A method and device for adjusting circuit operating parameters

Abstract

The present invention discloses a method and device for adjusting circuit operating parameters. The method includes: obtaining the initial circuit operating parameters of a device using plasma heating; inputting the initial circuit operating parameters into a preset first model to calculate plasma stability and system energy consumption, obtaining the initial stability value and the initial system energy consumption value of the circuit; taking the initial circuit operating parameters as the initial position parameters of each particle, performing fitness calculation according to the initial position parameters, the initial stability value, the initial system energy consumption value, the first model and a preset particle swarm optimization algorithm, obtaining the target circuit operating parameters that maximize the plasma stability value and minimize the system energy consumption value; and adjusting the initial circuit operating parameters to the target circuit operating parameters. This solution can dynamically adjust the working parameters of the boost circuit through the preset particle swarm optimization algorithm, significantly improve the stability of the plasma, reduce energy consumption, and improve the working efficiency of the device using plasma heating.

Description

Technical Field

[0001] The present invention relates to the technical field of circuit optimization, and particularly to a method and device for adjusting circuit operating parameters. Background Art

[0002] As an important industrial device, the boost circuit of a device using plasma heating directly affects the performance of the device in terms of its working efficiency and the stability of the plasma. In the prior art, the efficiency of the boost circuit and the plasma stability of a device using plasma heating usually rely on empirical adjustment and fixed parameter settings. This method cannot be adaptively optimized according to the real-time working state, resulting in high energy consumption and poor system stability. Summary of the Invention

[0003] The present invention aims to at least solve the technical problems existing in the prior art. To this end, in the first aspect of the present invention, a method for adjusting circuit operating parameters is proposed, and the method includes:

[0004] Obtain the initial circuit operating parameters of a device using plasma heating in the working state, where the initial circuit operating parameters include: the input voltage value of the boost circuit, the current value in the circuit, the working frequency of the circuit, and the electrode spacing; the electrode spacing represents the spacing between the discharge electrode and the ground electrode of the plasma generator of the device using plasma heating; the device using plasma heating is a device that converts electrical energy into a high-temperature plasma flame using the plasma heating principle;

[0005] Input the initial circuit operating parameters into a preset first model for calculating plasma stability and system energy consumption to obtain the initial stability value and the initial system energy consumption value of the circuit;

[0006] Use the initial circuit operating parameters as the initial position parameters of each particle, and perform fitness calculation according to the initial position parameters, the initial stability value, the initial system energy consumption value, the first model, and a preset adaptive multi-objective particle swarm optimization algorithm to obtain the target circuit operating parameters that maximize the plasma stability value and minimize the system energy consumption value;

[0007] Adjust the initial circuit operating parameters to the target circuit operating parameters.

[0008] Optionally, the first model includes a feature extraction layer, a feature fusion layer, a self-attention mechanism layer, and a fully connected layer. The step of inputting the initial circuit operating parameters into a preset first model for calculating plasma stability and system energy consumption to obtain the initial stability value and the initial system energy consumption value of the circuit includes:

[0009] Input the initial circuit operation parameters into the feature extraction layer and the feature fusion layer for initial feature extraction and feature fusion to obtain a first eigenvalue;

[0010] Input the first eigenvalue into the self-attention mechanism layer, adaptively calculate the target feature weight corresponding to each feature in the first eigenvalue by combining max pooling and average pooling, and weight the first eigenvalue using the target feature weight to obtain a second eigenvalue;

[0011] Input the second eigenvalue into the feature extraction layer for re-feature extraction to obtain a third eigenvalue;

[0012] Input the third eigenvalue into the fully connected layer for fully connected processing, and output the initial stability value and the initial system energy consumption value of the circuit.

[0013] Optionally, the feature extraction layer includes a first convolutional layer, a second convolutional layer, a third convolutional layer, a fourth convolutional layer, and a fifth convolutional layer. The step of inputting the initial circuit operation parameters into the feature extraction layer and the feature fusion layer for initial feature extraction and fusion to obtain a first eigenvalue includes:

[0014] Input the first eigenvalue into the first convolutional layer for feature extraction to obtain a first sub-eigenvalue;

[0015] Input the first eigenvalue into the second convolutional layer for feature extraction to obtain a second sub-eigenvalue;

[0016] Input the second eigenvalue into the third convolutional layer for feature extraction to obtain a third sub-eigenvalue;

[0017] Concatenate the first sub-eigenvalue and the third sub-eigenvalue to obtain a fourth sub-eigenvalue;

[0018] Input the fourth sub-eigenvalue into the fourth convolutional layer for feature extraction to obtain a fifth sub-eigenvalue;

[0019] Concatenate the second sub-eigenvalue and the fifth sub-eigenvalue to obtain a first eigenvalue.

[0020] Optionally, the loss function during the training of the first model includes a first error term, a second error term, and a regularization term;

[0021] The first error term represents the mean square error between the predicted plasma stability value and the true plasma stability value; the second error term represents the mean square error between the predicted system energy consumption value and the true system energy consumption value; the regularization term is used to control the physical reasonableness of the circuit operation parameters.

[0022] Optionally, taking the initial circuit operation parameters as the initial position parameters of each particle, and performing fitness calculation according to the initial position parameters, the initial stability value, the initial system energy consumption value, the first model, and a preset adaptive multi-objective particle swarm optimization algorithm includes:

[0023] Initialize the particle swarm parameters; the particle swarm parameters at least include the number of particles, the position range and velocity range of each particle, the inertia weight of the particle, the initial stability weight, and the initial energy consumption weight; the position range is from the minimum value to the maximum value of the circuit operation parameters;

[0024] Take the initial circuit operation parameters as the initial position parameters of each particle;

[0025] Within the position range and the velocity range, randomly generate the initial position and initial velocity of each particle in the initial state, and generate the initial individual optimal position and initial global optimal position of each particle;

[0026] According to the initial stability weight, the initial energy consumption weight, the initial position parameters, the initial system energy consumption value, the initial stability value, and a preset fitness function, calculate the initial fitness of each particle;

[0027] According to the particle swarm parameters and a preset velocity update function, perform velocity update of the particles within the velocity range to obtain an updated velocity;

[0028] According to the updated velocity and the initial position of the particle, perform position update of the particle within the position range to obtain an updated position;

[0029] Based on the position parameters of the particle at the updated position, calculate the new fitness of the particle;

[0030] If the new fitness is greater than the individual historical optimal value, then take the new fitness value as the current individual optimal value; if the new fitness is greater than the global historical optimal value, then take the new fitness value as the current global optimal value;

[0031] When the preset maximum number of iterations is reached or the fitness reaches the preset convergence threshold, stop the calculation, obtain the position parameters of the particle at the global optimal value, and obtain the optimal circuit parameters; the optimal circuit parameters are the target circuit operation parameters that maximize the plasma stability value and minimize the system energy consumption value.

