Nitrogen oxide intelligent control method and device based on multivariate model prediction
The intelligent control method based on multivariate model prediction solves the problems of insufficient control accuracy and low economy in the denitrification control of circulating fluidized bed boilers, realizes stable and optimized control of nitrogen oxides, and improves the safety and economy of the system.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- HUADIAN POWER INTERNATIONAL CORPORATION LTD
- Filing Date
- 2026-04-20
- Publication Date
- 2026-07-21
AI Technical Summary
Existing circulating fluidized bed boiler denitrification control technologies suffer from insufficient control precision and stability, high reducing agent consumption, difficulty in coordinating strong coupling of multiple variables, and a lack of safety and reliability mechanisms, resulting in unstable nitrogen oxide control and low economic efficiency.
An intelligent control method based on multivariate model prediction is adopted. By collecting process control data, multivariate modeling is performed to construct a high-precision prediction model, outputting nitrogen oxide concentration prediction data and generating target control commands. The DCS system is used for monitoring and evaluation to achieve stable and optimized control of nitrogen oxides.
It improves the accuracy and economy of denitrification control, achieves stable and optimized control of nitrogen oxide emissions, reduces reducing agent consumption, and enhances the level of automation and the safety and reliability of the system.
Smart Images
Figure CN122429360A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of combustion control technology, and in particular to a method and device for intelligent control of nitrogen oxides based on multivariate model prediction. Background Technology
[0002] Currently, in the denitrification control of circulating fluidized bed boilers, most existing technologies adopt traditional PID (Proportional-Integral-Derivative) control combined with manual intervention. These technologies mainly suffer from problems such as insufficient control accuracy and stability, high reductant consumption, difficulty in coordinating strong coupling of multiple variables, and lack of safety and reliability mechanisms. As a result, it is difficult to achieve stable, economical, and reliable control of nitrogen oxides, which urgently needs to be addressed. Summary of the Invention
[0003] This application provides a method and device for intelligent control of nitrogen oxides based on multivariate model prediction, in order to solve the problems of insufficient safety, limited adjustment accuracy, and low economic efficiency of existing circulating fluidized bed boiler denitrification control technology.
[0004] The first aspect of this application provides a method for intelligent control of nitrogen oxides based on multivariate model prediction, comprising the following steps: collecting process control data from a target power plant and performing a preset multivariate modeling operation on the process control data to construct a multivariate prediction model that meets preset accuracy requirements; inputting the process control data into the multivariate prediction model to output nitrogen oxide concentration prediction data for a target time period generated by the multivariate prediction model in each control cycle, solving for the corresponding target control command based on the nitrogen oxide concentration prediction data, and sending the target control command to the DCS system of the target power plant; displaying the current nitrogen oxide concentration trend, current control effect, and current system operating status corresponding to the target control command through a preset graphical monitoring interface in the DCS system, and generating a corresponding control performance evaluation report.
[0005] Optionally, in one embodiment of this application, the step of collecting process control data from the target power plant and performing a preset multivariate modeling operation on the process control data to construct a multivariate prediction model that meets preset accuracy requirements includes: connecting the target intelligent control server to the factory control network of the target power plant through a preset industrial Ethernet switch, and collecting the process control data of the target power plant using the OPC UA / DA standard interface provided by the DCS system and a preset step test strategy; constructing the response curve corresponding to the process control data, and performing preset tuning processing on the response curve to obtain the dynamic characteristics of a single control loop; constructing a causal relationship network between multiple variables according to a preset time-series causal algorithm, so as to determine the global coupling relationship between at least one key parameter in the process control data that meets preset key requirements through the causal relationship network, and constructing the multivariate prediction model based on the global coupling relationship and the dynamic characteristics.
[0006] Optionally, in one embodiment of this application, the step of inputting the process control data into the multivariate prediction model to output the nitrogen oxide concentration prediction data for the target time period generated by the multivariate prediction model in each control cycle, solving the corresponding target control command based on the nitrogen oxide concentration prediction data, and sending the target control command to the DCS system of the target power plant includes: inputting the global coupling relationship, the dynamic characteristics, and the process control data into the multivariate prediction model in each control cycle to output the nitrogen oxide concentration prediction data for the target time period; solving the target control command on a rolling basis based on the nitrogen oxide concentration prediction data to control the nitrogen oxide concentration to meet the preset smoothing requirements according to the target control command, and tracking the preset value of nitrogen oxide concentration, wherein the target control command includes the opening degree of the urea valve and the dilution water valve.
