Multi-stable ammonia synthesis control method and device, and electronic equipment

Abstract

This application discloses a multi-steady-state ammonia synthesis control method, apparatus, and electronic device, relating to the field of industrial control technology. A specific implementation of the method includes: based on historical operating data of the ammonia synthesis system; performing operating condition clustering on the historical operating data according to historical process parameters in the historical operating data to obtain at least one operating condition data set; performing data analysis on at least one historical operating parameter under each operating condition data set to obtain at least one safe operating boundary corresponding to the at least one operating condition data set; using the at least one safe operating boundary as the output constraint of the predictive control model of the ammonia synthesis system, and controlling the ammonia synthesis system according to the target operating parameters output by the predictive control model based on the output constraints and target process parameters. This achieves output optimization of the model, reduces dependence on model accuracy, effectively shortens the commissioning cycle, and improves the stability and safety of the system under fluctuating operating conditions.

Description

Technical Field

[0001] This application relates to the field of industrial control technology, specifically to a multi-steady-state ammonia synthesis control method, apparatus, and electronic equipment. Background Technology

[0002] Chemical synthesis towers (such as ammonia synthesis towers and methanol synthesis towers) are core equipment in chemical production, and their control level directly affects product output, energy consumption, and safety. Taking ammonia synthesis as an example, its internal reactions are characterized by strong exothermicity, nonlinearity, large inertia, and strong coupling of multiple variables. The control challenge lies in the strong coupling and dynamic characteristics between process variables.

[0003] Currently, the relevant technologies mainly use Model Predictive Control (MPC) to optimize the control of ammonia synthesis systems. MPC is an advanced control method for handling multivariable constraints, which achieves coordinated adjustment of various process parameters through rolling optimization.

[0004] However, the control performance of MPC is highly dependent on the accuracy of the model, and the synthetic ammonia process mechanism is complex and difficult to obtain an accurate model. In addition, differences in human operation and fluctuations in wind and solar loads can easily cause frequent changes in system operating conditions, resulting in long learning and debugging cycles for traditional MPC models, making it difficult to quickly put them into stable operation. Summary of the Invention

[0005] This application provides a multi-steady-state ammonia synthesis control method, device, and electronic equipment to solve the problems of traditional MPC control in related technologies, which rely on accurate models, have poor adaptability to operating conditions, have long commissioning and operation cycles, and cannot adapt to the stable operation of ammonia synthesis under multiple operating conditions in wind-solar coupled scenarios.

[0006] In a first aspect, embodiments of this application provide a multi-steady-state ammonia synthesis control method. The method includes: acquiring at least one historical operating data set of an ammonia synthesis system, where each historical operating data set includes at least one historical process parameter and at least one historical operating parameter corresponding to the at least one historical process parameter; performing condition clustering on the at least one historical operating data set based on the at least one historical process parameter to obtain at least one set of operating condition data; performing data analysis on at least one historical operating parameter under each set of operating condition data in the at least one set of operating condition data to obtain at least one safe operating boundary corresponding to the at least one set of operating condition data; and using the at least one safe operating boundary as the output constraint of a predictive control model for the ammonia synthesis system, so as to control the ammonia synthesis system according to the target operating parameter output by the predictive control model based on the output constraint and the target process parameter.

[0007] In some embodiments, using at least one safe operating boundary as the output constraint of a predictive control model for an ammonia synthesis system, and controlling the ammonia synthesis system based on the target operating parameters output by the predictive control model according to the output constraints and target process parameters, includes: obtaining target process parameters for the ammonia synthesis system; determining a target operating condition data set corresponding to the ammonia synthesis system based on the target process parameters and at least one operating condition data set; determining a target safe operating boundary corresponding to the target operating condition data set in at least one safe operating boundary; using the target process parameters as input to the predictive control model and the target safe operating boundary as the output constraint of the predictive control model, so as to control the ammonia synthesis system by using the target operating parameters output by the predictive control model.

[0008] In some embodiments, a predictive control model outputs target operating parameters to control an ammonia synthesis system. The method then includes: collecting operating data of the ammonia synthesis system during the control process based on the target operating parameters to obtain at least one target operating data; and updating at least one historical operating data based on the at least one target operating data to generate at least one updated safe operating boundary for constraining the predictive control model.

[0009] In some embodiments, performing condition clustering on at least one historical operating data to obtain at least one set of operating data based on at least one historical process parameter includes: performing condition clustering on at least one historical operating data using a preset clustering algorithm based on the similarity between at least one historical process parameter of each historical operating data in the at least one historical operating data, so as to divide at least one historical operating data into at least one set of operating data.

[0010] In some embodiments, at least one historical process parameter includes at least one key process parameter, which includes at least one of temperature, pressure, flow rate, and load parameters.

