An automatic control method and system for multiple regulating valves in fluorine chemical industry

Abstract

The embodiments of the present application relate to the technical field of automatic control of multiple regulating valves in fluorine chemical industry, and provide a method and system for automatic control of multiple regulating valves in fluorine chemical industry to solve the problems of low efficiency and poor safety in the automatic control of multiple regulating valves in fluorine chemical industry in the prior art. Among them, based on the Markov decision process, the optimal operating conditions under the current fluorine chemical production conditions are evaluated and the optimal operating conditions are predicted; based on the process safety limit and the product quality target, an ideal opening adjustment scheme is generated, and the pulse width modulation control instruction is sent to the actuator of the corresponding multiple regulating valves in fluorine chemical industry through the industrial communication bus to obtain the actual valve control strategy of the multiple regulating valves in fluorine chemical industry; the difference between the actual effect and the expected effect is compared to obtain an improved control strategy; the control strategy is continuously optimized according to the experience accumulated by the improved control strategy. The technical solution provided by the embodiments of the present application can improve the efficiency and safety of the automatic control of multiple regulating valves in fluorine chemical industry.

Description

Technical Field

[0001] The embodiments of the present application relate to the technical field of automatic control of multiple regulating valves in fluorine chemical industry, and in particular to an automatic control method and system for multiple regulating valves in fluorine chemical industry. Background Art

[0002] In the fluorine chemical industry, the precise control of multiple regulating valves is crucial for ensuring product quality, improving production efficiency, and reducing energy consumption. Due to the complex and ever-changing operating conditions in the production process, a method that can evaluate the optimal operating conditions in real time and dynamically adjust the valve opening according to these conditions is needed. In addition, to meet strict process safety limits and product quality goals, the control system must have a high degree of safety and reliability, and at the same time be able to adapt to equipment aging and environmental changes.

[0003] Existing automatic control methods for multiple regulating valves in fluorine chemical industry usually adopt the following steps: comparing the expected behavior of physical entities with predefined behavior patterns through a fuzzy rule base to identify the behavior deviation area; using fuzzy inference rules to quantitatively analyze the degree and type of behavior deviation, which can reduce uncertainty; adopting basic machine vision technology to monitor key interaction points, but lacking the ability to create a three-dimensional spatio-temporal model with fine-grained monitoring and spatio-temporal fusion algorithms; directly applying the correction instructions to the actual system without first simulating and executing them in the digital twin model, and the feedback mechanism is simple, usually only involving error integration for subsequent control adjustment.

[0004] Although the above existing solutions have improved the control level to a certain extent, there are still some significant deficiencies: traditional controllers and other static control strategies are difficult to quickly adapt to changes in operating conditions, which may lead to fluctuations in the production process and affect product quality; for complex systems with multiple variables, such as the control of multiple regulating valves in fluorine chemical industry, it is difficult for existing solutions to find the global optimal solution, especially when considering safety limits and product quality goals simultaneously; the adaptability of existing control systems to environmental changes and equipment aging is poor, and the initial control performance may not be maintained after long-term operation. Summary of the Invention

[0005] The embodiments of the present application provide an automatic control method and system for multiple regulating valves in fluorine chemical industry to solve the problems of low efficiency and poor safety in the automatic control of multiple regulating valves in fluorine chemical industry in the prior art.

[0006] In a first aspect, the embodiments of the present application provide an automatic control method for multiple regulating valves in fluorine chemical industry, including:

[0007] Evaluating the optimal operating conditions under the current fluorine chemical production conditions based on the Markov decision process, and performing prediction processing on the optimal operating conditions to obtain the best process state;

[0008] According to the optimal operating conditions and the best process state, the genetic algorithm is used to globally search the opening degrees of the fluorochemical multi-control valves, and an ideal opening degree adjustment scheme is generated based on the process safety limit and the product quality target. Among them, the ideal opening degree adjustment scheme meets the safety and quality requirements and achieves the highest energy efficiency ratio in the fluorochemical production;

[0009] Convert the ideal opening degree adjustment scheme into a pulse width modulation control instruction, send the pulse width modulation control instruction to the actuator of the corresponding fluorochemical multi-control valve through the industrial communication bus, and use fault prediction and health management technology to identify and handle potential equipment failure risks to obtain the actual valve control strategy of the fluorochemical multi-control valve;

[0010] Use the adaptive feedback loop of the deep neural network to compare the difference between the actual effect of the actual valve control strategy and the expected effect of the ideal opening degree adjustment scheme, and use the backpropagation algorithm to dynamically correct the actual valve control strategy to obtain an improved control strategy;

[0011] Use the online learning mechanism to continuously optimize the control strategy of the fluorochemical multi-control valve according to the experience accumulated during the operation of the improved control strategy.

[0012] Optionally, converting the ideal opening degree adjustment scheme into a pulse width modulation control instruction, sending the pulse width modulation control instruction to the actuator of the corresponding fluorochemical multi-control valve through the industrial communication bus, and using fault prediction and health management technology to identify and handle potential equipment failure risks to obtain the actual valve control strategy of the fluorochemical multi-control valve, including:

[0013] Based on the ideal opening degree adjustment scheme, convert the opening degree information in the ideal opening degree adjustment scheme into a pulse width modulation control instruction for the actuator of the fluorochemical multi-control valve to generate a pulse width modulation signal;

[0014] Based on the pulse width modulation signal and the industrial communication bus, combined with the time synchronization protocol, perform timestamp processing on the pulse width modulation control instruction, and optimize the scheduling of the pulse width modulation control instruction through distributed control to ensure that the pulse width modulation control instruction is sent to the actuator of the corresponding fluorochemical multi-control valve, and establish a communication connection between the industrial communication bus and the actuator of the fluorochemical multi-control valve;

[0015] Based on the communication connection, use fault prediction and health management technology, combined with real-time data analysis and pattern recognition algorithms, to monitor the operating state of the communication connection in real time, use anomaly detection algorithms to automatically identify abnormal operation modes of the communication connection, and evaluate potential risks through a machine learning model to generate a potential risk assessment report;

[0016] Based on the potential risk assessment report, adaptive filtering is used to filter the noise of the communication connection, and preventive measures to ensure the safe operation of the communication connection are generated;

[0017] Based on the preventive measures and the pulse width modulation signal, the actuator of the fluorochemical multi-control valve is intelligently adjusted to process the opening information, so as to generate an actual valve control strategy.

[0018] Optionally, based on the communication connection, using fault prediction and health management technology, combined with real-time data analysis and pattern recognition algorithms, the operating state of the communication connection is monitored in real time, and using anomaly detection algorithms, the abnormal operation modes of the communication connection are automatically identified, and the potential risks are evaluated through a machine learning model to generate a potential risk assessment report, including:

[0019] Based on the communication connection, using fault prediction and health management technology, combined with real-time data analysis and pattern recognition algorithms, the operating state of the communication connection is continuously monitored, the state information of the communication connection is collected through sensors on the industrial communication bus, and the state information is transmitted to the central processing unit of the communication connection to obtain the operating state of the communication connection;

[0020] According to the operating state of the communication connection, the collected operating state is analyzed and processed using an anomaly detection algorithm, and the abnormal operation modes of the communication connection are automatically identified to generate a potential abnormal operation mode report;

[0021] Based on the potential abnormal operation mode report, the potential risks are evaluated through a machine learning model to generate a potential risk assessment report.

[0022] Optionally, using the adaptive feedback loop of the deep neural network, the difference between the actual effect of the actual valve control strategy and the expected effect of the ideal opening adjustment scheme is compared, and the actual valve control strategy is dynamically corrected using the backpropagation algorithm to obtain an improved control strategy, including:

[0023] Based on the adaptive feedback loop of the deep neural network, the operating state of the actual valve control strategy is monitored and analyzed to obtain the actual effect of the actual valve control strategy;

[0024] Based on the actual effect of the actual valve control strategy and the expected effect of the ideal opening adjustment scheme, the difference between the actual effect and the expected effect is compared and analyzed to generate a difference analysis result;

[0025] According to the difference analysis result, use the backpropagation algorithm in the deep neural network to analyze the specific reasons for the differences in the difference analysis result, and adjust the weights of the deep neural network to generate a correction suggestion;

[0026] According to the correction suggestion, optimize the actual valve control strategy to improve the accuracy and efficiency of the actual valve control strategy and generate an improved control strategy.

[0027] Optionally, according to the difference analysis result, use the backpropagation algorithm in the deep neural network to analyze the specific reasons for the differences in the difference analysis result, and adjust the weights of the deep neural network to generate a correction suggestion, including:

[0028] According to the difference analysis result, quantify the gap between the obtained actual effect and the expected effect to obtain an initial error value, layer by layer transmit the initial error value through the backpropagation algorithm in the deep neural network, and identify the specific reasons for the occurrence of the gap to generate a preliminary identification result;

[0029] Based on the preliminary identification result, use principal component analysis to extract the key influencing factors in the preliminary identification result, and combine sensitivity analysis to refine the key influencing factors to obtain a list of key influencing factors;

[0030] According to the list of key influencing factors, use adaptive moment estimation to adjust the key influencing factors to narrow the difference between the actual effect and the expected effect to obtain a preliminary correction suggestion;

[0031] Based on the preliminary correction suggestion, adjust the weights of the deep neural network, and improve the obtained control strategy to generate a correction suggestion.

[0032] Optionally, according to the optimal operating conditions and the best process state, use the genetic algorithm to globally search for the opening degrees of the multi-control valves in the fluorochemical industry, and generate an ideal opening degree adjustment plan based on the process safety limit and the product quality target, including:

[0033] According to the optimal operating conditions and the best process state, analyze the opening degree settings of the multi-control valves in the fluorochemical industry to generate different combinations of opening degree settings;

[0034] Based on the combination of opening degree settings, initialize a group of the combination of opening degree settings representing different opening degree settings as the initial plan, and evaluate the energy efficiency ratio, safety, and product quality performance of each combination of opening degree settings according to the current optimal operating conditions and the best process state to obtain a candidate plan composed of the combination of opening degree settings with excellent performance;

[0035] Based on the candidate solutions, using the selection, crossover, and mutation steps in the genetic algorithm, explore the adjustment solutions for the opening setting combinations in the candidate solutions to generate a preliminary ideal opening adjustment solution;

[0036] Based on the preliminary ideal opening adjustment solution, continue iterative optimization, and generate an ideal opening adjustment solution according to the process safety limit and product quality target, and the ideal opening adjustment solution achieves the highest energy efficiency ratio of the fluorochemical production.

