Flame spray gun control method and device, medium and equipment

Abstract

The invention discloses a flame spray gun control method and device, a medium and equipment, and relates to the technical field of automatic control, a big data analysis technology is used for replacing manual work to achieve automatic control of a flame spray gun, historical data are deeply analyzed, feature data influencing the flame state are extracted, and the flame spray gun control efficiency is improved. A mathematical model established by a relationship between a flame state and an adjustment parameter is used as an adjustment core to improve prediction accuracy, a current flame state is used as an input to predict a corresponding target control parameter, real-time control parameters are compared to obtain an adjustment strategy of a flame spray gun, and finally, the spray gun parameters are controlled in an instruction form to achieve the purpose of optimization. The flame stability and the good combustion working effect can be ensured, and the control effect on the flame spray gun is improved.

Description

Technical Field

[0001] This application relates to the field of automatic control technology, specifically to a flame spray gun control method, device, medium, and equipment. Background Technology

[0002] Traditional flame torch operation typically relies on manual flame adjustment to adapt to different working environments and needs. This manual adjustment method is complex, as different operators have varying levels of experience and skill. The precision and stability of manual flame adjustment are difficult to guarantee, easily leading to inconsistent work quality, unsatisfactory heat treatment results on materials, and affecting the final product quality. Furthermore, manual flame adjustment requires operators to frequently stop and adjust, increasing operation time, reducing work efficiency, and even potentially causing explosions if improperly adjusted. Summary of the Invention

[0003] The main objective of this application is to provide a flame gun control method, device, medium, and equipment, aiming to solve the problem of poor control effect of flame guns in the prior art.

[0004] To achieve the above objectives, the technical solutions adopted in the embodiments of this application are as follows: In a first aspect, embodiments of this application provide a flame gun control method, comprising the following steps: Collect flame status data and real-time control parameters of the target flame spray gun during operation; Flame state data is input into the parameter adjustment model, and the target control parameters are output. The parameter adjustment model is obtained by performing machine learning based on the feature dataset and establishing the relationship between the flame state and the adjustment parameters. The feature dataset is obtained based on the historical usage data of the flame gun in operation. Based on the deviation between the target control parameters and the real-time control parameters, adjustment commands are generated to control the flame gun.

[0005] In one possible implementation of the first aspect, before inputting flame state data into the parameter adjustment model and outputting the target control parameters, the method further includes: Acquire historical usage data of the flame gun during operation; the historical usage data includes historical flame status data and its corresponding historical control parameters; Preprocess historical usage data to obtain a feature dataset; Machine learning is performed on the feature dataset to identify factors affecting flame performance and establish the relationship between flame state and adjustment parameters, thereby obtaining a parameter adjustment model.

[0006] In one possible implementation of the first aspect, historical usage data is preprocessed to obtain a feature dataset, including: Historical usage data is cleaned, and the cleaned data is then normalized. The normalized data is then subjected to feature extraction and dimensionality reduction to obtain a feature dataset.

[0007] In one possible implementation of the first aspect, the normalized data is subjected to feature extraction and dimensionality reduction to obtain a feature dataset, including: The normalized data is then subjected to feature extraction and dimensionality reduction to obtain feature data. The importance of feature data is calculated using a decision tree model. The feature data is then divided into training and test sets according to the calculated importance. The process of cleaning historical data and normalizing the cleaned data is repeated until the iteration requirements are met, thus obtaining the feature dataset.

[0008] In one possible implementation of the first aspect, machine learning is performed based on a feature dataset to identify factors affecting flame performance and establish the relationship between flame state and adjustment parameters, thereby obtaining a parameter adjustment model, including: Machine learning is used based on the feature dataset to identify factors that affect flame performance; Based on the factors affecting flame performance, the degree of influence of the adjustment parameters on flame performance is obtained, and the relationship between flame state and adjustment parameters is established to obtain the parameter adjustment model.

