Artificial-intelligence-based adaptive control method for direct current-direct current converter, and device

Abstract

Provided in the embodiments of the present invention are an artificial-intelligence-based adaptive control method for a direct current-direct current converter, and a device. The method comprises: collecting a voltage value and a current value which are output by a direct current-direct current converter in the current period; on the basis of the voltage value and the current value, determining operating condition parameters corresponding to the direct current-direct current converter, wherein the operating condition parameters are used for representing the current operating state of the direct current-direct current converter; on the basis of the operating condition parameters, determining a target control parameter; and on the basis of the target control parameter, controlling the direct current-direct current converter such that the direct current-direct current converter stably outputs a voltage. In the solution, by means of collecting, at fixed intervals, a voltage value and a current value which are output by a direct current-direct current converter, operating condition parameters currently corresponding to the direct current-direct current converter are determined, and the current operating state of the direct current-direct current converter is then determined; and on the basis of the operating state corresponding to the direct current-direct current converter, a control parameter of a controller is adjusted such that the direct current-direct current converter always keeps an optimal operating performance in each operating state.

Description

Artificial intelligence-based adaptive control method and device for DC-DC converters Technical Field

[0001] The present invention relates to the field of automation technology, and in particular to an artificial intelligence-based DC-DC converter adaptive control method and device. Background Art

[0002] DC-DC converters (DC-DC converters) can convert a DC input voltage level to another required DC voltage level and are widely used in various electronic devices, from rockets, airplanes, cars to mobile phones, calculators and remote controls.

[0003] In practical applications, when a DC-DC converter operates in an open-loop state, it often leads to long-term output voltage instability, steady-state errors, and robustness issues. A PID controller is usually used to control the DC-DC converter to avoid these issues.

[0004] However, since the PID controller is a linear controller, when the load resistance in the DC-DC converter changes, the DC-DC converter cannot be controlled to maintain optimal operating performance based on the control parameters corresponding to the PID controller.

[0005] Summary of the Invention

[0006] The embodiments of the present invention provide an artificial intelligence-based DC-DC converter adaptive control method and device for adaptively controlling the DC-DC converter so that the DC-DC converter maintains optimal operating performance in various operating states. Specifically:

[0007] In a first aspect, an embodiment of the present invention provides an artificial intelligence-based adaptive control method for a DC-DC converter, which is applied to a controller for controlling the DC-DC converter, comprising:

[0008] Collect the voltage and current values ​​output by the DC-DC converter in the current cycle;

[0009] determining an operating condition quantity corresponding to the DC-DC converter according to the voltage value and the current value, wherein the operating condition quantity is used to characterize a current operating state of the DC-DC converter;

[0010] determining target control parameters according to the operating condition;

[0011] The DC-DC converter is controlled according to the target control parameter so that the DC-DC converter stably outputs a voltage.

[0012] In a second aspect, an embodiment of the present invention provides an artificial intelligence-based DC-DC converter adaptive control device, located in a controller, comprising:

[0013] An acquisition module is used to acquire the voltage and current values ​​output by the DC-DC converter in the current cycle;

[0014] a first determining module, configured to determine an operating condition quantity corresponding to the DC-DC converter according to the voltage value and the current value, wherein the operating condition quantity is used to represent a current operating state of the DC-DC converter;

[0015] A second determining module is used to determine a target control parameter according to the operating condition;

[0016] A control module is configured to control the DC-DC converter according to the target control parameter so that the DC-DC converter stably outputs a voltage.

[0017] In a third aspect, an embodiment of the present invention further provides an electronic device comprising: a memory and a processor; the memory is used to store a computer program; the processor is coupled to the memory and is used to execute the computer program to implement the steps in the artificial intelligence-based DC-DC converter adaptive control method provided in an embodiment of the present invention.

[0018] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the processor implements the steps of the artificial intelligence-based DC-DC converter adaptive control method provided in an embodiment of the present invention.

[0019] The DC-DC converter control scheme provided in an embodiment of the present invention can be applied to a controller to control the DC-DC converter. Specifically, when controlling the DC-DC converter, the voltage and current values ​​output by the DC-DC converter in the current cycle are first collected, and the operating condition corresponding to the DC-DC converter is determined based on the voltage and current values. The operating condition is used to characterize the current operating state of the DC-DC converter. Next, the target control parameters of the controller are determined based on the current operating condition corresponding to the DC-DC converter, and then based on the target control parameters, the DC-DC converter is controlled so that the DC-DC converter outputs a stable voltage.

[0020] In the above scheme, by regularly collecting the voltage and current values ​​output by the DC-DC converter, the operating condition corresponding to the current DC-DC converter is determined, and then the current working state of the DC-DC converter is determined. According to the working state corresponding to the DC-DC converter, the control parameters corresponding to the controller are adjusted, and the DC-DC converter is controlled based on the adjusted target control parameters, so that the DC-DC converter always maintains optimal working performance under various working states. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following is a brief introduction to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0022] FIG1 is a schematic flow chart of an artificial intelligence-based DC-DC converter adaptive control method according to an embodiment of the present invention;

[0023] FIG2 is a schematic diagram of a flow chart of determining target control parameters according to an operating condition corresponding to a DC-DC converter, provided by an embodiment of the present invention;