[0011] In some embodiments, performing data analysis on at least one historical operating parameter under each operating condition data set in at least one operating condition data set to obtain at least one safe operating boundary corresponding to at least one operating condition data set includes: performing data statistics on at least one historical operating parameter under each operating condition data set in at least one operating condition data set to obtain at least one operating parameter data distribution corresponding to at least one operating condition data set; and determining at least one safe operating boundary corresponding to at least one operating condition data set based on the at least one operating parameter data distribution.

[0012] In some embodiments, determining at least one safe operating boundary corresponding to at least one set of operating condition data based on at least one operating parameter data distribution includes: performing boundary extraction on at least one operating parameter data distribution to obtain at least one safe operating boundary corresponding to at least one set of operating condition data, wherein boundary extraction includes extracting at least one of the maximum value, minimum value, mean value and confidence interval of the operating parameters.

[0013] In some embodiments, at least one safe operating boundary is used as the output constraint of the predictive control model of the ammonia synthesis system. Prior to this, the method includes: determining the coupling relationship between the process parameters and operating parameters of the ammonia synthesis system based on the process mechanism information of the ammonia synthesis system, wherein the process parameters include key controlled variables and disturbance variables, and the operating parameters include operating variables; and constructing a predictive control model based on the coupling relationship between the process parameters and operating parameters.

[0014] Secondly, embodiments of this application provide a multi-steady-state ammonia synthesis control device, the device comprising:

[0015] The acquisition unit is used to acquire at least one historical operating data of the ammonia synthesis system. Each historical operating data in the at least one historical operating data includes at least one historical process parameter and at least one historical operating parameter corresponding to the at least one historical process parameter. A partitioning unit is used to perform condition clustering on at least one historical operating data based on at least one historical process parameter, so as to obtain at least one set of operating data. The analysis unit is used to perform data analysis on at least one historical operating parameter under each operating condition data set in at least one operating condition data set, so as to obtain at least one safe operating boundary corresponding to at least one operating condition data set. A constraint unit is used to use at least one safe operating boundary as the output constraint of the predictive control model of the ammonia synthesis system, so as to control the ammonia synthesis system according to the target operating parameters output by the predictive control model based on the output constraints and the target process parameters.

[0016] Thirdly, embodiments of this application provide an electronic device, including: a processor and a memory for storing a computer program capable of running on the processor, wherein, when the processor runs the computer program, it performs the method described in any embodiment of the first aspect.

[0017] This application provides a multi-steady-state ammonia synthesis control method. It extracts safe operating boundaries corresponding to different operating conditions from historical operating data of the ammonia synthesis system and uses these safe operating boundaries as dynamic output constraints for a predictive control model. This optimizes the model's output, ensuring that even with low model accuracy, the operating parameters output by the model for controlling the ammonia synthesis system always remain within the historically validated safe and feasible range. This reduces reliance on model accuracy, effectively shortens the commissioning cycle, and further improves the system's stability and safety under fluctuating operating conditions.

[0018] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0019] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are merely embodiments of this application. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort, and this application can be applied to other similar scenarios based on the provided drawings.

[0020] Figure 1 A flowchart illustrating the first multi-stable ammonia synthesis control method provided in this application embodiment; Figure 2 A flowchart of the second multi-stable ammonia synthesis control method provided in the embodiments of this application; Figure 3 A schematic diagram of cluster analysis provided for an embodiment of this application; Figure 4 A flowchart illustrating the third multi-stable ammonia synthesis control method provided in this application embodiment; Figure 5 A schematic diagram of the overall process of a specific multi-stable ammonia synthesis control method provided in this application embodiment; Figure 6 This is a schematic diagram of a multi-stable-state ammonia synthesis control device provided in an embodiment of this application; Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0021] The present application will now be described in further detail with reference to the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and not intended to limit it. The described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0022] It should be noted that the terms "system," "device," "unit," and / or "module" used in this application are methods of distinguishing different components, elements, parts, sections, or assemblies at different levels. However, if other terms can achieve the same purpose, they can be replaced by other expressions.

[0023] Hereinafter, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first," "second," or "third" may explicitly or implicitly include one or more of that feature.

[0024] Chemical synthesis towers (such as ammonia synthesis towers and methanol synthesis towers) are core equipment in chemical production, and their control level directly affects product output, energy consumption, and safety. Taking ammonia synthesis as an example, the Harpo process reaction inside is a strongly exothermic, nonlinear, and highly inertial process. The control challenge lies in the strong coupling and dynamic characteristics between process variables.

[0025] Currently, traditional control strategies in related technologies include single-loop PID (Proportional-Integral-Derivative Controller) control, PID cascade and feedforward control, and Model Predictive Control (MPC). Among these, single-loop PID control is challenging for nonlinear, strongly coupled systems like synthesis towers, where PID controller parameter tuning is difficult, coordinating dynamic relationships between multiple variables is challenging, and manual intervention is heavily relied upon, resulting in poor control quality and low efficiency. While PID cascade and feedforward control can suppress some secondary disturbances and provide preliminary compensation for major disturbances (such as feed changes), its ability to handle large-scale, multi-variable, complex coupling and constraint problems is limited, requiring manual intervention. MPC methods heavily rely on accurate mechanistic models, but the synthetic ammonia process mechanism is complex, making accurate modeling difficult. Furthermore, differences in operator habits can lead to scattered operating data and drift of the optimal operating point. Frequent fluctuations in wind and solar hydrogen production loads result in traditional MPC requiring extremely long model learning and debugging cycles, making it difficult to quickly achieve stable operation and generate economic benefits.

