High-precision mass flow controller adjustment method based on artificial intelligence

Abstract

The application discloses a high-precision mass flow controller adjustment method based on artificial intelligence, and particularly relates to the technical field of mass flow controllers, and steps include: collecting identification delay information and difference control information of the high-precision mass flow controller, obtaining an identification fluctuation coefficient and a control fluctuation coefficient, establishing a fluctuation residual value model, generating a fluctuation residual value index, performing diversity evaluation on output signals of the high-precision mass flow controller and generating a signal composite coefficient, performing comprehensive evaluation according to the fluctuation residual value index and the signal composite coefficient, verifying signal stability of the high-precision mass flow controller, and proposing an intervention strategy according to a verification result, the application effectively improves the utilization efficiency of the artificial intelligence model, improves the accuracy and stability of the artificial intelligence model for mass flow control, and avoids the problem that when a data output fault occurs, a staff member is difficult to determine a fault source.

Description

Technical Field

[0001] This invention relates to the field of mass flow controller technology, and more specifically, to a high-precision mass flow controller adjustment method based on artificial intelligence. Background Technology

[0002] During the adjustment of high-precision mass flow controllers with nonlinear characteristics, minute fluctuations in the mass flow controller's input may cause drastic changes in the data acquired by artificial intelligence algorithms. This makes it difficult for AI-based prediction models to learn from historical data, grasp the patterns and characteristics of the mass flow controller, and effectively predict flow trends to achieve high-precision regulation and control. Furthermore, AI-based prediction models have black-box characteristics, making it difficult for staff to determine whether the fault is caused by defects in the AI ​​model itself or by instability in the model input by examining the model data. This poses challenges to staff inspection and verification.

[0003] To address the aforementioned shortcomings, a technical solution is proposed. Summary of the Invention

[0004] The purpose of this invention is to provide a high-precision mass flow controller adjustment method based on artificial intelligence to address the shortcomings in the prior art.

[0005] To achieve the above objectives, the present invention provides the following technical solution: a high-precision mass flow controller adjustment method based on artificial intelligence, the specific steps of which include: The system collects identification delay information and differential control information from the high-precision mass flow controller, and obtains the identification fluctuation coefficient and control fluctuation coefficient based on the identification delay information and differential control information. A residual value model for fluctuation is established based on the identified fluctuation coefficient and the control fluctuation coefficient. The impact of real-time signal identification and control output fluctuation on the regulation efficiency of the high-precision mass flow controller is evaluated, and a residual value index for fluctuation is generated. The output signal of a high-precision mass flow controller is evaluated for diversity, diversity information is obtained, and signal composite coefficients are generated based on the diversity information. The signal stability of the high-precision mass flow controller is verified by comprehensively evaluating the fluctuation residual value index and signal composite coefficient, and intervention strategies are proposed based on the verification results.

[0006] Preferably, the method for acquiring the identification delay information of the high-precision mass flow controller and obtaining the identification fluctuation coefficient based on the identification delay information is as follows: Obtain the signal recognition time of the high-precision mass flow controller within a time period T, and calibrate the signal recognition time as Tn, where... ,and It is a positive integer; The logic for obtaining the signal recognition time of the high-precision mass flow controller within the time period T is as follows: The time required for the sensor to convert temperature changes into electrical signals is obtained, and the time required for the sensor to convert temperature changes into electrical signals is calibrated as T1. The time required for the electrical signal to be converted into a recognizable mass flow rate value is obtained, and the time required for the electrical signal to be converted into a recognizable mass flow rate value is calibrated as T2; The method for calculating the signal recognition time Tn of a high-precision mass flow controller within a time period T is as follows: The signal recognition time of the high-precision mass flow controller within the calibration time period T. To identify delay information; The standard deviation Sp of the identified delay information within the time period T is calculated using the following expression: In the formula, m is the total number of identifiers for delayed information identified within the time period T. Let T be the average signal recognition time of the high-precision mass flow controller within a time period T, and its calculation expression is: ; The identification fluctuation coefficient is obtained based on the identification delay information. The calculation expression for the identification fluctuation coefficient is as follows: In the formula, To identify the fluctuation coefficient.