[0024] FIG3 is a schematic diagram of an application of an operating condition network function for determining an operating condition quantity corresponding to an operating condition quantity according to an embodiment of the present invention;

[0025] FIG4 is a schematic diagram of an application of optimal control parameters corresponding to a PID controller using a genetic algorithm according to an embodiment of the present invention;

[0026] FIG5 is a schematic diagram of an application of determining undetermined coefficients of Padé approximation provided by an embodiment of the present invention;

[0027] 6 is a schematic diagram of a flow chart of controlling a DC-DC converter according to a target control parameter so as to stabilize the output voltage of the DC-DC converter, provided by an embodiment of the present invention;

[0028] FIG7 is a numerical model corresponding to a step-down DC-DC converter provided by an embodiment of the present invention;

[0029] FIG8 is a schematic structural diagram of a DC-DC converter control device provided by an embodiment of the present invention;

[0030] FIG9 is a schematic structural diagram of an electronic device provided by an exemplary embodiment of the present invention. DETAILED DESCRIPTION

[0031] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0032] The terms used in the embodiments of the present invention are for the purpose of describing specific embodiments only and are not intended to limit the present invention. The singular forms "a," "an," "the," and "the" used in the embodiments of the present invention and the appended claims are also intended to include plural forms, and unless the context clearly indicates otherwise, "a plurality" generally includes at least two.

[0033] As used herein, the words "if" and "if" may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to the determination" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)," depending on the context.

[0034] In addition, the step sequence in the following method embodiments is only an example and not a strict limitation.

[0035] DC-DC converters are widely used in a variety of electronic devices, from rockets, aircraft, and automobiles to mobile phones, calculators, and remote controls. In practical applications, operating the DC-DC converter in an open-loop state often leads to problems such as unstable output and poor voltage regulation. Closed-loop control methods are often employed to optimize the DC-DC converter's transient and steady-state response.

[0036] In traditional AI-based adaptive control methods for DC-DC converters, a PID controller is typically used to control the DC-DC converter. However, due to the nonlinearity caused by the inherent switching characteristics of the DC-DC converter structure and the variable characteristics of the load resistance, when the load resistance changes, the original controller parameters cannot enable the DC-DC converter to maintain optimal operating performance.

[0037] In order to solve the above technical problems, an embodiment of the present invention provides a new artificial intelligence-based adaptive control method for a DC-DC converter. By monitoring the output voltage and current of the DC-DC converter, the current operating state of the DC-DC converter is determined, and the current operating state of the DC-DC converter is used as the operating condition quantity to determine the optimal target control parameters in the current state. The current control parameters are adjusted to the optimal target control parameters and substituted into the controller to control the DC-DC converter, so that the DC-DC converter can maintain optimal operating performance in each operating state.

[0038] The following embodiments of the present invention are described in detail with reference to the accompanying drawings. In the absence of conflicts between the embodiments, the following embodiments and features therein may be combined with each other.

[0039] FIG1 is a flow chart of an artificial intelligence-based DC-DC converter adaptive control method according to an embodiment of the present invention. Referring to FIG1 , the method may be performed by a DC-DC converter control device. It is understood that the control device may be implemented as software or a combination of software and hardware. The device may be applied to a controller to control the DC-DC converter. Specifically, the artificial intelligence-based DC-DC converter adaptive control method may include the following steps:

[0040] 101. Collect the voltage and current values ​​output by the DC-DC converter in the current cycle.

[0041] 102. Determine an operating condition quantity corresponding to the DC-DC converter based on the voltage value and the current value. The operating condition quantity is used to characterize a current operating state of the DC-DC converter.

[0042] 103. Determine the target control parameters based on the operating conditions.

[0043] 104. According to the target control parameter, control the DC-DC converter so that the DC-DC converter stably outputs the voltage.

[0044] The DC-DC converter control solution provided in the embodiment of the present invention can be used to control various DC-DC converters, such as a step-down DC-DC converter and a step-up DC-DC converter. In the embodiment of the present invention, the type of DC-DC converter is not limited.

[0045] Since the PID controller is a linear controller, the control parameters corresponding to the PID controller are fixed and cannot change with the load resistance in the DC-DC converter. Therefore, when the load resistance value in the DC-DC converter changes, controlling the DC-DC converter based on the current control parameters corresponding to the PID controller cannot enable the DC-DC converter to maintain optimal operating performance.

[0046] To ensure that the DC-DC converter maintains optimal performance under all operating conditions, the voltage and current values ​​output by the DC-DC converter can be collected periodically at fixed intervals. The corresponding control parameters of the controller can then be dynamically adjusted based on the voltage and current values. The DC-DC converter can then be controlled based on the adjusted target control parameters. This allows the target control parameters of the controller to be dynamically adjusted according to the operating state of the DC-DC converter, ensuring that the DC-DC converter always maintains optimal performance. The controller can be a PID controller, a variant of a PID controller, an ADRC controller, or the like.

[0047] Specifically, when controlling a DC-DC converter, the voltage and current values ​​output by the DC-DC converter during the current cycle can be collected. Then, based on the voltage and current values, the operating condition variable corresponding to the DC-DC converter is determined. The operating condition variable is used to characterize the current operating state of the DC-DC converter. Furthermore, the operating condition variable can be used as the operating condition variable of the DC-DC converter. The target control parameters of the controller can be adjusted based on the industrial control variables, so that the DC-DC converter can always maintain a stable output voltage under various operating conditions and provide optimal operating performance.