[0037] Optionally, it is characterized in that, using an online learning mechanism, according to the experience accumulated during the operation of the improved control strategy, continuously optimize the control strategy of the fluorochemical multi-control valve, including:

[0038] Based on the online learning mechanism, monitor and process the operation status of the improved control strategy to obtain an information report reflecting the actual operation effect of the improved control strategy;

[0039] Based on the information report, analyze the actual operation effect of the improved control strategy according to the information on the operation status of the improved control strategy collected in real time by the distributed sensor network, identify the operation modes of the successful improved control strategy, and accumulate the operation modes as experience to generate an experience library;

[0040] Based on the experience library, use machine learning to update the control strategy of the fluorochemical multi-control valve, adjust the weights in the control strategy to ensure that the control strategy adapts to the production requirements of the fluorochemical industry, and generate an updated control strategy;

[0041] Perform optimization suggestion processing on the updated control strategy to further improve the control accuracy and control efficiency of the fluorochemical multi-control valve, generate optimization suggestions, and apply the optimization suggestions to actual control to ensure that the control strategy of the fluorochemical multi-control valve is continuously optimized during operation.

[0042] Optionally, use fault prediction and health management technology to identify and handle potential equipment failure risks to obtain the actual valve control strategy of the fluorochemical multi-control valve, including:

[0043] Continuously monitor the health status of the equipment through fault prediction and health management technology to identify and handle potential equipment failure risks ;

[0044] Potential equipment failure risk The calculation formula:

[0045] ;

[0046] Where, is the potential risk of equipment failure, indicating the degree from no risk to high risk, with a value range between and represents the health index of the health management technology, reflecting the health status of the equipment at a future time point ; represents the preset safety threshold, that is, the safety upper limit of the health index. When is less than the safety threshold, it indicates the existence of the potential risk of equipment failure. represents the urgency of the predicted failure time, indicating the length of time from the current time to the predicted occurrence of equipment failure. represents the maximum predicted failure time urgency, used to standardize the maximum value of is the severity of equipment failure, indicating the degree of impact on the fluorochemical production process when the equipment failure occurs. is the maximum severity of equipment failure, used to standardize the maximum value of is the repair cost, indicating the cost or resource consumption required to repair the equipment failure. is the maximum repair cost, used to standardize the maximum value of is the weight coefficient, used to adjust the importance of the health index part. is the non-linear influence index of the health index, used to capture the non-linear trend of the change of the health index over time. is the weight coefficient, used to adjust the importance of the part of the urgency of the predicted failure time. is the weight coefficient, used to adjust the importance of the part of the severity of the equipment failure. is the weight coefficient, used to adjust the importance of the part of the repair cost;

[0047] Analyze and handle the potential risk of equipment failure to obtain the actual valve control strategy of the fluorochemical multi-control valve.

[0048] Optionally, according to the optimal operating conditions and the best process state, use the genetic algorithm to globally search for the opening of the fluorochemical multi-control valve, and generate an ideal opening adjustment plan based on the process safety limit and the product quality target. Among them, the ideal opening adjustment plan meets the safety and quality requirements and realizes the highest energy efficiency ratio of the fluorochemical production, including:

[0049] According to the optimal operating conditions and the best process state, use the genetic algorithm to globally search for the opening of the fluorochemical multi-control valve;

[0050] Global search calculation formula:

[0051] ;

[0052] Among them, is the global search calculation formula, that is, the optimal opening degree of the fluorochemical multi-control valve found, is the fitness function, which is used to evaluate the advantages and disadvantages of each opening degree setting, represents the opening degree setting space of all the fluorochemical multi-control valves, and the fitness function , represents the energy efficiency ratio of the fluorochemical production at the opening degree setting , represents the safety score, is the product quality score, , , , , , are the corresponding weight coefficients and non-linear exponents respectively, reflecting the importance of the safety score, the product quality score and the energy efficiency ratio of the fluorochemical production and their trends with time or conditions;

[0053] Based on the calculation results of the global search, an ideal opening degree adjustment plan is generated according to the process safety limit and the product quality target;

[0054] Calculation formula of the ideal opening degree adjustment plan:

[0055] ;

[0056] Among them, is the ideal opening degree adjustment plan, X represents the opening degree setting of the fluorochemical multi-control valve, is the penalty function, which is used to handle individuals that exceed the process safety limit and the product quality target;

[0057] Penalty function :

[0058] ;

[0059] Among them, represents the process safety limit, represents the product quality target, represents the actual process safety value at the current opening degree setting, is the actual product quality value at the current opening degree setting, and are the corresponding safety and quality penalty coefficients respectively, which are used to adjust the severity of violating the constraints;

[0060] Fitness function:

[0061] , represents the energy efficiency ratio of the fluorochemical production at the stated opening setting under which, represents the safety score, is the product quality score, , , , , , are respectively the corresponding weight coefficients and non - linear exponents, reflecting the importance of the safety score, the product quality score and the energy efficiency ratio of the fluorochemical production and their trends of change over time or conditions.

[0062] In a second aspect, an automatic control system for multiple regulating valves in fluorochemical production provided by an embodiment of the present application includes:

[0063] A prediction module that evaluates the optimal operating conditions under the current fluorochemical production conditions based on the Markov decision process and performs prediction processing on the optimal operating conditions to obtain the best process state;

[0064] A search module that globally searches for the opening degrees of the multiple regulating valves in fluorochemical production according to the optimal operating conditions and the best process state by using the genetic algorithm, and generates an ideal opening adjustment plan based on the process safety limit and the product quality target, wherein the ideal opening adjustment plan meets the safety and quality requirements and achieves the highest energy efficiency ratio of the fluorochemical production;

[0065] An identification module that converts the ideal opening adjustment plan into a pulse - width modulation control instruction, sends the pulse - width modulation control instruction to the actuator of the corresponding multiple regulating valves in fluorochemical production through an industrial communication bus, and uses fault prediction and health management technology to identify and handle potential equipment failure risks to obtain the actual valve control strategy of the multiple regulating valves in fluorochemical production;

[0066] A correction module that uses the adaptive feedback loop of the deep neural network to compare the difference between the actual effect of the actual valve control strategy and the expected effect of the ideal opening adjustment plan, and dynamically corrects the actual valve control strategy by using the backpropagation algorithm to obtain an improved control strategy;

[0067] An optimization module that uses an online learning mechanism to continuously optimize the control strategy of the multiple regulating valves in fluorochemical production according to the experience accumulated during the operation of the improved control strategy.

[0068] In a third aspect, an embodiment of the present application provides a computing device, including a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a method for automatically controlling multiple regulating valves in fluorochemical industry as described in the first aspect above.

[0069] In a fourth aspect, an embodiment of the present application provides a computer storage medium storing a computer program, which when executed by a computer, implements a method for automatically controlling multiple regulating valves in fluorochemical industry as described in the first aspect.

[0070] In the embodiment of the present application, based on the Markov decision process, the optimal operating conditions under the current fluorochemical production condition are evaluated, and the optimal operating conditions are predicted to obtain the best process state; according to the optimal operating conditions and the best process state, the genetic algorithm is used to globally search for the opening degrees of the multiple regulating valves in fluorochemical industry, and based on the process safety limit and the product quality target, an ideal opening degree adjustment scheme is generated, where the ideal opening degree adjustment scheme meets the safety and quality requirements and achieves the highest energy efficiency ratio of the fluorochemical production; the ideal opening degree adjustment scheme is converted into a pulse width modulation control instruction, and the pulse width modulation control instruction is sent to the actuator of the corresponding multiple regulating valves in fluorochemical industry through an industrial communication bus, and the fault prediction and health management technology is used to identify and handle potential equipment fault risks to obtain the actual valve control strategy of the multiple regulating valves in fluorochemical industry; using the adaptive feedback loop of the deep neural network, the difference between the actual effect of the actual valve control strategy and the expected effect of the ideal opening degree adjustment scheme is compared, and the actual valve control strategy is dynamically corrected using the backpropagation algorithm to obtain an improved control strategy; using an online learning mechanism, according to the experience accumulated during the operation of the improved control strategy, the control strategy of the multiple regulating valves in fluorochemical industry is continuously optimized.

[0071] The technical solution of the present application has the following beneficial effects:

[0072] The present application evaluates the optimal operating conditions under the current condition based on the Markov decision process and performs prediction processing to obtain the best process state, ensuring the high efficiency and stability of production; converts the ideal opening degree adjustment scheme into a control instruction and sends it to the actuator through an industrial communication bus, and at the same time uses the technology to identify and handle potential equipment fault risks, ensuring the practical feasibility and safety of the valve control strategy; uses the adaptive feedback loop of the deep neural network to compare the difference between the actual effect and the expected effect, dynamically corrects the control strategy through the backpropagation algorithm, and continuously optimizes the control strategy in combination with the online learning mechanism, ensuring that the system can self-learn and improve.

[0073] Furthermore, the time synchronization protocol and distributed control are used to optimize the scheduling of pulse width modulation control instructions, ensuring the timeliness and accuracy of instruction transmission; through real-time data analysis and pattern recognition algorithms, the status of communication connections is continuously monitored, abnormal operation modes are automatically identified, enhancing the reliability of the system; preventive measures are taken based on potential risk assessment reports, and the actuator is intelligently adjusted to process the opening information, reducing the failure rate and improving the safety of system operation.

[0074] Furthermore, the operating status of the communication connection is continuously monitored by sensors on the industrial communication bus to ensure that all relevant data is collected and transmitted to the central processing unit in a timely manner, providing comprehensive data support; the operating status is analyzed using anomaly detection algorithms, abnormal operation modes are automatically identified, and detailed reports on potential abnormal operation modes are generated to ensure quick problem location; potential risks are evaluated based on machine learning models, risk assessment reports are generated to guide the adoption of effective preventive measures, improving the predictability and response speed of the system, greatly enhancing the reliability and robustness of the system in the face of complex environmental changes, and ensuring the safe and stable operation of the fluorochemical production process.

[0075] These aspects or other aspects of the present application will be more clearly understood in the following description of the embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0076] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0077] Figure 1 Shows a flowchart of a method for automatically controlling multiple regulating valves in fluorochemical industry provided by the present application;

[0078] Figure 2 Shows a schematic structural diagram of a multi-regulating valve automatic control system for fluorochemical industry provided by the present application;

[0079] Figure 3 Shows a schematic structural diagram of a computing device provided by the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0080] In order to enable those skilled in the art to better understand the solution of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0081] In some processes described in the specification, claims, and above-mentioned drawings of the present application, a plurality of operations appear in a specific order. However, it should be clearly understood that these operations may not be executed in the order in which they appear herein or may be executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish different operations, and the serial numbers themselves do not represent any execution order. Additionally, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions such as "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent a sequence, and do not limit that "first" and "second" are of different types.

[0082] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative efforts shall fall within the protection scope of the present application.