[0009] In one possible implementation of the first aspect, based on the factors affecting flame performance, the degree of influence of the adjustment parameters on flame performance is obtained, and the relationship between the flame state and the adjustment parameters is established to obtain a parameter adjustment model, including: Based on the factors affecting flame performance, the degree of influence of the adjustment parameters on flame performance is obtained; Based on the degree of impact, determine the target parameters that need to be optimized; The target parameters are adjusted based on proportional gain, integral gain, and derivative gain, and the relationship between flame state and adjustment parameters is established to obtain a parameter adjustment model.

[0010] In one possible implementation of the first aspect, an adjustment command is generated to control the flame gun based on the deviation between the target control parameters and the real-time control parameters, including: Based on the deviation between the target control parameters and the real-time control parameters, adjustment instructions are generated; According to the adjustment instructions, the gas mixing ratio and the supply of compressed air are obtained; The flame gun is controlled according to the gas mixing ratio and the supply of compressed air.

[0011] Secondly, embodiments of this application provide a flame gun control device, comprising: The data acquisition module is used to collect flame status data and real-time control parameters of the target flame spray gun during operation. The adjustment module is used to input flame state data into the parameter adjustment model and output target control parameters. The parameter adjustment model is obtained by performing machine learning based on the feature dataset and establishing the relationship between the flame state and the adjustment parameters. The feature dataset is obtained based on the historical usage data of the flame gun in operation. The control module is used to generate adjustment commands to control the flame gun based on the deviation between the target control parameters and the real-time control parameters.

[0012] Thirdly, embodiments of this application provide a computer-readable storage medium storing a computer program, which, when loaded and executed by a processor, implements the flame gun control method provided in any of the first aspects above.

[0013] Fourthly, embodiments of this application provide an electronic device, including a processor and a memory, wherein, Memory is used to store computer programs; The processor is used to load and execute computer programs to cause electronic devices to perform the flame gun control method provided in any of the first aspects above.

[0014] Compared with the prior art, the beneficial effects of this application are: This application proposes a flame spray gun control method, device, medium, and equipment. The method includes: collecting flame state data and real-time control parameters of the target flame spray gun during operation; inputting the flame state data into a parameter adjustment model and outputting target control parameters; wherein the parameter adjustment model is obtained by machine learning based on a feature dataset and establishing a relationship between the flame state and the adjustment parameters, and the feature dataset is obtained based on historical usage data of the flame spray gun during operation; and generating adjustment commands to control the flame spray gun based on the deviation between the target control parameters and the real-time control parameters. This application utilizes big data analytics to replace manual control of the flame spray gun. By deeply analyzing historical data, it extracts feature data affecting the flame state and uses a mathematical model established based on the relationship between the flame state and the adjustment parameters as the core of the adjustment, improving the accuracy of prediction. Using the current flame state as input, it predicts the corresponding target control parameters and compares them with the real-time control parameters to obtain the flame spray gun adjustment strategy. Finally, it controls the spray gun parameters through commands to achieve optimization, ensuring flame stability and good combustion performance, and improving the control effect of the flame spray gun. Attached Figure Description

[0015] Figure 1 This is a schematic diagram of the electronic device structure of the hardware operating environment involved in the embodiments of this application; Figure 2A schematic flowchart illustrating the flame gun control method provided in this application embodiment; Figure 3 This is a schematic diagram of the module of the flame gun control device provided in the embodiments of this application; The diagram is labeled as follows: 101-Processor, 102-Communication bus, 103-Network interface, 104-User interface, 105-Memory. Detailed Implementation

[0016] It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit this application.