[0048] During offline design, a numerical model of the DC-DC converter can be established and calculated using a computer equipped with MATLAB to obtain the circuit's state equation. Based on this state equation, the voltage and current output of the DC-DC converter can be obtained. During online use, the voltage and / or current output of the DC-DC converter can be directly acquired using an analog-to-digital converter in an FPGA digital controller. These values ​​can then be calculated and controlled by the digital controller to generate a digital pulse-width modulation signal.

[0049] In practical applications, the load resistance of a DC-DC converter may constantly change, requiring constant adjustment of the controller's control parameters to ensure the converter maintains optimal performance. To better understand the converter's current operating state, a pre-set acquisition cycle can be used to collect the voltage and current output of the DC-DC converter. For example, the preset acquisition cycle can be 10ms, 20ms, or 40ms, and can be set based on actual needs. Alternatively, the DC-DC converter can be monitored for voltage and current output based on the control cycle.

[0050] After obtaining the voltage and current values ​​output by the DC-DC converter, the operating condition corresponding to the DC-DC converter can be determined based on the voltage and current values. The operating condition can be determined by taking the resistance value corresponding to the load resistor in the DC-DC converter or the power value corresponding to the load resistor. The operating condition can be determined based on actual needs.

[0051] Among them, the specific implementation method of determining the operating condition quantity corresponding to the DC-DC converter based on the voltage value and the current value can be: determining the resistance value corresponding to the load resistor in the DC-DC converter based on the voltage value and the current value, and determining the resistance value as the operating condition quantity corresponding to the DC-DC converter; or determining the power value corresponding to the load resistor in the DC-DC converter based on the voltage value and the current value, and determining the power value as the operating condition quantity corresponding to the DC-DC converter.

[0052] In practical applications, for example, assuming the DC-DC converter output voltage is V o , the current value can be I o , then by the formula Thus, the load resistance R of the DC-DC converter is equivalently calculated. o The resistance value.

[0053] After obtaining the operating conditions corresponding to the DC-DC converter, the target control parameters are then determined based on the operating conditions. These target control parameters refer to the optimal control parameters for the controller under the current state. The specific content of these target control parameters can be determined based on the type of controller. For example, if the controller is a PID controller, the target control parameters may include the proportional coefficient, integral coefficient, and differential coefficient.

[0054] In order to enable the DC-DC converter to maintain robust steady-state and transient performance within a large operating range, the mapping relationship between the operating conditions of the DC-DC converter and the control parameters of the controller can be determined first, and then the target control parameters corresponding to the controller can be determined based on the mapping relationship. In this way, better control parameters can be accurately obtained based on the operating conditions corresponding to the DC-DC converter, thereby effectively ensuring that the DC-DC converter can maintain robust steady-state and transient performance within a large operating range.

[0055] Specifically, in an optional embodiment, a working condition network function corresponding to the working condition variable can be first determined, wherein the working condition network function is used to describe the mapping relationship between the working condition variable of the DC-DC converter and the control parameters of the controller. Then, the target control parameters are determined based on the working condition variable and the working condition network function. In this case, a genetic algorithm can be used to adjust the control parameters corresponding to the controller using the integral of absolute error (ITAE) as a performance indicator to determine the optimal target control parameters corresponding to the controller when the load resistance in the DC-DC converter has different resistance values. The control parameter trajectory is determined based on the target control parameters under different load resistances through interpolation, and the working condition network function corresponding to the working condition variable is determined based on the control parameter trajectory.

[0056] After determining the optimal target control parameters for the DC-DC converter's current operating state, the DC-DC converter is controlled based on the target control parameters to ensure a stable output voltage. In a specific implementation, the target control parameters can be directly substituted into a controller, and a control variable at the next moment is determined based on the output error corresponding to the DC-DC converter in the current state and the target control parameters corresponding to the controller. The DC-DC converter is then controlled based on this control variable. The output error refers to the difference between the actual output voltage of the DC-DC converter and a set reference voltage.

[0057] In an embodiment of the present invention, by periodically collecting the voltage and current values ​​output by the DC-DC converter, the operating condition corresponding to the current DC-DC converter is determined, and then the current operating state of the DC-DC converter is determined. According to the operating state corresponding to the DC-DC converter, the control parameters corresponding to the controller are adjusted, and the DC-DC converter is controlled based on the adjusted target control parameters, so that the DC-DC converter always maintains optimal operating performance in each operating state.

[0058] The above embodiment introduces a specific implementation process of controlling a DC-DC converter using a controller. To facilitate the specific implementation process of determining the target control parameters according to the operating conditions corresponding to the DC-DC converter in the above embodiment, the specific implementation process is exemplified in conjunction with Figure 2.

[0059] FIG2 is a flow chart of determining a target control parameter based on an operating condition corresponding to a DC-DC converter according to an embodiment of the present invention. Referring to FIG2 , the resistance value corresponding to a load resistor in the DC-DC converter may be used as the operating condition corresponding to the DC-DC converter. Specifically, the method may include the following steps:

[0060] 201. Determine an operating condition network function corresponding to an operating condition variable, where the operating condition network function is used to describe a mapping relationship between an operating condition variable of a DC-DC converter and a control parameter of a controller.