[0083] Figure 1 A flowchart of an automatic control method for multiple regulating valves in fluorochemical industry is provided for an embodiment of the present application, as Figure 1 shown. The method includes:

[0084] 101. Evaluate the optimal operating conditions under the current fluorochemical production conditions based on the Markov decision process, and perform prediction processing on the optimal operating conditions to obtain the best process state;

[0085] In this step, the Markov decision process is a mathematical framework for modeling decision-making problems with randomness. It includes states, actions, transition probabilities, and reward functions. In fluorochemical production, the Markov decision process is used to evaluate the optimal operating conditions under the current working conditions. By collecting real-time data such as temperature, pressure, and flow rate, as well as historical operation records, a dynamic model is established to predict the results under different operating conditions. This information is used to determine the best process state, that is, the conditions most likely to achieve efficient, safe, and high-quality production.

[0086] In an application scenario of intelligent prediction and preventive maintenance in an embodiment of the application, assume that a fluorochemical plant faces the problem of raw material supply fluctuations. By deploying an extensive sensor network, engineers can obtain detailed production data streams. Using the model of the Markov decision process, the system can not only identify the current optimal operating settings but also anticipate upcoming challenges in advance, such as changes in reaction rates due to changes in raw material characteristics. This enables the plant to adjust production strategies before problems occur and avoid potential risks.

[0087] 102. According to the optimal operating conditions and the best process state, use the genetic algorithm to globally search for the opening degrees of the multi-control valves in the fluorochemical industry, and generate an ideal opening degree adjustment plan based on the process safety limit and the product quality target, where the ideal opening degree adjustment plan meets the safety and quality requirements and achieves the highest energy efficiency ratio in the fluorochemical production;

[0088] In this step, the genetic algorithm is a type of optimization algorithm that simulates natural selection and genetic mechanisms and is suitable for solving complex multi-variable optimization problems. In this step, the genetic algorithm is used to explore all possible valve opening combinations to find the optimal solution that not only meets the safety requirements but also ensures product quality. The genetic algorithm iteratively improves the quality of the solution through operations such as encoding candidate solutions, evaluating fitness, selection, crossover, and mutation, and finally converges to one or more approximate optimal solutions.

[0089] In the application embodiment, continuing the scenario in the above embodiment, after determining the best process state, the factory needs to further refine to the specific control level. At this time, the genetic algorithm begins to play a role. It finds a set of ideal settings that can both maintain high production and ensure that the product quality is not affected through the exploration of a large number of valve opening combinations. For example, some valves only need to be slightly adjusted under specific conditions to significantly improve energy efficiency without sacrificing product purity or safety.

[0090] 103. Convert the ideal opening degree adjustment plan into a pulse width modulation control instruction, send the pulse width modulation control instruction to the actuator of the corresponding multi-control valve in the fluorochemical industry through the industrial communication bus, and use fault prediction and health management technology to identify and handle potential equipment failure risks to obtain the actual valve control strategy of the multi-control valve in the fluorochemical industry;

[0091] In this step, pulse width modulation is a technology used to control power electronic devices, and the power transfer is adjusted by changing the duty cycle of the output signal. In this step, the ideal opening degree adjustment plan is converted into a pulse width modulation control instruction to accurately drive the actuator of the control valve. In addition, fault prediction and health management technology are used to monitor the health status of the equipment, timely detect and handle possible problems, so as to ensure the reliable operation of the system.

[0092] In the application embodiment, based on Embodiments 101 and 102, the factory has obtained an ideal valve opening adjustment scheme. Now, this scheme is converted into a pulse width modulation instruction and sent to each regulating valve through the industrial communication bus inside the factory. Meanwhile, the fault prediction and health management system is silently guarding the safety of the entire process in the background. For example, when a certain regulating valve shows an abnormal vibration mode, the fault prediction and health management respond quickly, adjust the working mode of the valve, and even suggest that the maintenance team conduct an inspection in advance, ensuring the continuity and stability of production.

[0093] 104. Use the adaptive feedback loop of the deep neural network to compare the difference between the actual effect of the actual valve control strategy and the expected effect of the ideal opening adjustment scheme, and use the backpropagation algorithm to dynamically correct the actual valve control strategy to obtain an improved control strategy.

[0094] In this step, the deep neural network is a form of machine learning and is particularly good at processing data with complex non-linear relationships. The adaptive feedback loop refers to the ability of the control system to continuously adjust its own behavior according to real-time feedback. In this step, the deep neural network is used to compare the effect of the actual valve control strategy with the expectation of the ideal scheme, learn the gap between the two through the backpropagation algorithm, and adjust the control logic accordingly to achieve better control accuracy and adaptability.

[0095] In the application embodiment, continuing the scenario of the above embodiment, the factory introduces an adaptive feedback loop of the deep neural network to improve the flexibility of the control system. Whenever the valve works according to the newly set opening, the deep neural network will compare the difference between the actual performance and the ideal effect. For example, if a certain valve fails to achieve the expected flow control at a specific opening, the deep neural network will fine-tune its control logic through the backpropagation algorithm to ensure better matching of the expectation under the same conditions next time. Over time, the system gradually learns how to respond more precisely to various working conditions.

[0096] 105. Use the online learning mechanism to continuously optimize the control strategy of the multi-regulating valves for fluorine chemical production according to the experience accumulated during the operation of the improved control strategy.

[0097] In this step, online learning means that the system can learn from the latest data and update its knowledge base without shutting down. For fluorine chemical production, this means that the control system can immediately adjust its own behavior mode according to the result of each operation without waiting for regular maintenance or restart. This method allows the system to quickly adapt to environmental changes and technological progress and always operate in the optimal state.

[0098] In the application embodiment, based on the previous steps, the factory has achieved true intelligent production. After each valve operates according to the latest adjusted strategy, the system records the results and compares them with the previous situation. If a better control method is found, the system will automatically adopt and apply it in subsequent operations. In this way, even when facing unprecedented challenges, such as a sudden surge in demand caused by a market change, the factory can rely on its highly adaptive control system to quickly adjust the production plan and ensure that it is always in the best operating state.

[0099] In summary, through steps 101 to 105, the present invention realizes the intelligent management of fluorochemical production by integrating the Markov decision process to evaluate the optimal operating conditions, the genetic algorithm to optimize the valve opening, the pulse-width modulation to precisely control the actuator, the deep neural network to dynamically correct the control strategy, and the online learning mechanism to continuously optimize. It not only improves production efficiency and product quality, ensures the maximization of process safety and energy efficiency ratio, but also enhances the reliability and adaptability of the system through fault prediction and health management technology, and finally achieves an advanced level of intelligent prediction and preventive maintenance.

[0100] Optionally, in step 103, converting the ideal opening adjustment scheme into a pulse-width modulation control instruction, sending the pulse-width modulation control instruction to the actuator of the corresponding fluorochemical multi-regulating valve through the industrial communication bus, and using fault prediction and health management technology to identify and handle potential equipment failure risks to obtain the actual valve control strategy of the fluorochemical multi-regulating valve, including:

[0101] Based on the ideal opening adjustment scheme, converting the opening information in the ideal opening adjustment scheme into a pulse-width modulation control instruction for the actuator of the fluorochemical multi-regulating valve to generate a pulse-width modulation signal; based on the pulse-width modulation signal and the industrial communication bus, combining with the time synchronization protocol, performing timestamp processing on the pulse-width modulation control instruction, and optimizing and scheduling the pulse-width modulation control instruction through distributed control to ensure that the pulse-width modulation control instruction is sent to the actuator of the corresponding fluorochemical multi-regulating valve and establishing a communication connection between the industrial communication bus and the actuator of the fluorochemical multi-regulating valve; based on the communication connection, using fault prediction and health management technology, combining real-time data analysis and pattern recognition algorithms, monitoring the operating state of the communication connection in real time, using anomaly detection algorithms to automatically identify abnormal operating modes of the communication connection, and evaluating potential risks through a machine learning model to generate a potential risk assessment report; based on the potential risk assessment report, using adaptive filtering to filter the noise of the communication connection to generate preventive measures to ensure the safe operation of the communication connection; based on the preventive measures and the pulse-width modulation signal, intelligently adjusting the adjustment process of the actuator of the fluorochemical multi-regulating valve for the opening information to generate an actual valve control strategy.

[0102] Optionally, based on the communication connection, using fault prediction and health management technology, combined with real-time data analysis and pattern recognition algorithms, the operating state of the communication connection is monitored in real time. Using an anomaly detection algorithm, the abnormal operation modes of the communication connection are automatically identified, and potential risks are evaluated through a machine learning model to generate a potential risk assessment report, including:

[0103] Based on the communication connection, using fault prediction and health management technology, combined with real-time data analysis and pattern recognition algorithms, the operating state of the communication connection is continuously monitored. The state information of the communication connection is collected through sensors on the industrial communication bus and transmitted to the central processing unit of the communication connection to obtain the operating state of the communication connection; according to the operating state of the communication connection, the collected operating state is analyzed and processed using an anomaly detection algorithm to automatically identify the abnormal operation modes of the communication connection to generate a potential abnormal operation mode report; based on the potential abnormal operation mode report, potential risks are evaluated through a machine learning model to generate a potential risk assessment report.

[0104] In this embodiment, the ideal opening adjustment scheme is converted into a pulse width modulation control instruction and sent to the actuator of the control valve through the industrial communication bus. The pulse width modulation signal is a technology for precisely controlling power electronic devices. It adjusts power transfer by changing the duty cycle of the output signal to ensure that the valve can operate according to the preset opening. The time synchronization protocol and the distributed control system ensure that the pulse width modulation instruction is accurately transmitted to each actuator, establishing a stable communication connection. The fault prediction and health management technology combines real-time data analysis, pattern recognition algorithms, and machine learning models to continuously monitor the state of the communication connection, automatically identify and evaluate potential risks, such as abnormal operation modes or noise interference, thereby generating preventive measures to ensure the stability and security of the system.

[0105] In the embodiment of the present application, first, the opening information in the ideal opening adjustment scheme is converted into a pulse width modulation control instruction suitable for the actuator to understand, generating an accurate pulse width modulation signal. Then, the pulse width modulation instruction is timestamped using the time synchronization protocol and optimized for scheduling through the distributed control system to ensure that the instruction reaches the target device in a timely and accurate manner, while establishing a stable communication connection between the industrial communication bus and the actuator. Then, the system uses fault prediction and health management technology based on the communication connection, combined with the state information collected by the sensors, analyzes the operating state through an anomaly detection algorithm, identifies abnormal operation modes, and generates a risk assessment report. Finally, preventive measures such as adaptive filtering are taken according to the risk assessment results to intelligently adjust the opening setting of the actuator, forming the final actual valve control strategy to achieve efficient and safe operation.