[0026] In the "electricity-hydrogen-ammonia" green coupling scenario, the second- or minute-level fluctuations in wind and solar power directly cause frequent changes in hydrogen production load and ammonia synthesis feed parameters, severely disrupting the system's material and thermal balance and posing stringent requirements for the stable control of ammonia synthesis. Therefore, there is an urgent need for a flexible control method that can be quickly deployed, is insensitive to model accuracy, and can adapt to multiple steady-state switching to ensure the safe, stable, and efficient operation of the ammonia synthesis unit under fluctuating conditions.

[0027] To address the problems in existing technologies, this application proposes a multi-steady-state ammonia synthesis control method. By extracting the corresponding safe operating boundaries under different operating conditions from the historical operating data of the ammonia synthesis system, and using these safe operating boundaries as dynamic output constraints of the MPC model, the operating parameters output by the model for controlling the ammonia synthesis system can always remain within the historically verified safe and feasible domain, even when the model accuracy is not high. This reduces the dependence on model accuracy, effectively shortens the commissioning cycle, and further improves the safe, stable, and efficient operation of the ammonia synthesis system under fluctuating operating conditions.

[0028] The following section provides a detailed description of a multi-stable ammonia synthesis control method provided in this application, with reference to the accompanying drawings.

[0029] Figure 1 A flowchart illustrating a multi-steady-state ammonia synthesis control method provided in an embodiment of this application is shown. Figure 1 As shown, the multi-steady-state ammonia synthesis control method includes steps 101-104.

[0030] Step 101: Obtain at least one historical operating data of the ammonia synthesis system. Each historical operating data includes at least one historical process parameter and at least one historical operating parameter corresponding to the at least one historical process parameter.

[0031] In the embodiments of this application, historical operating data refers to all data recorded by the ammonia synthesis system over a past period of time (at least one complete operating cycle, such as more than one month), including the historical process parameters and historical operating parameters of the ammonia synthesis system at each sampling time.

[0032] Among them, historical process parameters are physical parameters that describe the operating status of the ammonia synthesis system, such as temperature, pressure, flow rate, and load, and are used to determine the operating characteristics of the ammonia synthesis system; historical operating parameters are control parameters that describe control actions, such as valve opening and process setpoints, and are used to adjust the ammonia synthesis reaction state.

[0033] Specifically, collect historical operating data for one or more complete operating cycles (more than one month is recommended) of the ammonia synthesis system. This historical operating data needs to cover various operating conditions under different loads and different shifts.

[0034] Step 102: Based on at least one historical process parameter, perform condition clustering on at least one historical operating data to obtain at least one set of operating data.

[0035] In the embodiments of this application, operating condition clustering is an unsupervised learning method that automatically groups data points with "similar states" in historical operating data into one category. The operating condition dataset is an operating condition "cluster" obtained by dividing the historical operating data into operating condition clusters. Each operating condition "cluster" represents a typical steady-state operating condition of the ammonia synthesis system (such as high-load, medium-load, and low-load conditions). The historical operating data is valid operating data obtained after screening and removing invalid data to ensure the accuracy of the operating condition division.

[0036] Optionally, based on the similarity between at least one historical process parameter of each historical operating data in at least one historical operating data, a preset clustering algorithm is used to perform operating condition clustering processing on at least one historical operating data, so as to divide at least one historical operating data into at least one operating condition data set.

[0037] Optionally, at least one historical process parameter includes at least one critical process parameter, which includes at least one of temperature, pressure, flow rate, and load parameters.

[0038] Specifically, key process parameters such as temperature, pressure, flow rate, and load (key process parameters are process variables that can intuitively reflect the state of ammonia synthesis reaction) are used as clustering features to determine the similarity of process parameters between different data points. A preset clustering algorithm is used to automatically group data points with similar features into the same class, resulting in several sets of operating condition data.

[0039] Optionally, the preset clustering algorithm specifically refers to unsupervised clustering algorithms, including clustering algorithms such as K-Means, DBSCAN, or Gaussian mixture models.

[0040] Step 103: Perform data analysis on at least one historical operating parameter under each operating condition data set in at least one operating condition data set to obtain at least one safe operating boundary corresponding to at least one operating condition data set.

[0041] In the embodiments of this application, the safe operating boundary refers to the safe range or optimal value of the operating parameters allowed under a specific operating condition "cluster", including the maximum value (upper limit), minimum value (lower limit), mean value, optimal value (such as the representative value of the cluster center or the optimal performance interval), confidence interval, etc. of the operating parameters.