[0061] 202. Determine the target control parameters based on the operating condition quantity and the operating condition network function.

[0062] In an embodiment of the present invention, when determining target control parameters based on operating conditions corresponding to a DC-DC converter, a working condition network function corresponding to the working condition can be first determined. The target control parameters are then determined based on the working condition and the working condition network function. The working condition network function describes the mapping relationship between the DC-DC converter's working condition and the controller's control parameters.

[0063] The operating network function corresponding to the operating quantity can be obtained through experiments or offline modeling and simulation. Specifically, a genetic algorithm is used to adjust the control parameters of the controller using the integral of absolute error ITAE as a performance indicator to determine the optimal target control parameters of the controller when the load resistance in the DC-DC converter has different resistance values. Then, an interpolation method is used to determine the control parameter trajectory based on the target control parameters of the load resistance in the DC-DC converter at different resistance values, and the operating network function corresponding to the operating quantity is determined based on the control parameter trajectory.

[0064] Specifically, in an optional embodiment, the implementation process of determining the operating condition network function corresponding to the operating condition quantity may include: obtaining a preset resistance value corresponding to the load resistor in the DC-DC converter; adjusting the control parameters corresponding to the controller based on a genetic algorithm to obtain the optimal control parameters corresponding to the controller when the resistance value corresponding to the load resistor in the DC-DC converter is the preset resistance value; determining a mapping relationship between the resistance value corresponding to the load resistor and the control parameters corresponding to the controller based on the preset resistance value and the optimal control parameters; determining a Padé approximation of the control parameters corresponding to the controller, the Padé approximation being a second-order nonlinear function with a numerator and a denominator; determining multiple Padé approximation undetermined coefficients in the Padé approximation based on the mapping relationship; and determining the operating condition network function corresponding to the operating condition quantity based on the Padé approximation undetermined coefficients.

[0065] In which, based on the genetic algorithm, when the control parameters corresponding to the controller are adjusted to obtain a preset resistance value corresponding to the load resistor in the DC-DC converter, a specific implementation method of the optimal control parameters corresponding to the controller may include: collecting a current voltage value output by the DC-DC converter when the resistance value corresponding to the load resistor in the DC-DC converter is the preset resistance value; determining an output error corresponding to the DC-DC converter based on the current voltage value and the preset voltage value; determining a performance indicator corresponding to the current control parameter of the controller based on the output error; and determining the optimal control parameter corresponding to the controller based on the performance indicator.

[0066] From the above description, it can be seen that by determining the operating condition network function corresponding to the operating condition quantity, the mapping relationship between the operating condition quantity of the DC-DC converter and the control parameters of the controller can be obtained. Then, in actual applications, after obtaining the operating condition quantity of the DC-DC converter in the current state, the optimal target control parameters corresponding to the controller under the current working state of the DC-DC converter can be determined directly based on the currently determined operating condition quantity and the operating condition network function corresponding to the operating condition quantity. Based on the target control parameters, they are substituted into the controller to control the DC-DC converter, so that the DC-DC converter can stably output voltage under the current working state and maintain robust steady-state and transient performance within a large working range.

[0067] To facilitate understanding of the specific implementation process of the operating condition network function for determining the corresponding operating condition variable, the operating condition network function for determining the corresponding operating condition variable is described in conjunction with Figure 3. In the specific implementation, it is assumed that the controller is a PID controller, which is used to control the DC-DC converter, wherein the PID controller is connected to the DC-DC converter to form a closed-loop system.

[0068] First, select multiple different load resistors, load resistor R L Rated load R can be selected O The resistance values ​​are equally spaced within the range of ±50%. For example, the preset resistance values ​​corresponding to the selected load resistance are 0.5R O ,0.6R O ,0.7R O , Among them, the control quantity output by the PID controller is Among them, K P is the proportionality coefficient, K I is the integral coefficient, K D is the differential coefficient, s is the time domain parameter, and u is the control quantity.

[0069] Next, the current voltage value output by the DC-DC converter when the resistance value corresponding to the load resistor in the DC-DC converter is a preset resistance value is collected; the output error corresponding to the DC-DC converter is determined based on the current voltage value and the preset voltage value; the performance index corresponding to the current control parameter of the controller is determined based on the output error; and the optimal control parameter corresponding to the controller is determined based on the performance index.

[0070] Specifically, assuming the preset voltage value is V ref , the current output voltage value is V out The output error is e=V ref -V out . ITAE is selected as the performance indicator, where t is time, T is the end time, and e(t) is the output error corresponding to time t. set and given load R L Next, the parameters of the PID controller are given by the genetic algorithm GA, and the set value V set With the output voltage V out The output error Error is obtained, and the PWM result is calculated by the PID controller and transmitted to the DC-DC converter, which outputs the current voltage value V out Feedback is then fed back to the input, and the output voltage is compared with the preset voltage value to determine the output error. The output error can be evaluated using the ITAE metric and fed back to the genetic algorithm. The genetic algorithm is iterated in this way, ultimately determining the optimal control parameters for the PID controller. This method is used to obtain the optimal control coefficients for the PID controller under different preset resistance values. Based on the preset resistance value and the optimal control parameters, a mapping relationship is determined between the resistance value corresponding to the load resistor and the control parameters corresponding to the controller.