[0017] See attached document Figure 1 , attached Figure 1 This is a schematic diagram of the electronic device structure of the hardware operating environment involved in the embodiments of this application. The electronic device may include: a processor 101, such as a central processing unit (CPU), a communication bus 102, a user interface 104, a network interface 103, and a memory 105. The communication bus 102 is used to realize the connection and communication between these components. The user interface 104 may include a display screen and an input unit such as a keyboard. Optionally, the user interface 104 may also include a standard wired interface and a wireless interface. The network interface 103 may optionally include a standard wired interface and a wireless interface (such as a Wi-Fi interface). The memory 105 may be a storage device independent of the aforementioned processor 101. The memory 105 may be a high-speed random access memory (RAM) or a stable non-volatile memory (NVM), such as at least one disk storage device. The processor 101 may be a general-purpose processor, including a central processing unit, a network processor, etc., or it may be a digital signal processor, an application-specific integrated circuit, a field-programmable gate array or other programmable logic device, discrete gate or transistor logic device, or discrete hardware component.

[0018] Those skilled in the art will understand that the appendix Figure 1 The structure shown does not constitute a limitation on the electronic device and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0019] As attached Figure 1 As shown, the memory 105, which serves as a storage medium, may include an operating system, a network communication module, a user interface module, and a flame gun control device.

[0020] In the appendix Figure 1 In the electronic device shown, the network interface 103 is mainly used for data communication with the network server; the user interface 104 is mainly used for data interaction with the user; the processor 101 and the memory 105 in this application can be set in the electronic device, and the electronic device calls the flame gun control device stored in the memory 105 through the processor 101 and executes the flame gun control method provided in the embodiment of this application.

[0021] See attached document Figure 2 Based on the hardware device of the foregoing embodiments, embodiments of this application provide a flame gun control method, including the following steps: S10: Collect flame status data and real-time control parameters of the target flame gun during operation.

[0022] In practical implementation, the flame spray gun is the core device of the flame thermal spraying process. By adjusting the mixing ratio of oxygen, acetylene, and compressed air, the characteristics of the combustion flame and the feed rate of the sprayed material are controlled. The target flame spray gun is the flame spray gun that needs to be controlled, and its flame state data and real-time control parameters are collected in real time during operation. High-precision sensors can be used to detect flame state data in real time, such as key parameters like temperature, pressure, and morphology. Real-time control parameters refer to the parameters that control the flame sprayed by the flame spray gun, such as the fuel mixture ratio and the amount of compressed air supplied.

[0023] S20: Input flame state data into the parameter adjustment model and output target control parameters; wherein, the parameter adjustment model is obtained by performing machine learning based on the feature dataset and establishing the relationship between flame state and adjustment parameters, and the feature dataset is obtained based on the historical usage data of the flame gun in operation.

[0024] In the specific implementation process, a trained parameter adjustment model is used as a prediction model to output the optimal control parameters, i.e., the target control parameters, that match the real-time flame state data. The parameter adjustment model utilizes big data analytics and machine learning algorithms to establish the relationship between flame state and adjustment parameters based on deep learning of historical usage data. By learning this correspondence, it predicts a corresponding adjustment parameter for the input flame state data as the parameter corresponding to the optimal adjustment strategy.

[0025] Specifically: before inputting flame state data into the parameter adjustment model and outputting the target control parameters, the method also includes: Acquire historical usage data of the flame gun during operation; the historical usage data includes historical flame status data and its corresponding historical control parameters; Preprocess historical usage data to obtain a feature dataset; Machine learning is performed on the feature dataset to identify factors affecting flame performance and establish the relationship between flame state and adjustment parameters, thereby obtaining a parameter adjustment model.

[0026] In the specific implementation process, historical usage data is acquired to obtain feature data for training. Since it is necessary to establish the relationship between flame state and adjustment parameters, the historical usage data should at least include historical flame state and corresponding historical control parameters. The data is preprocessed to improve its quality and feature data is extracted to form a set of training samples. Machine learning is then used to identify factors affecting flame performance and to select the corresponding control parameters that need optimization and adjustment.

[0027] Data preprocessing may include data cleaning and normalization, that is: preprocessing historical usage data to obtain a feature dataset, including: The historical usage data is cleaned, and the cleaned data is then normalized. The normalized data is then subjected to feature extraction and dimensionality reduction to obtain a feature dataset.