[0007] Optionally, in one embodiment of this application, after sending the target control command to the DCS system of the target power plant, the method further includes: setting a switching button in the graphical monitoring interface of the DCS system to switch control between the target intelligent control server and the DCS system when manually triggered or when a preset anomaly detection requirement is met.
[0008] A second aspect of this application provides a nitrogen oxide intelligent control device based on multivariate model prediction, comprising: a modeling module for collecting process control data from a target power plant and performing preset multivariate modeling operations on the process control data to construct a multivariate prediction model that meets preset accuracy requirements; a prediction module for inputting the process control data into the multivariate prediction model to output nitrogen oxide concentration prediction data for a target time period generated by the multivariate prediction model in each control cycle, solving for the corresponding target control command based on the nitrogen oxide concentration prediction data, and sending the target control command to the DCS system of the target power plant; and a visualization module for displaying the current nitrogen oxide concentration trend, current control effect, and current system operating status corresponding to the target control command through a preset graphical monitoring interface in the DCS system, and generating a corresponding control performance evaluation report.
[0009] Optionally, in one embodiment of this application, the modeling module includes: a data acquisition unit, configured to connect the target intelligent control server to the factory control network of the target power plant via a preset industrial Ethernet switch, and acquire process control data of the target power plant using the OPC UA / DA standard interface provided by the DCS system and a preset step test strategy; a tuning unit, configured to construct a response curve corresponding to the process control data, and perform preset tuning processing on the response curve to obtain the dynamic characteristics of a single control loop; and a construction unit, configured to construct a causal relationship network among multiple variables according to a preset time-series causal algorithm, so as to determine the global coupling relationship between at least one key parameter in the process control data that meets preset key requirements through the causal relationship network, and construct the multivariate prediction model based on the global coupling relationship and the dynamic characteristics.
[0010] Optionally, in one embodiment of this application, the prediction module includes: an analysis unit, configured to input the global coupling relationship, the dynamic characteristics, and the process control data into the multivariate prediction model within each control cycle, so as to output nitrogen oxide concentration prediction data for the target time period; and a solution unit, configured to solve the target control command based on the nitrogen oxide concentration prediction data, so as to control the nitrogen oxide concentration to meet the preset smoothing requirements according to the target control command, and track the preset value of nitrogen oxide concentration, wherein the target control command includes the opening degree of the urea valve and the dilution water valve.
[0011] Optionally, in one embodiment of this application, it further includes: a switching module, configured to set a switching button in the graphical monitoring interface of the DCS system after the target control command is sent to the DCS system of the target power plant, so as to switch control between the target intelligent control server and the DCS system upon manual triggering or meeting preset anomaly detection requirements.
[0012] A third aspect of this application provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the intelligent control method for nitrogen oxides based on multivariate model prediction as described in the above embodiments.
[0013] A fourth aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described intelligent control method for nitrogen oxides based on multivariate model prediction.
[0014] A fifth aspect of this application provides a computer program product, including a computer program that is executed to implement the above-described intelligent control method for nitrogen oxides based on multivariate model prediction.
[0015] Therefore, the embodiments of this application have the following beneficial effects: The embodiments of this application can collect process control data from a target power plant and perform preset multivariate modeling operations on the process control data to construct a multivariate prediction model that meets preset accuracy requirements. The process control data is input into the multivariate prediction model to output nitrogen oxide concentration prediction data for the target time period generated by the multivariate prediction model in each control cycle. The corresponding target control command is then calculated based on the nitrogen oxide concentration prediction data and sent to the target power plant's DCS (Distributed Control System). The DCS system uses a preset graphical monitoring interface to display the current nitrogen oxide concentration trend, current control effect, and current system operating status corresponding to the target control command, and generates a corresponding control performance evaluation report. This application addresses the characteristics of strong multivariate coupling and significant nonlinearity between combustion and denitrification in circulating fluidized bed boilers. Through multivariate coordination and model predictive control, it achieves stable and optimized control of nitrogen oxide emissions, thereby making automatic denitrification control safe and controllable, and improving the accuracy and economy of denitrification control. This solves the problems of insufficient safety, limited adjustment accuracy, and low economy in existing circulating fluidized bed boiler denitrification control technologies.
