Intelligent parameter control method and system for ultrasonic generator

Abstract

The present application provides an intelligent parameter control method and system for an ultrasonic generator, and relates to the field of parameter control technology. The method includes: by collecting the operating status information of the ultrasonic generator, combining the adaptive learning mechanism to construct a parameter control model. According to the work requirements, multiple evaluation indicators are analyzed, and the target parameter optimization function is established to obtain the optimization constraint. The optimal control parameters are obtained among multiple groups of control parameters, and the control instructions are generated to achieve intelligent control. Through this application, it can be solved that the existing technology cannot use real-time data analysis and intelligent decision-making algorithms, resulting in the inability of the ultrasonic generator to dynamically adjust parameters according to the working environment and task requirements, further affecting the output efficiency, stability and reliability of the ultrasonic generator, as well as the user experience and satisfaction, to achieve efficient, stable and safe operation, improve the automation level of the equipment, and enhance the adaptability and ease of operation of the equipment.

Description

Technical Field

[0001] The present application relates to the technical field of parameter control, and in particular to an intelligent parameter control method and system for an ultrasonic generator. Background Art

[0002] Ultrasonic generator is a key device in ultrasonic technology, mainly used to generate ultrasonic signals. Ultrasonic waves are widely used in many fields such as medicine, industry, and military due to their high frequency, short wavelength, large propagation energy, and strong penetration ability. With the continuous advancement of technology, the control accuracy, stability, and efficiency of ultrasonic generators are increasingly required. Therefore, an intelligent parameter control method for ultrasonic generators has been developed.

[0003] Currently, existing ultrasonic generator control technologies often rely on the operator's experience and fixed procedures, and lack flexibility and adaptability.

[0004] In summary, the existing technology cannot utilize real-time data analysis and intelligent decision-making algorithms, resulting in the inability of the ultrasonic generator to dynamically adjust parameters according to the working environment and task requirements, further affecting the output efficiency, stability and reliability of the ultrasonic generator, as well as the user experience and satisfaction. Summary of the invention

[0005] The purpose of this application is to provide an intelligent parameter control method and system for an ultrasonic generator, so as to solve the problem that the existing technology cannot utilize real-time data analysis and intelligent decision-making algorithms, resulting in the inability of the ultrasonic generator to dynamically adjust parameters according to the working environment and task requirements, further affecting the output efficiency, stability and reliability of the ultrasonic generator, as well as the user experience and satisfaction.

[0006] In view of the above problems, the present application provides an intelligent parameter control method and system for an ultrasonic generator.

[0007] In the first aspect, the present application provides an intelligent parameter control method for an ultrasonic generator, which is implemented by an intelligent parameter control system for an ultrasonic generator, wherein the method includes: collecting operating status information of the ultrasonic generator; extracting features of the operating status information according to the output characteristics of the ultrasonic generator to generate operating status features, including environmental information features and equipment operating features; combining an adaptive learning mechanism to construct a parameter control model based on the environmental information features and the equipment operating features; obtaining multiple groups of control parameters according to work requirements and the parameter control model; analyzing work requirements to obtain multiple evaluation indicators, establishing a target parameter optimization function according to the multiple evaluation indicators, and obtaining optimization constraints; optimizing among the multiple groups of control parameters according to the optimization constraints to obtain optimal control parameters; generating control instructions according to the optimal control parameters, and inputting them into the ultrasonic generator for intelligent control.