[0106] In an application scenario of intelligent prediction and preventive maintenance, engineers in a fluorochemical plant deployed an intelligent control system integrating Markov decision process, genetic algorithm, and pulse width modulation. When the ideal opening adjustment scheme is converted into a pulse width modulation instruction and sent through an industrial communication bus, the system uses a time synchronization protocol to ensure that the instruction arrives at the control valve on time. During this period, fault prediction and health management technology continuously monitors the communication connection status. For example, a slight data transmission delay occurred in a certain control valve. The fault prediction and health management system quickly detected the anomaly through real-time data analysis and pattern recognition algorithms, evaluated the risk using a machine learning model, and generated preventive measures. The system automatically enabled an adaptive filter to reduce noise and optimized the data transmission priority to avoid potential network congestion. At the same time, it recommended that the maintenance team check the hardware to prevent faults in advance, ensuring production continuity and safety, and significantly improving energy efficiency and product quality.

[0107] Optionally, in step 104, an adaptive feedback loop of a deep neural network is used to compare the actual effect of the actual valve control strategy with the expected effect of the ideal opening adjustment scheme, and the backpropagation algorithm is used to dynamically correct the actual valve control strategy to obtain an improved control strategy, including:

[0108] Based on the adaptive feedback loop of the deep neural network, monitor and analyze the operating state of the actual valve control strategy to obtain the actual effect of the actual valve control strategy; based on the actual effect of the actual valve control strategy and the expected effect of the ideal opening adjustment scheme, compare and analyze the difference between the actual effect and the expected effect to generate a difference analysis result; according to the difference analysis result, use the backpropagation algorithm in the deep neural network to analyze the specific reasons for the difference in the difference analysis result and adjust the weights of the deep neural network to generate a correction suggestion; according to the correction suggestion, optimize the actual valve control strategy to improve the accuracy and efficiency of the actual valve control strategy and generate an improved control strategy.

[0109] Optionally, according to the difference analysis result, use the backpropagation algorithm in the deep neural network to analyze the specific reasons for the difference in the difference analysis result and adjust the weights of the deep neural network to generate a correction suggestion, including:

[0110] According to the difference analysis results, the gap between the actual effect obtained and the expected effect is quantified to obtain an initial error value, and the initial error value is transferred layer by layer through the back propagation algorithm in the deep neural network, and the specific cause of the gap is identified to generate a preliminary identification result; based on the preliminary identification result, the key influencing factors in the preliminary identification result are extracted using principal component analysis, and the key influencing factors are refined in combination with sensitivity analysis to obtain a list of key influencing factors; according to the list of key influencing factors, the key influencing factors are adjusted using adaptive moment estimation to narrow the difference between the actual effect and the expected effect to obtain preliminary correction suggestions; based on the preliminary correction suggestions, the weights of the deep neural network are adjusted, and the obtained control strategy is improved to generate correction suggestions.

[0111] In this embodiment, the adaptive feedback loop of the deep neural network is an intelligent control system for monitoring and analyzing the operating status of the actual valve control strategy. It generates a difference analysis result by comparing the difference between the actual effect and the expected effect of the ideal opening adjustment scheme. The back propagation algorithm passes the initial error value layer by layer in the deep neural network, identifies the specific cause of the difference, and adjusts the network weights to optimize the control strategy. Principal component analysis and sensitivity analysis help extract key influencing factors, while adaptive moment estimation is used to fine-tune these factors to ensure that the control strategy is more accurate and efficient.

[0112] In the embodiment of the present application, the scheme first uses the adaptive feedback loop of the deep neural network to monitor the effect of the actual valve control strategy, quantify the gap between the actual effect and the expected effect, and generate an initial error value. Then, the error is transmitted layer by layer through the back propagation algorithm to identify the specific cause and generate a preliminary identification result. Then, the key influencing factors are extracted by principal component analysis, and the sensitivity analysis is combined with the refinement processing to form a list of key influencing factors. Finally, based on this list, adaptive moment estimation is used to adjust the key factors, optimize the deep neural network weights, and improve the control strategy, thereby improving its accuracy and efficiency, and finally generating an improved control strategy.

[0113] In order to further improve the efficiency of intelligent prediction and preventive maintenance, in a fluorine chemical plant, based on the communication connection and real-time monitoring mechanism established in step 103, the system detected that the actual flow of a control valve did not meet expectations. Through quantitative processing, the deep neural network identified that temperature fluctuations were the main cause. Using the back propagation algorithm, the system adjusted the relevant parameters, and combined with principal component analysis and sensitivity analysis to determine the degree of influence of temperature on flow. Subsequently, the temperature control logic was fine-tuned through adaptive moment estimation, which significantly narrowed the gap between actual and expected results, improved the accuracy and energy efficiency of valve operation, and ensured the safe and stable operation of production.

[0114] Optionally, according to the optimal operating conditions and the best process state in step 102, the genetic algorithm is used to globally search the opening degrees of the fluorination multi-control valves, and based on the process safety limit and the product quality target, an ideal opening degree adjustment scheme is generated, including:

[0115] According to the optimal operating conditions and the best process state, analyze the opening degree settings of the fluorination multi-control valves to generate different combinations of opening degree settings; based on the combinations of opening degree settings, initialize a set of the combinations of opening degree settings representing different opening degree settings as the initial scheme, and according to the current optimal operating conditions and the best process state, evaluate the energy efficiency ratio, safety, and product quality performance of each combination of opening degree settings to obtain a candidate scheme composed of the combinations of opening degree settings with excellent performance; based on the candidate scheme, use the selection, crossover, and mutation steps in the genetic algorithm to explore the adjustment scheme of the combinations of opening degree settings in the candidate scheme to generate a preliminary ideal opening degree adjustment scheme; based on the preliminary ideal opening degree adjustment scheme, continue iterative optimization, and according to the process safety limit and the product quality target, generate an ideal opening degree adjustment scheme, and the ideal opening degree adjustment scheme achieves the highest energy efficiency ratio in the fluorination production.

[0116] In this embodiment, the genetic algorithm is an optimization method that simulates natural selection and genetic mechanisms and is used to solve complex multi-variable optimization problems. In this step, according to the optimal operating conditions and the best process state, analyze the opening degree settings of the fluorination multi-control valves to generate different combinations of opening degree settings. These combinations are initialized as a set of initial schemes representing different opening degree settings. The system evaluates the energy efficiency ratio, safety, and product quality performance of each combination of opening degree settings, and screens out the combinations with excellent performance to form a candidate scheme. The selection, crossover, and mutation steps in the genetic algorithm are used to explore the adjustment scheme in the candidate scheme, and finally an ideal opening degree adjustment scheme is generated.

[0117] In the embodiment of the present application, this scheme first analyzes the opening degree settings of the fluorination multi-control valves based on the optimal operating conditions and the best process state to generate multiple possible combinations of opening degree settings. Then, initialize a set of combinations of opening degree settings as the initial scheme, and evaluate the performance of each combination according to the current optimal operating conditions and the best process state, and screen out the candidate schemes with excellent performance. Next, use the selection, crossover, and mutation steps in the genetic algorithm to explore the adjustment scheme in the candidate scheme to generate a preliminary ideal opening degree adjustment scheme. Finally, through iterative optimization, combined with the process safety limit and the product quality target, generate the final ideal opening degree adjustment scheme to ensure the achievement of the highest energy efficiency ratio.

[0118] In a fluorochemical plant, based on the optimal operating conditions and the best process state determined in step 102, the system generates multiple opening setting combinations and screens out excellent candidate solutions from them. Subsequently, using the selection, crossover, and mutation steps of the genetic algorithm, it continuously explores better opening settings. In step 103, these ideal opening adjustment solutions are converted into pulse-width modulation control instructions and sent to the actuator, while monitoring the health of the communication connection. Further, in step 104, the adaptive feedback loop of the deep neural network continuously compares the difference between the actual effect and the expected effect, dynamically correcting the control strategy to ensure precise and efficient valve operation. This series of measures significantly improves production efficiency and product quality, ensuring the continuity and safety of production.

[0119] Optionally, in step 105, an online learning mechanism is used to continuously optimize the control strategy of the fluorochemical multi-control valve according to the experience accumulated during operation based on the improved control strategy, including:

[0120] Based on the online learning mechanism, monitor and process the operating state of the improved control strategy to obtain an information report reflecting the actual operating effect of the improved control strategy; based on the information report, analyze the actual operating effect of the improved control strategy according to the information on the operating state of the improved control strategy collected in real time by the distributed sensor network, identify the successful operation modes of the improved control strategy, and accumulate the operation modes as experience to generate an experience library; based on the experience library, use machine learning to update and process the control strategy of the fluorochemical multi-control valve, adjust the weights in the control strategy to ensure that the control strategy adapts to the production requirements of the fluorochemical industry, and generate an updated control strategy; perform optimization suggestion processing on the updated control strategy to further improve the control accuracy and control efficiency of the fluorochemical multi-control valve, generate optimization suggestions, and apply the optimization suggestions to actual control to ensure continuous optimization of the control strategy of the fluorochemical multi-control valve during operation.

[0121] In this embodiment, the online learning mechanism means that the system can continuously learn from the latest data and update its knowledge base during operation to adapt to the changing environment and technological progress. In this step, the system monitors the actual operating effect of the improved control strategy and generates an information report reflecting the actual operating effect. The distributed sensor network collects the operating state information of the improved control strategy in real time for analyzing the actual operating effect, identifying successful operation modes, and accumulating these modes into an experience library. The machine learning algorithm uses the experience library to update and process the control strategy of the fluorochemical multi-control valve, adjusts the weights in the control strategy to ensure its adaptation to production requirements, and thus generates an updated control strategy.

[0122] In the embodiment of the present application, based on the online learning mechanism, the running state of the improved control strategy is monitored, data reflecting the actual running effect is collected, and an information report is generated. Then, according to the running state information collected by the distributed sensor network in real time, the actual running effect of the improved control strategy is analyzed, successful operation modes are identified, and they are accumulated as experience to form an experience library. Next, machine learning technology is used to update the control strategy of the multi-regulating valves in fluorine chemical industry, the weights in the control strategy are adjusted to ensure its adaptation to production requirements, and an updated control strategy is generated. Finally, optimization suggestions are processed for the updated control strategy to further improve the control accuracy and efficiency, and the optimization suggestions are applied to actual control to ensure the continuous optimization of the control strategy during operation.

