Reactor bed temperature control system

Abstract

The invention relates to the technical field of monitoring control, and provides a reactor bed temperature control system. Collecting operation data from the reactor through a data interface of the sensor network, extracting a feature subset representing the current working attribute of the reactor from the operation data through data analysis, and determining a target variable based on the feature subset; key task parameters are extracted from current task information of the reactor; inputting the feature subset, the target variable and the key task parameter into a pre-trained temperature control model to generate a temperature control strategy corresponding to the current moment; and sending the temperature control strategy to a controller through a hardware interface, and controlling the flow and temperature of the cooling medium and the power of the heating element through the controller. According to the invention, accurate temperature control is realized, the accuracy and efficiency of temperature control are improved, the robustness and self-adaptability of the control system are enhanced, and a powerful guarantee is provided for stable operation of the reactor.

Description

Technical Field

[0001] This application relates to the technical field of monitoring and control, and more particularly, to a reactor bed temperature control system. Background Art

[0002] Reactor bed temperature control is a key link in reactor operation. During a chemical reaction process, temperature is an important factor affecting reaction rate, selectivity, and conversion rate. Especially in a fixed-bed reactor, since the catalyst bed is stationary and the reaction materials pass through the bed for reaction, the control of the bed temperature is particularly important. Fixed-bed reactors are widely used in the chemical industry, such as catalytic reforming in the oil refining industry, natural gas conversion, and processes such as ammonia synthesis, sulfur trioxide synthesis, and methanol synthesis in the chemical industry. These processes usually involve gas-solid catalytic reactions, and the activity, selectivity, and stability of the catalyst have a direct impact on the reaction results. Therefore, in order to maintain the best performance of the catalyst, the bed temperature must be precisely controlled.

[0003] In practical applications, during the process of controlling the reaction bed temperature, regulation is often carried out based on the real-time data of a single reaction bed. However, due to the large volume, high heat capacity of the bed layer, and significant hysteresis in temperature changes. When adjusting operating conditions to change the temperature, it takes a long time to see the effect of the temperature change. Especially in the case of different task requirements, this increases the difficulty and uncertainty of temperature control. Summary of the Invention

[0004] This application provides a reactor bed temperature control system, which can, to at least a certain extent, solve the problem of low accuracy and efficiency in the process of reaction bed temperature control under different task requirements.

[0005] Other features and advantages of this application will become apparent through the following detailed description, or will be partially learned through the practice of this application.

[0006] According to one aspect of this application, a reactor bed temperature control method is provided, including: collecting operation data from the reactor through the data interface of the sensor network, and obtaining the current task information of the reactor; extracting a feature subset characterizing the current working attributes of the reactor from the operation data through data analysis, and determining a target variable to be regulated from preset variables based on the feature subset; extracting key task parameters from the current task information of the reactor; the key task parameters include reaction time, temperature range, and pressure upper limit; inputting the feature subset, the target variable, and the key task parameters into a pre-trained temperature control model to generate a temperature control strategy corresponding to the current moment; sending the temperature control strategy to the controller through the hardware interface, and controlling the flow rate and temperature of the cooling medium and the power of the heating element through the controller.

[0007] In this application, based on the foregoing solution, extracting a feature subset representing the current working attributes of the reactor from the operation data through data analysis, and determining a target variable to be regulated from preset variables based on the feature subset includes: extracting a feature subset from the operation data through data analysis, where the feature subset is used to represent the current working attributes of the reactor; determining the linear relationship between the features in the feature subset and the preset variables according to the preset variables of the reactor; and determining the target variable to be regulated from the preset variables according to the linear relationship.

[0008] In this application, based on the foregoing solution, extracting a feature subset from the operation data through data analysis includes: selecting features from the operation data according to the correlation parameters between the operation data and preset tags to form a first subset; constructing a linear regression model, and recursively removing unnecessary features from the first subset until the number of features in the set reaches a preset number of features to generate a second subset; constructing an interaction network between the features in the second subset, and determining a feature subset according to the influence between the features in the interaction network.

[0009] In this application, based on the foregoing solution, extracting key task parameters from the current task information of the reactor includes: predicting the reaction time corresponding to this task according to the reactant concentration, estimated pressure, and activation energy in the task information; predicting the temperature range corresponding to this task according to the reaction heat, reactant concentration, and estimated pressure in the task information; and predicting the upper pressure limit corresponding to this task according to the reaction volume, reaction heat, reactant concentration, and estimated pressure in the task information.

[0010] In this application, based on the foregoing solution, before inputting the feature subset, the target variable, and the key task parameters into a pre-trained temperature control model to generate a temperature control strategy corresponding to the current moment, it further includes: determining a state space and a space action according to the equipment parameters of the reactor; determining a reward function according to the performance index of the reactor, where the reward function is used to evaluate the temperature control strategy through the reward function; generating a reinforcement learning algorithm according to the gradient strategy, and training based on the state space, the space action, and the reward function to generate the temperature control model.