[0032] Optionally, the performing velocity update of the particles within the velocity range according to the initial parameters and a preset velocity update function to obtain an updated velocity includes:

[0033] Calculate the first difference between the initial individual optimal position and the initial position of the particle, and the second difference between the initial global optimal position and the initial position;

[0034] Determine the product of the first difference, the individual learning factor, and a preset first random number to obtain a first product; and determine the product of the second difference, the global learning factor, and a preset second random number to obtain a second product;

[0035] Determine the product of the inertia weight and the initial velocity of the particle to obtain a third product;

[0036] Determine the sum of the first product, the second product, and the third product to obtain the initial update velocity;

[0037] If the initial update velocity is within the velocity range, use the initial update velocity as the update velocity.

[0038] Optionally, the calculating the initial fitness of each particle according to the initial stability weight, the initial energy consumption weight, the initial position parameter, the initial system energy consumption value, the initial stability value, and a preset fitness function includes:

[0039] Input the initial position parameter into the first model to obtain an initial plasma stability value and an initial system energy consumption value;

[0040] Substitute the initial position parameter into a preset regularization term to obtain a regularization value;

[0041] Determine the product of the initial stability weight and the initial plasma stability value to obtain a stability product; and determine the product of the initial energy consumption weight and the initial system energy consumption value to obtain an energy consumption product;

[0042] Determine the difference between the energy consumption product and the stability product, and determine the sum of the difference and the regularization value, and use the sum as the initial fitness of the particle.

[0043] A second aspect of the present invention provides a device for adjusting circuit operating parameters, the device includes:

[0044] A parameter acquisition module, configured to acquire initial circuit operating parameters of a device using plasma heating in a working state, the initial circuit operating parameters including: the input voltage value of a boost circuit, the current value in the circuit, the operating frequency of the circuit, and the electrode spacing; the electrode spacing represents the spacing between the discharge electrode and the ground electrode of the plasma generator of the device using plasma heating; the device using plasma heating refers to a device using the principle of plasma heating as a heat source;

[0045] A calculation module, configured to input the initial circuit operation parameters into a preset first model to calculate the plasma stability and system energy consumption, and obtain the initial stability value and the initial system energy consumption value of the circuit;

[0046] A target parameter determination module, configured to use the initial circuit operation parameters as the initial position parameters of each particle, and perform fitness calculation according to the initial position parameters, the initial stability value, the initial system energy consumption value, the first model, and a preset adaptive multi-objective particle swarm optimization algorithm, so as to obtain target circuit operation parameters that maximize the plasma stability value and minimize the system energy consumption value;

[0047] An adjustment module, configured to adjust the initial circuit operation parameters to the target circuit operation parameters.

[0048] A third aspect of the present invention provides a device using plasma heating, including: a controller; a memory for storing executable instructions of the controller; wherein, the controller is configured to execute the instructions to implement the circuit operation parameter adjustment method as described in the first aspect.

[0049] A fourth aspect of the present invention provides a computer-readable storage medium, when the instructions in the computer-readable storage medium are executed by a controller of a device using plasma heating, enabling the device using plasma heating to execute the circuit operation parameter adjustment method as described in the first aspect.

[0050] The embodiments of the present invention have the following beneficial effects:

[0051] In an embodiment of the present invention, initial circuit operating parameters of a device heated by plasma in a working state are obtained. The initial circuit operating parameters include: the input voltage value of a boost circuit, the current value in the circuit, the operating frequency of the circuit, and the electrode spacing. The electrode spacing represents the spacing between the discharge electrode and the ground electrode of the plasma generator of the device heated by plasma. The device heated by plasma refers to a device that uses the plasma heating principle as a heat source. The initial circuit operating parameters are input into a preset first model for plasma stability and system energy consumption calculation to obtain the initial stability value and the initial system energy consumption value of the circuit. The initial circuit operating parameters are used as the initial position parameters of each particle, and fitness calculation is performed according to the initial position parameters, the initial stability value, the initial system energy consumption value, the first model, and a preset particle swarm optimization algorithm to obtain target circuit operating parameters that maximize the plasma stability value and minimize the system energy consumption value. The initial circuit operating parameters are adjusted to the target circuit operating parameters. This solution can significantly improve the stability of the plasma, reduce energy consumption, and improve the working efficiency of the device heated by plasma by dynamically adjusting the working parameters of the boost circuit through the preset particle swarm optimization algorithm. Description of the Drawings

[0052] Figure 1 is a flowchart of the steps of a method for adjusting circuit operating parameters provided by an embodiment of the present invention;

[0053] Figure 2 is a block diagram of the structure of a device for adjusting circuit operating parameters provided by an embodiment of the present invention. Detailed Embodiments

[0054] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

[0055] Hereinafter, the terms "first" and "second" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the embodiments of the present disclosure, unless otherwise stated, the meaning of "a plurality" is two or more. Additionally, the use of "based on" or "in accordance with" means open and inclusive, as a process, step, calculation, or other action based on one or more of the stated conditions or values may, in practice, be based on additional conditions or values beyond those stated.

[0056] Figure 1 It is a flowchart of the steps of a method for adjusting circuit operating parameters provided by an embodiment of the present invention.

[0057] As Figure 1 shown, the method includes the following steps:

[0058] Step 101, obtain the initial circuit operating parameters of the device using plasma heating in the working state, where the initial circuit operating parameters include: the input voltage value of the boost circuit, the current value in the circuit, the operating frequency of the circuit, and the electrode spacing; the electrode spacing represents the spacing between the discharge electrode and the ground electrode of the plasma generator of the device using plasma heating; the device using plasma heating refers to a device that uses the principle of plasma heating as a heat source.