[0007] Preferably, the method for acquiring differential control information from a high-precision mass flow controller and obtaining the control fluctuation coefficient based on the differential control information is as follows: Obtain the effective control frequency range of the high-precision mass flow controller, and calibrate the effective control frequency range of the high-precision mass flow controller as follows. ,in, This is the lower limit of the effective control frequency range for a high-precision mass flow controller. This is the lower limit of the effective control frequency range for a high-precision mass flow controller. Obtain the frequency of the control command output by the high-precision mass flow controller based on the difference signal, and calibrate the frequency data of the control command output by the high-precision mass flow controller based on the difference signal as Pj; The frequency of the control commands output by the high-precision mass flow controller based on the differential signal is integrated into a data set, and the frequency data is labeled with j. Where k is a positive integer, the data set consisting of the frequency of the control command output by the high-precision mass flow controller based on the difference signal is the difference control information; Calculate the standard deviation of the difference control information, then the standard deviation In the formula, The average value of the differential control information is calculated using the following expression: ; The expression for calculating the control fluctuation coefficient is as follows: In the formula, To control the fluctuation coefficient.

[0008] Preferably, the method for establishing a volatility residual model based on the identified volatility coefficient and the controlled volatility coefficient, and generating a volatility residual index, is as follows: After normalizing the identification volatility coefficient and the control volatility coefficient, a volatility residual model is constructed. The expression for the volatility residual model is as follows: In the formula, For volatility residual value index, To identify the volatility coefficient, These are the weighting coefficients for identifying volatility coefficients and controlling volatility coefficients, respectively. All are positive numbers.

[0009] Preferably, the method for evaluating the diversity of the output signal of the high-precision mass flow controller and obtaining diversity information is as follows: Acquire the analog signal output by the high-precision mass flow controller within a time period T, and then convert the analog signal output by the high-precision mass flow controller within several consecutive time periods T. The original dataset is composed of [various components], and the original dataset is labeled as [specific data]. ,in Where v is the number of the analog signal output by the high-precision mass flow controller within the time period T, and r is a positive integer, and the original dataset consists of a first subset and a second subset. When it is odd, mark For the first subset of data, when When it is even, mark The second subset contains diversity information including both the first and second subsets.

[0010] Preferably, the method for generating signal composite coefficients based on diverse information is as follows: Based on the diversity information, the entropy of the first subset is calculated as follows: The entropy of the second subset is calculated as follows: In the formula, and The entropy of the first and second subsets are respectively. and Analog signals from the first and second subsets, respectively. The probability of taking a value; Calculate the joint entropy as In the formula, For joint entropy, express and The joint probability; Calculate the mutual information between the first and second subsets using the following expression: In the formula, The mutual information between the first and second subsets is set to a preset mutual information threshold. The calculated mutual information With preset mutual information threshold The signal composite coefficients are obtained by subtraction. The expression for calculating the signal composite coefficients is as follows: .

[0011] Preferably, the logic for verifying the signal stability of a high-precision mass flow controller by comprehensively evaluating the fluctuation residual value index and the signal composite coefficient is as follows: The logic for comprehensive evaluation based on the volatility residual index and signal composite coefficient is as follows: Construct a comprehensive evaluation model for In the formula, For comprehensive evaluation, For the volatility residual value index, a comprehensive evaluation threshold is set as follows: The threshold will be comprehensively evaluated. Compared with the overall assessment value Compare the values, if the overall evaluation value is... Greater than or equal to the comprehensive evaluation threshold If so, the stability of the marker model fails; If the comprehensive evaluation value Less than the comprehensive evaluation threshold Then the stability of the marker model will take effect.