[0042] Specifically, for each cluster of operating condition data sets, all historical operating parameter data are extracted. Statistical analysis is performed on each operating parameter to extract its maximum, minimum, mean, optimal value, and confidence interval (e.g., 95% confidence interval). This forms a mapping rule between "operating condition and safe operating boundary".

[0043] Step 104: Use at least one safe operating boundary as the output constraint of the predictive control model of the ammonia synthesis system, so as to control the ammonia synthesis system according to the target operating parameters output by the predictive control model based on the output constraints and the target process parameters.

[0044] In the embodiments of this application, the predictive control model (MPC) is established based on the coupling relationship between process parameters and operating parameters in the chemical ammonia synthesis process mechanism (such as manufacturer's instructions, P&ID diagrams, etc.). Process parameters include key controlled variables and disturbance variables, while operating control parameters include operating variables. Key controlled variables include temperature, flow rate, pressure, and load variables, while disturbance variables include local high temperature variables and differential pressure variables. Operating variables include valve opening variables. The predictive control model is used to achieve rolling optimization control and is a simplified model based on the process mechanism.

[0045] Optionally, based on the process mechanism information of the ammonia synthesis system, the coupling relationship between the process parameters and operating parameters of the ammonia synthesis system is determined; and a predictive control model is constructed based on the coupling relationship between the process parameters and operating parameters.

[0046] Specifically, before controlling the ammonia synthesis system, a predictive control model needs to be built in advance. This involves analyzing the coupling relationships between variables based on the ammonia synthesis process mechanism, distinguishing between key controlled variables, disturbance variables, and operating variables, and then constructing the predictive control model accordingly. This model does not require extremely high modeling accuracy; it primarily relies on safe operating boundary constraints for each operating condition to ensure the model's accuracy and control safety.

[0047] The target process parameters refer to the current process state parameters of the ammonia synthesis system. Specifically, based on the current process state parameters of the ammonia synthesis system, the operating condition category of the system is determined. The safe operating boundary corresponding to this operating condition is used as the output constraint for the current optimization calculation of the predictive control model. The predictive control model performs rolling optimization calculations within this constraint range, outputs the target operating parameters, and sends the target operating parameters as control commands to the ammonia synthesis system. After receiving the control commands, the ammonia synthesis system adjusts operating parameters such as valve openings, thereby realizing the control operation of the ammonia synthesis system.

[0048] The output constraint is used to limit the target operating parameters of the predictive control model output to be within the safe operating parameter range.

[0049] In summary, the multi-steady-state ammonia synthesis control method proposed in this application involves acquiring at least one historical operating data set of the ammonia synthesis system. Each historical operating data set includes at least one historical process parameter and at least one corresponding historical operating parameter. Based on the at least one historical process parameter, the at least one historical operating data set is clustered to obtain at least one set of operating conditions. Data analysis is performed on at least one historical operating parameter within each set of operating conditions to obtain at least one safe operating boundary corresponding to the at least one set of operating conditions. This safe operating boundary is used as the output constraint of the predictive control model for the ammonia synthesis system. The system is then controlled based on the target operating parameter output by the predictive control model according to the output constraint and the target process parameter. This method utilizes the safe operating boundaries extracted from historical operating data to constrain the output of the predictive control model. This ensures that even with low model accuracy, the control actions of the ammonia synthesis system remain within a historically validated safe and feasible domain, thereby reducing reliance on model accuracy, effectively shortening the commissioning cycle, and further improving the safe, stable, and efficient operation of the ammonia synthesis system under fluctuating operating conditions.

[0050] As one possible implementation method, Figure 2 A flowchart of the second multi-steady-state ammonia synthesis control method is shown. Based on the above embodiments, data analysis is performed on at least one historical operating parameter under each operating condition data set in at least one operating condition data set to obtain at least one safe operating boundary corresponding to at least one operating condition data set, including the following steps: Step 201: Perform data statistics on at least one historical operating parameter under each operating condition data set in at least one operating condition data set to obtain the data distribution of at least one operating parameter corresponding to at least one operating condition data set.

[0051] In the embodiments of this application, the operating parameter data distribution refers to the statistical distribution formed by all historical values ​​of the operating parameters under the same operating condition.

[0052] Specifically, for each set of operating condition data, all historical operating parameters within the set are extracted; statistical analysis is performed on each historical operating parameter to record the parameter fluctuation range, distribution pattern, etc., and the data distribution characteristics of each operating parameter under that operating condition are generated to obtain the data distribution of the operating parameters corresponding to that operating condition.

[0053] Step 202: Extract the boundary of at least one operating parameter data distribution to obtain at least one safe operating boundary corresponding to at least one set of operating condition data.

[0054] In embodiments of this application, boundary extraction includes extracting at least one of the maximum value, minimum value, mean value, and confidence interval of the operation parameters.