[0071] Then, determine the Padé approximation of the control parameters corresponding to the PID controller, determine multiple Padé approximation coefficients to be determined in the Padé approximation based on the mapping relationship, and finally determine the operating condition network function corresponding to the operating condition quantity based on the Padé approximation coefficients to be determined. Specifically, the Padé approximation of the control parameters corresponding to the PID controller can be a Padé approximation form with both the numerator and denominator being of order 2, such as the following:

[0072] Among them, d Pi ,d Ii ,d Di ,a Pk ,a Ik ,a Dk ,i=0,1,2,k=1, is the undetermined coefficient of Padé approximation, K P is the proportionality coefficient, K I is the integral coefficient, K Dis the differential coefficient.

[0073] Next, a genetic algorithm is used to determine the Padé approximation coefficients. For example, as shown in FIG4 , each preset resistance value corresponding to the load resistor is sequentially substituted into the Padé approximation form of the control parameters corresponding to the PID controller. The genetic algorithm is then used to determine the Padé approximation coefficients in the Padé approximation form of the control parameters corresponding to the PID controller. Based on the determined Padé approximation coefficients, the optimal control parameters for the PID controller are determined for each preset resistance value.

[0074] Specifically, the implementation process of using a genetic algorithm to determine the Padé approximation coefficients in the Padé approximation form of the control parameters corresponding to the PID controller can be shown in Figure 5. Among them, the Padé approximation coefficients can be randomly created, and the randomly created Padé approximation coefficients are used as the initial population. The working points corresponding to the preset resistance values ​​are determined as individuals, and the individuals are brought into the Padé approximation form of the control parameters corresponding to the PID controller to obtain output results. The output results and the experimental results (the experimental results obtained by performing experiments at various preset resistance values ​​in an actual circuit) are used to calculate the fitness MSE. If the calculation results meet the set termination conditions, the optimal Padé approximation coefficients are output. If the calculation results do not meet the set termination conditions, the selection operation, crossover operation, and mutation operation are continued, and the fitness calculation is performed again until the fitness calculation results meet the set termination conditions.

[0075] In an embodiment of the present invention, by determining the operating condition network function corresponding to the operating condition quantity, and determining the target control parameter based on the operating condition quantity and the operating condition network function, the mapping relationship between the operating condition quantity of the DC-DC converter and the control parameter of the controller can be accurately determined, so as to accurately determine the optimal target control parameter corresponding to each operating condition quantity, and then control the DC-DC converter based on the target control parameter so that the DC-DC converter maintains optimal operating performance under various operating conditions.

[0076] From the above description, it can be seen that the use of the trajectory control network (operating condition network function) and the application of the PID controller realizes adaptive control within a large working range, so that when the load resistance in the DC-DC converter changes, the PID controller can track the changing scheduling control parameters to achieve rapid convergence and obtain good steady-state performance and transient performance, which improves the global, steady-state and transient performance.

[0077] The above embodiment describes the specific implementation process for determining the target control parameters. In practical applications, after the target control parameters are determined, the DC-DC converter can be controlled based on the target control parameters to stabilize the output voltage of the DC-DC converter. To more clearly understand the specific implementation process of controlling the DC-DC converter based on the target control parameters, the specific implementation process of controlling the DC-DC converter based on the target control parameters to stabilize the output voltage of the DC-DC converter is illustrated in conjunction with FIG6 .

[0078] FIG6 is a flow chart of controlling a DC-DC converter according to a target control parameter to stabilize the output voltage of the DC-DC converter, according to an embodiment of the present invention. Referring to FIG6 , the resistance value corresponding to the load resistor in the DC-DC converter can be used as the operating condition quantity corresponding to the DC-DC converter. Specifically, the method may include the following steps:

[0079] 601. Determine a control variable corresponding to the DC-DC converter according to the target control parameter and the output error.

[0080] 602. Control the DC-DC converter according to the control variable so that the DC-DC converter stabilizes the output voltage.

[0081] After determining the target control parameters for the current operating state, the corresponding control variable of the DC-DC converter can be determined based on the target control parameters and the output error. The DC-DC converter is then controlled based on the control variable to ensure a stable output voltage, thereby ensuring that the DC-DC converter maintains optimal operating performance in the current operating state.

[0082] In a specific implementation, assuming a PID controller is used to control a DC-DC converter, the target control parameters to be determined include the proportional coefficient, the integral coefficient, and the differential coefficient. When determining the control variable corresponding to the DC-DC converter, the controller's corresponding error signal can be first determined based on the output error. Proportional, integral, and differential calculations are then performed on the error signal to determine the control variable corresponding to the next moment. Specifically, the controller's corresponding error signal is first determined based on the output error. Then, a proportional operation is performed on the error signal based on the proportional coefficient to obtain a proportional operation result; an integral operation is performed on the error signal based on the integral coefficient to obtain an integral operation result; and a differential operation is performed on the error signal based on the differential coefficient to obtain a differential operation result. Finally, the control variable corresponding to the DC-DC converter is determined based on the proportional operation result, the integral operation result, and the differential operation result.

