Loop parameter adaptive adjustment method and device of digital power supply loop and readable storage medium thereof

Abstract

The invention provides a loop parameter adaptive adjustment method and device for a digital power supply loop and a readable storage medium, and the method comprises the steps: switching a digital loop feedback source to a protection measurement value when the protection measurement value (such as Kelvin voltage drop) triggers an alarm, and setting a reference value as a safety value; pID control parameters are dynamically adjusted based on a reinforcement learning algorithm (such as a depth deterministic strategy gradient algorithm), increment adjustment of a proportionality coefficient, an integral coefficient and a differential coefficient is included, and rapid alarm elimination is achieved in combination with forced parameter switching (such as increasing the proportionality coefficient to two times and limiting the adjustment range of the integral coefficient by + / -5%). After the alarm is triggered, the adjustment time is shortened to 50 microseconds, the overshoot is reduced to be within 5%, the problem of circuit overheating caused by disconnection delay or invalid adjustment in a traditional scheme is solved, meanwhile, additional hardware is not needed, and the method is suitable for an embedded power supply control system.

Description

Technical Field

[0001] The present invention relates to the field of power supply control technology, and in particular to a method and device for adaptively adjusting loop parameters of a digital power supply loop, and a readable storage medium thereof, which are suitable for scenarios such as high-current power supply systems and automatic test equipment (such as chip testers). Background Art

[0002] Digital power loops are widely used in industrial power control due to their high precision, flexibility and integration advantages. In the prior art, digital loops usually use fixed parameter PID algorithms to adjust the output through voltage / current ADC feedback. However, when the system faces complex scenarios (such as sudden load changes, abnormal contact resistance), fixed parameters are difficult to dynamically adapt, resulting in insufficient adjustment speed, excessive overshoot, and even the risk of circuit burnout due to invalid feedback. For example, after triggering a protection measurement alarm (such as a Kelvin alarm), the traditional solution switches the feedback source to the protection measurement value (such as the Kelvin voltage drop) to quickly reduce the safety risk, but the loop parameters still rely on manual presets and cannot be dynamically optimized according to real-time load changes. In addition, existing adaptive control methods (such as fuzzy PID) require a preset rule base, which is difficult to cope with highly dynamic and multi-variable scenarios, and lacks deep coordination with the protection measurement alarm mechanism.

[0003] Therefore, there is an urgent need for a new method and device for adaptively adjusting loop parameters of a digital power loop and a readable storage medium thereof to solve the problems existing in the prior art. Summary of the invention

[0004] The embodiments of the present invention provide a method and device for adaptively adjusting loop parameters of a digital power supply loop and a readable storage medium thereof. The prior art currently exists in the art. When a protection measurement alarm is triggered, although the safety risk is reduced by switching feedback sources and adjusting fixed parameters, the fixed loop parameters lead to insufficient adjustment speed and poor stability in complex scenarios, and the control performance cannot be optimized in real time according to dynamic changes in the load.

[0005] The core technology of this invention is mainly the adaptive adjustment technology of loop parameters based on intelligent optimization algorithm. It optimizes PID parameters (such as proportional, integral and differential coefficients) in real time and dynamically through reinforcement learning (such as DDPG) and genetic algorithm, and combines the protection measurement feedback switching mechanism to achieve rapid response, high-precision control and circuit safety protection in complex scenarios.

[0006] In a first aspect, the present invention provides a method for adaptively adjusting loop parameters of a digital power loop, the method comprising the following steps: (a) Real-time collection of operating status data of the digital power supply, including output voltage, output current, protection measurement value, load impedance change rate and loop regulation error, to construct a state vector; (b) when the protection measurement value triggers an alarm, the feedback source of the digital loop is switched from the conventional power output measurement value to the protection measurement value, and the reference value is set to a preset safety value; (c) Dynamically adjust the control parameters of the digital loop based on the reinforcement learning algorithm, including: (c1) Through the Actor network in the deep deterministic policy gradient algorithm, the incremental adjustment of the proportional coefficient Kp, the integral coefficient Ki and the differential coefficient Kd is output according to the state vector; (c2) When the protection measurement alarm is triggered, the proportional coefficient Kp is forced to increase to a preset multiple of the current value, and the adjustment range of the integral coefficient Ki is limited to a preset percentage range or the integral coefficient is reduced to a preset percentage of the current value; (c3) updating the parameters of the PID controller in real time according to the incremental adjustment amount; (d) When the protection measurement value drops to a safe value, disconnect the digital loop feedback and cut off the physical connection between the power supply and the load.