[0055] Specifically, based on the distribution of operating parameter data, the safe operating boundaries of the corresponding operating parameters are extracted. For example, the optimal operating value and safe operating boundary values ​​(maximum value, minimum value, confidence interval) of each operating parameter are extracted to obtain the safe operating boundary under each operating condition. Figure 3 The diagram shows a cluster analysis. Figure 3 This demonstrates the historical valve opening distribution under different operating condition data sets (operating condition "clusters") obtained through operating condition cluster analysis of historical operating data of the ammonia synthesis system, and the safe operating boundary extracted from the distribution. Among these, Figure 3 In this context, low (low load), mid (medium load), and high (high load) represent three typical operating conditions; Opening / value represents the valve opening degree; and FlowBin represents the flow rate.

[0056] Based on the correspondence between the operating condition data set, optimal operating values, and safe operating boundary values, a set of "operating condition-safe operating boundary" mapping rules is formed. The safe operating boundary serves as the output constraint of the MPC controller, ensuring that the output target operating parameters do not exceed the historically verified safe range. This method, through clustering algorithms, determines the safe operating boundary based on historical successful operating experience. Essentially, it solidifies the practical knowledge and experience of operators in each shift into control rules. Even when there are errors in model predictions or when encountering unprecedented disturbances, it can ensure that the target operating parameters do not exceed the design safe range, greatly improving the system's anti-disturbance capability and operational safety.

[0057] In summary, this application obtains the distribution of operating parameter data for each operating condition by statistically analyzing the historical operating parameters under each set of operating conditions. Then, it extracts at least one of the maximum value, minimum value, mean value, and confidence interval from the distribution as a safe operating boundary, thereby quantifying historical operating experience into safety constraints that can be applied to online control.

[0058] As one possible implementation method, Figure 4 A flowchart of a third multi-steady-state ammonia synthesis control method is shown. Based on the above embodiments, at least one safe operating boundary is used as the output constraint of the predictive control model of the ammonia synthesis system. The ammonia synthesis system is then controlled according to the target operating parameters output by the predictive control model based on the output constraints and target process parameters. This includes the following steps: Step 301: Obtain the target process parameters for the ammonia synthesis system.

[0059] In the embodiments of this application, the target process parameters, i.e. the current real-time operating data of the ammonia synthesis system, reflect the current operating status of the system.

[0060] The system reads current process parameters in real time, including temperature, pressure, flow rate, and load. This real-time data serves as input to the predictive control model to determine the current system state and perform rolling optimization based on that state.

[0061] Step 302: Based on the target process parameters and at least one set of operating condition data, determine the target set of operating condition data corresponding to the ammonia synthesis system.

[0062] In the embodiments of this application, the current operating condition category of the system is determined based on the current operating state of the system (i.e., the target process parameters).

[0063] Specifically, based on the similarity between the current target process parameters and at least one set of operating condition data obtained through clustering, the set of operating condition data with the highest similarity is selected and determined as the target operating condition data set corresponding to the current ammonia synthesis system, thereby determining the current operating condition category of the system. For example, if the current temperature, pressure, and load are all within the typical range of the high-load operating condition cluster, then the system is determined to be in a "high-load operating condition".

[0064] Step 303: Determine the target safe operating boundary corresponding to the target operating condition data set in at least one safe operating boundary.

[0065] In the embodiments of this application, the target safe operating boundary is the safe operating boundary corresponding to the target operating condition data set, which includes the safe value range of each operating parameter under that operating condition (such as the upper and lower limits of valve opening) and the optimal operating value. Specifically, the target safe operating boundary corresponding to the target operating condition data set is determined from several safe operating boundaries according to a pre-established "operating condition-safe operating boundary" mapping rule.

[0066] Step 304: The target process parameters are used as inputs to the predictive control model, and the target safe operating boundary is used as the output constraint of the predictive control model, so as to use the target operating parameters output by the predictive control model to control the ammonia synthesis system.

[0067] In the embodiments of this application, the target process parameters of the ammonia synthesis system within the current continuous time period are used as model inputs, and the target safe operating boundary is used as the model output constraint. A predictive control model is used to perform rolling optimization calculations to calculate the target operating parameters corresponding to the target process parameters within the current continuous time period. These target operating parameters include parameters such as valve opening degree, and they fall within the range of the target safe operating boundary.

[0068] The target operating parameters serve as control commands for the ammonia synthesis system. These control commands act on the ammonia synthesis system to control and adjust parameters such as valve opening.

[0069] Optionally, the ammonia synthesis system is controlled by outputting target operating parameters from the predictive control model. Then, the operating data of the ammonia synthesis system during the control process based on the target operating parameters are collected to obtain at least one target operating data. Based on the at least one target operating data, at least one historical operating data is updated to generate at least one updated safe operating boundary for constraining the predictive control model.