[0059] In an embodiment of the invention, a device using plasma heating refers to a device that uses the principle of plasma heating as a heat source, and this device includes but is not limited to cookers, electric heaters, wall-hung boilers, electric grills, portable stoves, etc. The principle of plasma heating refers to generating an open flame by high-voltage breakdown of air at the end of the plasma, and heating related devices through the generated open flame.

[0060] The device using plasma heating includes a boost circuit for boosting the mains voltage. Obtain the circuit operating parameters of the device using plasma heating in the working state, and these circuit operating parameters include: the input voltage value (V) of the boost circuit, the current value (I) in the circuit, the operating frequency (f) of the circuit, and the electrode spacing (d).

[0061] Among them, the electrode spacing represents the spacing between the discharge electrode and the ground electrode of the plasma generator of the device using plasma heating.

[0062] A data acquisition module can be deployed on the device using plasma heating, and the data acquisition module obtains the initial circuit operating parameters of the device using plasma heating in the working state. The data acquisition module sends the initial circuit operating parameters to the controller, and the controller executes the method for adjusting circuit operating parameters of the present invention.

[0063] The controller can be deployed on the device using plasma heating or in the cloud, and those skilled in the art can set it according to actual application requirements.

[0064] Step 102, input the initial circuit operating parameters into a preset first model for plasma stability and system energy consumption calculation, and obtain the initial stability value and the initial system energy consumption value of the circuit.

[0065] The first model is a circuit simulation model built based on a deep neural network (DNN), which is used to determine the impact of circuit operating parameters on plasma stability and system energy consumption.

[0066] The input data of the first model are circuit operating parameters. Through feature extraction and processing of the circuit operating parameters by the deep neural network, estimated values of plasma stability and system energy consumption are output.

[0067] Step 103: Use the initial circuit operating parameters as the initial position parameters of each particle. According to the initial position parameters, the initial stability value, the initial system energy consumption value, the first model, and a preset adaptive multi-objective particle swarm optimization algorithm, perform fitness calculation to obtain target circuit operating parameters that maximize the plasma stability value and minimize the system energy consumption value.

[0068] The particle swarm optimization algorithm initializes a group of particles in the problem space. The particles move randomly through a specific algorithm and evaluate the quality of their movements through a fitness function. The particle swarm generates random solutions in the initialization stage and finds the optimal solution through iteration. In each iteration, the particles update themselves by tracking their own experience and the group experience. After updating, the fitness value is calculated and the global optimal position and local optimal position are updated. When it is judged that the termination condition is satisfied, the loop is exited; otherwise, the iteration continues. Finally, the optimal position and the optimal fitness value are output.

[0069] This solution improves the particle swarm optimization (PSO) algorithm, designs an adaptive multi-objective particle swarm optimization algorithm, and obtains the optimal circuit operating parameters.

[0070] Based on the standard PSO, the multi-objective particle swarm optimization algorithm introduces a multi-objective optimization method to simultaneously optimize the stability and energy consumption of the plasma beam. This method enables each particle to not only focus on a single objective but also consider the balance of multiple objectives.

[0071] This algorithm improves the particle swarm optimization algorithm by adopting a weighted dynamic adjustment mechanism for optimization objectives, a real-time feedback mechanism, and an adaptive particle update strategy, and adding soft constraint guidance.

[0072] Among them, the weighted dynamic adjustment mechanism for optimization objectives: can dynamically adjust the weights of stability (S) and energy consumption (E) in the PSO fitness function based on real-time measurement of the plasma beam behavior. In the initial stage, more attention is paid to stability, and after the circuit has been operating for a period of time, it turns to optimizing energy consumption.

[0073] Real-time feedback mechanism: When the circuit parameters change, the response of the plasma beam (such as fluctuations, stability changes, etc.) is monitored in real time and fed back to the PSO algorithm. This can obtain the real-time behavior of the plasma beam through multiple simulations or experimental data sets, and use this feedback information for the dynamic update of particles.

[0074] Adaptive particle update strategy: Dynamically adjust the way of updating the particle velocity according to the stability and response of the plasma beam. For example, during the process of adjusting the circuit parameters, the stability change of the plasma beam is evaluated in real time. If the stability of the plasma beam improves, the particles can be updated more significantly to explore more possible circuit configurations; if the stability decreases, the update amplitude of the particles is reduced to avoid over-adjustment. In the initial stage of the search, a higher weight is given to the individual learning factor to promote extensive exploration; in the convergence stage, the weight of the swarm learning factor is gradually increased to help the algorithm find the optimal solution.

[0075] Add soft constraint guidance: By punishing soft constraints such as excessive voltage, current, frequency, and electrode spacing, it effectively ensures that the optimized circuit parameters not only meet the performance requirements but also do not lead to unrealistic or unsafe working states, enhancing the feasibility and stability of the algorithm.

[0076] This scheme takes the initial circuit operating parameters as the initial position parameters of each particle, and by searching the space of voltage, current, frequency, and electrode spacing, finds the optimal target circuit operating parameters to minimize the fitness function. When the fitness function is minimized, the plasma stability value is the largest and the system energy consumption value is the smallest.

[0077] Step 104: Adjust the initial circuit operating parameters to the target circuit operating parameters.

[0078] Since the target circuit operating parameters can maximize the plasma stability value and minimize the system energy consumption value, adjusting the initial circuit operating parameters to the target circuit operating parameters can improve the boost circuit efficiency of the device using plasma heating and the stability of the plasma beam.