[0016] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description
[0017] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein: Figure 1 This is a flowchart illustrating a method for intelligent control of nitrogen oxides based on multivariate model prediction, according to an embodiment of this application. Figure 2 A schematic diagram of the logical architecture of a nitrogen oxide intelligent control method based on multivariate model prediction provided for one embodiment of this application; Figure 3 A schematic diagram illustrating the execution logic of a nitrogen oxide intelligent control method based on multivariate model prediction, provided as an embodiment of this application; Figure 4 A schematic diagram of a multivariable coordinated control structure is provided for one embodiment of this application; Figure 5 A schematic diagram illustrating the switching logic between a DCS system and a MIC (Measurement Instrumentation Control) system is provided as an embodiment of this application. Figure 6 This is an example diagram of a nitrogen oxide intelligent control device based on multivariate model prediction according to 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.
[0018] Among them, 10-Intelligent control device for nitrogen oxides based on multivariate model prediction, 100-Modeling module, 200-Prediction module, 300-Visualization module, 701-Memory, 702-Processor, and 703-Communication interface. Detailed Implementation
[0019] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.
[0020] The following description, with reference to the accompanying drawings, describes an intelligent nitrogen oxide (NOx) control method and apparatus based on multivariate model prediction, according to embodiments of this application. Addressing the problems mentioned in the background section, this application provides an intelligent NOx control method based on multivariate model prediction. In this method, process control data from a target power plant is collected, and a multivariate modeling operation is performed on the process control data to construct a multivariate prediction model that meets preset accuracy requirements. The process control data is input into the multivariate prediction model to output NOx concentration prediction data for the target time period generated by the multivariate prediction model in each control cycle. The corresponding target control command is then calculated based on the NOx concentration prediction data and sent to the DCS system of the target power plant. The DCS system uses a preset graphical monitoring interface to display the current NOx concentration trend, current control effect, and current system operating status corresponding to the target control command, and generates a corresponding control performance evaluation report. This application addresses the characteristics of strong multivariate coupling and significant nonlinearity between combustion and denitrification in circulating fluidized beds. By using multivariate coordination and model predictive control, stable and optimized control of NOx emissions is achieved, thereby making automatic denitrification control safe and controllable, and improving the accuracy and economy of denitrification control. This solves the problems of insufficient safety, limited adjustment accuracy, and low economic efficiency of existing circulating fluidized bed boiler denitrification control technology.
[0021] Specifically, Figure 1 This is a flowchart illustrating a method for intelligent control of nitrogen oxides based on multivariate model prediction, provided in an embodiment of this application.
[0022] like Figure 1 As shown, the intelligent control method for nitrogen oxides based on multivariate model prediction includes the following steps: In step S101, process control data of the target power plant is collected, and a preset multivariate modeling operation is performed on the process control data to construct a multivariate prediction model that meets the preset accuracy requirements.
[0023] The embodiments of this application can first collect the underlying process control data of the power plant and perform preset multivariate modeling operations on it, thereby constructing a high-precision (i.e., meeting the preset precision requirements) multivariate prediction model.
[0024] Optionally, in one embodiment of this application, process control data of the target power plant is collected, and a preset multivariate modeling operation is performed on the process control data to construct a multivariate prediction model that meets preset accuracy requirements. This includes: connecting the target intelligent control server to the factory control network of the target power plant through a preset industrial Ethernet switch, and collecting the process control data of the target power plant using the OPC UA / DA standard interface provided by the DCS system and a preset step test strategy; constructing the response curve corresponding to the process control data, and performing preset tuning processing on the response curve to obtain the dynamic characteristics of a single control loop; constructing a causal relationship network between multiple variables according to a preset time-series causal algorithm, so as to determine the global coupling relationship between at least one key parameter in the process control data that meets preset key requirements through the causal relationship network, and constructing a multivariate prediction model based on the global coupling relationship and dynamic characteristics.