[0070] Specifically, the ammonia synthesis system is controlled to operate stably at the target operating parameters for several months (e.g., three months), continuously collecting new operational data. A new round of clustering is triggered periodically (e.g., quarterly or semi-annually), updating the "operating condition-safe operating boundary" mapping rules using richer and higher-quality operational data. This allows for simultaneous re-identification and accuracy improvement of the predictive control model. Through a closed-loop iterative mechanism, this approach enables the ammonia synthesis system to adapt to long-term changes in the process unit, continuously optimizing the flexible control effect.

[0071] In summary, this application obtains the current target process parameters of the ammonia synthesis system, compares them with the clustered operating condition data set to determine the current target operating condition of the system; then, it selects the target safe operating boundary corresponding to the target operating condition from the pre-extracted safe operating boundaries; finally, it uses the target process parameters as the input of the predictive control model and the target safe operating boundary as the output constraint of the predictive control model, enabling the predictive control model to continuously optimize within the historically validated safe and feasible domain, and outputting the optimal control command to control the ammonia synthesis system. In this way, dynamic constraint adaptive control based on real-time operating conditions is achieved. Even when the model accuracy is not high, it can ensure that the control actions are always within the safe range, thereby reducing the dependence on accurate models and improving the stability and safety of the system under fluctuating operating conditions. This control method has the advantages of strong engineering practicality, short commissioning cycle, high model robustness, high safety, and strong adaptive and iterative optimization capabilities.

[0072] Furthermore, to help better understand the multistable ammonia synthesis control method provided in this application, such as Figure 5 As shown, Figure 5 This is a schematic diagram illustrating the overall flow of a specific multistable ammonia synthesis control method provided in this application. The multistable ammonia synthesis control method provided in this application may include four stages: a data preparation stage, an offline clustering learning stage, an online predictive control stage, and a closed-loop iteration stage.

[0073] Reference Figure 5In the data preparation phase, historical operating data covering multiple operating conditions is acquired, including historical process parameters and historical operating parameters. In the offline clustering learning phase, unsupervised clustering is used to extract operating conditions (i.e., operating condition data sets) and operating boundaries (i.e., safe operating boundaries) from the historical operating data, thereby generating a rule base for "operating conditions-operating boundaries". In the online predictive control phase, process variables (i.e., target process parameters) of the ammonia synthesis system are collected in real time for operating condition identification, and corresponding safe operating boundaries are dynamically loaded. The corresponding boundaries dynamically loaded according to the operating conditions are used as output constraints of the MPC (predictive control model), which performs rolling optimization and outputs the safest optimal control command (i.e., target operating parameters) to act on the synthesis tower system (taking the ammonia synthesis system as an example). In the closed-loop iteration phase, after the control command is applied to the ammonia synthesis system, new operating data is produced and stored in the database of the ammonia synthesis system. Through periodic triggering, a new round of unsupervised clustering analysis is performed on the new historical operating data to generate a new rule base for "operating conditions-safe operating boundaries", forming a closed-loop iteration.

[0074] To achieve the above embodiments, this application also provides a multi-stable ammonia synthesis control device. Figure 6 This is a schematic diagram of a multi-stable ammonia synthesis control device 600 provided in an embodiment of this application. Figure 6 As shown, the device includes: The acquisition unit 610 is used to acquire at least one historical operating data of the ammonia synthesis system. Each historical operating data in the at least one historical operating data includes at least one historical process parameter and at least one historical operating parameter corresponding to the at least one historical process parameter. The partitioning unit 620 is used to perform condition clustering on at least one historical operating data based on at least one historical process parameter to obtain at least one set of operating data. Analysis unit 630 is used to perform data analysis on at least one historical operating parameter under each operating condition data set in at least one operating condition data set, so as to obtain at least one safe operating boundary corresponding to at least one operating condition data set. The constraint unit 640 is used to use at least one safe operating boundary as the output constraint of the predictive control model of the ammonia synthesis system, so as to control the ammonia synthesis system according to the target operating parameters output by the predictive control model based on the output constraints and the target process parameters.

[0075] In some embodiments, the constraint unit 640 is configured to: acquire target process parameters of the ammonia synthesis system; determine a target operating condition data set corresponding to the ammonia synthesis system based on the target process parameters and at least one operating condition data set; determine a target safe operating boundary corresponding to the target operating condition data set in at least one safe operating boundary; use the target process parameters as input to a predictive control model and the target safe operating boundary as output constraints of the predictive control model, so as to control the ammonia synthesis system by using the target operating parameters output by the predictive control model.

[0076] In some embodiments, the apparatus includes: an iterative update unit, configured to control an ammonia synthesis system by outputting target operating parameters using a predictive control model, and then collect operating data of the ammonia synthesis system during the control process based on the target operating parameters to obtain at least one target operating data; and update at least one historical operating data based on the at least one target operating data to generate at least one updated safe operating boundary for constraining the predictive control model based on the updated at least one historical operating data.

[0077] In some embodiments, the partitioning unit 620 is configured to: perform condition clustering processing on at least one historical operating data based on the similarity between at least one historical process parameter of each historical operating data in at least one historical operating data, using a preset clustering algorithm, so as to divide at least one historical operating data into at least one set of operating condition data.