[0079] In summary, in the embodiment of the present invention, the initial circuit operating parameters of the device using plasma heating in the working state are obtained. The initial circuit operating parameters include: the input voltage value of the boost circuit, the current value in the circuit, the operating frequency of the circuit, and the electrode spacing. The electrode spacing represents the spacing between the discharge electrode and the ground electrode of the plasma generator of the device using plasma heating. The device using plasma heating refers to a device that uses the principle of plasma heating as a heat source. The initial circuit operating parameters are input into a preset first model for calculating plasma stability and system energy consumption, and the initial stability value and the initial system energy consumption value of the circuit are obtained. The initial circuit operating parameters are used as the initial position parameters of each particle, and fitness calculation is performed according to the initial position parameters, the initial stability value, the initial system energy consumption value, the first model, and a preset particle swarm optimization algorithm to obtain the target circuit operating parameters that maximize the plasma stability value and minimize the system energy consumption value. The initial circuit operating parameters are adjusted to the target circuit operating parameters. This solution can dynamically adjust the working parameters of the boost circuit through the preset particle swarm optimization algorithm, significantly improve the stability of the plasma, reduce energy consumption, and improve the working efficiency of the device using plasma heating.

[0080] As an optional embodiment, the first model includes a feature extraction layer, a feature fusion layer, a self-attention mechanism layer, and a fully connected layer. Step 102 includes:

[0081] Step 1021: Input the initial circuit operating parameters into the feature extraction layer and the feature fusion layer for primary feature extraction and feature fusion to obtain a first eigenvalue.

[0082] Step 1022: Input the first eigenvalue into the self-attention mechanism layer, and adaptively calculate the target feature weight corresponding to each feature in the first eigenvalue by combining max pooling and average pooling. Weight the first eigenvalue using the target feature weight to obtain a second eigenvalue.

[0083] Step 1023: Input the second eigenvalue into the feature extraction layer for secondary feature extraction to obtain a third eigenvalue.

[0084] Step 1024: Input the third eigenvalue into the fully connected layer for full connection processing, and output the initial stability value and the initial system energy consumption value of the circuit.

[0085] In steps 1021 - 1024, feature extraction and feature fusion are performed on the initial circuit operating parameters to obtain a first eigenvalue.

[0086] The feature extraction layer includes five convolutional layers, and a self-attention mechanism layer is introduced between the fourth convolutional layer and the fifth convolutional layer to adjust the weights of the first eigenvalues. The self-attention mechanism layer can capture the global dependencies between the input features and learn the importance of each feature.

[0087] Specifically, a combination of the max-pooling algorithm and the average-pooling algorithm is used to adaptively calculate the weights of the features in each layer of the first eigenvalues, and the target feature weights of each feature are obtained. The second eigenvalues are obtained by weighting and calculating the first eigenvalues using the target feature weights.

[0088] The second eigenvalues are input into the fifth convolutional layer of the feature extraction layer for further feature extraction to obtain the third eigenvalues.

[0089] After obtaining the third eigenvalues, a fully connected layer is used to further process the features. The fully connected layer includes a first fully connected layer and a second fully connected layer. The output dimension of the first fully connected layer is 64 neurons, and the output shape is [1, 64]; the output dimension of the second fully connected layer is 32 neurons, and the output shape is [1, 32].

[0090] The third eigenvalues are sequentially processed through the first fully connected layer and the second fully connected layer, and the initial stability value of the circuit and the initial system energy consumption value are output.

[0091] The activation function used by the first model can be GELU (Gaussian Error Linear Unit). GELU can provide more refined gradient optimization, which can finely adjust the task of the relationship between the circuit and the plasma beam stability, and can improve the circuit efficiency and the accuracy of beam stability prediction.

[0092] The first model uses the self-attention mechanism to dynamically adjust the weights of each feature in the final output, helping the model understand the mutual relationships between different circuit parameters, so as to better predict the stability and energy consumption of the plasma.

[0093] As an optional embodiment, the feature extraction layer includes a first convolutional layer, a second convolutional layer, a third convolutional layer, a fourth convolutional layer, and a fifth convolutional layer, and step 1021 includes:

[0094] Step 10211: Input the first eigenvalues into the first convolutional layer for feature extraction to obtain the first sub-eigenvalues;

[0095] Step 10212: Input the first eigenvalues into the second convolutional layer for feature extraction to obtain the second sub-eigenvalues;

[0096] Step 10213: Input the second eigenvalues into the third convolutional layer for feature extraction to obtain the third sub-eigenvalues;

[0097] Step 10214: Concatenate the first eigenvalue and the third eigenvalue to obtain a fourth sub - eigenvalue;

[0098] Step 10215: Input the fourth eigenvalue into the fourth convolutional layer for feature extraction to obtain a fifth sub - eigenvalue;

[0099] Step 10216: Concatenate the second sub - eigenvalue and the fifth sub - eigenvalue to obtain a first eigenvalue.

[0100] In steps 10211 - 10216, the feature extraction layer includes 5 convolutional layers. 1D (one - dimensional) convolution is used to extract features from 4 dimensions of the input voltage value, current value, operating frequency, and electrode spacing. At the same time, cross - layer connection is used for feature fusion to learn higher - dimensional features.

[0101] Among them, the first convolutional layer is a 1D convolution, outputting 32 feature maps with an output shape of [1, 32];

[0102] The second convolutional layer is a 1D convolution, outputting 64 feature maps with an output shape of [1, 64];

[0103] The third convolutional layer is a 1D convolution, outputting 128 feature maps with an output shape of [1, 128];

[0104] The fourth convolutional layer is a 1D convolution, outputting 64 feature maps with an output shape of [1, 64];

[0105] The fifth convolutional layer is a 1D convolution, outputting 32 feature maps with an output shape of [1, 32].

[0106] First, input the first eigenvalue into the first convolutional layer for feature extraction to obtain a first sub - eigenvalue; input the first eigenvalue into the second convolutional layer for feature extraction to obtain a second sub - eigenvalue; input the second eigenvalue into the third convolutional layer for feature extraction to obtain a third sub - eigenvalue.

[0107] Then, connect the first convolutional layer and the third convolutional layer. That is, concatenate the first sub - eigenvalue (32 features) and the third sub - eigenvalue (128 features) through concat to obtain a fourth sub - eigenvalue with an output shape of [1, 160]. Input the fourth sub - eigenvalue into the fourth convolutional layer for feature extraction to obtain a fifth sub - eigenvalue.

[0108] Then, connect the second convolutional layer and the fourth convolutional layer. That is, concatenate the second sub - eigenvalue (64 features) and the fifth sub - eigenvalue (64 features) through concat to obtain a first eigenvalue with an output shape of [1, 128].