[0011] In this application, based on the foregoing solution, it further includes: using a monitoring tool to perform real-time tracking and recording on the prediction performance of the temperature control model, and immediately triggering an adaptive adjustment mechanism once a decrease in model performance or an abnormal situation is found.

[0012] In this application, based on the foregoing solution, the operation data includes temperature, pressure, reactant concentration, and product generation rate.

[0013] According to one aspect of the present application, a reactor bed temperature control system is provided, including:

[0014] An acquisition unit, configured to collect operation data from a reactor through a data interface of a sensor network and obtain current task information of the reactor;

[0015] An extraction unit, configured to extract a feature subset characterizing the current working attributes of the reactor from the operation data through data analysis, and determine a target variable to be regulated from preset variables based on the feature subset;

[0016] A task unit, configured to extract key task parameters from the current task information of the reactor; the key task parameters include reaction time, temperature range, and pressure upper limit;

[0017] A training unit, configured to input the feature subset, the target variable, and the key task parameters into a pre-trained temperature control model to generate a temperature control strategy corresponding to the current moment;

[0018] A control unit, configured to send the temperature control strategy to a controller through a hardware interface, and control the flow rate and temperature of a cooling medium and the power of a heating element through the controller.

[0019] According to one aspect of the present application, a computer-readable medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the reactor bed temperature control system as described in the above embodiment is implemented.

[0020] According to one aspect of the present application, an electronic device is provided, including: one or more processors; a storage device, configured to store one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the reactor bed temperature control system as described in the above embodiment.

[0021] According to one aspect of the present application, a computer program product or a computer program is provided. The computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the reactor bed temperature control system provided in the above various optional implementation manners.

[0022] In the technical solution of this application, operation data is collected from the reactor through the data interface of the sensor network, and the current task information of the reactor is obtained; a feature subset characterizing the current working attributes of the reactor is extracted from the operation data through data analysis, and a target variable to be regulated is determined from the preset variables based on the feature subset; key task parameters are extracted from the current task information of the reactor; the key task parameters include reaction time, temperature range, and pressure upper limit; the feature subset, the target variable, and the key task parameters are input into a pre-trained temperature control model to generate a temperature control strategy corresponding to the current moment; the temperature control strategy is sent to the controller through the hardware interface, and the controller is used to control the flow rate and temperature of the cooling medium and the power of the heating element. The reactor bed temperature control system realizes precise temperature control by accurately extracting the operation data of the reactor, combining the key task parameters generated from the task information, performing model training and temperature control, adaptively combining the key task parameters based on the actual operating state of the reaction bed, which not only improves the accuracy and efficiency of temperature control, but also enhances the robustness and adaptability of the control system, providing a strong guarantee for the stable operation of the reactor.

[0023] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit this application. Brief Description of the Drawings

[0024] The drawings herein are incorporated into the specification and constitute a part of this specification, showing embodiments consistent with this application, and are used together with the specification to explain the principles of this application. Obviously, the drawings in the following description are only some embodiments of this application, and those of ordinary skill in the art can obtain other drawings without creative efforts based on these drawings.

[0025] Figure 1 Schematically shows the flowchart of the reactor bed temperature control system in an embodiment of this application.

[0026] Figure 2 Schematically shows the flowchart of determining the target variable in an embodiment of this application.

[0027] Figure 3 Schematically shows the schematic diagram of the reactor bed temperature control system in an embodiment of this application.

[0028] Figure 4 Shows the structural schematic diagram of the computer system of the electronic device suitable for implementing the embodiments of this application. Detailed Description of the Embodiments

[0029] Example embodiments will now be described more fully with reference to the accompanying drawings. However, the example embodiments can be implemented in various forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this application will be more complete and comprehensive, and will fully convey the concept of the example embodiments to those skilled in the art.

[0030] In addition, the described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of the embodiments of this application. However, those skilled in the art will realize that the technical solutions of this application can be practiced without one or more of the specific details, or other methods, components, devices, steps, etc. may be used. In other cases, well-known methods, devices, implementations, or operations are not shown or described in detail to avoid obscuring aspects of this application.

[0031] The block diagrams shown in the drawings are only functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0032] The flowcharts shown in the drawings are only illustrative and not necessarily include all the content and operations / steps, nor are they necessarily executed in the order described. For example, some operations / steps can be decomposed, while some operations / steps can be combined or partially combined, so the actual execution order may change according to the actual situation.

[0033] The implementation details of the technical solutions of this application are elaborated in detail below:

[0034] Figure 1 A flowchart of a reactor bed temperature control system according to an embodiment of this application is shown. Referring to Figure 1 as shown, the reactor bed temperature control system at least includes steps S110 to S150, which are introduced in detail as follows:

[0035] In step S110, operation data is collected from the reactor through the data interface of the sensor network, and the current task information of the reactor is obtained.