[0008] In a second aspect, the present application also provides an intelligent parameter control system for an ultrasonic generator, which is used to execute an intelligent parameter control method for an ultrasonic generator as described in the first aspect, wherein the system includes: an information acquisition module, which is used to collect operating status information of the ultrasonic generator; a feature extraction module, which is used to extract features of the operating status information according to the output characteristics of the ultrasonic generator, and generate operating status features, including environmental information features and equipment operating features; a model construction module, which is used to combine an adaptive learning mechanism to build a parameter control model based on the environmental information features and the equipment operating characteristics; a parameter acquisition module, which is used to obtain multiple groups of control parameters according to work requirements and the parameter control model; an optimization constraint acquisition module, which is used to analyze work requirements, obtain multiple evaluation indicators, establish a target parameter optimization function according to the multiple evaluation indicators, and obtain optimization constraints; a control parameter acquisition module, which is used to optimize among the multiple groups of control parameters according to the optimization constraints to obtain optimal control parameters; an intelligent control module, which is used to generate control instructions according to the optimal control parameters, and input them into the ultrasonic generator for intelligent control.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0010] The method collects the operating status information of the ultrasonic generator; extracts the features of the operating status information according to the output characteristics of the ultrasonic generator to generate operating status features, including environmental information features and equipment operating features; constructs a parameter control model based on the environmental information features and the equipment operating features in combination with an adaptive learning mechanism; obtains multiple groups of control parameters according to work requirements and the parameter control model; analyzes work requirements to obtain multiple evaluation indicators, establishes a target parameter optimization function according to the multiple evaluation indicators, and obtains optimization constraints; performs optimization among the multiple groups of control parameters according to the optimization constraints to obtain optimal control parameters; generates control instructions according to the optimal control parameters and inputs them into the ultrasonic generator for intelligent control, which effectively solves the problem that the existing technology cannot use real-time data analysis and intelligent decision-making algorithms, resulting in the inability of the ultrasonic generator to dynamically adjust parameters according to the working environment and task requirements, further affecting the output efficiency, stability and reliability of the ultrasonic generator, as well as the user experience and satisfaction, thereby achieving efficient, stable and safe operation, improving the automation level of the equipment, and enhancing the adaptability and ease of operation of the equipment.

[0011] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0013] Figure 1 This is a flow chart of an intelligent parameter control method for an ultrasonic generator according to the present application.

[0014] Figure 2 This is a schematic diagram of the structure of an intelligent parameter control system for an ultrasonic generator according to the present application.

[0015] Description of reference numerals:

[0016] Information collection module 11, feature extraction module 12, model construction module 13, parameter acquisition module 14, optimization constraint acquisition module 15, control parameter acquisition module 16, intelligent control module 17. DETAILED DESCRIPTION

[0017] The present application provides an intelligent parameter control method and system for an ultrasonic generator, which solves the problem that the existing technology cannot utilize real-time data analysis and intelligent decision-making algorithms, resulting in the inability of the ultrasonic generator to dynamically adjust parameters according to the working environment and task requirements, further affecting the output efficiency, stability and reliability of the ultrasonic generator, as well as the user experience and satisfaction, thereby achieving efficient, stable and safe operation, improving the automation level of the equipment, and enhancing the adaptability and ease of operation of the equipment.

[0018] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

[0019] Embodiment 1

[0020] Please see attached Figure 1 The present application provides an intelligent parameter control method for an ultrasonic generator, wherein the method is applied to an intelligent parameter control system for an ultrasonic generator, and the method specifically comprises the following steps:

[0021] S1: Collect the operating status information of the ultrasonic generator.

[0022] Specifically, temperature sensors are used to monitor the operating temperature of the ultrasonic generator, because temperature changes can affect the performance of its electronic components and the propagation efficiency of ultrasonic waves. Humidity sensors monitor ambient humidity, because humidity changes may affect the circuit performance of the ultrasonic generator and the corrosion of mechanical parts. Pressure sensors are used to detect the pressure applied inside or outside the ultrasonic generator to ensure that it works at the appropriate pressure. Vibration sensors monitor the vibration state of the ultrasonic transducer to evaluate its working effect and possible damage. Current sensors measure the output current of the ultrasonic generator to indirectly understand its power output and energy consumption. Voltage sensors monitor the stability of the output voltage, because voltage fluctuations may affect the strength and frequency of the ultrasonic signal. Use a microcontroller or data acquisition card to collect the above sensor data. Automatically read data from the sensor at fixed time intervals, such as milliseconds or seconds. Make sure the sampling rate of the data acquisition system is high enough to capture rapid changes in the operation of the ultrasonic generator.

[0023] S2: Extracting features of the operating status information according to the output characteristics of the ultrasonic generator to generate operating status features, including environmental information features and equipment operating features.

[0024] Specifically,

[0025] Environmental information features include temperature features, including average temperature, temperature fluctuation range, temperature trend, etc.; humidity features, including relative humidity, humidity change rate, etc.; pressure features, including pressure size, pressure stability, etc. Equipment operation features include electrical features, including output current, output voltage, power consumption, power factor, etc.; vibration features, including vibration frequency, vibration amplitude, vibration mode, etc.; acoustic features, including ultrasonic frequency, amplitude, waveform, phase, etc.; performance features, including transducer efficiency, equipment response time, working stability, etc.; fault features, including abnormal vibration mode, abnormal fluctuations in current or voltage, which may be early signs of equipment failure. Clean, denoise and normalize the collected data to eliminate the influence of measurement errors and outliers. Analyze the change trend of data on the time axis and extract relevant time domain features. Convert time domain data to frequency domain through Fourier transform and other methods to analyze the frequency components and energy distribution of the signal. Calculate data statistics, such as mean, variance, standard deviation, correlation coefficient, etc., to capture the statistical characteristics of the data.