[0109] As an alternative embodiment, the loss function of the first model during training includes a first error term, a second error term, and a regularization term;

[0110] The first error term represents the mean square error between the predicted plasma stability value and the true plasma stability value; the second error term represents the mean square error between the predicted system energy consumption value and the true system energy consumption value; the regularization term is used to control the physical rationality of the circuit operating parameters.

[0111] In the embodiment of the present invention, the loss function of the first model is a weighted multi-objective loss function, which combines the loss terms of multiple objectives such as plasma stability, energy consumption optimization, and physical rationality of circuit parameters, and achieves the balance of different objectives through weighting.

[0112] The loss function is as follows:

[0113]

[0114] Where, is the first error term, representing the mean square error between the predicted plasma stability value and the true plasma stability value; represents the second error term, representing the mean square error between the predicted system energy consumption value and the true system energy consumption value; represents the regularization term, which is used to control the physical rationality of the circuit operating parameters (the input voltage value of the boost circuit, the current value in the circuit, the operating frequency of the circuit, and the electrode spacing), and the regularization term can avoid over-optimizing a certain parameter.

[0115] During the model training process, based on the designed weighted multi-objective loss function, the loss function is minimized by the gradient descent method, and the model will continuously update the weights of the network during training. After each forward propagation to calculate the prediction result, the loss function evaluates the difference between the predicted value and the actual value, calculates the gradient through the backpropagation algorithm, and updates the network parameters. As the training progresses, the network will more and more accurately predict the impact of circuit parameters on stability and energy consumption.

[0116] The optimization algorithm in the training process of the first model adopts the Adam optimizer. The Adam optimizer shows good performance during training, can automatically adjust the learning rate, thereby accelerating convergence and improving training stability.

[0117] After training the initial first model, the first model is obtained. During the training process, first, the input voltage (V), current (I), frequency (f), and electrode spacing (d) are normalized and then passed to the input layer of the initial first model. The first to fifth convolutional layers extract low-level to high-level features from the input circuit parameters. Through 1D convolutional operations, the network identifies the relationships and patterns between different parameters. Cross-layer connections concatenate the outputs of the previous convolutional layers to integrate information from different levels, which helps enhance the feature representation ability, retain more information, and reduce information loss.

[0118] The self-attention mechanism calculates the relationships between input features and dynamically adjusts the importance of each feature to help the model capture the global dependencies between different circuit parameters. The weighted features output by the self-attention mechanism layer will enter the fully connected layer. Through the fully connected layer, the network transforms the features from high-dimensional to low-dimensional. The features processed by the fully connected layer will be passed to the output layer. The output layer contains 2 neurons, corresponding to the stability (S) of the plasma and the system energy consumption (E) respectively.

[0119] As an optional embodiment, step 103 includes:

[0120] Step 1031: Initialize the particle swarm parameters; the particle swarm parameters at least include the number of particles, the position range and velocity range of each particle, the inertia weight of the particle, the initial stability weight, and the initial energy consumption weight; the position range is from the minimum value to the maximum value of the circuit operating parameters.

[0121] Step 1032: Use the initial circuit operating parameters as the initial position parameters of each particle;

[0122] Step 1033: Randomly generate the initial position and initial velocity of each particle in the initial state within the position range and the velocity range, and generate the initial individual optimal position and initial global optimal position of each particle;

[0123] Step 1034: Calculate the initial fitness of each particle according to the initial stability weight, the initial energy consumption weight, the initial position parameters, the initial system energy consumption value, the initial stability value, and a preset fitness function;

[0124] Step 1035: Update the velocity of the particles within the velocity range according to the particle swarm parameters and a preset velocity update function to obtain the updated velocity;

[0125] Step 1036: Update the position of the particles within the position range according to the updated velocity and the initial position of the particles to obtain the updated position;

[0126] Step 1037: Calculate the new fitness of the particle based on the position parameters of the particle at the updated position.

[0127] Step 1038: If the new fitness is greater than the individual historical optimal value, then use the new fitness value as the current individual optimal value; if the new fitness is greater than the global historical optimal value, then use the new fitness value as the current global optimal value.

[0128] Step 1039: When the preset maximum number of iterations is reached or the fitness reaches the preset convergence threshold, stop the calculation, obtain the position parameters of the particle at the global optimal value, and get the optimal circuit parameters; the optimal circuit parameters are the target circuit operating parameters that maximize the plasma stability value and minimize the system energy consumption value.

[0129] In steps 1031 - 1039, first, define the following parameter ranges and objectives:

[0130] Voltage V: The input voltage of the circuit, with a range of 100V to 1000V; Current I: The operating current of the circuit, with a range of 1A to 10A; Frequency f: The operating frequency of the circuit, with a range of 50Hz to 200Hz; Electrode spacing d: The distance between the electrodes, with a range of 1mm to 10mm.

[0131] The objective of the algorithm optimization is to minimize the energy consumption and maximize the stability of the plasma beam by optimizing these circuit parameters. Therefore, it is necessary to design a fitness function to evaluate the performance of each combination of circuit parameters.

[0132] The fitness function is the core of the PSO optimization, which determines the performance of the state parameters (i.e., the combination of circuit parameters) of each particle. In this solution, the fitness function considers two main factors:

[0133] Stability of the plasma beam: Usually, there is a strong correlation between stability and voltage and current, which can be quantified through simulation calculations or experimental data; Energy consumption: The energy consumption of the circuit is usually proportional to the product of voltage and current.

[0134] Then, initialize the particle swarm parameters.

[0135] Specifically, the following particle swarm parameters can be set:

[0136] Number of particles N: The number of particles affects the comprehensiveness of the search and the convergence speed. Set it to 50.

[0137] Dimension D: The dimension of each particle corresponds to the optimization variable, and the dimension is 4 (voltage V, current I, frequency f, electrode spacing d).

[0138] Particle position: The position range of the particle is the minimum and maximum values of the circuit parameters.

[0139] Voltage V range: 100V to 1000V.

[0140] Current I range: 1A to 10A.

[0141] Frequency f range: 50Hz to 200Hz.

[0142] Electrode spacing d range: 1mm to 10mm.