[0007] Furthermore, the reward function of the reinforcement learning algorithm in step (c) is: R = -(αT s +βσ%+γe ss +λP DAC ) Among them, T s is the adjustment time, σ% is the overshoot, e ss is the steady-state error, P DAC is the DAC output power consumption, α is the weight coefficient of the adjustment time, β is the weight coefficient of the overshoot, γ is the weight coefficient of the steady-state error, and λ is the weight coefficient of the DAC output power consumption; When the protection measurement alarm is triggered, an additional penalty term R is imposed penalty = -100 × T alarm , T alarm The alarm duration.

[0008] Furthermore, the Actor network in step (c1) is a lightweight fully connected network, including an input layer, a hidden layer, and an output layer. The number of nodes in the input layer is the dimension of the state vector, and the number of nodes in the output layer is 3, corresponding to ΔKp, ΔKi, ΔKd. The network weights are quantized using 8-bit fixed-point numbers.

[0009] Furthermore, in step (c2), when the protection measurement alarm is triggered, the preset safety parameter combination is forcibly switched, including increasing the proportional coefficient to twice the current value and limiting the adjustment range of the integral coefficient to ±5%.

[0010] Furthermore, in step (c2), when the protection measurement alarm is triggered, a switch to a preset safety parameter combination is forced, including increasing the proportional coefficient to 2 times the current value and reducing the integral coefficient to 0.5 times the current value.

[0011] Furthermore, in step (c1), the state vector also includes: Protection measurement alarm trigger flag; Power output mode.

[0012] Furthermore, it also includes: Deploy reinforcement learning algorithms in embedded controllers to ensure that the control cycle is synchronized with the digital loop and the single inference time is ≤50 microseconds.

[0013] In a second aspect, the present invention provides a loop parameter adaptive adjustment device for a digital power loop, comprising: The data acquisition module collects the operating status data of the digital power supply in real time, including output voltage, output current, protection measurement value, load impedance change rate and loop regulation error, so as to construct a state vector; Feedback switching module, when the protection measurement value triggers an alarm, switches the feedback source of the digital loop from the conventional power output measurement value to the protection measurement value, and sets the reference value to a preset safety value; The reinforcement learning control module dynamically adjusts the control parameters of the digital loop based on the reinforcement learning algorithm, including: Through the Actor network in the deep deterministic policy gradient algorithm, the incremental adjustment of the proportional coefficient Kp, the integral coefficient Ki and the differential coefficient Kd is output according to the state vector; The execution module, when the protection measurement alarm is triggered, forces the proportional coefficient Kp to be increased to a preset multiple of the current value, and limits the adjustment range of the integral coefficient Ki to a preset percentage range or reduces the integral coefficient to a preset percentage of the current value; updates the parameters of the PID controller in real time according to the incremental adjustment amount; when the protection measurement value drops to a safe value, disconnects the digital loop feedback and cuts off the physical connection between the power supply and the load.

[0014] In a third aspect, the present invention provides an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the above-mentioned method for adaptively adjusting loop parameters of a digital power loop.

[0015] In a fourth aspect, the present invention provides a readable storage medium, in which a computer program is stored. The computer program includes a program code for controlling a process to execute a process. The process includes a method for adaptively adjusting loop parameters of the digital power supply loop according to the above-mentioned method.

[0016] The main contributions and innovations of the present invention are as follows: 1. Dynamic parameter optimization driven by reinforcement learning The deep deterministic policy gradient algorithm (DDPG) is used to optimize PID parameters in real time, breaking through the limitations of traditional fixed parameters that cannot adapt to dynamic working conditions such as load mutations and contact resistance fluctuations, and can shorten the adjustment time by more than 50% (compared with traditional PID).

[0017] The reward function introduces multi-objective optimization of adjustment time, overshoot, steady-state error and power consumption to ensure that the system achieves a balance between response speed, stability and energy efficiency.

[0018] 2. Mandatory parameter strategy when alarm is triggered When the protection measurement alarm is triggered, the proportional coefficient Kp is forced to increase (such as 2 times) and the integral coefficient Ki is limited (such as ±5% or reduced to 0.5 times), which significantly accelerates the decline rate of the protection measurement value.

[0019] Avoid the problem of failure to adjust traditional fixed parameters during alarm, such as invalid feedback or oscillation during Kelvin alarm.

[0020] 3. Lightweight algorithm and hardware collaborative optimization The Actor network uses 8-bit fixed-point quantization to reduce computing resource consumption and achieve real-time deployment on embedded controllers (such as STM32H7). The single inference time is ≤50μs, meeting the high-speed control requirements of digital loops.

[0021] The control cycle is synchronized with the loop to ensure that parameter adjustments are consistent with the system dynamic response.