[0026] S3: In combination with an adaptive learning mechanism, a parameter control model is constructed based on the environmental information characteristics and the equipment operation characteristics.

[0027] Specifically, organize and annotate the historical data collected from the ultrasonic generator, including environmental information features and equipment operation features. Ensure the quality and diversity of the data so that the model can learn the behavior patterns under different working conditions. Select appropriate machine learning models according to the complexity of the problem, such as linear regression, support vector machine, neural network, random forest, etc. Further process the extracted features, such as feature scaling, dimensionality reduction, interactive feature construction, etc., to improve the predictive ability of the model. Use feature selection techniques to determine the most influential features and reduce the complexity of the model and the risk of overfitting. Train the model using historical data and minimize the prediction error by adjusting the model parameters. Apply adaptive learning mechanisms, such as online learning or incremental learning, so that the model can be continuously updated and improved as new data arrives. Use an independent validation set to evaluate the performance of the model to ensure that the model has good generalization ability. Optimize the performance of the model on unknown data by adjusting the model structure and parameters.

[0028] S4: Obtain multiple groups of control parameters according to work requirements and the parameter control model.

[0029] Specifically, determine the specific goals of the ultrasonic generator in actual applications, such as the required ultrasonic power, frequency, waveform, action time, etc. Convert the work requirements into an input format that the model can understand, such as a numerical value, category, or vector. If the work requirements contain multiple goals, you may need to define priorities or weights for each goal. Use the parameter control model that has been built and trained to predict the best combination of control parameters based on the input work requirements. The model may output a series of parameter values, including the frequency, amplitude, pulse period, etc. of the ultrasonic generator. Based on the model prediction, generate multiple sets of possible control parameters. These parameter sets represent potential solutions under different control strategies.

[0030] S5: Analyze work requirements to obtain multiple evaluation indicators, establish a target parameter optimization function based on the multiple evaluation indicators, and obtain optimization constraints.

[0031] Specifically, determine the key performance indicators of the ultrasonic generator in operation, such as power output, frequency stability, energy efficiency, service life, cost-effectiveness, etc. Considering the working environment and technical limitations, determine which indicators are the most important. According to the work requirements, define multiple evaluation indicators, which should be able to fully reflect the performance of the ultrasonic generator. For example, power output may be an indicator, and its goal is to reduce power consumption as much as possible while ensuring the effect. Use the defined evaluation indicators to construct an objective function, which is usually a multivariate function of the control parameters. The objective function may be a utility function to be maximized or a cost function to be minimized, depending on the evaluation indicators and the optimization goal. According to the work requirements and technical specifications, determine the constraints of the optimization. These constraints can be upper and lower limits on parameter values, relationships between parameters, safety standards, etc. Constraints ensure that the optimization solution found is not only valid in theory, but also feasible and safe in practical applications.

[0032] S6: Optimizing among the multiple groups of control parameters according to the optimization constraints to obtain the optimal control parameters.

[0033] Specifically, determine the range of values ​​of the control parameters, that is, the parameter space. Each parameter has an upper and lower limit, which depends on the physical limitations and technical specifications of the ultrasonic generator. Use heuristic algorithms such as genetic algorithms, simulated annealing, particle swarm optimization, and ant colony optimization. Initialize the parameters of the optimization algorithm, such as learning rate, number of iterations, population size, crossover rate, mutation rate, etc. These parameters will affect the convergence speed and final results of the algorithm. Use the selected optimization algorithm to search in the parameter space to find the parameter combination that can maximize or minimize the objective function value. The algorithm will continuously evaluate the performance of the parameter combination and adjust the parameter value based on the evaluation results. During the optimization process, ensure that all solutions meet the pre-set constraints. Solutions that do not meet the constraints will be discarded or adjusted. The satisfaction of constraints is usually achieved through penalty functions or constrained optimization methods. Determine whether the optimization algorithm has converged to the optimal solution or a satisfactory solution. The convergence criteria can be that the algorithm reaches the maximum number of iterations, the change in the objective function value is less than a certain threshold, etc. Once the optimization algorithm converges, select the parameter combination with the best objective function value as the optimal control parameter.