[0143] Speed range: Control the variation amplitude of the particle in the search space, set to 10% - 20%.

[0144] Inertia weight: The initial value is set to 0.9 and gradually decays to 0.4. The strategy of inertia weight decay adopts adaptive adjustment and dynamically adjusts according to the fitness to improve the speed.

[0145] Individual learning factor and swarm learning factor: Set to 2.0, indicating the weight balance between the individual and the swarm. In the initial stage of the search, give a higher weight to the individual learning factor to promote extensive exploration; in the convergence stage, gradually increase the weight of the swarm learning factor to help the algorithm find the optimal solution.

[0146] Weight coefficient of stability and energy consumption: In the initial stage, the weight coefficient is set to α = 1.0, β = 0.5, focusing on stability optimization; as the algorithm iterates, gradually adjust to α = 0.5, β = 1.0, paying more attention to energy consumption optimization.

[0147] Maximum number of iterations: 300.

[0148] Fitness convergence threshold: 0.0005.

[0149] The state of each particle represents a set of circuit parameters (i.e., voltage, current, frequency, and electrode spacing), and the initial circuit operating parameters are used as the initial position parameters of each particle. Within the position range and speed range, randomly generate the initial position and initial speed of each particle in the initial state, and generate the initial individual optimal position and initial global optimal position of each particle. Then evaluate the performance of these parameter combinations through the fitness function to obtain the initial fitness.

[0150] According to the particle swarm parameters and the preset speed update function, update the speed of the particle within the speed range to obtain the updated speed; according to the updated speed and the initial position of the particle, update the position of the particle within the position range to obtain the updated position.

[0151] Based on the position parameters of the particles at the updated position (i.e., voltage, current, frequency, and electrode spacing), calculate the new fitness of the particles. If the new fitness is greater than the individual historical optimal value , then update , that is, take the new fitness value as the current individual optimal value; if the new fitness is greater than the global historical optimal value , then update , that is, take the new fitness value as the current global optimal value.

[0152] When the preset maximum number of iterations is reached or the fitness reaches the preset convergence threshold, stop the calculation, obtain the position parameters of the particles at the global optimal value, and obtain the optimal circuit parameters, that is, the optimal input voltage value, the optimal current value, the optimal operating frequency, and the optimal electrode spacing. The optimal circuit parameters are the target circuit operating parameters that maximize the plasma stability value and minimize the system energy consumption value.

[0153] As an alternative embodiment, step 1035 includes:

[0154] Step 10351, calculate the first difference between the initial individual optimal position and the initial position of the particle, and the second difference between the initial global optimal position and the initial position;

[0155] Step 10352, determine the product of the first difference, the individual learning factor, and the preset first random number to obtain the first product; and determine the product of the second difference, the global learning factor, and the preset second random number to obtain the second product;

[0156] Step 10353, determine the product of the inertia weight and the initial velocity of the particle to obtain the third product;

[0157] Step 10354, determine the sum of the first product, the second product, and the third product to obtain the initial update velocity;

[0158] Step 10355, if the initial update velocity is within the velocity range, take the initial update velocity as the update velocity.

[0159] In steps 10351 - 10355, the velocity update function is as follows:

[0160]

[0161] Among them, represents the velocity at time t + 1, represents the velocity at time t. W represents the inertia weight, represents the initial individual optimal position, represents the initial position of the particle, Represents the initial global optimal position, respectively represent the individual learning factor and the group learning factor, 、 respectively represent the first random number and the second random number, and the ranges of the first random number and the second random number are [0, 1].

[0162] If the t moment can represent the initial moment, then represents the initial velocity represents the initial update velocity. Determine whether the initial update velocity is within the preset velocity range. If so, use the initial update velocity as the update velocity. If not, use the maximum velocity within the velocity range as the update velocity.

[0163] In addition, an adaptive update strategy is also adopted to adjust the velocity update amplitude of the particles. Specifically, the update amplitude of the particles is adjusted according to the change in the stability of the circuit parameters. If the stability of the circuit parameters improves, the velocity of the particles increases for a wider search; if the stability of the circuit parameters decreases, the velocity of the particles decreases to avoid over-adjustment.

[0164] As an alternative embodiment, step 1036 includes:

[0165] According to the update velocity, the initial position of the particle, and a preset position update function, perform position update of the particle within the position range to obtain an updated position.

[0166] The position update function is as follows:

[0167]

[0168] where, represents the updated position, represents the initial position, represents the update velocity.

[0169] Limit the position within the preset position range to ensure that the updated position of the particle is within the allowable ranges of voltage, current, frequency, and electrode spacing. The position update will perform range correction at each iteration to ensure that the particle does not go out of the search space.

[0170] As an alternative embodiment, step 1034 includes:

[0171] Step 10341: Input the initial position parameters into the first model to obtain an initial plasma stability value and an initial system energy consumption value;

[0172] Step 10342: Substitute the initial position parameters into a preset regularization term to obtain a regularization value;

[0173] Step 10343: Determine the product of the initial stability weight and the initial plasma stability value to obtain a stability product; and determine the product of the initial energy consumption weight and the initial system energy consumption value to obtain an energy consumption product.

[0174] Step 10344: Determine the difference between the energy consumption product and the stability product, and determine the sum of the difference and the regularization value, and use the sum as the initial fitness of the particle.

[0175] In Steps 10341 - 10344, first input the initial position parameters into the first model, and the first model outputs the initial plasma stability value and the initial system energy consumption value.

[0176] Then, using the initial stability weight, the initial energy consumption weight, the initial position parameters, the initial system energy consumption value, the initial stability value, and a preset fitness function, calculate the initial fitness of each particle.

[0177] Specifically, the fitness function is expressed as a combination of the system energy consumption E and the stability S of the plasma beam. The goal is to maximize S and minimize E. Therefore, the fitness function can be expressed as:

[0178]

[0179] Where, is a regularization term used to control the physical rationality of circuit parameters (voltage 、current 、frequency 、electrode spacing ). This regularization term can avoid over - optimizing a certain parameter.

[0180] E represents the system energy consumption, and S represents the stability of the plasma.

