage active PFC circuit and / or the rear-stage DC-DC conversion circuit according to the current optimization search result, and transmits the control signal to the front-stage active PFC circuit and / or the rear-stage DC-DC conversion circuit.

2. The power converter remote control method according to claim 1, characterized in that: The electrical parameter acquisition circuit includes a front-stage input voltage acquisition subcircuit, a bus capacitor voltage acquisition subcircuit, a rear-stage output voltage acquisition subcircuit and / or a rear-stage output current acquisition subcircuit, wherein the front-stage input voltage acquisition subcircuit is electrically connected to the input end of the front-stage active PFC circuit and is used to collect the front-stage input voltage sampling value of the front-stage active PFC circuit in real time, the bus capacitor voltage acquisition subcircuit is electrically connected to the anode of the bus capacitor and is used to collect the capacitor voltage sampling value of the bus capacitor in real time, the rear-stage output voltage acquisition subcircuit is electrically connected to the output end of the rear-stage DC-DC conversion circuit and is used to collect the rear-stage output voltage sampling value of the rear-stage DC-DC conversion circuit in real time, and the rear-stage output current acquisition subcircuit is electrically connected to the output end of the rear-stage DC-DC conversion circuit and is used to collect the rear-stage output current sampling value of the rear-stage DC-DC conversion circuit in real time.

3. The power converter remote control method according to claim 1, characterized in that: The multi-dimensional feature data and the power factor mapping model are pre-trained according to the following steps: The sample data is obtained in the following manner: a plurality of electrical parameter historical sampling values ​​from the electrical parameter acquisition circuit and a control parameter historical value that is contemporaneous with the plurality of electrical parameter historical sampling values ​​and is used to generate a control signal for the front-stage active PFC circuit and / or the rear-stage DC-DC conversion circuit are used as model input items, and a power factor historical value that is contemporaneous with the plurality of electrical parameter historical sampling values ​​and is measured for the front-stage active PFC circuit is used as a model output item, and then the model input item and the model output item are used as a sample data; All the sample data are applied to perform model training and verification on a machine learning model based on an artificial intelligence algorithm to obtain a verified multidimensional feature data and a power factor mapping model, wherein the multidimensional feature data and the power factor mapping model are used to output a power factor value having a mapping relationship with the multidimensional feature data including the electrical parameter sampling values ​​at the multiple different positions and the control parameter values ​​corresponding to the control parameters.

4. The power converter remote control method according to claim 1, characterized in that: The control parameters include a first control parameter for controlling the constant voltage output of the front-stage active PFC circuit, a second control parameter for controlling the same phase of the input voltage and current in the front-stage active PFC circuit, a third control parameter for controlling the switching speed of the switch tube in the rear-stage DC-DC conversion circuit, a fourth control parameter for controlling the switching pulse width of the switch tube in the rear-stage DC-DC conversion circuit and / or a fifth control parameter for controlling the switching pulse phase shift angle of different switch tubes in the rear-stage DC-DC conversion circuit.