[0022] 4. Multi-dimensional state perception and working condition adaptation The state vector contains information such as the protection alarm flag and power output mode. The algorithm can dynamically adjust the optimization target according to different working conditions (constant voltage / constant current / short circuit) to improve adaptability in complex scenarios.

[0023] Real-time estimation of load impedance change rate (based on Kalman filtering) can predict parameter adjustment needs in advance and reduce overshoot by more than 60%.

[0024] 5. Improved security and reliability Additional penalty for alarm (R penalty = -100 × T alarm ) Strengthen constraints on alarm duration to ensure that risks are quickly eliminated.

[0025] Synchronous control and parameter gradient transition algorithm at the hardware level avoid system oscillation caused by sudden parameter changes and enhance stability.

[0026] 6. Versatility and scalability The reinforcement learning model can be continuously optimized through online learning to adapt to new operating conditions; the modular design facilitates integration into existing digital power systems without the need for additional hardware costs.

[0027] The details of one or more embodiments of the invention are set forth in the following drawings and description so that other features, objects, and advantages of the invention are more readily apparent. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings: Figure 1 is a flow chart of a method for adaptively adjusting loop parameters of a digital power loop according to an embodiment of the present invention; Figure 2 is a flow chart of dynamically adjusting control parameters of a digital loop based on a reinforcement learning algorithm according to an embodiment of the present invention; Figure 3 is a schematic diagram of a digital power supply loop of the prior art; Figure 4 4 is a schematic diagram of the hardware structure of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0029] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with one or more embodiments of this specification. Instead, they are merely examples of devices and methods consistent with some aspects of one or more embodiments of this specification as detailed in the appended claims.

[0030] It should be noted that: in other embodiments, the steps of the corresponding method are not necessarily performed in the order shown and described in this specification. In some other embodiments, the steps included in the method may be more or less than those described in this specification. In addition, a single step described in this specification may be decomposed into multiple steps for description in other embodiments; and multiple steps described in this specification may be combined into a single step for description in other embodiments.

[0031] like Figure 3The figure shows a schematic diagram of an existing digital power loop based on protection measurement feedback. After a protection measurement alarm (such as a Kelvin alarm) is triggered, this solution can quickly reduce the protection measurement value (Kelvin Voltage Drop measurement value, Kelvin high voltage drop or Kelvin low voltage drop) to below a safe value (such as 0) by using the protection measurement value as feedback of the digital loop and setting a safety reference.

[0032] However, when the system faces complex scenarios (such as sudden load changes and abnormal contact resistance), fixed parameters are difficult to adapt dynamically, resulting in insufficient adjustment speed, excessive overshoot, and even the risk of circuit burnout due to invalid feedback. For example, after triggering a protection measurement alarm (such as a Kelvin alarm), the traditional solution switches the feedback source to the protection measurement value (such as the Kelvin voltage drop) to quickly reduce the safety risk, but the loop parameters still rely on manual presets and cannot be dynamically optimized according to real-time load changes. In addition, existing adaptive control methods (such as fuzzy PID) require a preset rule base, which makes it difficult to cope with highly dynamic and multi-variable scenarios, and lacks deep coordination with the protection measurement alarm mechanism.

[0033] Based on this, the present invention solves the problems existing in the prior art based on reinforcement learning.

[0034] Embodiment 1 exist Figure 3 On the basis of the present invention, the loop parameter adaptive adjustment system of the digital power loop is mainly composed of a data acquisition module, a feedback switching module, a reinforcement learning control module and an execution module. The actual hardware used includes a controller, a digital-to-analog converter (DAC), an analog-to-digital converter (ADC), a protection measurement module, and a digital isolator.

[0035] Among them, the controller: runs the digital loop algorithm (such as PID control) and the reinforcement learning algorithm (DDPG), and can use an embedded processor (such as ARM Cortex-M7 or STM32H7).

[0036] Digital-to-analog converter (DAC): converts the digital signal output by the controller into an analog signal to drive the power supply output, such as Figure 3 The main DAC in the .

[0037] Analog-to-digital converter (ADC): including conventional voltage / current ADC (feedback power supply output value) and protection measurement ADC (such as Kelvin voltage drop ADC, monitoring the contact resistance between the force line and the load, such as Figure 3 four ADCs in the ADC).

[0038] Power amplifier: amplifies the DAC output signal and drives the power supply output terminal, such as Figure 3 The power amplifier in.

[0039] Digital isolator (optional): Isolates and protects the measurement signal from the main power signal to prevent interference.

[0040] Physical switch: cuts off the connection between the power supply and the load after the alarm is lifted, such as Figure 3 Output connection switch in.