[0123] To further improve the efficiency of intelligent prediction and preventive maintenance, in a fluorine chemical plant, based on the ideal opening adjustment scheme generated in step 102, in step 103, the system converts these schemes into pulse width modulation control instructions and sends them to the actuator, while monitoring the health status of the communication connection using fault prediction and health management technology. In step 104, the adaptive feedback loop of the deep neural network dynamically corrects the control strategy to ensure precise and efficient valve operation. On this basis, through the online learning mechanism, the system monitors the actual running effect of the improved control strategy, generates an information report, and combines the data of the distributed sensor network to identify successful operation modes and accumulate them into an experience library. Subsequently, machine learning algorithms are used to update the control strategy and adjust the weights to ensure its adaptation to production requirements. Finally, by processing optimization suggestions for the updated control strategy, the control accuracy and efficiency are further improved, ensuring the continuous optimization of the control strategy of the multi-regulating valves during operation, and significantly enhancing the continuity and stability of production.

[0124] The present application considers that in fluorine chemical production, ensuring the stable operation of multi-regulating valves is crucial for maintaining process safety and product quality. Traditional fault detection methods are inefficient and difficult to cope with sudden situations. Fault prediction and health management technology has gradually become a key means to ensure equipment health and improve production continuity. Developing a calculation formula for potential equipment fault risks aims to more accurately evaluate the equipment health status, identify and handle potential fault risks in advance, achieve intelligent prediction and preventive maintenance, and ensure production efficiency and safety. Therefore, a new optional solution is proposed, which includes:

[0125] Optionally, using fault prediction and health management technology to identify and handle potential equipment fault risks to obtain the actual valve control strategy of the multi-regulating valves in fluorine chemical industry, including:

[0126] Continuously monitor the health status of the equipment through fault prediction and health management technology, and identify and handle potential equipment fault risks ;

[0127] Potential equipment failure risk Calculation formula:

[0128] ;

[0129] Wherein, is the potential equipment failure risk, representing the degree from no risk to high risk, with a value range between ; represents the health index of the health management technology, reflecting the health status of the equipment at the future time point ; represents a preset safety threshold, that is, the safety upper limit of the health index. When is less than the safety threshold, it indicates the existence of the potential equipment failure risk, represents the urgency of the predicted failure time, indicating the length of time from the current time to the predicted occurrence time of the equipment failure, represents the maximum predicted failure time urgency, used to standardize the maximum value of; is the equipment failure severity, indicating the degree of influence on the fluorochemical production process when the equipment failure occurs, is the maximum equipment failure severity, used to standardize the maximum value of; is the repair cost, indicating the cost or resource consumption required to repair the equipment failure, is the maximum repair cost, used to standardize the maximum value of; is the weight coefficient, used to adjust the importance of the health index part, is the non-linear influence index of the health index, used to capture the non-linear trend of the health index changing over time, is the weight coefficient, used to adjust the importance of the predicted failure time urgency part, is the weight coefficient, used to adjust the importance of the equipment failure severity part, is the weight coefficient, used to adjust the importance of the repair cost part;

[0130] Analyze and process the potential equipment failure risk to obtain the actual valve control strategy of the fluorochemical multi-control valve.

[0131] The formula comprehensively evaluates the potential failure risks of multiple regulating valves in the fluorochemical industry. By quantifying factors such as the health index, urgency of expected failure time, severity of equipment failure, and repair cost, it provides a comprehensive risk assessment. The summation of each sub-item ensures multi-dimensional consideration, and the weight coefficients adjust the importance of each factor, making the risk assessment more scientific and accurate. This helps to identify and handle potential failures in advance, ensuring production safety and efficiency.

[0132] The following briefly explains the design reasons for each sub-item in the formula:

[0133] Potential equipment failure risk Design reason for the calculation formula: The formula comprehensively and accurately evaluates the potential equipment failure risk, helping decision-makers take preventive measures in a timely manner, reducing unplanned downtime and maintenance costs, and enhancing production continuity and safety.

[0134] Formula expression:

[0135] Potential equipment failure risk : Represents the degree from no risk to high risk, with a value range between and. The closer it is to 1, the higher the potential failure risk;

[0136] Health index : Reflects the health status of the equipment at a future time point , usually calculated from sensor data and historical records, with a full score possibly being 100 or other standardized values;

[0137] Health threshold : The safety upper limit of the equipment health index. When is less than this threshold, it indicates the existence of potential equipment failure risk;

[0138] Urgency of expected failure time : Represents the length of time from the current time to the expected occurrence of equipment failure, that is, the possible time point of failure, used to evaluate the urgency of failure occurrence;

[0139] Maximum urgency of expected failure time : Used to standardize the maximum value of, ensuring is between [0, 1];

[0140] Maximum urgency of expected failure time : Used to standardize the maximum value of, ensuring is between [0, 1];

[0141] Severity of equipment failure : Represents the impact degree on the fluorochemical production process when equipment failures occur, such as downtime, product quality degradation, etc. The full score may be 100 or other standardized values;

[0142] Maximum equipment failure severity : Used for standardization of the maximum value to ensure is between [0, 1];

[0143] Repair cost : Represents the cost or resource consumption required to repair equipment failures, such as material costs, labor costs, etc.;

[0144] Maximum repair cost : Used for standardization of the maximum value to ensure is between [0, 1];

[0145] Weight coefficient , , , , : Used to adjust the importance of each sub-item. For example, and respectively adjust the importance of the health index part and its non-linear impact, while , , respectively adjust the importance of the urgency of the predicted failure time, equipment failure severity, and repair cost parts;

[0146] : This part mainly considers the change trend of the equipment health index. As the health index decreases, the potential failure risk increases. Introduce to capture the non-linear trend of the health index changing over time, so that the formula can more accurately reflect the speed of health status deterioration. The weight coefficient is used to adjust the importance of this factor in the entire risk assessment;

[0147] : This part evaluates the urgency of the predicted failure time. The closer to the failure time, the higher the risk. By standardizing to , ensure its value is within for easy comparison with other factors. The weight coefficient is used to adjust the importance of this factor in the entire risk assessment;

[0148] : This part evaluates the impact degree on the production process when equipment failures occur. If the failure seriously affects production, the risk is naturally higher. By standardizing to , ensure its value is within , facilitating comparison with other factors. The weight coefficient is used to adjust the importance of this factor in the overall risk assessment;

[0149] : This part assesses the cost of repairing faults. A high repair cost means a higher risk because the repair cost may exceed the budget or cause other resource constraints. By normalizing to , ensure its value is within , facilitating comparison with other factors. The weight coefficient is used to adjust the importance of this factor in the overall risk assessment;

[0150] The reason for adding up each sub-item is that each factor independently reflects the potential fault risks in different aspects. By adding them up, the impacts of multiple factors can be comprehensively considered to form a comprehensive risk assessment indicator.

[0151] The following briefly explains how to obtain each parameter of the formula:

[0152] Health index : Real-time data such as temperature, pressure, vibration, etc. are collected through a sensor network deployed on the device. Combining historical maintenance records and performance indicators, machine learning or statistical models are used to predict the health status of the device at a future time point . The health index is usually normalized to or other ranges;

[0153] Health threshold : Set according to industry standards, equipment manufacturer recommendations, or historical fault data analysis. This threshold represents the safety upper limit of the device's health status. When the health index is lower than this value, it is considered that there is a potential fault risk;

[0154] Urgency of expected fault time : Use a fault prediction model to predict the time length from the current time to the possible time of device failure. This prediction is based on historical fault data, current operating conditions, and trend analysis;

[0155] Maximum urgency of expected fault time : Set as the longest time fault warning period that the device may occur. Usually determined according to historical data or expert experience, used to normalize , ensure its value is within [0,1];

[0156] Severity of device failure : Evaluate the impact degree of equipment failures on the production process, including factors such as downtime and product quality decline, obtained through expert evaluation, simulation analysis or summary of historical failure cases, usually standardized to or other ranges;

[0157] Maximum equipment failure severity : Set according to the most serious historical failure case or theoretical maximum impact, used for standardization , ensuring that its value is within ;

[0158] Repair cost : Estimate the cost or resource consumption required to repair equipment failures, including material costs, labor costs, downtime losses, etc., calculated through a cost estimation model or referring to the actual repair costs of similar failures;

[0159] Maximum repair cost : Set based on the highest historical repair cost case or theoretical maximum repair cost, used for standardization , ensuring that its value is within ;

[0160] Weighting coefficient , , , , : The weighting coefficients are set by domain experts based on experience and actual needs, or automatically adjusted through sensitivity analysis and optimization algorithms. These coefficients reflect the relative importance of each factor in risk assessment, ensuring that the formula can accurately reflect the actual situation.

[0161] In the embodiment of this application, in a modern fluorochemical plant, engineers deployed an advanced fault prediction and health management system to monitor the health status of multiple control valves. Suppose there is currently a control valve that needs to evaluate its potential equipment failure risk . The following are the specific implementation steps:

[0162] Health index : Through the data collected by the sensor network, it is found that the health index of this valve at a future time point is 75 (out of 100), while the preset safety threshold is 85. This means that the health status of the valve has approached the critical point;

[0163] Estimated urgency of failure time : According to historical data and trend analysis, it is estimated that this valve will fail within the next 6 months, that is, = 6 months, and the maximum estimated urgency of failure time is set to 12 months;

[0164] Severity of equipment failure : The assessment shows that if this valve fails, it will have a serious impact on the production line. Therefore, the severity of equipment failure is set to 90 (out of 100), and the maximum severity of equipment failure is also 100;

[0165] Repair cost : It is estimated that the cost required to repair the valve failure is 20,000 yuan, and the maximum repair cost is set to 50,000 yuan;

[0166] Weighting factor , , , , : According to expert opinions and experience, they are set to 0.4, 2, 0.2, 0.2, and 0.2 respectively;

[0167] Substitute the values into the formula to calculate the potential equipment failure risk R:

[0168]

[0169] The result of the formula calculation shows that the potential equipment failure risk of this regulating valve is 0.36552, indicating a medium level of risk. Specifically: The contribution of the health index part is relatively small because although it is lower than the safety threshold, the gap is not large; The urgency of the expected failure time is medium, meaning that the time when the failure may occur is relatively close, but it is not imminent; The severity of equipment failure is relatively high, indicating that once a failure occurs, it will have a greater impact on the production process; The repair cost is relatively low and will not cause too much pressure on the budget.

[0170] Based on this conclusion, the engineer decides to take preventive measures, such as arranging preventive maintenance in advance or replacing the valve, and adjusting the production plan to reduce the impact of potential failures. At the same time, continue to closely monitor the status of this valve to ensure that any abnormalities can be detected and handled in a timely manner, thereby ensuring the continuity and safety of production.