[0034] S7: Generate control instructions according to the optimal control parameters and input them into the ultrasonic generator for intelligent control.

[0035] Specifically, specific control instructions are generated according to the optimal control parameters. These instructions include the setting values ​​of the ultrasonic generator's frequency, amplitude, pulse width, duty cycle and other parameters. The control instructions need to be converted into a signal format that the ultrasonic generator can understand, such as a digital signal or an analog signal. The generated control instructions are transmitted to the control unit of the ultrasonic generator through an appropriate communication interface. Ensure the reliability and real-time transmission of the instructions to avoid signal loss or delay. After receiving the control instructions, the control unit of the ultrasonic generator parses them and adjusts the working state of the internal circuits and mechanical components according to the contents of the instructions. For example, adjust the driving signal of the piezoelectric transducer to change the output frequency and power of the ultrasonic wave. After the control instructions are executed, continue to monitor the operating state of the ultrasonic generator in real time and collect feedback data. The monitoring data includes actual output power, frequency, temperature, vibration, etc., which are used to evaluate the control effect. According to the real-time monitoring data, the control parameters are fine-tuned to achieve closed-loop control. Closed-loop control can improve the stability and response speed of the system. If the monitoring data shows that the output state deviates from the expected, the control system will automatically adjust the parameters to achieve the expected performance.

[0036] Furthermore, step S2 of the present application also includes:

[0037] According to the output characteristics of the ultrasonic generator, the principal components are selected, including power stability, frequency stability, and waveform distortion; the operating status information is standardized to obtain a standard data set; the covariance matrix of the standard data set is calculated; the eigenvalue and eigenvector of the covariance matrix are calculated using eigenvalue decomposition, wherein the eigenvalue represents the importance of the eigenvector in the covariance matrix, and the eigenvector represents the distribution of data in each characteristic direction; the first k largest eigenvalues ​​are selected according to the size of the eigenvalue, and the first k largest eigenvalues ​​correspond to the first k largest eigenvectors; the principal component scores are calculated using the eigenvectors corresponding to the selected first k largest eigenvalues; the data are reconstructed using the principal component scores and the corresponding eigenvectors to generate the operating status characteristics.

[0038] Specifically, according to the output characteristics of the ultrasonic generator, several factors that have the greatest impact on performance, such as power stability, frequency stability, and waveform distortion, are determined. These factors will become the main input of principal component analysis to extract the key features of the data. The collected operating status information is standardized to eliminate the influence of different dimensions and scales. Standardization can be achieved by subtracting the mean and dividing by the standard deviation to obtain a standard data set. After standardizing the data set, the covariance matrix of the data is calculated, which reflects the correlation between different features. The covariance matrix is ​​a very important matrix in principal component analysis because it contains information about the distribution of the data. The eigenvalue decomposition method is used to calculate the eigenvalues ​​and eigenvectors of the covariance matrix. The eigenvalue indicates the importance of the corresponding eigenvector in the data, while the eigenvector indicates the distribution of the data in these directions. According to the size of the eigenvalue, the first k largest eigenvalues ​​are selected, which correspond to the most important feature directions in the data. These eigenvalues ​​explain most of the variance of the data, thereby retaining the main information of the data. The selected k eigenvectors are used to calculate the principal component scores, which are the projections of the data on these main feature directions. The principal component scores can be used to represent the main features of the original data, and are usually used for dimensionality reduction or feature extraction. Using the principal component scores and the corresponding eigenvectors, the main features of the data can be reconstructed to generate operating status characteristics. This reconstructed data can be used for subsequent analysis and modeling, such as the construction of parameter control models.

[0039] Furthermore, step S3 of the present application also includes:

[0040] Establish a data connection channel between the intelligent sensor and the parameter control model; set a data buffer to cache the real-time monitoring data and the corresponding operation records; use small batch gradient descent to update the model weight according to the data in the data buffer.