[0036] In an embodiment of this application, operation data, including data such as temperature, pressure, and reactant concentration, is automatically and real-time collected from the reactor through the data interface of the sensor network. And the current task information executed by the reactor, such as reaction formula, target product, and expected output, is synchronously obtained to provide basic data support for subsequent data analysis and temperature control strategy formulation.

[0037] Collecting operation data through the data interface of the sensor network ensures the real-time and accuracy of the data. Obtaining the current task information of the reactor provides a basis for subsequent temperature control strategies. Implementing comprehensive monitoring of the reactor operation status provides a reliable data source for subsequent data analysis and strategy formulation.

[0038] In step S120, a feature subset characterizing the current working attributes of the reactor is extracted from the operation data through data analysis, and a target variable to be regulated is determined from preset variables based on the feature subset.

[0039] In an embodiment of the present application, an in-built data analysis module is used to deeply process the operation data collected from the reactor. Key features that can accurately characterize the current working state of the reactor are identified and extracted through algorithms to form a feature subset. These features may cover temperature fluctuations during the reaction process, pressure stability, change trends of reactant concentrations, and dynamics of product formation rates, etc. Subsequently, the system further analyzes the feature subset based on preset rules or machine learning models to determine the key factors affecting the temperature control of the reactor, i.e., the target variables, such as the cooling rate adjustment requirement, the optimization direction of reactant ratio, etc., thereby providing a decision basis for formulating subsequent temperature control strategies.

[0040] As Figure 2 shown, in an embodiment of the present application, a feature subset characterizing the current working attributes of the reactor is extracted from the operation data through data analysis, and a target variable to be regulated is determined from preset variables based on the feature subset, including:

[0041] S210, extracting a feature subset from the operation data through data analysis, where the feature subset is used to characterize the current working attributes of the reactor;

[0042] S220, determining the linear relationship between the features in the feature subset and the preset variables according to the preset variables of the reactor;

[0043] S230, determining the target variable to be regulated from the preset variables according to the linear relationship.

[0044] Specifically, in an embodiment of the present application, extracting a feature subset from the operation data through data analysis in S210 includes:

[0045] Selecting features from the operation data according to the correlation parameters between the operation data and preset labels to form a first subset;

[0046] Construct a linear regression model, and recursively remove unnecessary features from the first subset until the number of features in the set reaches a preset number of features, generating a second subset;

[0047] Construct an interaction network among the features in the second subset, and determine a feature subset according to the influence between the features in the interaction network.

[0048] In an embodiment of the present application, methods such as Pearson correlation coefficient, Spearman rank correlation coefficient, or mutual information can be used to calculate the correlation parameters between the features and the labels in the operation data, and the features with the highest correlation parameters are selected to form the first subset.

[0049] Specifically, for the application scenario of the reaction bed based on this solution, calculate the correlation parameters as:

[0050]

[0051] where, and represent the feature value and the label value corresponding to the i-th feature respectively, and represent the mean values of the feature value and the label value respectively, represents the weight of feature i, i represents the feature identifier, and n represents the number of samples.

[0052] After that, construct a linear regression model, and recursively determine and remove unnecessary features from the first subset until the predetermined number of features is reached or the model performance no longer improves significantly. In the process of determining unnecessary features, based on the feature values in the first subset, the regression coefficients corresponding to adjacent feature values, and the preset regularization parameter, determine the regression parameters corresponding to the features in the first subset as:

[0053]

[0054] where, represents the feature value of the i-th, is the dependent variable corresponding to the i-th feature, represents the regression coefficient corresponding to the i-th feature, represents the preset regularization parameter, represents the regression coefficient corresponding to the j-th feature adjacent to i.

[0055] The regression parameters calculated in this embodiment are used to measure the necessity among the features in the first subset. Then, a comparison is made between the regression parameters and a set threshold, and the features with regression parameters greater than or equal to the set threshold are determined as unnecessary features, and the unnecessary features are deleted until the number of features in the set reaches a preset number of features, generating a second subset.

[0056] After generating the second subset, not only the least important features are removed, but also the interaction effects of the features are considered. Therefore, in this embodiment, an interaction network is constructed among the features in the second subset, the impact on the entire network structure after removing the features is evaluated, and a feature subset is determined according to the influence among the features in the interaction network, so as to more accurately select the feature subset.

[0057] The above process optimizes the feature subset through correlation parameter calculation, linear regression model recursion, and interaction network construction. It improves the quality of the feature subset, makes the temperature control strategy more dependent on key features, and reduces unnecessary interference.