[0083] After determining the control variable, the DC-DC converter can be controlled based on the control variable to stabilize the output voltage of the DC-DC converter. In an optional embodiment, the specific implementation process of controlling the DC-DC converter based on the control variable to stabilize the output voltage of the DC-DC converter can be: determining a control signal corresponding to the controller based on the control variable, and controlling the DC-DC converter based on the control signal to stabilize the output voltage of the DC-DC converter. The control signal can be a pulse width modulation signal, in which the frequency of the PWM switching pulse is constant, and the DC-DC converter is controlled by changing the pulse output width to stabilize the output voltage.

[0084] The DC-DC converter is driven by the pulse width modulation signal PWM to control the on or off of the DC-DC converter to achieve control of the DC-DC converter. In the specific implementation, it is assumed that the period T of the PWM signal is s , the signal frequency is The opening time is T on , the off time is T off , so the duty cycle is The duty cycle D y As a control quantity.

[0085] In an embodiment of the present invention, a control quantity corresponding to the DC-DC converter is determined based on a target control parameter and an output error, and then the DC-DC converter is controlled based on the control quantity so that the DC-DC converter stabilizes the output voltage. Based on the operating state of the DC-DC converter, the target control parameter corresponding to the controller is adjusted in a timely manner, and the control quantity corresponding to the DC-DC converter is adjusted in a timely manner, so that the DC-DC converter can maintain optimal operating performance in all operating states.

[0086] In specific applications, this application embodiment provides a step-down type artificial intelligence-based DC-DC converter adaptive control method. Specifically, the control method may include the following steps:

[0087] Step 1: Build a numerical model of the step-down DC-DC converter.

[0088] Specifically, a numerical model corresponding to the step-down DC-DC converter shown in FIG7 can be established. w1 and S w2 The power transistor (MOSFET) is driven by a pulse width modulation signal PWM (Pulse Width Modulation, pulse width modulation, referred to as PWM) to control its conduction or shutdown. The period of the PWM signal is T s , the signal frequency is The opening time is T on , the off time is Toff , so the duty cycle is Duty cycle D y As the control variable. In order to establish the numerical model of the step-down DC-DC converter more accurately, the parasitic effects of the components are considered, and the switching characteristics of the MOSFET are still ideal, that is, zero turn-on voltage, zero turn-off current, and zero switching time.

[0089] Step 2: Obtain the voltage and current values ​​output by the step-down DC-DC converter in the current cycle.

[0090] Specifically, the present invention is limited to the continuous conduction mode (CCM) of the inductor current. Based on the above assumptions, the state equation of the circuit can be obtained according to Kirchhoff's voltage and current laws.

[0091] 1) When the switch tube Open, switch tube When shutting down:

[0092] 2) When Shutdown, When open:

[0093] 3) Output voltage V out for:

[0094] Among them, V in Indicates the input DC power supply, Sw1 and Sw2 indicate switch tube 1 and switch tube 2, Represents the equivalent resistance of switch tube 1, represents the equivalent resistance of switch tube 2, L represents inductance, R L represents the equivalent resistance of the inductor L, C represents the capacitance, and R C Represents the equivalent resistance of capacitor C, R O Indicates the rated load resistance, V O In addition, the controller in this embodiment aims to make the output voltage of the step-down DC-DC converter V out Equal to the reference voltage V ref , the control variable is the pulse width modulation signal PWM.

[0095] Step 3: Tune the controller parameters using the genetic algorithm and ITAE (the absolute value of the error multiplied by the integral of the time term over time) as the performance indicator.

[0096] Step 4: Determine the resistance value corresponding to the load resistor in the step-down DC-DC converter as the operating condition variable corresponding to the step-down DC-DC converter, change the resistance value of the load resistor in the step-down DC-DC converter, adjust multiple sets of controller parameters at different operating points, and determine the operating condition network function through interpolation.

[0097] The specific implementation process of determining the working condition network function can refer to the specific implementation method corresponding to Figure 3 above, and will not be repeated here.

[0098] Step 5: Verify the above control method and also use simulation method to verify its rapid convergence under load changes.

[0099] Specifically, first, select the rated load R o Several values ​​different from the previous steps are taken within the range of ±50%, and R o Substitute the expression to calculate the corresponding PID parameters Next, a genetic algorithm is used to find the optimal PID controller parameters corresponding to the load resistance. Then, use the parameters found under rated load Calculated parameters and The controller performance (ITAE) of the parameters under the corresponding load is compared. The performance of the output control parameters is closer to the best performance under the load than the parameter performance under the rated load.

[0100] By varying the value of the load resistor and performing a limited number of experiments, good performance can be obtained over a large operating range. By increasing the number of experiments, even better performance can be achieved.

[0101] Step 6: Collect the voltage and current values ​​output by the step-down DC-DC converter in the current cycle.

[0102] After determining the operating condition network function corresponding to the operating condition variable and verifying its rapid convergence, the operating condition network function can be directly used in actual applications to perform corresponding control operations. Specifically, the voltage and current values ​​output by the step-down DC-DC converter during the current cycle are first collected to understand the current operating status of the step-down DC-DC converter during the current cycle.

[0103] Step 7: Determine the operating condition quantity corresponding to the step-down DC-DC converter based on the voltage value and the current value. The operating condition quantity is used to characterize the current operating state of the step-down DC-DC converter.

[0104] Step 8: Determine the target control parameters based on the operating conditions.