[0041] Specifically, ensure that the smart sensor can establish a stable communication connection with the parameter control model. This can be achieved through a wired connection, such as USB, Ethernet, etc., or a wireless connection, such as Wi-Fi, Bluetooth, LoRa, etc. If it is a wireless connection, you need to configure the network settings, including IP address, port number, security authentication, etc. Set up a data buffer between the sensor and the model to temporarily store real-time monitoring data and corresponding operation records. The data buffer can be a data structure in memory, such as a queue or a ring buffer, or a temporary file on the disk. The smart sensor collects the operating status information of the ultrasonic generator in real time and transmits this data to the data buffer in real time. At the same time, record operation records, such as timestamps, device status, user instructions, etc., for subsequent analysis. In order to update the weights of the parameter control model, a small batch gradient descent algorithm is used. A small batch of data is randomly extracted from the data buffer to calculate the gradient and update the model weights. Compared with batch gradient descent and stochastic gradient descent, small batch gradient descent has achieved a better balance between computational efficiency and convergence speed. The gradient of the loss function with respect to the model weight is calculated based on the small batch data. The model weights are adjusted using the calculated gradient to optimize the loss function, that is, to improve the accuracy of the model prediction. The updating process may require multiple iterations until the model converges or a predetermined number of iterations is reached.

[0042] Furthermore, step S5 of the present application also includes:

[0043] Identify factors that affect equipment performance, including cleaning efficiency, energy consumption, and equipment life; establish target parameter optimization functions: ; Among them, f(P, t, L) is the minimization performance index, w1, w2, w3 are weight factors, C is the equipment energy consumption index, L is the equipment life index, and E is the cleaning efficiency index.

[0044] Specifically, the performance indicators are defined. The cleaning efficiency E represents the efficiency of the equipment cleaning operation, which may be measured by cleaning speed, cleaning quality or other related indicators. Energy consumption C represents the energy consumption of the equipment during operation, usually measured in kilowatt-hours or fuel consumption. Equipment life L represents the expected service life of the equipment, which may be measured in operating hours, number of repairs or frequency of component replacement. Weight factors w1, w2, and w3 determine the importance of each performance indicator in the overall optimization goal. These factors can be set according to actual application requirements and priorities. The objective function f(P, t, L) is a function designed to minimize the performance indicator, where P, t, and L represent parameters that affect performance, such as power, time, load, etc.

[0045] Furthermore, the present application also includes:

[0046] Collect equipment limitations, safety standards, and resource limitations in the working environment; based on the collected information, define constraints, including equipment power limit P_max, operating time limit t_max, energy consumption budget limit C_max, equipment life requirement L_min, and cleaning efficiency requirement E_min.

[0047] Specifically, determine the working environment of the ultrasonic generator, including environmental factors such as temperature, humidity, and dust content. Identify the spatial limitations of the equipment location, such as height, width, depth, etc. Identify the operating temperature range, vibration limits, pressure range, etc. Safety standards such as safety requirements such as protection against electric shock, fire, and explosion. Resource limitations such as power supply, fuel supply, and available maintenance resources such as maintenance personnel, spare parts inventory, etc. The equipment power limit P_max ensures that the power output of the ultrasonic generator does not exceed the maximum power limit of the equipment to prevent equipment overload or damage. The operating time limit t_max ensures that the operating time of the ultrasonic generator does not exceed the set maximum limit to avoid excessive use of the equipment. The energy consumption budget limit C_max ensures that the energy consumption of the ultrasonic generator does not exceed the preset energy consumption budget to control costs and reduce energy waste. The equipment life requirement L_min ensures that the expected life of the ultrasonic generator meets the minimum requirements to ensure the economy and durability of the equipment. The cleaning efficiency requirement E_min ensures that the cleaning efficiency of the ultrasonic generator meets the preset minimum requirements to meet the quality standards of the cleaning operation.

[0048] Furthermore, the present application also includes:

[0049] A plurality of groups of control parameters are used as the first initial population, wherein each individual represents a group of control parameters; it is determined whether each individual in the first initial population violates the optimization constraints, i.e., P<=P_max; t<=t_max; C<=C_max; L>=L_min; E>=E_min; the population violating the optimization constraints in the first initial population is eliminated to obtain the second initial population.

[0050] Specifically, multiple groups of control parameters are generated, and each individual represents a set of control parameters representing a possible control scheme. For each individual in the initial population, check whether its control parameters violate the optimization constraints. Check whether each parameter satisfies the following conditions: P<=P_max; t<=t_max; C<=C_max; L>=L_min; E>=E_min; For individuals that violate any constraint, remove them from the initial population. Retain individuals that meet all constraints to form a second initial population. If all individuals in the first initial population violate the constraints, the second initial population will be empty. In this case, the first initial population may be regenerated and screened again. For individuals that do not meet the constraints, they can be adjusted to meet the constraints. This includes randomly selecting parameter values ​​that meet the constraints, or using heuristic methods to find parameter combinations that meet the constraints.