[0078] In some embodiments, at least one historical process parameter includes at least one key process parameter, which includes at least one of temperature, pressure, flow rate, and load parameters.

[0079] In some embodiments, the analysis unit 630 is configured to: perform data statistics on at least one historical operating parameter under each operating condition data set in at least one operating condition data set to obtain at least one operating parameter data distribution corresponding to at least one operating condition data set; and determine at least one safe operating boundary corresponding to at least one operating condition data set based on the at least one operating parameter data distribution.

[0080] In some embodiments, the analysis unit 630 is configured to: perform boundary extraction on the distribution of at least one operating parameter data to obtain at least one safe operating boundary corresponding to at least one set of operating condition data, wherein the boundary extraction includes extracting at least one of the maximum value, minimum value, mean value and confidence interval of the operating parameter.

[0081] In some embodiments, the apparatus includes: a construction unit for using at least one safe operating boundary as the output constraint of a predictive control model of a synthetic ammonia system, wherein, prior to determining the coupling relationship between process parameters and operating parameters of the synthetic ammonia system based on process mechanism information of the synthetic ammonia system, the process parameters include key controlled variables and disturbance variables, and the operating parameters include operating variables; and constructing a predictive control model based on the coupling relationship between the process parameters and operating parameters.

[0082] Since the apparatus provided in this application corresponds to the methods provided in the above-mentioned embodiments, the implementation of the methods is also applicable to the apparatus provided in this embodiment, and will not be described in detail in this embodiment.

[0083] The methods and apparatus provided in the embodiments of this application have been described above. To implement the functions of the methods provided in the embodiments of this application, the electronic device may include a hardware structure and software modules, and may implement the above functions in the form of a hardware structure, software modules, or a hardware structure plus software modules. One of the above functions may be executed in the form of a hardware structure, software modules, or a hardware structure plus software modules.

[0084] Figure 7 This is a block diagram illustrating an electronic device 700 for implementing the above-described multi-steady-state ammonia synthesis control method according to an exemplary embodiment. (Refer to...) Figure 7 The electronic device 700 may include a communication interface 701, capable of interacting with other devices; a processor 702, connected to the communication interface 701 to interact with other devices, used to execute the methods provided by one or more of the above-mentioned technical solutions when running a computer program; and a memory 703, on which the computer program is stored. Specifically, the specific processing procedure of the processor 702 can refer to the multistable ammonia synthesis control method described in the above embodiments of this application.

[0085] Of course, in practical applications, the various components in electronic device 700 are coupled together through bus system 704. It can be understood that bus system 704 is used to realize the connection and communication between these components. In addition to a data bus, bus system 704 also includes a power bus, a control bus, and a status signal bus. However, for the sake of clarity, in... Figure 7 The general designated all buses as Bus System 704.

[0086] The memory 703 in this embodiment is used to store various types of data to support the operation of the electronic device 700. Examples of such data include any computer program used to operate on the electronic device 700.

[0087] The methods disclosed in the embodiments of this application can be applied to processor 702, or implemented by processor 702. Processor 702 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the integrated logic circuit of the hardware in processor 702 or by instructions in the form of software. The processor 702 may be a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Processor 702 can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. A general-purpose processor may be a microprocessor or any conventional processor, etc. The steps of the methods disclosed in the embodiments of this application can be directly manifested as being executed by a hardware decoding processor, or being executed by a combination of hardware and software modules in the decoding processor. The software modules may be located in a storage medium, which is located in memory 703. Processor 702 reads the information in memory 703 and combines its hardware to complete the steps of the aforementioned method.

[0088] In an exemplary embodiment, the electronic device 700 may be implemented by one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field-programmable gate arrays (FPGAs), general-purpose processors, controllers, microcontrollers (MCUs), microprocessors, or other electronic components to perform the aforementioned method.

[0089] Embodiments of this application also propose a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to execute the multistable ammonia synthesis control method described in the above embodiments of this application.

[0090] Embodiments of this application also propose a computer program product, including a computer program that is executed by a processor using the multistable ammonia synthesis control method described in the above embodiments of this application.

[0091] Embodiments of this application also propose a chip including one or more interface circuits and one or more processors; the interface circuits are used to receive signals from the memory of an electronic device and send signals to the processors, the signals including computer instructions stored in the memory, and when the processor executes the computer instructions, it causes the electronic device to perform the multistable ammonia synthesis control method described in the above embodiments of this application.

[0092] It should be noted that the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0093] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "illustrative embodiment," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with an embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0094] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing a particular logical function or process, and the scope of the preferred embodiments of the invention includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as will be understood by those skilled in the art to which embodiments of the invention pertain.

[0095] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processing module, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (control method), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which programs can be printed, because programs can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0096] It should be understood that various parts of the embodiments of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0097] Those skilled in the art will understand that all or part of the steps of the methods described in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0098] Furthermore, the functional units in the various embodiments of the present invention can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc.