[0025] It should be noted that, in this embodiment, a dedicated MIC (Measurement Instrumentation Control) server can first be deployed on-site. This server connects to the factory control network via an industrial Ethernet switch and utilizes the OPC UA / DA standard interface provided by the power plant's DCS system to achieve real-time, bidirectional, and secure communication with the underlying process control data. This logical architecture is as follows: Figure 2 As shown.
[0026] Secondly, the embodiments of this application can perform data acquisition and model building operations. As one possible approach, the acquired process data can be processed using the response curve tuning method, and the dynamic characteristics of a single control loop can be obtained using step tests. Simultaneously, the embodiments of this application can employ a time-series causal algorithm to construct a causal relationship network among multiple variables and clarify the global coupling relationships between key parameters. Furthermore, the embodiments of this application can integrate the above two types of analysis results (i.e., global coupling relationships and dynamic characteristics) to establish a high-precision multivariate prediction model. The specific execution process is as follows: Figure 3 As shown.
[0027] Therefore, the embodiments of this application can effectively solve the problem of multivariate strong coupling control, and in view of the characteristics of the interrelation and interactive influence of combustion and denitrification processes in circulating fluidized beds, through advanced modeling and multivariate coordinated control, the system decoupling and overall optimization of key parameters such as urea flow rate, dilution water volume, and bed temperature can be achieved.
[0028] In step S102, process control data is input into the multivariate prediction model to output the nitrogen oxide concentration prediction data for the target time period generated by the multivariate prediction model in each control cycle. The corresponding target control command is then calculated based on the nitrogen oxide concentration prediction data and sent to the DCS system of the target power plant.
[0029] In step S103, the DCS system uses a preset graphical monitoring interface to display the current nitrogen oxide concentration trend, current control effect, and current system operating status corresponding to the target control command, and generates a corresponding control performance evaluation report.
[0030] Furthermore, embodiments of this application can input process control data into a multivariate prediction model to output NOx concentration prediction data for future time periods, thereby solving for the corresponding target control command (i.e., optimal control command) and sending it to the power plant's DCS system.
[0031] Finally, the embodiments of this application can provide a graphical monitoring interface to display NOx concentration trends, control effects and system operating status in real time, and can automatically generate control performance evaluation reports, including quantitative calculations of self-control rate, stability rate and cost savings.
[0032] It is understood that the embodiments of this application can significantly improve control accuracy and stability, achieve stable and precise control of NOx emission concentration, and effectively reduce reducing agent consumption and save operating costs by optimizing control strategies. Secondly, the embodiments of this application greatly improve the automation level of the device, maintain a high automatic control rate for a long time, significantly reduce manual intervention, and reduce labor intensity and operational risks. At the same time, the embodiments of this application have a complete safety switching mechanism and anti-misoperation logic to ensure safe commissioning and enhance overall operational reliability. In addition, the model predictive control algorithm used in the embodiments of this application has rolling optimization and feedback correction capabilities, can adapt to changes in operating conditions such as load and coal quality, has strong anti-interference ability, and excellent robustness.
[0033] Optionally, in one embodiment of this application, process control data is input into a multivariate prediction model to output nitrogen oxide concentration prediction data for the target time period generated by the multivariate prediction model in each control cycle, and the corresponding target control command is solved based on the nitrogen oxide concentration prediction data, and the target control command is sent to the DCS system of the target power plant. This includes: in each control cycle, inputting global coupling relationship, dynamic characteristics and process control data into the multivariate prediction model to output nitrogen oxide concentration prediction data for the target time period; based on the nitrogen oxide concentration prediction data, continuously solving the target control command to control the nitrogen oxide concentration to meet the preset smoothing requirements according to the target control command, and tracking the preset value of nitrogen oxide concentration, wherein the target control command includes the opening degree of the urea valve and the dilution water valve.
[0034] It should be noted that, in each control cycle, this application embodiment can, based on the prediction of the system output over a future period by a multivariate prediction model, continuously solve for a set of optimal control commands, such as the opening degree of the urea valve and the dilution water valve, so that the NOx concentration smoothly and accurately tracks the set value. This multivariate coordinated control structure is as follows: Figure 4 As shown.
[0035] Therefore, the embodiments of this application can achieve economically optimal control under environmental constraints, and while ensuring that emissions meet standards, the NOx concentration is stably controlled within an economic range close to the upper limit, thereby minimizing the consumption of reducing agents.