[0012] Preferably, the logic for proposing an intervention strategy based on the verification results is as follows: If the model stability fails, the staff will be notified that the robustness of the artificial intelligence model is unbalanced; if the model stability is effective, the staff will be notified that the robustness of the artificial intelligence model is sufficient.

[0013] The technical effects and advantages provided by the present invention in the above technical solution are as follows: This application obtains the identification delay information and differential control information of a high-precision mass flow controller to acquire the identification fluctuation coefficient and control fluctuation coefficient, respectively. Based on the identification fluctuation coefficient and control fluctuation coefficient, modeling and analysis are performed to verify the stability of the output data for the artificial intelligence model. In addition, the diversity evaluation is performed in combination with the output signal of the high-precision mass flow controller to verify the generalization effect of the output signal and output mode on the artificial intelligence model. This effectively improves the utilization efficiency of the artificial intelligence model, enhances the accuracy and stability of the artificial intelligence model in mass flow control, and avoids the problem that it is difficult for staff to determine the source of the fault when data output failure occurs. Attached Figure Description

[0014] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this invention. For those skilled in the art, other drawings can be obtained based on these drawings.

[0015] Figure 1 This is a flowchart of the method of the present invention. Detailed Implementation

[0016] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0017] Example 1: Please refer to Figure 1 As shown, this invention is a high-precision mass flow controller adjustment method based on artificial intelligence, and the specific steps include: The system collects identification delay information and differential control information from the high-precision mass flow controller, and obtains the identification fluctuation coefficient and control fluctuation coefficient based on the identification delay information and differential control information. A residual value model for fluctuation is established based on the identified fluctuation coefficient and the control fluctuation coefficient. The impact of real-time signal identification and control output fluctuation on the regulation efficiency of the high-precision mass flow controller is evaluated, and a residual value index for fluctuation is generated. The output signal of a high-precision mass flow controller is evaluated for diversity, and signal composite coefficients are generated. Based on a comprehensive evaluation using the fluctuation residual value index and signal composite coefficient, the signal stability of the high-precision mass flow controller is verified, and an intervention strategy is proposed.

[0018] The high-precision mass flow controller consists of a sensor, a regulating valve, and an amplification and control circuit. The sensor part includes a heating element and a temperature sensor. The heating element generates heat and exchanges heat with the flowing gas. The temperature sensor monitors the temperature change of the heating element. When the gas flows through the sensor part, the heating element in the sensor exchanges heat with the gas, causing the temperature of the heating element to change. The temperature sensor monitors the temperature change and converts the temperature change into an electrical signal. The electrical signal represents the mass flow rate of the gas. The electrical signal output by the temperature sensor is amplified and filtered to convert it into a recognizable mass flow rate value. The amplification, filtering, and conversion of electrical signals are all analyzed and processed by the electronic control system within the high-precision mass flow controller. The generation of electrical signals varies, and sensors based on different principles have different efficiencies in acquiring different temperature changes. The movement patterns of the flowing gas also vary, meaning that the processing and conversion efficiency of the electronic control system for different electrical signals varies.

[0019] If there is a delay or fluctuation in the processing of electrical signals into identifiable mass flow values ​​after each acquisition, excessive delay or fluctuation will have the following adverse effects on subsequent flow control and the construction and prediction of artificial intelligence models: Delay fluctuations can slow down the response speed of flow controllers, making it impossible to adjust in a timely manner according to the current flow conditions. In situations requiring rapid response, such as real-time flow control in industrial production, delays may lead to production instability or even safety accidents. Delay fluctuations introduce additional errors, which reduce the adjustment accuracy of the flow controller, potentially leading to unstable product quality, increased scrap rate, and reduced production efficiency. Latency fluctuations can lead to a decrease in the quality of data used for model training. Latency fluctuations introduce temporal inconsistencies, which weaken the correlation between data and thus affect the training effect of the model. Due to impaired data quality, the trained artificial intelligence model cannot effectively generalize to new data. In other words, the artificial intelligence model does not perform as well as expected in learning from real-time data in practical applications and cannot accurately predict and control traffic. Delayed fluctuations disrupt the continuity of time series data, making it difficult for artificial intelligence models to accurately capture the changing trends between data, resulting in reduced prediction accuracy of artificial intelligence models and an inability to provide reliable prediction basis for flow control. Excessive latency fluctuations can cause predictions to lag behind actual traffic conditions. This lag renders AI model predictions meaningless and unable to provide effective support for real-time traffic control.