[0099] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. A method for controlling multi-stable-state ammonia synthesis, characterized in that, The method includes: Acquire at least one historical operating data of the ammonia synthesis system, wherein each historical operating data includes at least one historical process parameter and at least one historical operating parameter corresponding to the at least one historical process parameter; Based on the at least one historical process parameter, the at least one historical operating data is subjected to operating condition clustering to obtain at least one operating condition data set; Data analysis is performed on at least one historical operating parameter under each operating condition data set in the at least one operating condition data set to obtain at least one safe operating boundary corresponding to at least one operating condition data set. The at least one safe operating boundary is used as the output constraint of the predictive control model of the ammonia synthesis system, so as to control the ammonia synthesis system according to the target operating parameters output by the predictive control model based on the output constraint and the target process parameters.

2. The method according to claim 1, characterized in that, The step of using the at least one safe operating boundary as the output constraint of the predictive control model of the ammonia synthesis system, and controlling the ammonia synthesis system according to the target operating parameters output by the predictive control model based on the output constraints and the target process parameters, includes: Obtain the target process parameters of the ammonia synthesis system; Based on the target process parameters and the at least one set of operating condition data, the target set of operating condition data corresponding to the ammonia synthesis system is determined; Determine the target safe operating boundary corresponding to the target operating condition data set in the at least one safe operating boundary; The target process parameters are used as inputs to the predictive control model, and the target safe operating boundary is used as the output constraint of the predictive control model, so as to control the ammonia synthesis system by using the target operating parameters output by the predictive control model.

3. The method according to claim 2, characterized in that, The method involves controlling the ammonia synthesis system by outputting the target operating parameters from the predictive control model, followed by: Collect operating data of the ammonia synthesis system during the control process of the ammonia synthesis system according to the target operating parameters, and obtain at least one target operating data; Based on the at least one target operating data, the at least one historical operating data is updated to generate at least one updated safe operating boundary for constraining the predictive control model.

4. The method according to claim 1, characterized in that, The step of performing condition clustering on the at least one historical operating data based on the at least one historical process parameter to obtain at least one set of operating condition data includes: Based on the similarity between at least one historical process parameter of each historical operating data in the at least one historical operating data, a preset clustering algorithm is used to perform operating condition clustering processing on the at least one historical operating data to divide the at least one historical operating data into at least one operating condition data set.

5. The method according to claim 4, characterized in that, The at least one historical process parameter includes at least one key process parameter, which includes at least one of temperature, pressure, flow rate, and load parameters.

6. The method according to claim 1, characterized in that, The step of performing data analysis on at least one historical operating parameter under each operating condition data set in the at least one operating condition data set to obtain at least one safe operating boundary corresponding to at least one operating condition data set includes: Data statistics are performed on at least one historical operating parameter under each operating condition data set in the at least one operating condition data set to obtain the data distribution of at least one operating parameter corresponding to the at least one operating condition data set. Based on the distribution of the at least one operating parameter data, at least one safe operating boundary is determined corresponding to at least one set of operating condition data.

7. The method according to claim 6, characterized in that, The step of determining at least one safe operating boundary corresponding to at least one set of operating condition data based on the distribution of at least one operating parameter data includes: Boundary extraction is performed on the distribution of the at least one operating parameter data to obtain at least one safe operating boundary corresponding to the at least one set of operating condition data. The boundary extraction includes extracting at least one of the maximum value, minimum value, mean value and confidence interval of the operating parameter.

8. The method according to claim 1, characterized in that, Prior to using the at least one safe operating boundary as the output constraint of the predictive control model of the ammonia synthesis system, the method includes: Based on the process mechanism information of the ammonia synthesis system, the coupling relationship between the process parameters and operating parameters of the ammonia synthesis system is determined. The process parameters include key controlled variables and disturbance variables, and the operating parameters include operating variables. The predictive control model is constructed based on the coupling relationship between the process parameters and the operating parameters.

9. A control device for an ammonia synthesis system, characterized in that, The device includes: The acquisition unit is used to acquire at least one historical operating data of the ammonia synthesis system, wherein each historical operating data in the at least one historical operating data includes at least one historical process parameter and at least one historical operating parameter corresponding to the at least one historical process parameter. A partitioning unit is used to perform condition clustering on the at least one historical operating data according to the at least one historical process parameter, so as to obtain at least one set of operating data. The analysis unit is used to perform data analysis on at least one historical operating parameter under each operating condition data set in the at least one operating condition data set, so as to obtain at least one safe operating boundary corresponding to at least one operating condition data set. A constraint unit is used to use the at least one safe operating boundary as the output constraint of the predictive control model of the ammonia synthesis system, so as to control the ammonia synthesis system according to the target operating parameters output by the predictive control model based on the output constraints and the target process parameters.

10. An electronic device, characterized in that, include: The processor and the memory used to store computer programs that can run on the processor. When the processor is used to run the computer program, it performs the method according to any one of claims 1 to 8.

Images