[0041] The specific implementation modes of the present invention are described in detail below in conjunction with each module.

[0042] Specifically, an embodiment of the present invention provides a method for adaptively adjusting loop parameters of a digital power loop. Specifically, referring to Figure 1 , the method comprising: (a) Real-time collection of operating status data of the digital power supply, including output voltage, output current, protection measurement value, load impedance change rate and loop regulation error, to construct a state vector; In this embodiment, step (a) includes an initialization step: 1. Set general loop parameters: Configure the initial parameters of the PID controller (integrated in the controller) (Kp=1.0, Ki=0.05, Kd=0.1); Set the power output mode to voltage source (reference voltage 2.5V) or current source (reference current 1A).

[0043] 2. Real-time monitoring parameters: Output voltage Vout: sampled by voltage ADC, accuracy ±0.1%; Output current Iout: sampled by current ADC, accuracy ±0.1%; Protection measurement value Vprot: The protection measurement value is Kelvin voltage drop, which is collected by Kelvin high / low voltage drop ADC, such as Kelvin high voltage drop ADC and Kelvin low voltage drop ADC, with a measurement range of 0-5V; Load impedance change rate: According to Ohm's law R(t)=Iout / Vout, the controller is used to calculate the real-time collected Vout and Iout to obtain the instantaneous value R(t) of the load impedance. The controller performs time series analysis on R(t) and uses the differential method to estimate the load impedance change rate dR / dt:

[0044] Where Δt is the sampling interval, which is synchronized with the sampling rate of the ADC. If the ADC sampling rate is 1MHz, then Δt=1μs). R(t) and dR / dt can also be filtered, such as using a 5-point moving average filter, with the window size synchronized with the ADC sampling rate (e.g., the window is 5μs at 1MHz), Kalman filter parameters (e.g., process noise covariance Q=0.01, observation noise covariance R=0.1), and Kalman filter parameters Q and R are dynamically adjusted according to the load mutation rate: when dR / dt≥100Ω / μs, Q=0.1 (increase process noise to adapt to mutation), R=0.05 (reduce observation noise weight); in normal scenarios, Q=0.01 and R=0.1.

[0045] The loop adjustment error e(t) can be divided into two cases: When the alarm is not triggered, it is the difference between the power supply output value (voltage or current) and the measured power supply output value. In the voltage source mode, e(t) = the set target voltage value - the real-time measurement value of the voltage ADC; in the current source mode, e(t) = the set target current value - the real-time measurement value of the current ADC; When the alarm is triggered, it is the difference between the protection measurement value (such as Kelvin voltage drop) and the safety setting value, such as e(t) = preset safety value (such as 0) - real-time measurement value of Kelvin high voltage drop ADC.

[0046] In this way, based on the input parameters: Kelvin voltage drop (protection measurement value Vprot), load impedance change rate (dR / dt), PID current parameters (Kp, Ki, Kd), protection measurement alarm flag (0 / 1), power supply output mode (voltage source / current source); output parameters: incremental adjustment of PID parameters (ΔKp, ΔKi, ΔKd).

[0047] In this way, the state vector State can be constructed, such as: State=[Vout,Iout,Vprot,dR / dt,e(t),alarm_flag,mode] Among them, alarm_flag is 0-no alarm, 1-alarmed; mode is 0-constant voltage mode (voltage source), 1-constant current mode (current source).

[0048] 3. Configure Kelvin loop parameters: Set the Kelvin voltage drop alarm threshold (such as 5V) and safety reference value (0V); Kelvin ADC via digital gain adjustment ( Figure 3 In the ADC, the resolution of the Kelvin high voltage and Kelvin low voltage drop refers to the ADC) to match the resolution of the voltage ADC (for example, both are adjusted to 12-bit accuracy, or 16-bit, 24-bit, etc.).

[0049] 4. Enable the alarm function: Enable Kelvin voltage drop monitoring interrupt and set the priority to the highest.

[0050] (b) when the protection measurement value triggers an alarm, the feedback source of the digital loop is switched from the conventional power output measurement value to the protection measurement value, and the reference value is set to a preset safety value; In this embodiment, when the Kelvin voltage drop exceeds 5V, the protection measurement module triggers an interrupt, and the controller responds immediately: recording the current power output status (voltage / current, load impedance, etc.); forcibly stopping the regular loop operation and saving the current PID parameters.