[0020] To avoid the above adverse effects, the method for collecting the identification delay information of the high-precision mass flow controller and obtaining the identification fluctuation coefficient based on the identification delay information is as follows: Obtain the signal recognition time of the high-precision mass flow controller within a time period T, and calibrate the signal recognition time as Tn, where... ,and It is a positive integer; The logic for obtaining the signal recognition time of the high-precision mass flow controller within the time period T is as follows: The time required for the sensor to convert temperature changes into electrical signals is obtained, and the time required for the sensor to convert temperature changes into electrical signals is calibrated as T1. The time required for the electrical signal to be converted into a recognizable mass flow rate value is obtained, and the time required for the electrical signal to be converted into a recognizable mass flow rate value is calibrated as T2; The method for calculating the signal recognition time Tn of a high-precision mass flow controller within a time period T is as follows: The signal recognition time of the high-precision mass flow controller within the calibration time period T. To identify delay information; It should be noted that the time required for the sensor to convert temperature changes into electrical signals depends on the type and performance of the temperature sensor and is obtained by professionals in the field through actual testing. The time required for the electrical signal to be converted into a recognizable mass flow value depends on the processing speed and algorithm complexity of the electronic control system and is obtained by conducting performance tests on the electronic control system or consulting the technical specifications. The standard deviation Sp of the identified delay information within the time period T is calculated using the following expression: In the formula, m is the total number of identifiers for delayed information identified within the time period T. Let T be the average signal recognition time of the high-precision mass flow controller within a time period T, and its calculation expression is: ; The identification fluctuation coefficient is obtained based on the identification delay information. The calculation expression for the identification fluctuation coefficient is as follows: In the formula, To identify the fluctuation coefficient.

[0021] After obtaining the identifiable mass flow rate value, the electronic control system compares the identifiable mass flow rate value with the preset mass flow rate threshold to obtain the difference signal between the identifiable mass flow rate value and the preset mass flow rate threshold. The electronic control system then sends a control signal to the regulating valve based on the difference signal to precisely control the gas flow rate. If the frequency of sending control commands based on the difference signal fluctuates excessively, such fluctuations will have the following adverse effects on flow control and the construction and prediction of artificial intelligence models: Fluctuations in command frequency can cause instability in the opening adjustment of the flow control valve, resulting in fluctuations in the actual flow rate. Unstable flow control directly affects the stability of the production process and the consistency of product quality. When the command frequency fluctuates too much, it may be unable to respond and adjust the flow in a timely manner, resulting in control lag. In flow control that requires a fast response, this may lead to production accidents or equipment damage. Frequent command fluctuations and valve opening adjustments will exacerbate equipment wear and fatigue, which will not only reduce equipment lifespan but may also increase maintenance costs and downtime. Fluctuations in instruction frequency can lead to a decrease in the quality of data used for training artificial intelligence models. Instability and noise in the data can affect the training effect of artificial intelligence models, reducing their accuracy and generalization ability. When data quality declines, the training process of artificial intelligence models may become more difficult and complex, further increasing the requirements for the amount of data and training time for artificial intelligence models; Fluctuations in command frequency can disrupt the continuity and stability of data, making it difficult for artificial intelligence models to accurately capture the changing trends between data, resulting in reduced prediction accuracy of the models and an inability to provide reliable prediction basis for flow control. When the command frequency fluctuates too much, the prediction results of the artificial intelligence model may be delayed. The delay may render the prediction results meaningless and unable to provide effective support for real-time flow control.