[0028] In practice, data cleaning can handle missing values ​​and remove outliers and duplicate data. Missing values ​​can be imputed using the mean, median, or mode. Outliers and duplicate data can be identified and removed based on business rules or statistical methods. For example, imputing missing values ​​using the mean is as follows:

[0029] in, For missing values, This represents the number of non-missing values. X j It is the j-th non-missing value.

[0030] Normalization, or standardization, aims to maintain the extracted feature data at the same scale. This can be achieved through Z-score standardization or Min-Max normalization. Taking Z-score standardization as an example:

[0031] in, The original data values, The mean, The standard deviation is denoted as .

[0032] Feature extraction includes generating new features, selecting important features, and using dimensionality reduction techniques to perform feature engineering. Generating new features can be achieved through feature combination, aggregate statistics, or time series feature extraction. Feature selection can utilize correlation analysis, model-based importance ranking methods, etc., to determine important features. Dimensionality reduction techniques, such as Principal Component Analysis (PCA), can help reduce the number of features and decrease data complexity. For example, in PCA, the formula for calculating principal components during dimensionality reduction is:

[0033] in, The data matrix after dimensionality reduction. The original data matrix, This is the eigenvector matrix.

[0034] In one embodiment, the normalized data is subjected to feature extraction and dimensionality reduction to obtain a feature dataset, including: The normalized data is then subjected to feature extraction and dimensionality reduction to obtain feature data. The importance of feature data is calculated using a decision tree model. The feature data is then divided into training and test sets according to the calculated importance. The process of cleaning historical data and normalizing the cleaned data is repeated until the iteration requirements are met, thus obtaining the feature dataset.

[0035] In the specific implementation process, the feature importance calculation is performed using the decision tree model:

[0036] in, This results in a decrease in the purity of each node in the decision tree. After the above processing, the data is divided into training and testing sets for subsequent modeling and evaluation. The entire process involves iterative iteration and continuous optimization based on data and business needs to obtain a high-quality feature dataset. Iteration requirements are used to indicate the end of an iteration, such as when the iteration meets design requirements or the set number of iterations is reached.

[0037] In one embodiment, machine learning is performed based on a feature dataset to identify factors affecting flame performance and establish the relationship between flame state and adjustment parameters to obtain a parameter adjustment model, including: Machine learning is used based on the feature dataset to identify factors that affect flame performance; Based on the factors affecting flame performance, the degree of influence of the adjustment parameters on flame performance is obtained, and the relationship between flame state and adjustment parameters is established to obtain the parameter adjustment model.

[0038] In the implementation process, big data processing technology is used to accumulate and deeply analyze the usage data of flame spray guns over a long period, identifying key factors affecting flame performance and optimal adjustment strategies. Based on the analysis of historical data, a mathematical model is established between flame state and adjustment parameters. Assuming that the flame state can be described by multiple variables, the relationship between these variables and the adjustment parameters can be expressed as:

[0039] in, Indicates the flame state. To adjust the parameters.

[0040] The preprocessed dataset is divided into training and test sets, and cross-validation is used to ensure the model's generalization ability. An appropriate machine learning algorithm, such as linear regression, support vector machine (SVM), decision tree, or random forest, is selected to establish a model of the relationship between the flame state and the adjustment parameters. Assuming a linear regression model is chosen, the mathematical representation of the model is as follows:

[0041] in, Indicates the flame state. For the nth adjustment parameter, The regression coefficients to be estimated are: This represents the error term. These regression coefficients are estimated using the least squares (OLS) method, with the following formula:

[0042] in, These are the estimated regression coefficients. It is a design matrix that includes all features. This is a vector of target variables. After obtaining the regression coefficients, the flame state can be predicted using the following formula:

[0043] During model training, overfitting can be prevented by adjusting model parameters and using regularization techniques (such as ridge regression and Lasso regression). The loss function for ridge regression is:

[0044] The loss function for Lasso regression is:

[0045] in, For regularization parameters, This represents the sum of squared residuals. After training the model, it is validated on the test set, and evaluation metrics such as mean squared error (MSE) and coefficient of determination (R²) are calculated to assess model performance. Finally, through model interpretability analysis, the parameters that have the greatest impact on flame performance are identified, and these parameters are optimized to improve flame condition.