[0105] Based on the voltage and current values ​​output by the step-down DC-DC converter, the current working state of the step-down DC-DC converter in the current cycle can be understood, and whether the working performance of the DC-DC converter in the current working state is better can be determined. If the current step-down DC-DC converter cannot always maintain the best functional performance, the corresponding target control parameters of the controller can be adjusted.

[0106] Step 9: According to the target control parameter, the step-down DC-DC converter is controlled so that the step-down DC-DC converter outputs a stable voltage.

[0107] The detailed implementation and beneficial effects of each step in the artificial intelligence-based DC-DC converter adaptive control method provided in the embodiment of the present invention have been described in detail in the aforementioned embodiment and will not be elaborated on here. For the specific content, please refer to the above detailed description.

[0108] The following describes in detail one or more embodiments of the DC-DC converter control device of the present invention. Those skilled in the art will appreciate that these devices can be constructed using commercially available hardware components and configured according to the steps taught in this solution.

[0109] FIG8 is a schematic structural diagram of a DC-DC converter control device provided by an embodiment of the present invention. As shown in FIG8 , the device includes: an acquisition module 11 , a first determination module 12 , a second determination module 13 , and a control module 14 .

[0110] The acquisition module 11 is used to acquire the voltage value and the current value output by the DC-DC converter in the current cycle.

[0111] The first determining module 12 is configured to determine an operating condition variable corresponding to the DC-DC converter according to the voltage value and the current value, where the operating condition variable is used to represent a current operating state of the DC-DC converter.

[0112] The second determining module 13 is configured to determine a target control parameter according to the operating condition variable.

[0113] The control module 14 is configured to control the DC-DC converter according to the target control parameter so that the DC-DC converter stably outputs a voltage.

[0114] In an optional embodiment, the first determination module 12 can be specifically used to: determine a resistance value corresponding to the load resistor in the DC-DC converter based on the voltage value and the current value, and determine the resistance value as the operating condition quantity corresponding to the DC-DC converter; or determine a power value corresponding to the load resistor in the DC-DC converter based on the voltage value and the current value, and determine the power value as the operating condition quantity corresponding to the DC-DC converter.

[0115] In an optional embodiment, the second determination module 13 can be specifically used to: determine the operating condition network function corresponding to the operating condition quantity, where the operating condition network function is used to describe the mapping relationship between the operating condition quantity of the DC-DC converter and the control parameters of the controller; and determine the target control parameters based on the operating condition quantity and the operating condition network function.

[0116] In an optional embodiment, the second determination module 13 may be specifically configured to: obtain a preset resistance value corresponding to the load resistor in the DC-DC converter; adjust the control parameters corresponding to the controller based on a genetic algorithm to obtain the optimal control parameters corresponding to the controller when the resistance value corresponding to the load resistor in the DC-DC converter is the preset resistance value; determine a mapping relationship between the resistance value corresponding to the load resistor and the control parameters corresponding to the controller based on the preset resistance value and the optimal control parameters; determine a Padé approximation of the control parameters corresponding to the controller, the Padé approximation being a second-order nonlinear function with a numerator and a denominator; determine a plurality of Padé approximation undetermined coefficients in the Padé approximation based on the mapping relationship; and determine an operating condition network function corresponding to the operating condition quantity based on the Padé approximation undetermined coefficients.

[0117] In an optional embodiment, the second determination module 13 can be specifically used to: collect the current voltage value output by the DC-DC converter when the resistance value corresponding to the load resistor in the DC-DC converter is the preset resistance value; determine the output error corresponding to the DC-DC converter based on the current voltage value and the preset voltage value; determine the performance index corresponding to the current control parameter of the controller based on the output error; and determine the optimal control parameter corresponding to the controller based on the performance index.

[0118] In an optional embodiment, the control module 14 can be specifically used to: determine a control quantity corresponding to the DC-DC converter based on the target control parameter and the output error; and control the DC-DC converter based on the control quantity so that the DC-DC converter stabilizes the output voltage.

[0119] In an optional embodiment, the target control parameters include a proportional coefficient, an integral coefficient, and a differential coefficient. The control module 14 can be specifically used to: determine the error signal corresponding to the controller based on the output error; perform a proportional operation on the error signal based on the proportional coefficient to obtain a proportional operation result; perform an integral operation on the error signal based on the integral coefficient to obtain an integral operation result; perform a differential operation on the error signal based on the differential coefficient to obtain a differential operation result; and determine the control quantity corresponding to the DC-DC converter based on the proportional operation result, the integral operation result, and the differential operation result.

[0120] In an optional embodiment, the control module 14 may be specifically configured to: determine a control signal corresponding to the controller according to the control variable; and control the DC-DC converter according to the control signal so that the DC-DC converter stabilizes the output voltage.

[0121] The device shown in FIG8 can execute the steps introduced in the aforementioned embodiments. For detailed execution process and technical effects, please refer to the description in the aforementioned embodiments and will not be repeated here.

[0122] In one possible design, the structure of the DC-DC converter control device shown in FIG8 can be implemented as an electronic device, as shown in FIG9 . The electronic device may include: a memory 21, a processor 22, and a communication interface 23. The memory 21 stores executable code. When the executable code is executed by the processor 22, the processor 22 can at least implement the artificial intelligence-based DC-DC converter adaptive control method provided in the aforementioned embodiment.