[0022] To avoid the above adverse effects, the method for collecting differential control information from a high-precision mass flow controller and obtaining the control fluctuation coefficient based on this information is as follows: Obtain the effective control frequency range of the high-precision mass flow controller, and calibrate the effective control frequency range of the high-precision mass flow controller as follows. ,in, This is the lower limit of the effective control frequency range for a high-precision mass flow controller. This is the lower limit of the effective control frequency range for a high-precision mass flow controller. It should be noted that by conducting performance tests on the high-precision mass flow controller and observing its control stability and accuracy at different frequencies, the upper and lower limits of the effective control frequency of the high-precision mass flow controller can be determined, or this can be obtained by consulting the technical specifications and relevant literature of the high-precision mass flow controller.

[0023] Obtain the frequency of the control command output by the high-precision mass flow controller based on the difference signal, and calibrate the frequency data of the control command output by the high-precision mass flow controller based on the difference signal as Pj; The frequency of the control commands output by the high-precision mass flow controller based on the differential signal is integrated into a data set, and the frequency data is labeled with j. Where k is a positive integer, the data set consisting of the frequency of the control command output by the high-precision mass flow controller based on the difference signal is the difference control information; Calculate the standard deviation of the difference control information, then the standard deviation In the formula, The average value of the differential control information is calculated using the following expression: ; The expression for calculating the control fluctuation coefficient is as follows: In the formula, To control the fluctuation coefficient.

[0024] A residual value model for fluctuation is established based on the identified fluctuation coefficient and the control fluctuation coefficient. The impact of real-time signal identification and control output fluctuation on the regulation efficiency of the high-precision mass flow controller is evaluated, and a residual value index for fluctuation is generated. The method for establishing a volatility residual model and generating a volatility residual index based on the identified volatility coefficient and the controlled volatility coefficient is as follows: After normalizing the identification volatility coefficient and the control volatility coefficient, a volatility residual model is constructed. The expression for the volatility residual model is as follows: In the formula, For volatility residual value index, To identify the volatility coefficient, These are the weighting coefficients for identifying volatility coefficients and controlling volatility coefficients, respectively. All are positive numbers.

[0025] The output signal of a high-precision mass flow controller is evaluated for diversity, diversity information is obtained, and signal composite coefficients are generated based on the diversity information. Acquire the analog signal output by the high-precision mass flow controller within a time period T, and then convert the analog signal output by the high-precision mass flow controller within several consecutive time periods T. The original dataset is composed of [various components], and the original dataset is labeled as [specific data]. ,in Where v is the number of the analog signal output by the high-precision mass flow controller within the time period T, and r is a positive integer, and the original dataset consists of a first subset and a second subset. When it is odd, mark For the first subset of data, when When it is even, mark For the second subset, diversity information includes both the first and second subsets. The method for generating signal composite coefficients based on diverse information is as follows: Based on the diversity information, the entropy of the first subset is calculated as follows: The entropy of the second subset is calculated as follows: In the formula, and The entropy of the first and second subsets are respectively. and Analog signals from the first and second subsets, respectively. The probability of taking a value; Calculate the joint entropy as In the formula, For joint entropy, express and The joint probability; Calculate the mutual information between the first and second subsets using the following expression: In the formula, The mutual information between the first and second subsets is set to a preset mutual information threshold. The calculated mutual information With preset mutual information threshold The signal composite coefficients are obtained by subtraction. The expression for calculating the signal composite coefficients is as follows: .

[0026] It should be noted that the mutual information threshold The settings are determined by professionals in the field based on the output performance of the high-precision mass flow controller, which will not be elaborated here. The analog signals output by the high-precision mass flow controller within several time periods T are cross-classified and evaluated according to odd and even numbers, which effectively improves the accuracy of mutual information calculation and the evaluation efficiency of the diversity of output signals within the period T.