[0171] This application takes into account that in fluorochemical production, it is crucial to ensure that the opening settings of multiple regulating valves not only meet safety and quality requirements but also achieve the highest energy efficiency ratio. Traditional methods are difficult to handle complex working conditions. The genetic algorithm optimizes the opening settings through global search, combines process safety and quality goals, generates an ideal adjustment plan, improves production efficiency and safety, and meets the needs of intelligent prediction and preventive maintenance. Therefore, a new alternative solution is proposed, and this solution includes:

[0172] Optionally, according to the optimal operating conditions and the best process state, the genetic algorithm is used to globally search for the opening degree of the fluorochemical multi-regulating valve, and an ideal opening degree adjustment scheme is generated based on the process safety limit and the product quality target, where the ideal opening degree adjustment scheme meets the safety and quality requirements and achieves the highest energy efficiency ratio of the fluorochemical production, including:

[0173] According to the optimal operating conditions and the best process state, the genetic algorithm is used to globally search for the opening degree of the fluorochemical multi-regulating valve;

[0174] Global search calculation formula:

[0175] ;

[0176] Wherein, is the global search calculation formula, that is, the best opening degree of the fluorochemical multi-regulating valve found, is the fitness function, used to evaluate the advantages and disadvantages of each opening degree setting, represents all the opening degree setting spaces of the fluorochemical multi-regulating valve, and the fitness function , represents the energy efficiency ratio of the fluorochemical production under the opening degree setting , represents the safety score, is the product quality score, , , , , , are the corresponding weight coefficients and non-linear exponents respectively, reflecting the importance of the safety score, the product quality score and the energy efficiency ratio of the fluorochemical production and their trends with time or conditions;

[0177] Based on the calculation results of the global search, an ideal opening degree adjustment scheme is generated according to the process safety limit and the product quality target;

[0178] Ideal opening degree adjustment scheme calculation formula:

[0179] ;

[0180] Wherein, is the ideal opening degree adjustment scheme, represents the opening degree setting of the fluorochemical multi-regulating valve, is the penalty function, used to handle individuals that exceed the process safety limit and the product quality target;

[0181] Penalty function :

[0182] ;

[0183] Wherein, represents the process safety limit, represents the product quality target, represents the actual process safety value under the current opening setting, is the actual product quality value under the current opening setting, and are the corresponding safety and quality penalty coefficients respectively, used to adjust the severity of violating the constraints;

[0184] Fitness function:

[0185] , represents the energy efficiency ratio of the fluorination production under the opening setting below, represents the safety score, is the product quality score, , , , , , are the corresponding weight coefficients and non - linear exponents respectively, reflecting the importance of the safety score, the product quality score and the energy efficiency ratio of the fluorination production and their trends of change over time or conditions.

[0186] The design of the above formula aims to globally search for the opening degrees of multiple regulating valves in fluorination through the genetic algorithm, and generate an ideal opening degree adjustment plan by combining the process safety limit and the product quality target. This method not only improves the flexibility and efficiency of production, but also ensures the safety of operation and the product quality, meeting the requirements of modern chemical production for intelligent prediction and preventive maintenance.

[0187] The following briefly explains the design reasons for each item in the formula:

[0188] Design reason for the global search calculation formula: It aims to find the optimal solution in the space 𝑋 of all possible opening settings through the genetic algorithm. The fitness function 𝑓(𝑥) comprehensively evaluates the energy efficiency ratio, safety and product quality, ensuring that the selected opening setting is not only efficient but also meets the safety and quality requirements, realizing the optimization of the production process.

[0189] Formula expression:

[0190] Represents the opening setting of the best fluorochemical multi-control valve found through global search, that is, among all possible opening setting spaces 𝑋, the opening setting that maximizes the fitness function reached.

[0191] : Fitness function, used to evaluate the overall quality of each opening setting by comprehensively considering three key factors: energy efficiency ratio, safety, and product quality, ensuring that the selected opening setting is not only efficient but also meets safety and quality requirements;

[0192] : Weight coefficients, which respectively adjust the relative importance of the energy efficiency ratio, safety, and product quality in the fitness function. These coefficients can be set according to specific production requirements and priorities to reflect the importance of different factors;

[0193] : Nonlinear exponent, used to capture the trend of each factor changing over time or conditions. For example, the nonlinear exponent can be used to represent how the influence of a certain factor increases or decreases as the opening setting changes. This enables the formula to more accurately reflect the actual situation;

[0194] : Energy efficiency ratio score, indicating the energy efficiency ratio of fluorochemical production at the opening setting , usually standardized to or other ranges, where 1 represents the highest energy efficiency ratio. This score reflects the energy utilization efficiency at a specific opening setting;

[0195] : Safety score, indicating the safety level of equipment operation at the opening setting , also standardized to or other ranges, where 1 represents the safest operating state. This score reflects the safety risk level at a specific opening setting;

[0196] : Product quality score, indicating the quality of the product at the opening setting , standardized to or other ranges, where 1 represents the highest product quality. This score reflects the consistency and quality standards of the product at a specific opening setting;

[0197] : This part mainly considers the energy efficiency ratio of fluorochemical production. The weight coefficient is used to adjust the importance of the energy efficiency ratio in the entire fitness function, and the nonlinear exponent captures the nonlinear trend of the energy efficiency ratio changing with the opening setting. This ensures that the formula can more accurately reflect the actual impact of different opening settings on the energy efficiency ratio;

[0198] : This part evaluates the safety of equipment operation, and the weight coefficient is used to adjust the importance of safety in the entire fitness function, and the non-linear exponent captures the non-linear trend of safety changing with the opening setting, which ensures that the formula can comprehensively consider the safety risks under different opening settings;

[0199] : This part evaluates the product quality, and the weight coefficient is used to adjust the importance of product quality in the entire fitness function, and the non-linear exponent captures the non-linear trend of product quality changing with the opening setting, which ensures that the formula can accurately reflect the impact of different opening settings on product quality;

[0200] The reason for adding each sub-item is that each sub-item independently reflects the performance indicators in different aspects. By adding them together, the influence of multiple factors can be comprehensively considered to form a comprehensive risk assessment index.

[0201] Reason for designing the ideal opening adjustment scheme: On the basis of global search, the penalty function 𝑃(𝑥) is introduced to ensure that the finally selected opening setting meets the process safety limit and product quality target. When the opening setting results in the actual process safety value being lower than the safety limit , or the actual product quality value being lower than the quality target at this time, the penalty function will increase additional costs or reduce the fitness score. The fitness function 𝑓(𝑥) can comprehensively and accurately evaluate the overall advantages and disadvantages of each opening setting, helping decision-makers find the best opening setting that can not only improve production efficiency but also ensure safety and quality. This ensures that the finally selected opening setting not only has the best performance but also strictly complies with safety and quality constraints, guaranteeing the continuity and reliability of production.

[0202] Formula expression:

[0203] : The ideal opening adjustment scheme represents the opening setting that maximizes the fitness function minus the penalty function among all possible opening settings , ensuring that the finally selected opening setting not only has the best performance but also strictly complies with safety and quality constraints;

[0204] : The space of all possible opening settings of the fluorochemical multi-control valve represents all feasible opening configuration options;

[0205] : Fitness function, used to evaluate the overall quality of each opening setting by comprehensively considering three key factors: energy efficiency ratio, safety, and product quality;

[0206] : Penalty function, used to handle situations that exceed the process safety limit and product quality target. If a certain opening setting violates these limits, its fitness score is reduced through the penalty function;

[0207] : Process safety limit, representing the safety threshold for equipment operation. Exceeding this value means there are potential safety hazards;

[0208] : Product quality target, representing the desired product quality standard. Falling below this value means the product quality does not meet the standard;

[0209] : Actual process safety value under the current opening setting, reflecting whether the current setting meets the safety requirements;

[0210] : Actual product quality value under the current opening setting, reflecting whether the current setting meets the quality requirements;

[0211] and : Safety and quality penalty coefficients, used to adjust the severity of constraint violations. A larger coefficient means a more severe penalty for constraint violations;

[0212] , , , , , : Weight coefficients and non - linear exponents, which respectively adjust the relative importance of the energy efficiency ratio, safety, and product quality in the fitness function and their trends with time or conditions;

[0213] : This part mainly considers the energy efficiency ratio of fluorochemical production. The weight coefficient is used to adjust the importance of the energy efficiency ratio in the overall fitness function, while the non - linear exponent captures the non - linear trend of the energy efficiency ratio with the change of the opening setting, which ensures that the formula can more accurately reflect the actual impact of different opening settings on the energy efficiency ratio.

[0214] : This part evaluates the safety of equipment operation. The weight coefficient is used to adjust the importance of safety in the overall fitness function, while the non - linear exponent Capture the non - linear trend of capture safety varying with the opening setting, which ensures that the formula can comprehensively consider the safety risks under different opening settings;

[0215] : This part evaluates the product quality, and the weight coefficient is used to adjust the importance of product quality in the entire fitness function, and the non - linear exponent captures the non - linear trend of product quality varying with the opening setting, which ensures that the formula can accurately reflect the impact of different opening settings on product quality;

[0216] By subtracting the penalty function from the fitness function, it is ensured that the final selection is not only excellent in performance but also strictly complies with safety and quality constraints. This approach enables the optimization process to pursue efficiency without sacrificing safety and quality, thus achieving the optimization of the production process.

[0217] The following is a brief explanation of the methods for obtaining each parameter of the formula:

[0218] : Through genetic algorithms or other optimization methods, search in the space of all possible opening settings to find the optimal opening setting that maximizes the fitness function minus the penalty function;

[0219] : The opening - setting space is defined by engineers based on the equipment operation range and historical data, usually including a series of discrete or continuous opening values, ensuring coverage of all feasible adjustment ranges;

[0220] : The fitness function comprehensively evaluates the energy efficiency ratio, safety, and product quality of each opening setting, and the specific values are calculated through simulation models, historical data, and real - time monitoring data;

[0221] : The penalty function is used to handle situations that exceed the process safety limit and product quality target, and the specific values are calculated based on safety and quality monitoring data in actual operations;

[0222] and : The safety and quality penalty coefficients are set by domain experts based on experience and industry standards, or determined through sensitivity analysis. These coefficients reflect the severity of violating safety and quality constraints;

[0223] : The process safety limit is provided by equipment manufacturers or industry specifications, representing the safety threshold for equipment operation. For example, the maximum allowable values of parameters such as temperature, pressure, etc.;

[0224] : The product quality target is set by production standards or customer requirements, representing the expected product quality standards. For example, indicators such as purity and impurity content;

[0225] : The actual process safety value under the current opening setting is obtained through the analysis of real-time sensor data (such as temperature, pressure, vibration, etc.) and historical data;

[0226] : The actual product quality value under the current opening setting is obtained through on-line detection instruments, laboratory analysis or historical quality records;

[0227] , , , , , : The weight coefficient and non-linear index are set by domain experts according to experience and specific requirements, or automatically adjusted through machine learning methods. These coefficients determine the relative importance of each factor in the fitness function and its trend of change over time or conditions;

[0228] : The energy efficiency ratio score is predicted through a simulation model or historical data, reflecting the energy utilization efficiency under a specific opening setting. For example, the ratio of energy consumption to production;

[0229] : The safety score is evaluated through fault prediction and health management technology, combining real-time sensor data and historical fault data to predict the safety state of the equipment at a future time point;

[0230] : The product quality score is obtained through on-line detection instruments, laboratory analysis or historical quality records, reflecting the product quality level under a specific opening setting.