[0123] In addition, an embodiment of the present invention provides a non-transitory machine-readable storage medium, on which executable code is stored. When the executable code is executed by a processor of an electronic device, the processor can at least implement the artificial intelligence-based DC-DC converter adaptive control method provided in the aforementioned embodiment.

[0124] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separate. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Those skilled in the art can understand and implement the present invention without inventive effort.

[0125] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by adding a necessary general hardware platform, and of course can also be implemented by a combination of hardware and software. Based on this understanding, the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a computer product. The present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0126] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. An artificial intelligence-based DC-DC converter adaptive control method, characterized in that: Applied to a controller, the controller is used to control a DC-DC converter, the method comprising: Collect the voltage and current values output by the DC-DC converter in the current cycle; determining an operating condition quantity corresponding to the DC-DC converter according to the voltage value and the current value, wherein the operating condition quantity is used to characterize a current operating state of the DC-DC converter; determining target control parameters according to the operating condition; The DC-DC converter is controlled according to the target control parameter so that the DC-DC converter stably outputs a voltage.

2. The method according to claim 1, characterized in that The determining, based on the voltage value and the current value, an operating condition quantity corresponding to the DC-DC converter includes: determining a resistance value corresponding to a load resistor in the DC-DC converter according to the voltage value and the current value, and determining the resistance value as an operating condition quantity corresponding to the DC-DC converter; Alternatively, a power value corresponding to the load resistance in the DC-DC converter is determined according to the voltage value and the current value, and the power value is determined as the operating condition quantity corresponding to the DC-DC converter.

3. The method according to claim 1, characterized in that Determining the target control parameter according to the operating condition includes: determining an operating condition network function corresponding to the operating condition quantity, wherein the operating condition network function is used to describe a mapping relationship between the operating condition quantity of the DC-DC converter and a control parameter of the controller; A target control parameter is determined according to the operating condition quantity and the operating condition network function.

4. The method according to claim 3, characterized in that Determining the operating condition network function corresponding to the operating condition quantity includes: Obtaining a preset resistance value corresponding to a load resistor in the DC-DC converter; Adjusting control parameters corresponding to the controller based on a genetic algorithm to obtain optimal control parameters corresponding to the controller when the resistance value corresponding to the load resistor in the DC-DC converter is the preset resistance value; Determining a mapping relationship between a resistance value corresponding to the load resistor and a control parameter corresponding to the controller according to the preset resistance value and the optimal control parameter; Determining a Padé approximation of a control parameter corresponding to the controller, wherein the Padé approximation is a nonlinear function with a numerator and a denominator of second order; Determining a plurality of Padé approximation undetermined coefficients in the Padé approximation formula according to the mapping relationship; The operating condition network function corresponding to the operating condition quantity is determined according to the undetermined coefficients of the Padé approximation.

5. The method according to claim 4, characterized in that The step of adjusting the control parameters corresponding to the controller based on the genetic algorithm to obtain the optimal control parameters corresponding to the controller when the resistance value corresponding to the load resistor in the DC-DC converter is the preset resistance value includes: collecting a current voltage value output by the DC-DC converter when the resistance value corresponding to the load resistor in the DC-DC converter is the preset resistance value; Determining an output error corresponding to the DC-DC converter according to the current voltage value and the preset voltage value; Determining a performance indicator corresponding to a current control parameter of the controller according to the output error; According to the performance index, the optimal control parameters corresponding to the controller are determined.

6. The method according to claim 5, characterized in that The step of controlling the DC-DC converter according to the target control parameter so that the DC-DC converter stabilizes the output voltage includes: determining a control variable corresponding to the DC-DC converter according to the target control parameter and the output error; The DC-DC converter is controlled according to the control variable so that the DC-DC converter stabilizes the output voltage.

7. The method according to claim 6, characterized in that The target control parameters include a proportional coefficient, an integral coefficient, and a differential coefficient. Determining a control quantity corresponding to the DC-DC converter according to the target control parameters and the output error includes: determining an error signal corresponding to the controller according to the output error; performing a proportional operation on the error signal based on the proportional coefficient to obtain a proportional operation result; performing an integration operation on the error signal based on the integration coefficient to obtain an integration operation result; performing a differential operation on the error signal based on the differential coefficient to obtain a differential operation result; A control variable corresponding to the DC-DC converter is determined based on the proportional operation result, the integral operation result, and the differential operation result.

8. The method according to claim 7, characterized in that The step of controlling the DC-DC converter according to the control amount so that the DC-DC converter stabilizes the output voltage includes: Determining a control signal corresponding to the controller according to the control quantity; According to the control signal, the DC-DC converter is controlled to stabilize the output voltage of the DC-DC converter.

9. An electronic device, characterized in that: include: A memory, a processor, and a communication interface; wherein the memory stores executable code, and when the executable code is executed by the processor, the processor executes the artificial intelligence-based DC-DC converter adaptive control method according to any one of claims 1 to 8.

10. A non-transitory machine-readable storage medium, characterized in that The non-transitory machine-readable storage medium stores executable code, and when the executable code is executed by a processor of an electronic device, the processor executes the artificial intelligence-based DC-DC converter adaptive control method according to any one of claims 1 to 8.

Images