[0027] Based on a comprehensive evaluation using the fluctuation residual value index and signal composite coefficient, the signal stability of the high-precision mass flow controller is verified, and an intervention strategy is proposed. The logic for comprehensive evaluation based on the volatility residual index and signal composite coefficient is as follows: Construct a comprehensive evaluation model for In the formula, For comprehensive evaluation, For the volatility residual value index, a comprehensive evaluation threshold is set as follows: The threshold will be comprehensively evaluated. Compared with the overall assessment value Compare the values, if the overall evaluation value is... Greater than or equal to the comprehensive evaluation threshold If the model fails to maintain stability, the staff will be notified of the imbalance in the robustness of the artificial intelligence model. If the comprehensive evaluation value Less than the comprehensive evaluation threshold If the model stability is confirmed, the robustness of the artificial intelligence model will be fully demonstrated to the staff.

[0028] This application obtains the identification delay information and differential control information of a high-precision mass flow controller to acquire the identification fluctuation coefficient and control fluctuation coefficient, respectively. Based on the identification fluctuation coefficient and control fluctuation coefficient, modeling and analysis are performed to verify the stability of the output data for the artificial intelligence model. In addition, the diversity evaluation is performed in combination with the output signal of the high-precision mass flow controller to verify the generalization effect of the output signal and output mode on the artificial intelligence model. This effectively improves the utilization efficiency of the artificial intelligence model, enhances the accuracy and stability of the artificial intelligence model in mass flow control, and avoids the problem that it is difficult for staff to determine the source of the fault when data output failure occurs.

[0029] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0030] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as computer program goods. The computer program goods include one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive.