5. The power converter remote control method according to claim 1, characterized in that: The current sampling values ​​of the multiple electrical parameters and the pre-trained multi-dimensional feature data and power factor mapping model are applied in real time, and the control parameters of the power converter are optimized based on the optimization algorithm to obtain the control parameters and the current optimal search result for maximizing the power factor of the front-stage active PFC circuit, including the following steps S201-S212: S201. Initialize the particle swarm optimization algorithm and include the population size , maximum number of iterations , Self-learning factor and the global learning factor The algorithm parameters are used, and the initial position of each particle in the particle population is randomly generated, and then step S202 is performed, wherein the initial position of each particle is randomly generated based on the following formula: In the formula, represents a positive integer, Indicates less than or equal to A positive integer, represents the number of dimensions of a parameter vector to be optimized, wherein the parameter vector to be optimized includes control parameters of the power converter to be optimized, represents the first The particle is the first particle in the parameter vector to be optimized The initial position in the dimension, Indicated in the The upper limit of the parameter search space in dimensions, Indicated in the The lower bound of the parameter search space in dimensions, Represents a purely decimal random generator function; S202. For each particle, the current sampling values ​​of the multiple electrical parameters and the corresponding initial positions are imported into the pre-trained multi-dimensional feature data and power factor mapping model, and the corresponding power factor initial value is output, and the power factor initial value is used as the corresponding fitness , then executing step S203, wherein the multidimensional feature data and power factor mapping model is used to output a power factor value having a mapping relationship with the multidimensional feature data including the electrical parameter sampling values ​​at the plurality of different positions and the control parameter value corresponding to the control parameter; S203. Determine whether the maximum value among the fitness of each particle is greater than or equal to a preset threshold value. If so, use the initial position corresponding to the maximum value as the control parameter and the current optimization search result for maximizing the power factor of the front-stage active PFC circuit. Otherwise, execute step S204; S204. Take the initial position of a particle with the maximum fitness as the initial global optimal position , remember the The position of the particle in the iteration process and corresponding to the maximum fitness is the The local optimal position reached by particles , and the position of the particle population in the iteration process corresponding to the maximum fitness is recorded as the global optimal position reached by the particle population , and remember the The moving speed of a particle is , and finally initialize the local optimal position , and initialize the moving speed is zero, and the particle movement inertia coefficient range is also set to [ ], and initialize the period of periodic reduction of the inertia coefficient A randomly selected value within the range of the particle movement inertia coefficient is set, and the particle movement inertia coefficient is also initialized to a value greater than zero during the iteration process, and the current number of iterations is also initialized. is 0, then execute step S205; S205. Update the particle movement inertia coefficient of each particle, and then execute step S206, wherein the update formula of the particle movement inertia coefficient is as follows: In the formula, Indicated in After the iteration, the The particle in the The inertia coefficient of particle movement in dimensions, Indicated in iterations ago and the The particle in the The inertia coefficient of particle movement in dimensions, Represents the previous iteration number For the cycle The result of the modulo operation, and if If it is less than 0, a new value is randomly selected within the range of the particle's moving inertia coefficient as the new period. , and recalculate ,until Not less than 0; S206. Update the moving speed of each particle, and then execute step S207, wherein the updating formula of the moving speed is as follows: In the formula, Indicated in After the iteration, the The particle in the The speed of movement in one dimension, Indicated in iterations ago and the The particle in the The speed of movement in one dimension, represents the first random number uniformly distributed in (0,1), Indicates in front During the iteration, The particle in the The local optimal position reached in dimensions, Indicated in iterations ago and the The particle in the The position in the dimension, represents the second random number uniformly distributed in (0,1), Indicates in front In the first iteration, the particle population The global optimal position achieved in dimensions; S207. Update the position of each particle, and then execute step S208, wherein the update formula of the position is as follows: In the formula, Indicated in After the iteration, the The particle in the Position in one dimension; S208. For each particle, the current sampling values ​​of the multiple electrical parameters and the corresponding positions are imported into the multidimensional feature data and power factor mapping model, and the corresponding new power factor value is output, and the new power factor value is used as the corresponding fitness , then execute step S209; S209. Determine whether the maximum value among the current fitness of each particle is greater than or equal to the preset threshold value. If so, use the position corresponding to the maximum value as the control parameter and the current optimization search result for maximizing the power factor of the front-stage active PFC circuit. Otherwise, execute step S210; S210. Determine the local optimal position Is the corresponding fitness less than the The current fitness of the particle, if so, the local optimal position Updated to the The current position of the particle, then execute step S211, otherwise directly execute step S211; S211. Determine the global optimal position Is the corresponding fitness less than the maximum value among the current fitness of each particle? If so, the global optimal position Update to the current position of any particle with the maximum value, and then execute step S212, otherwise directly execute step S212; S212. Make the current number of iterations Add 1 to the current number of iterations. Whether the maximum number of iterations has been reached If so, the position corresponding to the global optimal fitness is used as the control parameter and the current optimal search result for maximizing the power factor of the pre-stage active PFC circuit, otherwise, the process returns to step S205, wherein the global optimal fitness refers to the position corresponding to the global optimal position The corresponding fitness.