[0058] After extracting the feature subset, the linear relationship between the features therein and preset variables (such as the temperature, pressure, reaction rate, etc. of the reactor) is determined. Linear fitting can be performed near each data point, and then the results of all local models are integrated to predict the global trend, obtaining the linear relationship between each feature in the feature subset and the preset variable.

[0059] After determining the linear relationship between the feature subset and the preset variable, according to the strength of the linear relationship, variables strongly correlated with the feature subset are extracted from the preset variables as target variables. Specifically, the target variables include variables that have an important impact on the reactor performance or product quality and can be adjusted through control strategies, such as the cooling rate and the reactant ratio, etc.

[0060] Through the detailed elaboration and execution process of the above steps, not only can a feature subset representing the current working attributes of the reactor be extracted from the operation data, but also the linear relationship between these features and the preset variables can be accurately determined, and finally the target variables that have an important impact on the reactor performance or product quality can be extracted. Through feature extraction and target variable determination, the complexity of the temperature control problem is simplified, making the control strategy more accurate and efficient.

[0061] In step S130, key task parameters are extracted from the current task information of the reactor; the key task parameters include the reaction time, temperature range, and pressure upper limit.

[0062] In an embodiment of the present application, after receiving the current task information of the reactor, various details in the task information are parsed, such as the types and ratios of reactants, the specification requirements of the target product, etc. Subsequently, based on this detailed information, the key task parameters required for the reaction are predicted and calculated. These parameters specifically include the expected duration of the reaction process (i.e., the reaction time), the allowable temperature fluctuation range during the reaction process (i.e., the temperature range), and the maximum pressure limit set to ensure the safe progress of the reaction (i.e., the pressure upper limit). Through this step, the specific requirements of the current task of the reactor can be comprehensively grasped, providing necessary constraint conditions and target orientations for the formulation of subsequent temperature control strategies.

[0063] In an embodiment of the present application, key task parameters are extracted from the current task information of the reactor, including:

[0064] Predict the reaction time corresponding to this task based on the reactant concentration, estimated pressure, and activation energy in the task information;

[0065] Predict the temperature range corresponding to this task based on the heat of reaction, reactant concentration, and estimated pressure in the task information;

[0066] Predict the pressure upper limit corresponding to this task based on the reaction volume, heat of reaction, reactant concentration, and estimated pressure in the task information.

[0067] In an embodiment of the present application, rules can be preset to refine the key task parameters initially extracted from the task information. For example, if the task description mentions "high-temperature reaction", the rule library can refine it into a specific temperature range, such as "200°C to 400°C".

[0068] Furthermore, based on the historical working data of the reactor, in this embodiment, it is creatively proposed to determine data such as the reaction time, temperature range, and pressure upper limit of this task based on the task information as key task parameters.

[0069] Specifically, predict the reaction time corresponding to this task based on the reactant concentration, estimated pressure, and activation energy in the task information as:

[0070]

[0071] where C represents the reactant concentration, P represents the estimated pressure, E represents the activation energy, R represents the reaction rate constant calculated based on historical data, 、 、 and are constants obtained by fitting experimental data.

[0072] Based on the heat of reaction, reactant concentration, and estimated pressure in the task information, the minimum and maximum values in the temperature range corresponding to this task are predicted to be:

[0073]

[0074]

[0075] where, represents the temperature range, ΔH represents the heat of reaction, and the meanings of the other symbols are the same as above. This formula determines the temperature range through a quadratic equation about temperature, taking into account the effects of heat of reaction and pressure on temperature, making the calculated temperature range more accurate.

[0076] Based on the reaction volume, heat of reaction, reactant concentration, and estimated pressure in the task information, predict the upper limit of the pressure corresponding to this task is:

[0077]

[0078] where, V represents the reaction volume, and k represents a constant related to gas properties measured according to historical data. This formula takes into account the effects of reaction rate, concentration, temperature, and volume on pressure, making the calculated upper limit of pressure more accurate.

[0079] The above process predicts key parameters such as reaction time, temperature range, and pressure upper limit from the task information, providing more specific and accurate constraint conditions for the formulation of the temperature control strategy, and ensuring the effectiveness and safety of the control strategy.

[0080] In step S140, input the feature subset, the target variable, and the key task parameters into a pre-trained temperature control model to generate a temperature control strategy corresponding to the current moment.

[0081] In an embodiment of the present application, the extracted feature subset, the determined target variable, and the parsed key task parameters are used as inputs and passed to a temperature control model pre-trained with a large amount of historical data and expert knowledge. This model integrates complex algorithmic logics internally, can analyze the input data quickly and accurately, comprehensively consider the current working state, target requirements, and operation limitations of the reactor, and then intelligently generate an optimal temperature control strategy for the current moment. This strategy may include instructions for adjusting the flow rate of the cooling medium, suggestions for setting the power of the heating element, etc., aiming to ensure that the reactor can operate in a safe and efficient state while meeting the specific requirements of the production task.