[0051] (c) Dynamically adjust the control parameters of the digital loop based on the reinforcement learning algorithm, such as Figure 2 As shown, specifically including: (c1) Through the Actor network in the deep deterministic policy gradient algorithm (DDPG), the incremental adjustment of the proportional coefficient Kp, the integral coefficient Ki and the differential coefficient Kd is output according to the state vector; Among them, the Actor network is a lightweight fully connected network (10 nodes in the input layer → 8 nodes in the hidden layer → 3 nodes in the output layer (corresponding to the incremental adjustment of the PID parameters (ΔKp, ΔKi, ΔKd))), the output layer uses the Tanh activation function (such as the output range [-1,1], corresponding to the parameter adjustment range of ±10%), the hidden layer uses the ReLU activation function, and the weights are quantized in 8-bit fixed-point. In this way, the network size can be compressed to 21KB (input layer 10×8 + hidden layer 8×3 = 104 parameters), meeting the real-time control requirements. The output layer is mapped to the PID parameter increment, and the proportional coefficient is forced to be adjusted in combination with the alarm flag to achieve rapid response in emergency scenarios. For example, ΔKp=Kp×Scale Factor×tanh(Actor output value), where Scale Factor is the preset adjustment range (such as 10%).

[0052] DDPG also has a Critic network, which is one of the core components of the Actor-Critic architecture. Its core function is to evaluate the value (Q value) of the state-action pair and guide the Actor network optimization strategy. In the present invention, the Critic network is used to dynamically adjust the PID parameters (such as the proportional coefficient Kp, the integral coefficient Ki, and the differential coefficient Kd) to improve the control performance of the digital power loop in the protection measurement alarm scenario. When the protection measurement alarm is triggered, the Critic network predicts the long-term benefits of the action (for example: the adjustment time is reduced by 50μs, and the overshoot is reduced to less than 5%) based on the real-time status (such as the current value of the Kelvin voltage drop, the load mutation rate) and the Actor's action (ΔKp=+10%, ΔKi=-5%, etc.). Therefore, the network structure of the Critic network of the present invention is: Input layer: 13 nodes (state vector 10 dimensions + action vector 3 dimensions); Hidden layer: 16-node fully connected layer, using LeakyReLU activation function; Output layer: 1 node, output Q value (state-action value), using linear activation function.

[0053] Among them, the learning rate of the Critic network can be 1e-3, the soft update coefficient τ can be 0.01, and the specific parameters can be set according to actual needs.

[0054] The reward function is set as: R = -(αT s +βσ%+γe ss +λP DAC ) Among them, T s is the adjustment time, σ% is the overshoot, e ss is the steady-state error, P DAC is the DAC output power consumption, α is the weight coefficient of the adjustment time, β is the weight coefficient of the overshoot, γ is the weight coefficient of the steady-state error, and λ is the weight coefficient of the DAC output power consumption. When the protection measurement alarm is triggered, an additional penalty term R is applied. penalty = -100 × T alarm , T alarm is the alarm duration, so the Critic network uses the penalty term R penaltyThe driver Actor network prioritizes reducing the duration of the alarm to solve the problem of "circuit burnout risk". The weight coefficients α, β, γ, and λ are determined by grid search: α ranges from 0.5 to 1.5 (adjustment time optimization weight), β is 1.0 to 2.0 (overshoot suppression weight), γ is 0.1 to 0.5 (steady-state error weight), and λ is 0.01 to 0.1 (power consumption optimization weight). The optimal combination is selected by cross-validation (e.g., α=1.0, β=1.5, γ=0.2, λ=0.05).

[0055] Among them, overshoot σ (Overshoot) is a key indicator used to describe the dynamic response characteristics of the control system. It refers to the maximum instantaneous deviation of the system output value exceeding the target setting value during the adjustment process, usually expressed as a percentage.

[0056] In this embodiment, the Actor-Critic network can build a digital power simulation model in MATLAB / Simulink to simulate ADC sampling, DAC output and protection measurement alarm; generate an initial experience pool (100,000 data) by randomly initializing the Actor-Critic network; use batch gradient descent (Batch Size=64) to optimize the network, with learning rates Actor=1e-4 and Critic=1e-3. The initial training data generates 100,000 state-action pairs under random load mutation scenarios through MATLAB / Simulink simulation. The experience replay buffer has a capacity of 10,000, a sampling interval of 50ms, and 128 data are updated each time, where the alarm trigger event is marked as 3 times the priority coefficient; save the optimal network weights and embed them into the controller firmware. For example, in the STM32H7 controller, the CMSIS-NN library is used to optimize 8-bit quantized reasoning, and the memory usage is compressed to 21KB; the interrupt priority is set to the highest (priority 0), and the task scheduling adopts a time slice rotation strategy. The single reasoning time is measured to be 48μs (±2μs).