[0231] In the embodiment of the present application, in a modern fluorochemical plant, engineers apply genetic algorithms to optimize the opening settings of multiple regulators. Assume that currently it is necessary to determine the optimal opening of a regulator , in order to achieve the highest energy efficiency ratio, the best safety and product quality. The following are the specific implementation steps:

[0232] Define the fitness function : The fitness function comprehensively considers the energy efficiency ratio , the safety score and the product quality score . The weight coefficient , , , , , are respectively set to 0.4, 2, 0.3, 1.5, 0.3 and 1.2, reflecting the importance of each factor and its non-linear influence.

[0233] Generate a set of random opening settings as the initial population according to the optimal operating conditions and the best process state , and each individual represents a possible opening setting.

[0234] Evaluate fitness: For each opening setting calculate the fitness function ,

[0235] (with a full score of 1)

[0236] (with a full score of 1)

[0237] (with a full score of 1)

[0238] Global search calculation:

[0239] Use the selection, crossover and mutation operations of the genetic algorithm to iteratively find the optimal solution . Assume that the fitness value of the best opening setting found after multiple rounds of iteration is:

[0240]

[0241] Introduce a penalty function :

[0242] Check whether it meets the process safety limit and the product quality target , (below the safety limit ), the actual product quality value (above the quality target ); then the penalty function is:

[0243]

[0244] Generate an ideal opening adjustment plan :

[0245] The final ideal opening adjustment plan is the maximum fitness value after considering the penalty:

[0246]

[0247] The calculation results show that the optimal opening setting obtained through the global search of the genetic algorithm After considering the safety and quality constraints, the fitness value is 0.8197. The specific conclusions are as follows:

[0248] Energy efficiency ratio: Although it reaches a relatively high level (0.85), it is not the highest because safety and quality also need to be considered.

[0249] Safety: Although it is lower than the safety limit , but due to the small gap, the penalty term has little impact.

[0250] Product quality: it exceeds the quality target , indicating that the product quality is well guaranteed.

[0251] Based on this result, the engineer decides to adopt as the final opening adjustment plan, which ensures the safety of the production process and the product quality, and at the same time achieves a relatively high energy efficiency ratio. This plan not only improves the continuity and stability of production, but also reduces the risk of potential failures, providing strong support for intelligent prediction and preventive maintenance.

[0252] Figure 2 This application example provides a structural schematic diagram of an automatic control system for multiple fluorination valves, as Figure 2 shown. The device includes:

[0253] A prediction module 21, which evaluates the optimal operating conditions under the current fluorination production conditions based on the Markov decision process and performs prediction processing on the optimal operating conditions to obtain the best process state;

[0254] A search module 22, which, according to the optimal operating conditions and the best process state, uses the genetic algorithm to globally search for the opening of the multiple fluorination valves, and generates an ideal opening adjustment plan based on the process safety limit and the product quality target, where the ideal opening adjustment plan meets the safety and quality requirements and achieves the highest energy efficiency ratio of the fluorination production;

[0255] An identification module 23, which converts the ideal opening adjustment plan into a pulse width modulation control instruction, sends the pulse width modulation control instruction to the actuator of the corresponding multiple fluorination valves through the industrial communication bus, and uses the fault prediction and health management technology to identify and process the potential equipment failure risks to obtain the actual valve control strategy of the multiple fluorination valves;

[0256] The correction module 24 uses an adaptive feedback loop of a deep neural network to compare the difference between the actual effect of the actual valve control strategy and the expected effect of the ideal opening adjustment scheme, and uses the backpropagation algorithm to dynamically correct the actual valve control strategy to obtain an improved control strategy;

[0257] The optimization module 25 uses an online learning mechanism to continuously optimize the control strategy of the multi-regulating valve for fluorochemical industry according to the experience accumulated during the operation of the improved control strategy.

[0258] Figure 2 The described automatic control system for multi-regulating valves in fluorochemical industry can execute Figure 1 The described automatic control method for multi-regulating valves in fluorochemical industry in the illustrated embodiment, and its implementation principle and technical effects will not be elaborated further. For the automatic control system for multi-regulating valves in fluorochemical industry in the above embodiment, the specific ways for each module and unit to execute operations have been described in detail in the embodiments related to the method, and will not be elaborated here.

[0259] In a possible design, Figure 2 The automatic control system for multi-regulating valves in fluorochemical industry in the illustrated embodiment can be implemented as a computing device, as Figure 3 shown, and this computing device can include a storage component 31 and a processing component 32;

[0260] The storage component 31 stores one or more computer instructions, where the one or more computer instructions are for the processing component 32 to call and execute.

[0261] The processing component 32 is used for the Figure 1 described automatic control method for multi-regulating valves in fluorochemical industry in the above embodiment.

[0262] Among them, the processing component 32 can include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component can also be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components for executing the above method.

[0263] The storage component 31 is configured to store various types of data to support the operations of the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0264] Of course, the computing device may necessarily further include other components, such as input / output interfaces, display components, communication components, etc.

[0265] The input / output interface provides an interface between the processing component and the peripheral interface module, and the above-mentioned peripheral interface module may be an output device, an input device, etc.

[0266] The communication component is configured to facilitate communication between the computing device and other devices in a wired or wireless manner, etc.

[0267] Among them, the computing device may be a physical device or an elastic computing host provided by a cloud computing platform, etc. At this time, the computing device may refer to a cloud server, and the above-mentioned processing component, storage component, etc. may be basic server resources leased or purchased from a cloud computing platform.

[0268] The embodiment of the present application also provides a computer storage medium storing a computer program, and when the computer program is executed by a computer, it can implement the above Figure 1 shown embodiment of an automatic control method for multiple regulating valves in fluorine chemical industry.

[0269] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described systems, devices, and units can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein.

[0270] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative labor.

[0271] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0272] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, and are not intended to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A fluorine chemical multi-regulating valve automatic control method, characterized in that: include: Based on the Markov decision process, the optimal operating conditions under the current fluorine chemical production conditions are evaluated, and the optimal operating conditions are predicted and processed to obtain the optimal process state; According to the optimal operating conditions and the optimal process state, a genetic algorithm is used to perform a global search for the opening of the fluorine chemical multi-regulating valve, and an ideal opening adjustment scheme is generated based on the process safety limit and the product quality target, wherein the ideal opening adjustment scheme meets the safety and quality requirements and achieves the highest energy efficiency ratio of the fluorine chemical production; Convert the ideal opening adjustment scheme into a pulse width modulation control instruction, send the pulse width modulation control instruction to the corresponding actuator of the fluorine chemical multi-control valve through an industrial communication bus, and use fault prediction and health management technology to identify and handle potential equipment failure risks, so as to obtain an actual valve control strategy for the fluorine chemical multi-control valve; Using an adaptive feedback loop of a deep neural network, the difference between the actual effect of the actual valve control strategy and the expected effect of the ideal opening adjustment scheme is compared, and the actual valve control strategy is dynamically corrected using a back propagation algorithm to obtain an improved control strategy; Using an online learning mechanism, the control strategy of the fluorine chemical multi-control valve is continuously optimized based on the experience accumulated during the operation of the improved control strategy; According to the optimal operating conditions and the optimal process state, a genetic algorithm is used to perform a global search for the opening of the fluorine chemical multi-regulating valve, and an ideal opening adjustment scheme is generated based on the process safety limit and the product quality target, wherein the ideal opening adjustment scheme meets the safety and quality requirements and achieves the highest energy efficiency ratio of the fluorine chemical production, including: According to the optimal operating conditions and the optimal process state, a genetic algorithm is used to perform a global search on the opening of the fluorine chemical multi-regulating valve; Global search calculation formula: ； in, is the global search calculation formula, i.e., the best opening of the fluorine chemical multi-regulating valve found, is the fitness function, which is used to evaluate the quality of each opening setting. Represents the opening setting space of all the fluorine chemical multi-control valves, fitness function , Represents the opening setting The energy efficiency ratio of fluorine chemical production under represents the safety score, is the product quality rating, , , , , , are the corresponding weight coefficient and nonlinear index, respectively, reflecting the importance of the safety score, the product quality score and the energy efficiency ratio of the fluorine chemical production and their trends over time or conditions; Based on the calculation results of the global search, an ideal opening adjustment plan is generated according to the process safety limit and the product quality target; The calculation formula for the ideal opening adjustment scheme is: ； in, is the ideal opening adjustment scheme, X represents the opening setting of the fluorine chemical multi-regulating valve, is a penalty function used to deal with individuals that exceed the process safety limit and the product quality target; Penalty Function : ； in, represents the process safety limit, Represents the product quality target, Represents the actual process safety value under the current opening setting. is the actual product quality value under the current opening setting, and are the corresponding safety and quality penalty coefficients, which are used to adjust the severity of constraint violations; Fitness function: , Represents the opening setting The energy efficiency ratio of fluorine chemical production under represents the safety score, is the product quality rating, , , , , , are the corresponding weight coefficient and nonlinear index, respectively, reflecting the importance of the safety score, the product quality score and the energy efficiency ratio of the fluorine chemical production and their trends over time or conditions.

2. The method according to claim 1, characterized in that The ideal opening adjustment scheme is converted into a pulse width modulation control instruction, and the pulse width modulation control instruction is sent to the corresponding actuator of the fluorine chemical multi-control valve through an industrial communication bus, and the potential equipment failure risk is identified and processed by using fault prediction and health management technology to obtain the actual valve control strategy of the fluorine chemical multi-control valve, including: Based on the ideal opening adjustment scheme, converting the opening information in the ideal opening adjustment scheme into a pulse width modulation control instruction of the actuator of the fluorine chemical multi-regulating valve to generate a pulse width modulation signal; Based on the pulse width modulation signal and the industrial communication bus, in combination with the time synchronization protocol, the pulse width modulation control instruction is timestamped, and the pulse width modulation control instruction is optimized and scheduled through distributed control to ensure that the pulse width modulation control instruction is sent to the corresponding actuator of the fluorine chemical multi-regulating valve, and a communication connection is established between the industrial communication bus and the actuator of the fluorine chemical multi-regulating valve; Based on the communication connection, using fault prediction and health management technology, combined with real-time data analysis and pattern recognition algorithms, the operation status of the communication connection is monitored in real time, an abnormality detection algorithm is used to automatically identify abnormal operation modes of the communication connection, and potential risks are evaluated through a machine learning model to generate a potential risk assessment report; Based on the potential risk assessment report, adaptive filtering is used to filter noise of the communication connection, and preventive measures are generated to ensure safe operation of the communication connection; Based on the preventive measures and the pulse width modulation signal, the actuator of the fluorine chemical multi-control valve adjusts the opening information intelligently to generate an actual valve control strategy.