[0036] Optionally, in one embodiment of this application, after sending the target control command to the DCS system of the target power plant, the method further includes: setting a switching button in the graphical monitoring interface of the DCS system to switch control between the target intelligent control server and the DCS system when manually triggered or when a preset abnormality detection requirement is met.
[0037] As a feasible approach to ensure system operational safety, this embodiment of the application can include a "one-click switching" button on the DCS operation screen. Whether manually triggered or when the system detects an anomaly, control can be switched bidirectionally, seamlessly, and instantaneously between the MIC system and the existing DCS, with the actuator position remaining unchanged during the switching process. Figure 5 As shown, this avoids process fluctuations.
[0038] Therefore, the embodiments of this application can construct a safe and reliable advanced control architecture. While introducing predictive control algorithms to improve regulation quality, it designs a control system with intelligent switching, anti-misoperation protection, and multiple fault-tolerant mechanisms to ensure that it can smoothly and seamlessly revert to the basic control mode under abnormal operating conditions, thus ensuring the long-term stable operation of the device. In addition, the embodiments of this application can promote the intelligent upgrade of power plant control. By providing standardized, hardware-software decoupled solutions, it reduces the application threshold and implementation cycle of advanced control in circulating fluidized bed units, thereby helping traditional power plants achieve digital and automated transformation of the control layer and improve operational consistency and maintainability.
[0039] In summary, this application proposes an integrated solution with outstanding advantages to address the multivariable, strongly coupled, and nonlinear control challenges in the combustion and denitrification processes of circulating fluidized bed boilers. It constructs a complete technical closed loop integrating modeling, control, and safety. By combining dynamic characteristic identification and multivariable predictive control, and incorporating an industrial-grade safety architecture to achieve seamless switching and anti-misoperation protection, it forms a highly mature and easily engineering-implementable overall control strategy suitable for circulating fluidized bed operating conditions. Furthermore, this application adheres to the principle of "balancing efficiency and safety," ensuring safe and reliable system commissioning and operation while achieving optimized control and economic benefits.
[0040] The intelligent nitrogen oxide (NOx) control method based on multivariate model prediction proposed in this application collects process control data from a target power plant and performs pre-defined multivariate modeling operations on the process control data to construct a multivariate prediction model that meets pre-defined accuracy requirements. The process control data is input into the multivariate prediction model to output NOx concentration prediction data for the target time period generated by the multivariate prediction model in each control cycle. The corresponding target control command is then calculated based on the NOx concentration prediction data and sent to the DCS system of the target power plant. The DCS system uses a pre-defined graphical monitoring interface to display the current NOx concentration trend, current control effect, and current system operating status corresponding to the target control command, and generates a corresponding control performance evaluation report. This application addresses the characteristics of strong multivariate coupling and significant nonlinearity between combustion and denitrification in circulating fluidized beds. Through multivariate coordination and model predictive control, it achieves stable and optimized control of NOx emissions, thereby making automatic denitrification control safe and controllable, and improving the accuracy and economy of denitrification control.
[0041] Secondly, with reference to the accompanying drawings, a nitrogen oxide intelligent control device based on multivariate model prediction proposed according to an embodiment of this application is described.
[0042] Figure 6 This is a block diagram of a nitrogen oxide intelligent control device based on multivariate model prediction according to an embodiment of this application.
[0043] like Figure 6 As shown, the intelligent control device 10 for nitrogen oxides based on multivariate model prediction includes: a modeling module 100, a prediction module 200, and a visualization module 300.
[0044] The modeling module 100 is used to collect process control data of the target power plant and perform preset multivariate modeling operations on the process control data to construct a multivariate prediction model that meets preset accuracy requirements.
[0045] The prediction module 200 is used to input the process control data into the multivariate prediction model, output the nitrogen oxide concentration prediction data for the target time period generated by the multivariate prediction model in each control cycle, solve the corresponding target control command based on the nitrogen oxide concentration prediction data, and send the target control command to the DCS system of the target power plant.
[0046] The visualization module 300 is used to display the current nitrogen oxide concentration trend, current control effect and current system operating status corresponding to the target control command through a preset graphical monitoring interface of the DCS system, and generate a corresponding control performance evaluation report.