[0057] In this embodiment, online learning can also be used to adopt Priority Experience Replay (PER) to focus on learning alarm trigger event data and improve the response speed in emergency scenarios. The state vector, action, reward and next state are recorded in real time, and the alarm trigger event is marked as a high priority and stored in the playback buffer; 128 data are sampled from the buffer every 50ms to update the Actor-Critic network; in the alarm state, the integral coefficient adjustment range is limited (±5% or 10%) to prevent parameter mutations. Among them, during the online learning process, action limits are set: ΔKp adjustment range ≤±20%, ΔKi ≤±10%, ΔKd ≤±5%; the exploration noise uses OU process noise, and the standard deviation decays with the number of training steps (initial σ=0.1, decaying to 0.01 every 1000 steps) to avoid parameter mutations causing system oscillations.

[0058] For example, in the actual system, dR / dt=500Ω / μs is detected, triggering the Kelvin alarm; the Actor network outputs ΔKp=+100% (Kp=2.0), ΔKi=-50% (Ki=0.5), and the alarm is lifted within 50μs; PER (priority experience recovery, a means of online learning) marks the event as high priority, and the adjustment time for similar scenarios in subsequent training is optimized to 30μs.

[0059] In this way, basic performance is ensured through pre-training, and online learning improves the robustness of complex scenarios, which is seamlessly connected with the "dynamic parameter adaptation" technical feature.

[0060] (c2) When the protection measurement alarm is triggered, the proportional coefficient Kp is forced to increase to a preset multiple of the current value, and the adjustment range of the integral coefficient Ki is limited to a preset percentage range or the integral coefficient is reduced to a preset percentage of the current value; For example, in a scenario where a large current mutation causes extreme overshoot (overshoot ≥ 10% or load mutation rate ≥ 100A / μs), when the protection measurement alarm is triggered, it is forced to switch to the preset safety parameter combination, including increasing the proportional coefficient to 2 times the current value and reducing the integral coefficient to 0.5 times the current value. This can quickly suppress overshoot and urgently reduce the protection measurement value.

[0061] In conventional alarm scenarios where smooth adjustment is required (overshoot <10% and load mutation rate <100A / μs), when the protection measurement alarm is triggered, it is forced to switch to the preset safety parameter combination, including increasing the proportional coefficient to twice the current value and limiting the adjustment range of the integral coefficient to ±5%.

[0062] Among them, the extreme scenario judgment threshold (overshoot ≥10%, load mutation rate ≥100A / μs) is determined based on the power supply specifications: for power supply systems with a rated current ≥50A, the load mutation rate threshold is adjusted to 200A / μs; when the alarm is triggered, the parameter combination (Kp×2, Ki×0.5) is forced to switch, and the stability is verified through hardware-in-the-loop testing.

[0063] In this way, the hierarchical mechanism is enabled only when the alarm is triggered, and preset parameters are used to force switching in extreme scenarios. In normal scenarios, dynamic optimization is achieved through reinforcement learning. By introducing a hierarchical adjustment mechanism, the emergency suppression and stable regulation logic are separated, and the alarm triggering scenario is bound to the feedback source switching.

[0064] (c3) updating the parameters of the PID controller in real time according to the incremental adjustment amount; (d) When the protection measurement value drops to a safe value, disconnect the digital loop feedback and cut off the physical connection between the power supply and the load.

[0065] This specific implementation fully discloses the hardware architecture, algorithm implementation and operation process, and solves the problem of rapid response and stability in protection measurement alarm scenarios through the coordination of dynamic switching of feedback sources and optimization of reinforcement learning parameters. This solution can be directly integrated into the existing digital power system without additional hardware costs.

[0066] Embodiment 2 Based on the same concept, the present invention also proposes a loop parameter adaptive adjustment device for a digital power loop, comprising: The data acquisition module collects the operating status data of the digital power supply in real time, including output voltage, output current, protection measurement value, load impedance change rate and loop regulation error, so as to construct a state vector; Feedback switching module, when the protection measurement value triggers an alarm, switches the feedback source of the digital loop from the conventional power output measurement value to the protection measurement value, and sets the reference value to a preset safety value; The reinforcement learning control module dynamically adjusts the control parameters of the digital loop based on the reinforcement learning algorithm, including: Through the Actor network in the deep deterministic policy gradient algorithm, the incremental adjustment of the proportional coefficient Kp, the integral coefficient Ki and the differential coefficient Kd is output according to the state vector; The execution module, when the protection measurement alarm is triggered, forces the proportional coefficient Kp to be increased to a preset multiple of the current value, and limits the adjustment range of the integral coefficient Ki to a preset percentage range or reduces the integral coefficient to a preset percentage of the current value; updates the parameters of the PID controller in real time according to the incremental adjustment amount; when the protection measurement value drops to a safe value, disconnects the digital loop feedback and cuts off the physical connection between the power supply and the load.