3. The method according to claim 2, characterized in that Based on the communication connection, the operation status of the communication connection is monitored in real time by using fault prediction and health management technology, combined with real-time data analysis and pattern recognition algorithms, and abnormal operation modes of the communication connection are automatically identified by using anomaly detection algorithms. Potential risks are evaluated by machine learning models to generate a potential risk assessment report, including: Based on the communication connection, using fault prediction and health management technology, combined with real-time data analysis and pattern recognition algorithms, continuously monitoring the operating status of the communication connection, collecting status information of the communication connection through sensors on the industrial communication bus, and transmitting the status information to the central processing unit of the communication connection to obtain the operating status of the communication connection; According to the operation status of the communication connection, the collected operation status is analyzed and processed using an anomaly detection algorithm to automatically identify abnormal operation modes of the communication connection to generate a potential abnormal operation mode report; Based on the potential abnormal operation mode report, potential risks are evaluated through a machine learning model to generate a potential risk assessment report.

4. The method according to claim 1, characterized in that: Using an adaptive feedback loop of a deep neural network, the difference between the actual effect of the actual valve control strategy and the expected effect of the ideal opening adjustment scheme is compared, and the actual valve control strategy is dynamically corrected using a back propagation algorithm to obtain an improved control strategy, including: Based on the adaptive feedback loop of the deep neural network, the operating state of the actual valve control strategy is monitored and analyzed to obtain the actual effect of the actual valve control strategy; Based on the actual effect of the actual valve control strategy and the expected effect of the ideal opening adjustment scheme, a comparison is performed to analyze the difference between the actual effect and the expected effect to generate a difference analysis result; According to the difference analysis results, using the back propagation algorithm in the deep neural network, analyzing the specific reasons causing the differences in the difference analysis results, and adjusting the weights of the deep neural network to generate correction suggestions; According to the correction suggestion, the actual valve control strategy is optimized to improve the accuracy and efficiency of the actual valve control strategy and generate an improved control strategy.

5. The method according to claim 4, characterized in that According to the difference analysis results, the back propagation algorithm in the deep neural network is used to analyze the specific reasons causing the differences in the difference analysis results, and the weights of the deep neural network are adjusted to generate correction suggestions, including: According to the difference analysis result, the gap between the actual effect obtained and the expected effect is quantified to obtain an initial error value, the initial error value is transmitted layer by layer through the back propagation algorithm in the deep neural network, and the specific cause of the gap is identified to generate a preliminary recognition result; Based on the preliminary identification results, the key influencing factors in the preliminary identification results are extracted by principal component analysis, and the key influencing factors are refined in combination with sensitivity analysis to obtain a list of key influencing factors; According to the list of key influencing factors, using adaptive moment estimation, adjusting the key influencing factors to reduce the difference between the actual effect and the expected effect, so as to obtain preliminary correction suggestions; Based on the preliminary correction suggestions, the weights of the deep neural network are adjusted, and the obtained control strategy is improved to generate correction suggestions.

6. The method according to claim 1, characterized in that According to the optimal operating conditions and the optimal process state, a genetic algorithm is used to perform a global search for the opening of the fluorine chemical multi-control valve, and based on the process safety limit and product quality target, an ideal opening adjustment plan is generated, including: Analyzing the opening settings of the fluorine chemical multi-regulating valve according to the optimal operating conditions and the optimal process state to generate different opening setting combinations; Based on the opening setting combination, a group of the opening setting combinations representing different opening settings are initialized as initial solutions, and according to the current optimal operating conditions and the optimal process state, the energy efficiency ratio, safety and product quality performance of each of the opening setting combinations are evaluated to obtain candidate solutions composed of the opening setting combinations with excellent performance; Based on the candidate solutions, using the selection, crossover and mutation steps in the genetic algorithm, exploring the adjustment solutions of the opening setting combinations in the candidate solutions to generate a preliminary ideal opening adjustment solution; Based on the preliminary ideal opening adjustment plan, the iterative optimization is continued, and an ideal opening adjustment plan is generated according to the process safety limit and product quality goals. The ideal opening adjustment plan achieves the highest energy efficiency ratio of the fluorine chemical production.

7. The method according to claim 1, characterized in that By using an online learning mechanism, based on the experience accumulated during the operation of the improved control strategy, the control strategy of the fluorine chemical multi-control valve is continuously optimized, including: Based on the online learning mechanism, the operating status of the improved control strategy is monitored to obtain an information report reflecting the actual operating effect of the improved control strategy; Based on the information report, according to the information of the operating status of the improved control strategy collected in real time by the distributed sensor network, the actual operating effect of the improved control strategy is analyzed, the successful operating mode of the improved control strategy is identified, and the operating mode is accumulated as experience to generate an experience library; Based on the experience database, the control strategy of the fluorine chemical multi-control valve is updated by using machine learning, the weight in the control strategy is adjusted, the control strategy is ensured to adapt to the production needs of the fluorine chemical industry, and an updated control strategy is generated; The updated control strategy is processed with optimization suggestions to further improve the control accuracy and control efficiency of the fluorine chemical multi-control valve, so as to generate optimization suggestions, and the optimization suggestions are applied to actual control to ensure that the control strategy of the fluorine chemical multi-control valve is continuously optimized during operation.

8. The method according to claim 7, characterized in that Fault prediction and health management technology is used to identify and handle potential equipment failure risks to obtain the actual valve control strategy of the fluorine chemical multi-control valve, including: Continuously monitor the health status of equipment through fault prediction and health management technology to identify and address potential equipment failure risks ; Potential equipment failure risk The calculation formula is: ； in, is the potential equipment failure risk, ranging from no risk to high risk, with a value range of between, The health index representing the health management technology reflects the health of the device at a future point in time. health status, represents the preset safety threshold, that is, the safety upper limit of the health index. When it is less than the safety threshold, it indicates that there is a potential risk of equipment failure. Represents the urgency of the expected failure time, indicating the distance from the expected time of equipment failure to the current time. Represents the maximum expected failure time urgency, used for standardization The maximum value of The severity of the equipment failure indicates the degree of impact on the fluorine chemical production process when the equipment failure occurs. is the maximum device fault severity, used to normalize The maximum value of is the repair cost, which represents the cost or resource consumption required to repair the equipment failure. is the maximum repair cost, used for normalization The maximum value of is the weight coefficient used to adjust the importance of the health index part, is the nonlinear influence index of the health index, used to capture the nonlinear trend of the health index changing over time, is the weight coefficient used to adjust the importance of the urgency of the estimated failure time part, is the weight coefficient used to adjust the importance of the device failure severity component, is a weight coefficient used to adjust the importance of the repair cost component; The potential equipment failure risk is analyzed and processed to obtain the actual valve control strategy of the fluorine chemical multi-regulating valve.

9. A fluorine chemical multi-regulating valve automatic control system, characterized in that: include: A prediction module, which evaluates the optimal operating conditions under the current fluorine chemical production conditions based on the Markov decision process, and performs prediction processing on the optimal operating conditions to obtain the optimal process state; A search module, which uses a genetic algorithm to perform a global search for the opening of the fluorine chemical multi-regulating valve according to the optimal operating conditions and the optimal process state, and generates an ideal opening adjustment plan based on process safety limits and product quality targets, wherein the ideal opening adjustment plan meets safety and quality requirements and achieves the highest energy efficiency ratio of the fluorine chemical production; An identification module converts the ideal opening adjustment scheme into a pulse width modulation control instruction, sends the pulse width modulation control instruction to the corresponding actuator of the fluorine chemical multi-control valve through an industrial communication bus, and uses fault prediction and health management technology to identify and handle potential equipment failure risks to obtain an actual valve control strategy for the fluorine chemical multi-control valve; A correction module, using an adaptive feedback loop of a deep neural network, compares the difference between the actual effect of the actual valve control strategy and the expected effect of the ideal opening adjustment scheme, and dynamically corrects the actual valve control strategy using a back propagation algorithm to obtain an improved control strategy; An optimization module, utilizing an online learning mechanism to continuously optimize the control strategy of the fluorine chemical multi-control valve according to the experience accumulated during the operation of the improved control strategy; According to the optimal operating conditions and the optimal process state, a genetic algorithm is used to perform a global search for the opening of the fluorine chemical multi-regulating valve, and an ideal opening adjustment scheme is generated based on the process safety limit and the product quality target, wherein the ideal opening adjustment scheme meets the safety and quality requirements and achieves the highest energy efficiency ratio of the fluorine chemical production, including: According to the optimal operating conditions and the optimal process state, a genetic algorithm is used to perform a global search on the opening of the fluorine chemical multi-regulating valve; Global search calculation formula: ； in, is the global search calculation formula, i.e., the best opening of the fluorine chemical multi-regulating valve found, is the fitness function, which is used to evaluate the quality of each opening setting. Represents the opening setting space of all the fluorine chemical multi-control valves, fitness function , Represents the opening setting The energy efficiency ratio of fluorine chemical production under represents the safety score, is the product quality rating, , , , , , are the corresponding weight coefficient and nonlinear index, respectively, reflecting the importance of the safety score, the product quality score and the energy efficiency ratio of the fluorine chemical production and their trends over time or conditions; Based on the calculation results of the global search, an ideal opening adjustment plan is generated according to the process safety limit and the product quality target; The calculation formula for the ideal opening adjustment scheme is: ； in, is the ideal opening adjustment scheme, X represents the opening setting of the fluorine chemical multi-regulating valve, is a penalty function used to deal with individuals that exceed the process safety limit and the product quality target; Penalty Function : ； in, represents the process safety limit, Represents the product quality target, Represents the actual process safety value under the current opening setting. is the actual product quality value under the current opening setting, and are the corresponding safety and quality penalty coefficients, which are used to adjust the severity of constraint violations; Fitness function: , Represents the opening setting The energy efficiency ratio of fluorine chemical production under represents the safety score, is the product quality rating, , , , , , are the corresponding weight coefficient and nonlinear index, respectively, reflecting the importance of the safety score, the product quality score and the energy efficiency ratio of the fluorine chemical production and their trends over time or conditions.

Images