[0046] In one embodiment, based on factors affecting flame performance, the degree of influence of adjustment parameters on flame performance is obtained, and the relationship between flame state and adjustment parameters is established to obtain a parameter adjustment model, including: Based on the factors affecting flame performance, the degree of influence of the adjustment parameters on flame performance is obtained; Based on the degree of impact, determine the target parameters that need to be optimized; The target parameters are adjusted based on proportional gain, integral gain, and derivative gain, and the relationship between flame state and adjustment parameters is established to obtain a parameter adjustment model.

[0047] In the specific implementation process, the parameters of the PID controller were optimized through deep learning and identification of historical data, enabling it to adjust adaptively, as shown in the following formula:

[0048] in: , , This is the initial gain; , , This is the gain adjustment amount; Based on deviation and historical data The adjustment function.

[0049] Machine learning models (such as neural networks or decision trees) are used to predict and optimize control parameters. Assuming a neural network model is used, the model's output is the optimized control parameters:

[0050] in, These are the optimized control parameters; , This is the weight matrix; , For bias; For activation functions; The input feature vector includes the current flame state and historical data.

[0051] S30: Generate adjustment commands to control the flame gun based on the deviation between the target control parameters and the real-time control parameters.

[0052] In the specific implementation process, the optimized parameters, i.e., the target control parameters, are compared with the deviations of the real-time monitored data to generate corresponding adjustment commands to control the flame gun and optimize the flame state. Specifically: based on the deviations between the target control parameters and the real-time control parameters, adjustment commands are generated to control the flame gun, including: Based on the deviation between the target control parameters and the real-time control parameters, adjustment instructions are generated; According to the adjustment instructions, the gas mixing ratio and the supply of compressed air are obtained; The flame gun is controlled according to the gas mixing ratio and the supply of compressed air.

[0053] In the specific implementation process, the algorithm inside the control module calculates the corresponding adjustment instructions based on the deviation between the target parameters and real-time monitoring data. This deviation is used to measure the difference between the current state and the target state of the system. The specific calculation method is as follows:

[0054] in, For deviation; This is the set value (target control parameter); For real-time monitoring data (process variables).

[0055] The dynamic adjustment of the gas mixture ratio, which includes fuel and combustion-supporting gas (taking acetylene and pure oxygen as an example), involves adjusting the mixture ratio and the supply of compressed air. By precisely controlling solenoid valves and proportional valves, the flow rates of fuel and combustion-supporting gas can be accurately controlled, refining the flame combustion state. Specifically: The controller calculates the control signal based on the deviation and adjusts the operation of the flame gun.

[0056]

[0057] in, For control signals; For proportional gain; For integral gain; The gain is the differential gain. The entire method forms a closed-loop control system with rapid response capability, enabling timely adaptive adjustment of flame parameters to adapt to changes in the external environment and operating conditions, such as air pressure, temperature fluctuations, and wire feed speed.

[0058] In this embodiment, big data analytics is used to replace manual control of the flame gun. By deeply analyzing historical data, feature data affecting the flame state are extracted, and a mathematical model based on the relationship between the flame state and adjustment parameters is used as the core of the adjustment to improve the accuracy of prediction. Using the current flame state as input, the corresponding target control parameters are predicted, and the adjustment strategy of the flame gun is obtained by comparing it with the real-time control parameters. Finally, the flame gun parameters are controlled by commands to achieve the optimization purpose, which can ensure the stability of the flame and good combustion effect, and improve the control effect of the flame gun.