[0051] Furthermore, the present application also includes:

[0052] Calculate the target parameter optimization function value of each individual in the second initial population, and evaluate the fitness of the target parameter optimization function value; select a parent population according to the fitness, perform a mutation operation on the parent population, generate a candidate solution, and evaluate whether the candidate solution satisfies the optimization constraint; if so, add the candidate solution to the second initial population to generate an updated population; until the termination condition is met, the control parameter represented by the individual that satisfies the optimization constraint and has the highest fitness is used as the optimal control parameter.

[0053] Specifically, for each individual in the second initial population, the value of the target parameter optimization function is calculated. The fitness of these target function values ​​is evaluated, and individuals with high fitness have a higher probability of survival. According to the fitness of the individual, the individual with the highest fitness is selected as the parent population. The selection strategy can be roulette selection, tournament selection or elite retention strategy. The selected parent population is mutated to generate a new candidate solution. The mutation operation can be to randomly change a part of the individual's control parameters to increase the diversity of the population. Evaluate whether the mutated candidate solution meets the optimization constraint. If the candidate solution meets all the constraints, it is retained; otherwise, it is discarded. The candidate solution that meets the constraints is added to the second initial population to generate an updated population. The updated population may contain the original second initial population and the mutated candidate solution. Repeat the above steps for multiple generations of iterations until the termination condition is met. The termination condition can be that the predetermined number of iterations is reached, the fitness change is less than a certain threshold, etc. In the iterative process, the individual with the highest fitness is selected. The control parameter represented by the individual is the optimal control parameter that meets the optimization constraint.

[0054] In summary, the intelligent parameter control method of an ultrasonic generator provided in this application has the following technical effects:

[0055] The method collects the operating status information of the ultrasonic generator; extracts the features of the operating status information according to the output characteristics of the ultrasonic generator to generate operating status features, including environmental information features and equipment operating features; constructs a parameter control model based on the environmental information features and the equipment operating features in combination with an adaptive learning mechanism; obtains multiple groups of control parameters according to work requirements and the parameter control model; analyzes work requirements to obtain multiple evaluation indicators, establishes a target parameter optimization function according to the multiple evaluation indicators, and obtains optimization constraints; performs optimization among the multiple groups of control parameters according to the optimization constraints to obtain optimal control parameters; generates control instructions according to the optimal control parameters and inputs them into the ultrasonic generator for intelligent control, which effectively solves the problem that the existing technology cannot use real-time data analysis and intelligent decision-making algorithms, resulting in the inability of the ultrasonic generator to dynamically adjust parameters according to the working environment and task requirements, further affecting the output efficiency, stability and reliability of the ultrasonic generator, as well as the user experience and satisfaction, thereby achieving efficient, stable and safe operation, improving the automation level of the equipment, and enhancing the adaptability and ease of operation of the equipment.

[0056] Embodiment 2

[0057] Based on the same inventive concept as the intelligent parameter control method of an ultrasonic generator in the aforementioned embodiment, the present application also provides an intelligent parameter control system for an ultrasonic generator, see the attached Figure 2 , the system comprising:

[0058] The information collection module 11 is used to collect the operating status information of the ultrasonic generator.

[0059] The feature extraction module 12 is used to extract features from the operation status information according to the output characteristics of the ultrasonic generator, and generate operation status features, including environmental information features and equipment operation features.

[0060] The model building module 13 is used to build a parameter control model based on the environmental information characteristics and the equipment operation characteristics in combination with an adaptive learning mechanism.

[0061] The parameter acquisition module 14 is used to obtain multiple groups of control parameters according to work requirements and the parameter control model.

[0062] The optimization constraint acquisition module 15 is used to analyze the work requirements, obtain multiple evaluation indicators, establish a target parameter optimization function according to the multiple evaluation indicators, and obtain optimization constraints.

[0063] The control parameter acquisition module 16 is used to perform optimization among the multiple groups of control parameters according to the optimization constraints to obtain the optimal control parameters.

[0064] The intelligent control module 17 is used to generate a control instruction according to the optimal control parameters and input the control instruction into the ultrasonic generator for intelligent control.