[0067] Embodiment 3 This embodiment also provides an electronic device, referring to Figure 4 , comprises a memory 404 and a processor 402, wherein the memory 404 stores a computer program, and the processor 402 is configured to run the computer program to execute the steps in any of the above method embodiments.

[0068] Specifically, the processor 402 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiment of the present invention.

[0069] Among them, the memory 404 may include a large capacity memory 404 for data or instructions. For example, but not limitation, the memory 404 may include a hard disk drive (HDD), a floppy disk drive, a solid state drive (SSD), a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. In appropriate cases, the memory 404 may include a removable or non-removable (or fixed) medium. In appropriate cases, the memory 404 may be inside or outside the data processing device. In a specific embodiment, the memory 404 is a non-volatile memory. In a specific embodiment, the memory 404 includes a read-only memory (ROM) and a random access memory (RAM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically alterable ROM (EAROM) or a flash memory (FLASH), or a combination of two or more of these. In appropriate circumstances, the RAM may be a static random access memory (SRAM) or a dynamic random access memory (DRAM), wherein the DRAM may be a fast page mode dynamic random access memory 404 (FPMDRAM), an extended data output dynamic random access memory (EDODRAM), a synchronous dynamic random access memory (SDRAM), etc.

[0070] The memory 404 may be used to store or cache various data files required for processing and / or communication, as well as possible computer program instructions executed by the processor 402 .

[0071] The processor 402 reads and executes computer program instructions stored in the memory 404 to implement any one of the loop parameter adaptive adjustment methods for a digital power loop in the above embodiments.

[0072] Optionally, the electronic device may further include a transmission device 406 and an input / output device 408 , wherein the transmission device 406 is connected to the processor 402 , and the input / output device 408 is connected to the processor 402 .

[0073] The transmission device 406 can be used to receive or send data via a network. Specific examples of the above-mentioned network may include a wired or wireless network provided by a communication provider of the electronic device. In one example, the transmission device includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 406 can be a radio frequency (Radio Frequency, referred to as RF) module, which is used to communicate with the Internet wirelessly.

[0074] Input / output devices 408 are used to input or output information.

[0075] Embodiment 4 This embodiment further provides a readable storage medium, in which a computer program is stored. The computer program includes a program code for controlling a process to execute a process. The process includes a loop parameter adaptive adjustment method of a digital power loop according to the first embodiment.

[0076] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementation modes, and this embodiment will not be described in detail here.

[0077] In general, various embodiments may be implemented in hardware or dedicated circuits, software, logic, or any combination thereof. Some aspects of the invention may be implemented in hardware, while other aspects may be implemented in firmware or software executed by a controller, microprocessor, or other computing device, but the invention is not limited thereto. Although various aspects of the invention may be shown and described as block diagrams, flow charts, or using some other graphical representation, it should be understood that, as non-limiting examples, the boxes, devices, systems, techniques, or methods described herein may be implemented in hardware, software, firmware, dedicated circuits or logic, general-purpose hardware or controllers or other computing devices, or some combination thereof.

[0078] Embodiments of the present invention may be implemented by computer software that is executable by a data processor of a mobile device, such as in a processor entity, or by hardware, or by a combination of software and hardware. Computer software or programs (also referred to as program products) including software routines, applets and / or macros may be stored in any device-readable data storage medium, and they include program instructions for performing specific tasks. A computer program product may include one or more computer executable components configured to perform an embodiment when the program is run. One or more computer executable components may be at least one software code or a portion thereof. In addition, at this point, it should be noted that, for example, Figure 1 Any block of the logic flow in the program may represent program steps, or interconnected logic circuits, blocks and functions, or a combination of program steps and logic circuits, blocks and functions. The software may be stored on physical media such as memory chips or storage blocks implemented within the processor, magnetic media such as hard disks or floppy disks, and optical media such as, for example, DVDs and their data variants, CDs, etc. Physical media are non-transitory media.

[0079] Those skilled in the art should understand that the technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0080] The above embodiments only express several implementation methods of the present invention, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present invention. It should be pointed out that, for those of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the attached claims.