[0047] Optionally, in one embodiment of this application, the modeling module 100 includes: an acquisition unit, an adjustment unit, and a construction unit.
[0048] The acquisition unit is used to connect the target intelligent control server to the factory control network of the target power plant through a preset industrial Ethernet switch, and to acquire the process control data of the target power plant using the OPC UA / DA standard interface provided by the DCS system and a preset step test strategy.
[0049] The tuning unit is used to construct the response curve corresponding to the process control data and to perform preset tuning processing on the response curve to obtain the dynamic characteristics of a single control loop.
[0050] The construction unit is used to construct a causal relationship network among multiple variables according to a preset time-series causal algorithm, so as to determine the global coupling relationship among at least one key parameter in the process control data that meets the preset key requirements through the causal relationship network, and construct the multivariate prediction model based on the global coupling relationship and the dynamic characteristics.
[0051] Optionally, in one embodiment of this application, the prediction module 200 includes an analysis unit and a solution unit.
[0052] The analysis unit is used to input the global coupling relationship, the dynamic characteristics, and the process control data into the multivariate prediction model in each control cycle, so as to output the predicted nitrogen oxide concentration data for the target time period.
[0053] The solving unit is used to solve the target control command on a rolling basis based on the predicted nitrogen oxide concentration data, so as to control the nitrogen oxide concentration to meet the preset smoothing requirements according to the target control command, and track the preset value of nitrogen oxide concentration, wherein the target control command includes the opening degree of the urea valve and the dilution water valve.
[0054] Optionally, in one embodiment of this application, the nitrogen oxide intelligent control device 10 based on multivariate model prediction of this application embodiment further includes: a switching module, used to set a switching button in the graphical monitoring interface of the DCS system after the target control command is sent to the DCS system of the target power plant, so as to switch control between the target intelligent control server and the DCS system when manually triggered or when the preset abnormal detection requirements are met.
[0055] It should be noted that the foregoing explanation of the embodiment of the intelligent control method for nitrogen oxides based on multivariate model prediction also applies to the intelligent control device for nitrogen oxides based on multivariate model prediction in this embodiment, and will not be repeated here.
[0056] The intelligent nitrogen oxide control device based on multivariate model prediction proposed in this application includes a modeling module 100, used to collect process control data from a target power plant and perform preset multivariate modeling operations on the process control data to construct a multivariate prediction model that meets preset accuracy requirements; a prediction module 200, used to input the process control data into the multivariate prediction model to output nitrogen oxide concentration prediction data for the target time period generated by the multivariate prediction model in each control cycle, and to solve for the corresponding target control command based on the nitrogen oxide concentration prediction data, and send the target control command to the DCS system of the target power plant; and a visualization module 300, used to display the current nitrogen oxide concentration trend, current control effect, and current system operating status corresponding to the target control command through a preset graphical monitoring interface in the DCS system, and to generate a corresponding control performance evaluation report. This application addresses the characteristics of strong multivariate coupling and significant nonlinearity between combustion and denitrification in circulating fluidized bed systems, achieving stable and optimized control of nitrogen oxide emissions through multivariate coordination and model predictive control, thereby making automatic denitrification control safe and controllable, and improving the accuracy and economy of denitrification control.
[0057] Figure 7 A schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device may include: The memory 701, the processor 702, and the computer program stored on the memory 701 and executable on the processor 702.
[0058] When the processor 702 executes the program, it implements the intelligent control method for nitrogen oxides based on multivariate model prediction provided in the above embodiments.
[0059] Furthermore, electronic devices also include: Communication interface 703 is used for communication between memory 701 and processor 702.
[0060] The memory 701 is used to store computer programs that can run on the processor 702.
[0061] The memory 701 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.
[0062] If the memory 701, processor 702, and communication interface 703 are implemented independently, then the communication interface 703, memory 701, and processor 702 can be interconnected via a bus to complete communication between them. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of representation, Figure 7 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.
[0063] Optionally, in a specific implementation, if the memory 701, processor 702, and communication interface 703 are integrated on a single chip, then the memory 701, processor 702, and communication interface 703 can communicate with each other through an internal interface.
[0064] The processor 702 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.
[0065] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the above-described intelligent control method for nitrogen oxides based on multivariate model prediction.