6. A remote control device for a power converter, characterized in that: Suitable for being arranged in a control device of a power converter remote control system, wherein the power converter remote control system further comprises a power converter, an electrical parameter acquisition circuit, a communication circuit and a control signal generation circuit, the power converter comprises a front-stage active PFC circuit, a bus capacitor and a rear-stage DC-DC conversion circuit, the anode of the bus capacitor is electrically connected to the positive output end of the front-stage active PFC circuit and the positive input end of the rear-stage DC-DC conversion circuit respectively, the cathode of the bus capacitor is electrically connected to the negative output end of the front-stage active PFC circuit and the negative input end of the rear-stage DC-DC conversion circuit respectively, the electrical parameter acquisition circuit is electrically connected to the power converter and is used to collect electrical parameter sampling values ​​of the power converter at multiple different positions in real time, the output end of the electrical parameter acquisition circuit is communicatively connected to the input end of the communication circuit, the output end of the communication circuit is communicatively connected to the input end of the control signal generation circuit, the output end of the control signal generation circuit is communicatively connected to the controlled end of the front-stage active PFC circuit and / or the rear-stage DC-DC conversion circuit, and the communication circuit is also wirelessly connected to the control device; The power converter remote control device comprises a sampling data acquisition unit, a control parameter optimization unit and an optimization result transmission unit which are sequentially communicatively connected; The sampling data acquisition unit is used to acquire multiple current sampling values ​​of electrical parameters from the electrical parameter acquisition circuit in real time through the communication circuit; The control parameter optimization unit is used to apply the current sampling values ​​of the multiple electrical parameters and the pre-trained multi-dimensional feature data and power factor mapping model in real time, optimize the control parameters of the power converter based on the optimization algorithm, and obtain the control parameters and the current optimal search result for maximizing the power factor of the front-stage active PFC circuit, wherein the multi-dimensional feature data and power factor mapping model is used to output a power factor value having a mapping relationship with the multi-dimensional feature data including the electrical parameter sampling values ​​at the multiple different positions and the control parameter values ​​corresponding to the control parameters; The optimization result transmission unit is used to transmit the current optimization search result to the control signal generation circuit in real time through the communication circuit, so that the control signal generation circuit generates a control signal for the front-stage active PFC circuit and / or the rear-stage DC-DC conversion circuit according to the current optimization search result, and transmits the control signal to the front-stage active PFC circuit and / or the rear-stage DC-DC conversion circuit.

7. A remote control system for a power converter, characterized in that: The invention comprises a control device, a power converter, an electrical parameter acquisition circuit, a communication circuit and a control signal generation circuit, wherein the power converter comprises a front-stage active PFC circuit, a bus capacitor and a rear-stage DC-DC conversion circuit, the anode of the bus capacitor is electrically connected to the positive output end of the front-stage active PFC circuit and the positive input end of the rear-stage DC-DC conversion circuit respectively, the cathode of the bus capacitor is electrically connected to the negative output end of the front-stage active PFC circuit and the negative input end of the rear-stage DC-DC conversion circuit respectively, the electrical parameter acquisition circuit is electrically connected to the power converter and is used to collect electrical parameter sampling values ​​of the power converter at multiple different positions in real time, the output end of the electrical parameter acquisition circuit is communicatively connected to the input end of the communication circuit, the output end of the communication circuit is communicatively connected to the input end of the control signal generation circuit, the output end of the control signal generation circuit is communicatively connected to the controlled end of the front-stage active PFC circuit and / or the rear-stage DC-DC conversion circuit, and the communication circuit is also wirelessly connected to the control device; The control device is used to execute the power converter remote control method as claimed in any one of claims 1 to 5.

8. A control device, characterized in that: It includes a storage module, a processing module and a transceiver module which are communicatively connected in sequence, wherein the storage module is used to store computer programs, the transceiver module is used to send and receive messages, and the processing module is used to read the computer program to execute the power converter remote control method as described in any one of claims 1 to 5.

9. A computer readable storage product, characterized in that The computer-readable storage product stores instructions, and when the instructions are executed on the computer, the power converter remote control method as described in any one of claims 1 to 5 is executed.

10. A computer program product comprising a computer program or instructions, characterized in that When the computer program or the instruction is executed by a computer, the power converter remote control method according to any one of claims 1 to 5 is implemented.

Images