[0082] In an embodiment of the present application, before inputting the feature subset, the target variable, and the key task parameters into a pre-trained temperature control model to generate a temperature control strategy corresponding to the current moment, the following steps are further included:

[0083] Determine the state space and the spatial actions according to the equipment parameters of the reactor;

[0084] Determine a reward function according to the performance indicators of the reactor, which is used to evaluate the temperature control strategy through the reward function;

[0085] Generate a reinforcement learning algorithm according to the gradient policy, and train based on the state space, the spatial actions, and the reward function to generate the temperature control model.

[0086] In an embodiment of the present application, according to the actual situation of the reactor, the state space is defined. In this embodiment, the state space includes key variables such as the current temperature, the reactant concentration, and the pressure that can reflect the state of the reactor. Define the action space, that is, the set of actions that the reinforcement learning model can execute. In the temperature control task, the action space may include control instructions such as the heating rate and the cooling rate.

[0087] Design a reward function according to the performance indicators of the reactor, such as the product purity, the reaction rate, and the energy consumption. In this embodiment, the reward function is used to evaluate the quality of each temperature control strategy and is the optimization goal of the reinforcement learning model. In the process of determining the reward function in this embodiment, the characteristics and control requirements of the reactor are fully considered to ensure that the model can learn effective temperature control strategies.

[0088] Select a suitable reinforcement learning algorithm according to the task characteristics and data scale, such as policy gradient. Implement the reinforcement learning algorithm, which includes key steps such as state representation, action selection, reward calculation, and policy update. During the training process, the temperature control strategy will be continuously tried and adjusted to maximize the reward function. Through a large number of iterations and experiments, the optimal strategy will be found. Use the preprocessed data to train the reinforcement learning model. During the training process, the model will learn how to select the optimal action according to the current state to maximize the cumulative reward. Verify the trained model and evaluate its performance on unknown data.

[0089] Deploy the trained reinforcement learning model to the control system of the reactor to achieve automated temperature control. During the actual operation process, continuously collect new data for further optimization and update of the model.

[0090] In the above process, aiming at maximizing the reward function through the reinforcement learning model, the performance indicators of the reactor, such as product purity, reaction rate, etc., can be optimized, enabling the model to learn a more accurate temperature control strategy, improving the control accuracy and stability of the reactor. At the same time, the reinforcement learning model can automatically adjust the control strategy according to the actual situation and changes of the reactor, enhancing the adaptability and robustness of the system. By optimizing the temperature control strategy, the reinforcement learning model helps to reduce the energy consumption of the reactor, enabling the temperature control model to adaptively adjust the control strategy to maximize the performance indicators and improve the energy utilization rate.

[0091] In one embodiment of the present application, it further includes: using a monitoring tool to track and record the prediction performance of the temperature control model in real time. Once a decrease in model performance or an abnormal situation is detected, an adaptive adjustment mechanism is immediately triggered.

[0092] In one embodiment of the present application, a suitable monitoring tool is selected according to the characteristics and requirements of the temperature control model. These tools should have functions such as real-time data collection, anomaly detection, and performance analysis. Configure the model performance indicators to be monitored in the monitoring tool, such as prediction accuracy, mean square error, and mean absolute error, etc. At the same time, set the threshold and alarm rules for anomaly detection. Connect the monitoring tool to the data source of the temperature control model to ensure that the prediction data and actual data of the model can be obtained in real time.

[0093] The monitoring tool periodically or in real time collects the prediction data and actual data of the temperature control model, as well as the relevant performance indicators. Preprocess and analyze the collected data, and calculate the performance indicators of the model, such as prediction accuracy, etc. Record the analysis results in the database of the monitoring system for subsequent analysis and query.

[0094] The monitoring tool determines whether there is a decrease in model performance or an abnormal situation according to the preset anomaly detection threshold and rules. Once an anomaly is detected, the monitoring tool immediately triggers an alarm mechanism and notifies relevant personnel by means of emails, text messages, system notifications, etc. Record the anomaly information in the log of the monitoring system, including the time, type, and scope of influence of the anomaly. According to the cause of the anomaly, formulate an adaptive adjustment strategy, such as retraining the model, adjusting model parameters, optimizing the data preprocessing process, etc.

[0095] Optionally, the formulated adjustment strategy can be input into the monitoring tool, and the monitoring tool automatically or manually executes the adjustment operation. For example, if it is determined that the performance degradation is caused by model parameter drift, the model parameters can be automatically adjusted through the monitoring tool; if it is a data quality problem, the data preprocessing process needs to be optimized.

[0096] This solution uses a real-time monitoring tool to track and record the prediction performance of the temperature control model in real time. Once an anomaly is detected, it immediately triggers an adaptive adjustment mechanism, achieving continuous optimization and improvement of the model. This real-time monitoring and adaptive adjustment method has higher efficiency and accuracy compared to traditional manual monitoring and adjustment.