[0059] See attached document Figure 3 Based on the same inventive concept as in the foregoing embodiments, this application also provides a flame gun control device, including: The data acquisition module is used to collect flame status data and real-time control parameters of the target flame spray gun during operation. The adjustment module is used to input flame state data into the parameter adjustment model and output target control parameters. The parameter adjustment model is obtained by performing machine learning based on the feature dataset and establishing the relationship between the flame state and the adjustment parameters. The feature dataset is obtained based on the historical usage data of the flame gun in operation. The control module is used to generate adjustment commands to control the flame gun based on the deviation between the target control parameters and the real-time control parameters.

[0060] Those skilled in the art should understand that the division of the various modules in the embodiments is merely a logical functional division. In actual applications, they can be fully or partially integrated into one or more actual carriers. These modules can be implemented entirely in software through processing unit calls, entirely in hardware, or a combination of software and hardware. It should be noted that each module in the flame gun control device in this embodiment corresponds one-to-one with each step in the flame gun control method in the aforementioned embodiments. Therefore, the specific implementation of this embodiment can refer to the implementation of the aforementioned flame gun control method, which will not be repeated here.

[0061] Based on the same inventive concept as in the foregoing embodiments, embodiments of this application also provide a computer-readable storage medium storing a computer program, which, when loaded and executed by a processor, implements the flame gun control method provided in the embodiments of this application.

[0062] Based on the same inventive concept as in the foregoing embodiments, embodiments of this application also provide an electronic device, including a processor and a memory, wherein, Memory is used to store computer programs; The processor is used to load and execute computer programs to cause electronic devices to perform the flame gun control method provided in the embodiments of this application.

[0063] In some embodiments, the computer-readable storage medium may be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, flash memory, magnetic surface memory, optical disk, or CD-ROM; or it may be a device including one or any combination of the above-mentioned memories. The computer may be a variety of computing devices, including smart terminals and servers.

[0064] In some embodiments, executable instructions may take the form of a program, software, software module, script, or code, written in any form of programming language (including compiled or interpreted languages, or declarative or procedural languages), and may be deployed in any form, including as a standalone program or as a module, component, subroutine, or other unit suitable for use in a computing environment.

[0065] As an example, executable instructions may, but do not necessarily, correspond to files in the file system. They may be stored as part of a file that holds other programs or data, for example, in one or more scripts in a Hyper Text Markup Language (HTML) document, in a single file dedicated to the program in question, or in multiple collaborative files (e.g., a file that stores one or more modules, subroutines, or code sections).

[0066] As an example, executable instructions can be deployed to execute on a single computing device, or on multiple computing devices located in one location, or on multiple computing devices distributed across multiple locations and interconnected via a communication network.

[0067] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0068] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0069] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as read-only memory / random access memory, magnetic disk, optical disk) and includes several instructions to cause a multimedia terminal device (which may be a mobile phone, computer, television receiver, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0070] In summary, this application provides a flame spray gun control method, apparatus, medium, and device. The method includes: collecting flame state data and real-time control parameters of the target flame spray gun during operation; inputting the flame state data into a parameter adjustment model and outputting target control parameters; wherein the parameter adjustment model is obtained by machine learning based on a feature dataset and establishing a relationship between the flame state and the adjustment parameters, and the feature dataset is obtained based on historical usage data of the flame spray gun during operation; and generating adjustment commands to control the flame spray gun based on the deviation between the target control parameters and the real-time control parameters. This application utilizes big data analytics to replace manual control of the flame spray gun. By deeply analyzing historical data, it extracts feature data affecting the flame state and uses a mathematical model established based on the relationship between the flame state and the adjustment parameters as the core of the adjustment, improving the accuracy of prediction. Using the current flame state as input, it predicts the corresponding target control parameters and compares them with the real-time control parameters to obtain the flame spray gun adjustment strategy. Finally, it controls the spray gun parameters through commands to achieve optimization, ensuring flame stability and good combustion performance, and improving the control effect of the flame spray gun.