[0031] It should be understood that in the various embodiments of this application, the order of the above-mentioned processes does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0032] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0033] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working process of the system described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0034] If the aforementioned functions are implemented as software functional units and sold or used as independent goods, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of software goods. This computer software goods are stored in a storage medium and include several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0035] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A high-precision mass flow controller adjustment method based on artificial intelligence, characterized in that, The specific steps include: The system collects identification delay information and differential control information from the high-precision mass flow controller, and obtains the identification fluctuation coefficient and control fluctuation coefficient based on the identification delay information and differential control information. A residual value model for fluctuation is established based on the identified fluctuation coefficient and the control fluctuation coefficient. The impact of real-time signal identification and control output fluctuation on the regulation efficiency of the high-precision mass flow controller is evaluated, and a residual value index for fluctuation is generated. The output signal of a high-precision mass flow controller is evaluated for diversity, diversity information is obtained, and signal composite coefficients are generated based on the diversity information. The signal stability of the high-precision mass flow controller is verified by comprehensively evaluating the fluctuation residual value index and the signal composite coefficient, and intervention strategies are proposed based on the verification results. The method for acquiring the identification delay information of a high-precision mass flow controller and obtaining the identification fluctuation coefficient based on the identification delay information is as follows: Obtain the signal recognition time of the high-precision mass flow controller within a time period T, and calibrate the signal recognition time as Tn, where... ,and It is a positive integer; The logic for obtaining the signal recognition time of the high-precision mass flow controller within the time period T is as follows: The time required for the sensor to convert temperature changes into electrical signals is obtained, and the time required for the sensor to convert temperature changes into electrical signals is calibrated as T1. The time required for the electrical signal to be converted into a recognizable mass flow rate value is obtained, and the time required for the electrical signal to be converted into a recognizable mass flow rate value is calibrated as T2; The method for calculating the signal recognition time Tn of a high-precision mass flow controller within a time period T is as follows: The signal recognition time of the high-precision mass flow controller within the calibration time period T. To identify delay information; The standard deviation Sp of the identified delay information within the time period T is calculated using the following expression: In the formula, m is the total number of identifiers for delayed information identified within the time period T. Let T be the average signal recognition time of the high-precision mass flow controller within a time period T, and its calculation expression is: ; The identification fluctuation coefficient is obtained based on the identification delay information. The calculation expression for the identification fluctuation coefficient is as follows: In the formula, To identify the volatility coefficient; The method for acquiring differential control information from a high-precision mass flow controller and obtaining the control fluctuation coefficient based on this information is as follows: Obtain the effective control frequency range of the high-precision mass flow controller, and calibrate the effective control frequency range of the high-precision mass flow controller as follows. ,in, This is the lower limit of the effective control frequency range for a high-precision mass flow controller. This is the lower limit of the effective control frequency range for a high-precision mass flow controller. Obtain the frequency of the control command output by the high-precision mass flow controller based on the difference signal, and calibrate the frequency data of the control command output by the high-precision mass flow controller based on the difference signal as Pj; The frequency of the control commands output by the high-precision mass flow controller based on the differential signal is integrated into a data set, and the frequency data is labeled with j. Where k is a positive integer, the data set consisting of the frequency of the control command output by the high-precision mass flow controller based on the difference signal is the difference control information; Calculate the standard deviation of the difference control information, then the standard deviation In the formula, The average value of the differential control information is calculated using the following expression: ; The expression for calculating the control fluctuation coefficient is as follows: In the formula, To control the fluctuation coefficient; The method for establishing a volatility residual model and generating a volatility residual index based on the identified volatility coefficient and the controlled volatility coefficient is as follows: After normalizing the identification volatility coefficient and the control volatility coefficient, a volatility residual model is constructed. The expression for the volatility residual model is as follows: In the formula, For volatility residual value index, To identify the volatility coefficient, These are the weighting coefficients for identifying volatility coefficients and controlling volatility coefficients, respectively. All are positive numbers; The method for evaluating the diversity of the output signal of a high-precision mass flow controller and obtaining diversity information is as follows: Acquire the analog signal output by the high-precision mass flow controller within a time period T, and then convert the analog signal output by the high-precision mass flow controller within several consecutive time periods T. The original dataset is composed of [various components], and the original dataset is labeled as [specific data]. ,in Where v is the number of the analog signal output by the high-precision mass flow controller within the time period T, and r is a positive integer, and the original dataset consists of a first subset and a second subset. When it is odd, mark For the first subset of data, when When it is even, mark For the second subset, diversity information includes both the first and second subsets. The method for generating signal composite coefficients based on diverse information is as follows: Based on the diversity information, the entropy of the first subset is calculated as follows: The entropy of the second subset is calculated as follows: In the formula, and The entropy of the first and second subsets are respectively. and Analog signals from the first and second subsets, respectively. The probability of taking a value; Calculate the joint entropy as In the formula, For joint entropy, express and The joint probability; Calculate the mutual information between the first and second subsets using the following expression: In the formula, The mutual information between the first and second subsets is set to a preset mutual information threshold. The calculated mutual information With preset mutual information threshold The signal composite coefficients are obtained by subtraction. The expression for calculating the signal composite coefficients is as follows: .

2. The high-precision mass flow controller adjustment method based on artificial intelligence according to claim 1, characterized in that, The logic for verifying the signal stability of a high-precision mass flow controller based on a comprehensive evaluation using the fluctuation residual value index and signal composite coefficient is as follows: The logic for comprehensive evaluation based on the volatility residual index and signal composite coefficient is as follows: Construct a comprehensive evaluation model for In the formula, For comprehensive evaluation, For the volatility residual value index, a comprehensive evaluation threshold is set as follows: The threshold will be comprehensively evaluated. Compared with the overall assessment value Compare the values, if the overall evaluation value is... Greater than or equal to the comprehensive evaluation threshold If so, the stability of the marker model fails; If the comprehensive evaluation value Less than the comprehensive evaluation threshold Then the stability of the marker model will take effect.

3. The high-precision mass flow controller adjustment method based on artificial intelligence according to claim 2, characterized in that, The logic for proposing an intervention strategy based on the verification results is as follows: If the model stability fails, the staff will be notified that the robustness of the artificial intelligence model is unbalanced; if the model stability is effective, the staff will be notified that the robustness of the artificial intelligence model is sufficient.

Images