[0181] and are the weight coefficients of stability and energy consumption, and γ is the weight coefficient of the regularization term, which controls the influence of the constrained parameters on the fitness function.

[0182] As an optional embodiment, after Step 1038, it further includes:

[0183] Dynamically adjust the stability weight and the energy consumption weight according to the number of iterations.

[0184] In the embodiments of the present invention, the weights of stability and energy consumption are dynamically adjusted according to the number of iterations. In the initial stage of iteration, more attention is paid to stability, that is, the stability weight is greater than the energy consumption weight; in the later stage of iteration, it gradually turns to energy consumption optimization, that is, the energy consumption weight is greater than the stability weight.

[0185] In this solution, the circuit parameters are dynamically optimized through an adaptive multi-objective particle swarm optimization algorithm, considering stability, energy consumption, and physical constraints simultaneously. The real-time feedback mechanism and adaptive particle update strategy in the algorithm can be adjusted according to the real-time behavior of the circuit, thus improving the optimization efficiency and the quality of the solution. By dynamically adjusting the weights of the fitness function, the optimization process can prioritize stability or energy consumption at different stages, and finally obtain the optimal circuit parameters that meet the requirements.

[0186] In summary, the circuit operating parameter adjustment method provided by this solution realizes the real-time optimization of circuit parameters through the combination of deep neural network simulation and particle swarm optimization algorithm. This method can significantly improve the working efficiency of equipment using plasma heating, reduce energy consumption, and enhance the stability and output quality of the plasma beam, and has good application value in the field of equipment using plasma heating.

[0187] Figure 2 It is the structural block diagram of a circuit operating parameter adjustment device provided by an embodiment of the present invention. As Figure 2 shown, the device 200 includes:

[0188] A parameter acquisition module 201, configured to acquire the initial circuit operating parameters of the equipment using plasma heating in the working state, where the initial circuit operating parameters include: the input voltage value of the boost circuit, the current value in the circuit, the operating frequency of the circuit, and the electrode spacing; the electrode spacing represents the spacing between the discharge electrode and the ground electrode of the plasma generator of the equipment using plasma heating; the equipment using plasma heating refers to the equipment using the plasma heating principle as the heat source;

[0189] A calculation module 202, configured to input the initial circuit operating parameters into a preset first model for plasma stability and system energy consumption calculation, and obtain the initial stability value and the initial system energy consumption value of the circuit;

[0190] A target parameter determination module 203, configured to use the initial circuit operating parameters as the initial position parameters of each particle, and perform fitness calculation according to the initial position parameters, the initial stability value, the initial system energy consumption value, the first model, and a preset adaptive multi-objective particle swarm optimization algorithm, so as to obtain the target circuit operating parameters that maximize the plasma stability value and minimize the system energy consumption value;

[0191] An adjustment module 204, configured to adjust the initial circuit operating parameters to the target circuit operating parameters.

[0192] Regarding the device in the above embodiments, the specific manners in which each module performs operations have been described in detail in the embodiments related to the method, and will not be elaborated here.

[0193] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. This computer program can be stored in a non-volatile computer-readable storage medium. When this computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the various embodiments provided in this application can include non-volatile and / or volatile memories. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0194] After considering the specification and practicing the invention disclosed herein, those skilled in the art will readily conceive of other embodiments of the present disclosure. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include known common knowledge or conventional technical means in the technical field not disclosed in the present disclosure. The specification and embodiments are only to be considered as exemplary, and the true scope and spirit of the present disclosure are pointed out by the following claims.

[0195] It should be understood that the present disclosure is not limited to the exact structures described above and shown in the drawings, and various modifications and changes can be made without departing from its scope. The scope of the present disclosure is only limited by the appended claims.

Claims

1. A method for adjusting circuit operating parameters, characterized in that, The method includes: Obtaining initial circuit operating parameters of a device using plasma heating in a working state, where the initial circuit operating parameters include: the input voltage value of the boost circuit, the current value in the circuit, the operating frequency of the circuit, and the electrode spacing; the electrode spacing represents the spacing between the discharge electrode and the ground electrode of the plasma generator of the device using plasma heating; the device using plasma heating is a device that converts electrical energy into a high-temperature plasma flame using the principle of plasma heating; Inputting the initial circuit operating parameters into a preset first model for plasma stability and system energy consumption calculation to obtain the initial stability value and the initial system energy consumption value of the circuit; Taking the initial circuit operating parameters as the initial position parameters of each particle, and performing fitness calculation according to the initial position parameters, the initial stability value, the initial system energy consumption value, the first model, and a preset adaptive multi-objective particle swarm optimization algorithm to obtain the target circuit operating parameters that maximize the plasma stability value and minimize the system energy consumption value; Adjusting the initial circuit operating parameters to the target circuit operating parameters; The first model includes a feature extraction layer, a feature fusion layer, a self-attention mechanism layer, and a fully connected layer. The step of inputting the initial circuit operating parameters into the preset first model for plasma stability and system energy consumption calculation to obtain the initial stability value and the initial system energy consumption value of the circuit includes: Inputting the initial circuit operating parameters into the feature extraction layer and the feature fusion layer for primary feature extraction and feature fusion to obtain a first eigenvalue; Inputting the first eigenvalue into the self-attention mechanism layer, adaptively calculating the target feature weight corresponding to each feature in the first eigenvalue using a combination of max pooling and average pooling, and weighting the first eigenvalue using the target feature weight to obtain a second eigenvalue; Inputting the second eigenvalue into the feature extraction layer for secondary feature extraction to obtain a third eigenvalue; Inputting the third eigenvalue into the fully connected layer for full connection processing, and outputting the initial stability value and the initial system energy consumption value of the circuit.

2. The method according to claim 1, characterized in that, The feature extraction layer includes a first convolutional layer, a second convolutional layer, a third convolutional layer, a fourth convolutional layer, and a fifth convolutional layer. The step of inputting the initial circuit operating parameters into the feature extraction layer and the feature fusion layer for primary feature extraction and fusion to obtain a first eigenvalue includes: Inputting the first eigenvalue into the first convolutional layer for feature extraction to obtain a first sub-eigenvalue; Inputting the first eigenvalue into the second convolutional layer for feature extraction to obtain a second sub-eigenvalue; Inputting the second eigenvalue into the third convolutional layer for feature extraction to obtain a third sub-eigenvalue; Concatenating the first sub-eigenvalue and the third sub-eigenvalue to obtain a fourth sub-eigenvalue; Inputting the fourth sub-eigenvalue into the fourth convolutional layer for feature extraction to obtain a fifth sub-eigenvalue; Concatenating the second sub-eigenvalue and the fifth sub-eigenvalue to obtain a first eigenvalue.