[0097] In step S150, the temperature control strategy is sent to the controller through a hardware interface, and the controller controls the flow rate and temperature of the cooling medium and the power of the heating element.

[0098] In an embodiment of the present application, the generated temperature control strategy is sent to the controller in the form of a digital signal through a hardware interface (such as a serial communication interface, an Ethernet interface, etc.). This hardware interface ensures efficient and accurate data transmission between the computer and the controller.

[0099] After receiving the temperature control strategy from the computer system, the controller parses it. The parsing process includes identifying the instruction type (such as cooling medium flow rate adjustment or heating element power setting, etc.), extracting the specific parameter values (such as flow rate magnitude, temperature set value, and power level, etc.), and preparing to convert these parameter values into corresponding control signals. According to the parsed parameter values, the flow rate and temperature of the cooling medium are precisely adjusted through its internal actuators (such as solenoid valves, proportional valves, temperature sensors, and power regulators, etc.), and at the same time, the power of the heating element is set. These actuators adjust the heat exchange conditions of the reactor in real time according to the controller's instructions to achieve the goals required by the temperature control strategy.

[0100] Through the fast data transmission between the computer and the controller, and the immediate parsing and execution of the temperature control strategy by the controller, the entire system can achieve real-time response and adjustment of the reactor temperature. This helps to ensure the stable operation of the reactor under complex and changing working conditions. The formulation of the temperature control strategy is based on the current working state, target requirements, and operation limitations of the reactor, so precise temperature control can be achieved. It improves the automation level of the control system, reduces the labor intensity of the operators, and improves the reliability and stability of the system.

[0101] In the technical solution of this application, operation data is collected from the reactor through the data interface of the sensor network, and the current task information of the reactor is obtained; through data analysis, a feature subset characterizing the current working attributes of the reactor is extracted from the operation data, and a target variable to be regulated is determined from the preset variables based on the feature subset; key task parameters are extracted from the current task information of the reactor; the key task parameters include reaction time, temperature range, and pressure upper limit; the feature subset, the target variable, and the key task parameters are input into a pre-trained temperature control model to generate a temperature control strategy corresponding to the current moment; the temperature control strategy is sent to the controller through the hardware interface, and the controller is used to control the flow rate and temperature of the cooling medium and the power of the heating element. The reactor bed temperature control system realizes precise temperature control by accurately extracting the operation data of the reactor, combining the key task parameters generated by the task information, performing model training and temperature control, and adaptively combining the key task parameters based on the actual operating state of the reaction bed, which not only improves the accuracy and efficiency of temperature control, but also enhances the robustness and adaptability of the control system, providing a strong guarantee for the stable operation of the reactor.

[0102] The following introduces the device embodiments of this application, which can be used to implement the reactor bed temperature control system in the above embodiments of this application. It can be understood that the device can be a computer program (including program code) running in a computer device, for example, the device is an application software; the device can be used to execute the corresponding steps in the method provided in the embodiments of this application. For the details not disclosed in the device embodiments of this application, please refer to the embodiments of the reactor bed temperature control system above in this application.

[0103] Figure 3 The block diagram of a reactor bed temperature control system according to an embodiment of this application is shown.

[0104] Refer to Figure 3 As shown, a reactor bed temperature control system according to an embodiment of this application includes:

[0105] An acquisition unit 310, configured to collect operation data from the reactor through the data interface of the sensor network, and obtain the current task information of the reactor;

[0106] An extraction unit 320, configured to extract a feature subset characterizing the current working attributes of the reactor from the operation data through data analysis, and determine a target variable to be regulated from the preset variables based on the feature subset;

[0107] A task unit 330, configured to extract key task parameters from the current task information of the reactor; the key task parameters include reaction time, temperature range, and pressure upper limit;

[0108] A training unit 340, configured to input the feature subset, the target variable, and the key task parameters into a pre-trained temperature control model to generate a temperature control strategy corresponding to the current moment;

[0109] A control unit 350, configured to send the temperature control strategy to a controller through a hardware interface, and control the flow rate and temperature of a cooling medium and the power of a heating element through the controller.

[0110] In this application, based on the foregoing solution, extracting a feature subset characterizing the current working attributes of the reactor from the operation data through data analysis, and determining a target variable to be regulated from preset variables based on the feature subset includes: extracting a feature subset from the operation data through data analysis, where the feature subset is used to characterize the current working attributes of the reactor; determining a linear relationship between the features in the feature subset and the preset variables according to the preset variables of the reactor; and determining a target variable to be regulated from the preset variables according to the linear relationship.