[0065] Furthermore, the feature extraction module 12 in the system is also used for:

[0066] According to the output characteristics of the ultrasonic generator, the principal components are selected, including power stability, frequency stability, and waveform distortion; the operating status information is standardized to obtain a standard data set; the covariance matrix of the standard data set is calculated; the eigenvalue and eigenvector of the covariance matrix are calculated using eigenvalue decomposition, wherein the eigenvalue represents the importance of the eigenvector in the covariance matrix, and the eigenvector represents the distribution of data in each characteristic direction; the first k largest eigenvalues ​​are selected according to the size of the eigenvalue, and the first k largest eigenvalues ​​correspond to the first k largest eigenvectors; the principal component scores are calculated using the eigenvectors corresponding to the selected first k largest eigenvalues; the data are reconstructed using the principal component scores and the corresponding eigenvectors to generate the operating status characteristics.

[0067] Furthermore, the model building module 13 in the system is also used for:

[0068] Establish a data connection channel between the intelligent sensor and the parameter control model; set a data buffer to cache the real-time monitoring data and the corresponding operation records; use small batch gradient descent to update the model weight according to the data in the data buffer.

[0069] Furthermore, the optimization constraint acquisition module 15 in the system is also used for:

[0070] Identify factors that affect equipment performance, including cleaning efficiency, energy consumption, and equipment life; establish target parameter optimization functions: ; Among them, f(P, t, L) is the minimization performance index, w1, w2, w3 are weight factors, C is the equipment energy consumption index, L is the equipment life index, and E is the cleaning efficiency index.

[0071] Furthermore, the system further comprises a constraint definition module, wherein the constraint definition module is used to:

[0072] Collect equipment limitations, safety standards, and resource limitations in the working environment; based on the collected information, define constraints, including equipment power limit P_max, operating time limit t_max, energy consumption budget limit C_max, equipment life requirement L_min, and cleaning efficiency requirement E_min.

[0073] Furthermore, the system further includes a second initial population generation module, wherein the second initial population generation module is used for:

[0074] A plurality of groups of control parameters are used as the first initial population, wherein each individual represents a group of control parameters; it is determined whether each individual in the first initial population violates the optimization constraints, i.e., P<=P_max; t<=t_max; C<=C_max; L>=L_min; E>=E_min; the population violating the optimization constraints in the first initial population is eliminated to obtain the second initial population.

[0075] Furthermore, the system further comprises an optimal control parameter acquisition module, and the optimal control parameter acquisition module is used to:

[0076] Calculate the target parameter optimization function value of each individual in the second initial population, and evaluate the fitness of the target parameter optimization function value; select a parent population according to the fitness, perform a mutation operation on the parent population, generate a candidate solution, and evaluate whether the candidate solution satisfies the optimization constraint; if so, add the candidate solution to the second initial population to generate an updated population; until the termination condition is met, the control parameter represented by the individual that satisfies the optimization constraint and has the highest fitness is used as the optimal control parameter.

[0077] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. Figure 1 The intelligent parameter control method and specific examples of an ultrasonic generator in the first embodiment are also applicable to an intelligent parameter control system of an ultrasonic generator in the present embodiment. Through the above detailed description of the intelligent parameter control method of an ultrasonic generator, those skilled in the art can clearly know the intelligent parameter control system of an ultrasonic generator in the present embodiment, so for the sake of brevity of the specification, it will not be described in detail here. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the description of the method part.

[0078] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0079] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.

Claims

1. An intelligent parameter control method for an ultrasonic generator, characterized in that: The method comprises: Collecting the operating status information of the ultrasonic generator; Extracting features of the operating status information according to the output characteristics of the ultrasonic generator to generate operating status features, including environmental information features and equipment operating features; In combination with an adaptive learning mechanism, a parameter control model is constructed based on the environmental information characteristics and the equipment operation characteristics; Obtain multiple groups of control parameters according to work requirements and the parameter control model; Analyze work requirements to obtain multiple evaluation indicators, establish a target parameter optimization function based on the multiple evaluation indicators, and obtain optimization constraints; Searching for the best control parameter among the multiple groups of control parameters according to the optimization constraints; Generate a control instruction according to the optimal control parameter, and input it into the ultrasonic generator for intelligent control; According to the output characteristics of the ultrasonic generator, the operating state information is feature extracted to generate operating state features, including environmental information features and equipment operating features, including: According to the output characteristics of the ultrasonic generator, the main components are selected, including power stability, frequency stability, and waveform distortion; Performing standardization processing on the operating status information to obtain a standard data set; Calculating the covariance matrix of the standard data set; Calculate the eigenvalues ​​and eigenvectors of the covariance matrix using eigenvalue decomposition, wherein the eigenvalues ​​represent the importance of the eigenvectors in the covariance matrix, and the eigenvectors represent the distribution of data in each characteristic direction; Selecting the first k largest eigenvalues ​​according to the magnitude of the eigenvalues, wherein the first k largest eigenvalues ​​correspond to the first k largest eigenvectors; Calculate the principal component score using the eigenvectors corresponding to the selected first k largest eigenvalues; The principal component scores and corresponding feature vectors are used to reconstruct data to generate the operating status features.