3. The method according to claim 1, wherein The loss function of the first model during the training process includes a first error term, a second error term, and a regularization term; The first error term represents the mean square error between the predicted plasma stability value and the true plasma stability value; The second error term represents the mean square error between the predicted system energy consumption value and the true system energy consumption value; The regularization term is used to control the physical rationality of the circuit operating parameters.

4. The method according to claim 1, characterized in that, The step of taking the initial circuit operating parameters as the initial position parameters of each particle and performing fitness calculation according to the initial position parameters, the initial stability value, the initial system energy consumption value, the first model, and a preset adaptive multi-objective particle swarm optimization algorithm includes: Initializing particle swarm parameters; the particle swarm parameters at least include the number of particles, the position range and velocity range of each particle, the inertia weight of the particle, the initial stability weight, and the initial energy consumption weight; the position range is from the minimum value to the maximum value of the circuit operating parameters; Taking the initial circuit operating parameters as the initial position parameters of each particle; Within the position range and the velocity range, randomly generate the initial position and initial velocity of each particle in the initial state, and generate the initial individual best position and initial global best position of each particle; Calculate the initial fitness of each particle according to the initial stability weight, the initial energy consumption weight, the initial position parameters, the initial system energy consumption value, the initial stability value, and a preset fitness function; According to the particle swarm parameters and a preset velocity update function, update the velocity of the particle within the velocity range to obtain an updated velocity; According to the updated velocity and the initial position of the particle, update the position of the particle within the position range to obtain an updated position; Calculate the new fitness of the particle based on the position parameters of the particle at the updated position; If the new fitness is greater than the individual historical best value, then take the new fitness as the current individual best value; if the new fitness is greater than the global historical best value, then take the new fitness as the current global best value; When reaching the preset maximum number of iterations or the fitness reaches the preset convergence threshold, stop the calculation, obtain the position parameters of the particle at the global best value, and obtain the optimal circuit parameters; the optimal circuit parameters are the target circuit operating parameters that maximize the plasma stability value and minimize the system energy consumption value.

5. The method according to claim 4, wherein The step of according to the particle swarm parameters and a preset velocity update function, updating the velocity of the particle within the velocity range to obtain an updated velocity includes: Calculating a first difference between the initial individual best position and the initial position of the particle, and a second difference between the initial global best position and the initial position of the particle; Determining the product of the first difference, the individual learning factor, and a preset first random number to obtain a first product; and determining the product of the second difference, the global learning factor, and a preset second random number to obtain a second product; Determining the product of the inertia weight and the initial velocity of the particle to obtain a third product; Determine the sum of the first product, the second product, and the third product to obtain an initial update speed. If the initial update speed is within the speed range, use the initial update speed as the update speed.

6. The method according to claim 4, wherein The calculating the initial fitness of each particle according to the initial stability weight, the initial energy consumption weight, the initial position parameter, the initial system energy consumption value, the initial stability value, and a preset fitness function includes: Input the initial position parameter into the first model to obtain an initial plasma stability value and an initial system energy consumption value. Substitute the initial position parameter into a preset regularization term to obtain a regularization value. Determine the product of the initial stability weight and the initial plasma stability value to obtain a stability product; and determine the product of the initial energy consumption weight and the initial system energy consumption value to obtain an energy consumption product. Determine the difference between the energy consumption product and the stability product, and determine the sum of the difference and the regularization value, and use the sum as the initial fitness of the particle.

7. A device for adjusting circuit operating parameters, characterized in that, The device includes: A parameter acquisition module, configured to acquire initial circuit operation parameters of a device using plasma heating during a working state, where the initial circuit operation parameters include: an input voltage value of a boost circuit, a current value in the circuit, a working frequency of the circuit, and an electrode spacing; the electrode spacing represents the spacing between a discharge electrode and a ground electrode of a plasma generator of the device using plasma heating; the device using plasma heating refers to a device using the plasma heating principle as a heat source. A calculation module, configured to input the initial circuit operation parameters into a preset first model for plasma stability and system energy consumption calculation to obtain an initial stability value and an initial system energy consumption value of the circuit. A target parameter determination module, configured to use the initial circuit operation parameters as the initial position parameters of each particle, and perform fitness calculation according to the initial position parameters, the initial stability value, the initial system energy consumption value, the first model, and a preset adaptive multi-objective particle swarm optimization algorithm to obtain target circuit operation parameters that maximize the plasma stability value and minimize the system energy consumption value. An adjustment module, configured to adjust the initial circuit operation parameters to the target circuit operation parameters. The first model includes a feature extraction layer, a feature fusion layer, a self-attention mechanism layer, and a fully connected layer. Specifically, the calculation module is configured to: Input the initial circuit operation parameters into the feature extraction layer and the feature fusion layer for primary feature extraction and feature fusion to obtain a first eigenvalue. Input the first eigenvalue into the self-attention mechanism layer, adaptively calculate the target feature weight corresponding to each feature in the first eigenvalue by combining max pooling and average pooling, and weight the first eigenvalue using the target feature weight to obtain a second eigenvalue. Input the second eigenvalue into the feature extraction layer for secondary feature extraction to obtain a third eigenvalue. Input the third eigenvalue into the fully connected layer for fully connected processing, and output the initial stability value and the initial system energy consumption value of the circuit.

8. A device using plasma heating, characterized in that, Includes: A controller; A memory for storing executable instructions of the controller; Wherein, the controller is configured to execute the instructions to implement the circuit operation parameter adjustment method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, When the instructions in the computer-readable storage medium are executed by a controller of a device using plasma heating, the device using plasma heating is enabled to execute the circuit operation parameter adjustment method according to any one of claims 1 to 6.

Images