[0111] In this application, based on the foregoing solution, extracting a feature subset from the operation data through data analysis includes: selecting features from the operation data according to the association parameters between the operation data and preset labels to form a first subset; constructing a linear regression model, and recursively removing unnecessary features from the first subset until the number of features in the set reaches a preset number of features to generate a second subset; and constructing an interaction network between the features in the second subset, and determining a feature subset according to the influence between the features in the interaction network.

[0112] In this application, based on the foregoing solution, extracting key task parameters from the current task information of the reactor includes: predicting the reaction time corresponding to this task according to the reactant concentration, estimated pressure, and activation energy in the task information; predicting the temperature range corresponding to this task according to the reaction heat, reactant concentration, and estimated pressure in the task information; and predicting the upper pressure limit corresponding to this task according to the reaction volume, reaction heat, reactant concentration, and estimated pressure in the task information.

[0113] In this application, based on the foregoing solution, before inputting the feature subset, the target variable, and the key task parameters into a pre-trained temperature control model to generate a temperature control strategy corresponding to the current moment, the following steps are further included: determining a state space and a spatial action according to the equipment parameters of the reactor; determining a reward function according to the performance index of the reactor for evaluating the temperature control strategy through the reward function; generating a reinforcement learning algorithm according to the gradient strategy and training based on the state space, the spatial action, and the reward function to generate the temperature control model.

[0114] In this application, based on the foregoing solution, the following is further included: real-time tracking and recording of the prediction performance of the temperature control model through a monitoring tool, and immediately triggering an adaptive adjustment mechanism once a decrease in model performance or an abnormal situation is detected.

[0115] In this application, based on the foregoing solution, the operation data includes temperature, pressure, reactant concentration, and product generation rate.

[0116] In the technical solution of this application, operation data is collected from the reactor through the data interface of the sensor network, and the current task information of the reactor is obtained; a feature subset characterizing the current working attributes of the reactor is extracted from the operation data through data analysis, and a target variable to be regulated is determined from the preset variables based on the feature subset; key task parameters are extracted from the current task information of the reactor; the key task parameters include reaction time, temperature range, and pressure upper limit; the feature subset, the target variable, and the key task parameters are input into a pre-trained temperature control model to generate a temperature control strategy corresponding to the current moment; the temperature control strategy is sent to the controller through the hardware interface, and the flow rate and temperature of the cooling medium are controlled through the controller, and the power of the heating element is controlled. The reactor bed temperature control system realizes precise temperature control by accurately extracting the operation data of the reactor, combining the key task parameters generated from the task information, performing model training and temperature control, and adaptively combining the key task parameters based on the actual operating state of the reaction bed, which not only improves the accuracy and efficiency of temperature control, but also enhances the robustness and self-adaptability of the control system, providing a strong guarantee for the stable operation of the reactor.

[0117] Figure 4 The structural schematic diagram of a computer system of an electronic device suitable for implementing the embodiments of this application is shown.

[0118] It should be noted that the computer system of the electronic device in this embodiment is only an example and should not bring any limitation to the functions and usage scopes of the embodiments of this application.

[0119] In this embodiment, the computer system includes a central processing unit 401, which can perform various appropriate actions and processes according to the program stored in the read-only memory 402 or the program loaded from the storage section 408 into the random access memory 403, such as executing the reactor bed temperature control system described in the above embodiment. In the random access memory 403, various programs and data required for system operation are also stored. The central processing unit 401, the read-only memory 402, and the random access memory 403 are connected to each other via a bus 404. The input / output interface 405 is also connected to the bus 404.

[0120] The following components are connected to the input / output interface 405: an input section 406 including a keyboard, a mouse, etc.; an output section 407 including, for example, a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 408 including a hard disk, etc.; and a communication section 409 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 409 performs communication processing via a network such as the Internet. The drive 410 is also connected to the input / output interface 405 as needed. A removable medium 411, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 410 as needed so that a computer program read from it can be installed into the storage section 408 as needed.

[0121] Specifically, according to the embodiments of the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments of the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication section 409, and / or installed from the removable medium 411. When the computer program is executed by the central processing unit 401, various functions defined in the system of the present application are executed.

[0122] It should be noted that the computer-readable medium shown in the embodiments of the present application can be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the computer-readable storage medium can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, the computer-readable storage medium can be any tangible medium that contains or stores a program, and this program can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present application, a computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable computer program is carried. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer-readable signal medium can also be any computer-readable medium other than the computer-readable storage medium, and this computer-readable medium can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The computer program contained on the computer-readable medium can be transmitted by any suitable medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0123] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present application. Among them, each block in the flowchart or block diagram can represent a module, a program segment, or a part of the code, and the above module, program segment, or part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram or flowchart, and the combination of blocks in the block diagram or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0124] The units involved in the embodiments of the present application can be implemented in software or in hardware, and the described units can also be provided in a processor. Among them, the names of these units do not constitute a limitation to the units themselves in some cases.