2. The intelligent parameter control method of an ultrasonic generator according to claim 1, characterized in that: In combination with the adaptive learning mechanism, a parameter control model is constructed based on the environmental information characteristics and the equipment operation characteristics, and further includes: Establishing a data connection channel between the intelligent sensor and the parameter control model; Set up a data buffer to cache real-time monitoring data and corresponding operation records; Use mini-batch gradient descent to update the model weights based on the data in the data buffer.

3. The intelligent parameter control method of an ultrasonic generator according to claim 1, characterized in that: Analyze the work requirements to obtain multiple evaluation indicators, and establish a target parameter optimization function according to the multiple evaluation indicators, further comprising: Identify factors that affect equipment performance, including cleaning efficiency, energy consumption, and equipment life; Establish the target parameter optimization function: ； Among them, f(P, t, L) is the minimization performance index, w1, w2, w3 are weight factors, C is the equipment energy consumption index, L is the equipment life index, and E is the cleaning efficiency index.

4. The intelligent parameter control method of an ultrasonic generator according to claim 3, characterized in that: Obtain optimization constraints, including: Gather equipment restrictions, safety standards, and resource limitations in your work environment; Based on the collected information, constraints are defined, including equipment power limit P_max, operating time limit t_max, energy consumption budget limit C_max, equipment life requirement L_min, and cleaning efficiency requirement E_min.

5. The intelligent parameter control method of an ultrasonic generator according to claim 4, characterized in that: Optimizing the multiple groups of control parameters according to the optimization constraints to obtain the optimal control parameters, further comprising: Using multiple groups of control parameters as a first initial population, wherein each individual represents a group of control parameters; Determine whether each individual in the first initial population violates the optimization constraint, that is, P<=P_max; t<=t_max; C<=C_max; L>=L_min; E>=E_min, where P_max is the equipment power limit, ensuring that the power output of the ultrasonic generator does not exceed the maximum power limit of the equipment, t_max is the operating time limit, ensuring that the operating time of the ultrasonic generator does not exceed the set maximum limit, C_max is the energy consumption budget limit, ensuring that the energy consumption of the ultrasonic generator does not exceed the preset energy consumption budget, L_min is the equipment life requirement, ensuring that the expected life of the ultrasonic generator meets the minimum requirement, and E_min is the cleaning efficiency requirement, ensuring that the cleaning efficiency of the ultrasonic generator reaches the preset minimum requirement; The population that violates the optimization constraint in the first initial population is eliminated to obtain a second initial population.

6. The intelligent parameter control method of an ultrasonic generator according to claim 5, characterized in that: Also includes: Calculating the target parameter optimization function value of each individual in the second initial population, and evaluating the fitness of the target parameter optimization function value; Selecting a parent population according to the fitness, performing a mutation operation on the parent population to generate a candidate solution, and evaluating whether the candidate solution satisfies the optimization constraint; If satisfied, the candidate solution is added to the second initial population to generate an updated population; Until the termination condition is met, the control parameters of the individual representative that meets the optimization constraints and has the highest fitness are taken as the optimal control parameters.

7. An intelligent parameter control system for an ultrasonic generator, characterized in that: The system is used to implement the steps of the intelligent parameter control method of an ultrasonic generator as described in any one of claims 1 to 6, comprising: An information collection module is used to collect the operating status information of the ultrasonic generator; A feature extraction module, used to extract features of the operating status information according to the output characteristics of the ultrasonic generator, and generate operating status features, including environmental information features and equipment operating features; A model building module, used to build a parameter control model based on the environmental information characteristics and the equipment operation characteristics in combination with an adaptive learning mechanism; A parameter acquisition module, used to obtain multiple groups of control parameters according to work requirements and the parameter control model; An optimization constraint acquisition module is used to analyze work requirements, obtain multiple evaluation indicators, establish a target parameter optimization function according to the multiple evaluation indicators, and obtain optimization constraints; A control parameter acquisition module, used to optimize the multiple groups of control parameters according to the optimization constraints to obtain the optimal control parameters; The intelligent control module is used to generate control instructions according to the optimal control parameters and input them into the ultrasonic generator for intelligent control.

Images