[0071] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method for controlling a flamethrower, characterized in that, Includes the following steps: Collect flame status data and real-time control parameters of the target flame spray gun during operation; The flame state data is input into the parameter adjustment model, and the target control parameters are output. The parameter adjustment model is obtained by performing machine learning based on the feature dataset and establishing the relationship between the flame state and the adjustment parameters. The feature dataset is obtained based on the historical usage data of the flame gun in operation. Based on the deviation between the target control parameters and the real-time control parameters, an adjustment command is generated to control the flame gun.

2. The flame gun control method according to claim 1, characterized in that, Before inputting the flame state data into the parameter adjustment model and outputting the target control parameters, the method further includes: Acquire historical usage data of the flame gun during operation; wherein, the historical usage data includes historical flame state data and its corresponding historical control parameters; The historical usage data is preprocessed to obtain the feature dataset; Machine learning is performed on the feature dataset to identify factors affecting flame performance and establish the relationship between flame state and adjustment parameters, thereby obtaining the parameter adjustment model.

3. The flame gun control method according to claim 2, characterized in that, The preprocessing of the historical usage data to obtain the feature dataset includes: The historical usage data is cleaned, and the cleaned data is normalized. The normalized data is then subjected to feature extraction and dimensionality reduction to obtain the feature dataset.

4. The flame gun control method according to claim 3, characterized in that, The step of extracting features and reducing dimensionality from the normalized data to obtain the feature dataset includes: The normalized data is then subjected to feature extraction and dimensionality reduction to obtain feature data; The importance of the feature data is calculated using a decision tree model. The feature data is then divided into a training set and a test set according to the calculated importance. The process of cleaning the historical data and normalizing the cleaned data is repeated until the iteration requirements are met, thus obtaining the feature dataset.

5. The flame gun control method according to claim 2, characterized in that, The step of performing machine learning based on the feature dataset to identify factors affecting flame performance and establish the relationship between flame state and adjustment parameters to obtain the parameter adjustment model includes: Machine learning is performed based on the aforementioned feature dataset to identify factors affecting flame performance; Based on the factors affecting flame performance, the degree of influence of the adjustment parameters on flame performance is obtained, and the relationship between flame state and adjustment parameters is established to obtain the parameter adjustment model.

6. The flame gun control method according to claim 5, characterized in that, The step of obtaining the degree of influence of the adjustment parameters on flame performance based on the factors affecting flame performance, and establishing the relationship between flame state and adjustment parameters to obtain the parameter adjustment model includes: Based on the factors affecting flame performance, the degree of influence of the adjustment parameters on flame performance is obtained; Based on the degree of impact, determine the target parameters that need to be optimized; The target parameters are adjusted based on proportional gain, integral gain, and derivative gain, and the relationship between flame state and adjustment parameters is established to obtain the parameter adjustment model.

7. The flame gun control method according to claim 1, characterized in that, The step of generating adjustment commands to control the flame gun based on the deviation between the target control parameters and the real-time control parameters includes: An adjustment command is generated based on the deviation between the target control parameter and the real-time control parameter; According to the adjustment instructions, the gas mixing ratio and the supply of compressed air are obtained; The flame gun is controlled according to the gas mixing ratio and the supply of compressed air.

8. A flame gun control device, characterized in that, include: The data acquisition module is used to collect flame status data and real-time control parameters of the target flame spray gun during operation. The adjustment module is used to input the flame state data into the parameter adjustment model and output the target control parameters; wherein, the parameter adjustment model is obtained by performing machine learning based on the feature dataset and establishing the relationship between the flame state and the adjustment parameters, and the feature dataset is obtained based on the historical usage data of the flame gun in operation; The control module is used to generate adjustment commands to control the flame gun based on the deviation between the target control parameters and the real-time control parameters.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is loaded and executed by the processor, it implements the flame gun control method as described in any one of claims 1-7.

10. An electronic device, characterized in that, Including processor and memory, among which, The memory is used to store computer programs; The processor is used to load and execute the computer program to cause the electronic device to perform the flame gun control method as described in any one of claims 1-7.

Images