Claims

1. A method for adaptively adjusting loop parameters of a digital power loop, characterized in that: The following steps are involved: (a) Real-time collection of operating status data of the digital power supply, including output voltage, output current, protection measurement value, load impedance change rate and loop regulation error, to construct a state vector; (b) when the protection measurement value triggers an alarm, switching the feedback source of the digital loop from the conventional power output measurement value to the protection measurement value, and setting the reference value to a preset safety value; (c) Dynamically adjust the control parameters of the digital loop based on the reinforcement learning algorithm, including: (c1) outputting incremental adjustments of the proportional coefficient Kp, the integral coefficient Ki and the differential coefficient Kd according to the state vector through the Actor network in the deep deterministic policy gradient algorithm; (c2) When the protection measurement alarm is triggered, the proportional coefficient Kp is forced to increase to a preset multiple of the current value, and the adjustment range of the integral coefficient Ki is limited to a preset percentage range or the integral coefficient is reduced to a preset percentage of the current value; (c3) updating the parameters of the PID controller in real time according to the incremental adjustment amount; (d) When the protection measurement value drops to the safety value, the digital loop feedback is disconnected and the physical connection between the power supply and the load is cut off.

2. A method for adaptively adjusting loop parameters of a digital power loop as claimed in claim 1, characterized in that: The reward function of the reinforcement learning algorithm described in step (c) is: R=-(αT s +βσ%+γe ss +λP DAC ) Among them, T s is the adjustment time, σ% is the overshoot, e ss is the steady-state error, P DAC is the DAC output power consumption, α is the weight coefficient of the adjustment time, β is the weight coefficient of the overshoot, γ is the weight coefficient of the steady-state error, and λ is the weight coefficient of the DAC output power consumption; When the protection measurement alarm is triggered, an additional penalty term R is imposed penalty = -100 × T alarm , T alarm The alarm duration.

3. The method for adaptively adjusting loop parameters of a digital power loop according to claim 1, characterized in that: The Actor network described in step (c1) is a lightweight fully connected network, which includes an input layer, a hidden layer and an output layer. The number of nodes in the input layer is the dimension of the state vector, and the number of nodes in the output layer is 3, corresponding to ΔKp, ΔKi, ΔKd. The network weights are quantized using 8-bit fixed-point numbers.

4. The method for adaptively adjusting loop parameters of a digital power loop according to claim 1, characterized in that: In step (c2), when the protection measurement alarm is triggered, the system is forced to switch to the preset safety parameter combination, including increasing the proportional coefficient to twice the current value and limiting the adjustment range of the integral coefficient to ±5%.

5. The method for adaptively adjusting loop parameters of a digital power loop according to claim 1, characterized in that: In step (c2), when the protection measurement alarm is triggered, the preset safety parameter combination is forced to be switched, including increasing the proportional coefficient to 2 times the current value and reducing the integral coefficient to 0.5 times the current value.

6. The method for adaptively adjusting loop parameters of a digital power loop according to claim 1, characterized in that: In step (c1), the state vector also includes: Protection measurement alarm trigger flag; Power output mode.

7. A method for adaptively adjusting loop parameters of a digital power loop according to any one of claims 1 to 6, characterized in that: Also includes: The reinforcement learning algorithm is deployed in an embedded controller to ensure that the control cycle is synchronized with the digital loop and the single inference time is ≤50 microseconds.

8. A loop parameter adaptive adjustment device for a digital power loop, characterized in that: include: The data acquisition module collects the operating status data of the digital power supply in real time, including output voltage, output current, protection measurement value, load impedance change rate and loop regulation error, so as to construct a state vector; A feedback switching module, when the protection measurement value triggers an alarm, switches the feedback source of the digital loop from the conventional power supply output measurement value to the protection measurement value, and sets the reference value to a preset safety value; The reinforcement learning control module dynamically adjusts the control parameters of the digital loop based on the reinforcement learning algorithm, including: Outputting incremental adjustments of the proportional coefficient Kp, the integral coefficient Ki, and the differential coefficient Kd according to the state vector through the Actor network in the deep deterministic policy gradient algorithm; The execution module, when the protection measurement alarm is triggered, forces the proportional coefficient Kp to be increased to a preset multiple of the current value, and limits the adjustment range of the integral coefficient Ki to a preset percentage range or reduces the integral coefficient to a preset percentage of the current value; updates the parameters of the PID controller in real time according to the incremental adjustment amount; when the protection measurement value drops to the safety value, disconnects the digital loop feedback and cuts off the physical connection between the power supply and the load.

9. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to run the computer program to execute the loop parameter adaptive adjustment method of a digital power loop according to any one of claims 1 to 7.

10. A readable storage medium, characterized in that: A computer program is stored in the readable storage medium, wherein the computer program includes a program code for controlling a process to execute a process, wherein the process includes the method for adaptively adjusting loop parameters of a digital power loop according to any one of claims 1 to 7.

Images