[0125] According to one aspect of the present application, there is provided a computer program product or a computer program, the computer program product or the computer program including computer instructions, and the computer instructions are stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the methods provided in the above various alternative implementation manners.

[0126] As another aspect, the present application further provides a computer-readable medium, which may be included in the electronic device described in the above embodiments; or may exist alone without being assembled into the electronic device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by an electronic device, the electronic device implements the reactor bed temperature control system described in the above embodiments.

[0127] It should be noted that although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present application, the features and functions of the two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0128] Through the description of the above embodiments, those skilled in the art can easily understand that the example embodiments described herein can be implemented by software or by a combination of software and necessary hardware. Therefore, the technical solutions according to the embodiments of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (such as a personal computer, a server, a touch terminal, or a network device, etc.) to execute the methods according to the embodiments of the present application.

[0129] After considering the specification and practicing the disclosed embodiments herein, those skilled in the art will readily conceive of other embodiments of the present application. The present application is intended to cover any variations, uses, or adaptations of the present application, which follow the general principles of the present application and include common general knowledge or conventional technical means in the technical field not disclosed in the present application.

[0130] It should be understood that the present application is not limited to the exact structures described above and shown in the drawings, and various modifications and changes can be made without departing from its scope. The scope of the present application is only limited by the appended claims.

Claims

1. A reactor bed temperature control system, characterized in that: include: An acquisition unit, used to collect operation data from the reactor through a data interface of the sensor network and acquire current task information of the reactor; An extraction unit, configured to extract a feature subset representing a current working property of the reactor from the operation data through data analysis, and determine a target variable to be regulated from preset variables based on the feature subset; A task unit, used to extract key task parameters from the current task information of the reactor; the key task parameters include reaction time, temperature range and upper pressure limit; A training unit, used for inputting the feature subset, the target variable and the key task parameter into a pre-trained temperature control model to generate a temperature control strategy corresponding to the current moment; The control unit is used to send the temperature control strategy to the controller through the hardware interface, and control the flow and temperature of the cooling medium and the power of the heating element through the controller.

2. The reactor bed temperature control system according to claim 1, characterized in that: Extracting a feature subset representing the current working properties of the reactor from the operating data through data analysis, and determining a target variable to be regulated from preset variables based on the feature subset, including: Extracting a feature subset from the operation data by data analysis, wherein the feature subset is used to characterize the current working properties of the reactor; According to the preset variables of the reactor, determining the linear relationship between the features in the feature subset and the preset variables; According to the linear relationship, the target variable to be regulated is determined from the preset variables.

3. The reactor bed temperature control system according to claim 2, characterized in that: Extracting a feature subset from the operational data through data analysis includes: Selecting features from the operation data according to association parameters between the operation data and the preset tags to form a first subset; Constructing a linear regression model, recursively removing unnecessary features from the first subset until the number of features in the set reaches a preset number of features, and generating a second subset; An interaction network is constructed between the features of the second subset, and a feature subset is determined according to the influence between the features in the interaction network.

4. The reactor bed temperature control system according to claim 1, characterized in that: Extract key mission parameters from the reactor's current mission information, including: Predicting the reaction time corresponding to the task according to the reactant concentration, estimated pressure and activation energy in the task information; Predicting the temperature range corresponding to the task based on the reaction heat, reactant concentration and estimated pressure in the task information; The upper pressure limit corresponding to the task is predicted based on the reaction volume, reaction heat, reactant concentration and estimated pressure in the task information.

5. The reactor bed temperature control system according to claim 1, characterized in that: Before inputting the feature subset, the target variable and the key task parameter into a pre-trained temperature control model to generate a temperature control strategy corresponding to the current moment, the method further includes: Determining the state space and the spatial action according to the equipment parameters of the reactor; Determining a reward function according to the performance indicator of the reactor, and evaluating the temperature control strategy through the reward function; A reinforcement learning algorithm is generated according to a gradient strategy, and training is performed based on the state space, the spatial action, and the reward function to generate the temperature control model.

6. The reactor bed temperature control system according to claim 5, characterized in that: Also includes: The predicted performance of the temperature control model is tracked and recorded in real time by a monitoring tool, and once a degradation or abnormality in the model performance is found, an adaptive adjustment mechanism is triggered.

7. The reactor bed temperature control system according to claim 1, characterized in that: The operating data include temperature, pressure, reactant concentrations, and product formation rates.

8. The reactor bed temperature control system according to claim 1, characterized in that: The task information includes reaction formula, target product and expected yield.

9. The reactor bed temperature control system according to claim 3, characterized in that: According to the association parameters between the operation data and the preset tags, including: The Pearson correlation coefficient or the Spearman rank correlation coefficient between the features and the labels in the operation data is calculated as the association parameter.

10. The reactor bed temperature control system according to claim 5, characterized in that: The state space includes the current temperature, reactant concentrations, and pressure of the reactor.

Images