[0066] This application also provides a computer program product, including a computer program, which, when executed, is used to implement the above-described intelligent control method for nitrogen oxides based on multivariate model prediction.
[0067] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. 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. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.
[0068] Furthermore, the terms "first" and "second" 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" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.
[0069] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application 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 should be understood by those skilled in the art to which embodiments of this application pertain.
[0070] 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 processor-included system, 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 (electronic device), 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). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.
[0071] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. 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.
[0072] Those skilled in the art will understand that all or part of the steps of the methods 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.
[0073] Furthermore, the functional units in the various embodiments of this application 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.
[0074] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.
Claims
1. A smart control method for nitrogen oxides based on multivariate model prediction, characterized in that, Includes the following steps: Collect process control data from the target power plant and perform preset multivariate modeling operations on the process control data to construct a multivariate prediction model that meets preset accuracy requirements; The process control data is input into the multivariate prediction model to output the nitrogen oxide concentration prediction data for the target time period generated by the multivariate prediction model in each control cycle. The corresponding target control command is solved based on the nitrogen oxide concentration prediction data, and the target control command is sent to the DCS system of the target power plant. The DCS system uses a preset graphical monitoring interface to display the current nitrogen oxide concentration trend, current control effect, and current system operating status corresponding to the target control command, and generates a corresponding control performance evaluation report.
2. The method according to claim 1, characterized in that, The process control data of the target power plant is collected, and a preset multivariate modeling operation is performed on the process control data to construct a multivariate prediction model that meets preset accuracy requirements, including: The target intelligent control server is connected to the factory control network of the target power plant through a preset industrial Ethernet switch, and the process control data of the target power plant is collected using the OPC UA / DA standard interface provided by the DCS system and the preset step test strategy. Construct the response curve corresponding to the process control data, and perform preset tuning on the response curve to obtain the dynamic characteristics of a single control loop; A causal relationship network among multiple variables is constructed based on a preset time-series causal algorithm. The global coupling relationship among at least one key parameter in the process control data that meets preset key requirements is determined through the causal relationship network. Based on the global coupling relationship and the dynamic characteristics, the multivariate prediction model is constructed.
3. The method according to claim 2, characterized in that, The process of inputting the process control data into the multivariate prediction model to output the nitrogen oxide concentration prediction data for the target time period generated by the multivariate prediction model in each control cycle, solving for the corresponding target control command based on the nitrogen oxide concentration prediction data, and sending the target control command to the DCS system of the target power plant includes: Within each control cycle, the global coupling relationship, the dynamic characteristics, and the process control data are input into the multivariate prediction model to output the predicted nitrogen oxide concentration data for the target time period. Based on the predicted nitrogen oxide concentration data, the target control command is solved in a rolling manner to control the nitrogen oxide concentration to meet the preset smoothing requirements and track the preset value of nitrogen oxide concentration. The target control command includes the opening degree of the urea valve and the dilution water valve.
4. The method according to claim 3, characterized in that, After sending the target control command to the DCS system of the target power plant, the method further includes: A switching button is set in the graphical monitoring interface of the DCS system to switch control between the target intelligent control server and the DCS system when manually triggered or when preset anomaly detection requirements are met.
5. A smart control device for nitrogen oxides based on multivariate model prediction, characterized in that, include: The modeling module is used to collect process control data from the target power plant and perform preset multivariate modeling operations on the process control data to construct a multivariate prediction model that meets preset accuracy requirements. The prediction module is used to input the process control data into the multivariate prediction model, output the nitrogen oxide concentration prediction data for the target time period generated by the multivariate prediction model in each control cycle, solve the corresponding target control command based on the nitrogen oxide concentration prediction data, and send the target control command to the DCS system of the target power plant. The visualization module is used to display the current nitrogen oxide concentration trend, current control effect, and current system operating status corresponding to the target control command through a preset graphical monitoring interface of the DCS system, and to generate a corresponding control performance evaluation report.
6. The apparatus according to claim 5, characterized in that, The modeling module includes: The acquisition unit is used to connect the target intelligent control server to the factory control network of the target power plant through a preset industrial Ethernet switch, and to acquire the process control data of the target power plant using the OPC UA / DA standard interface provided by the DCS system and a preset step test strategy. The tuning unit is used to construct the response curve corresponding to the process control data and to perform preset tuning processing on the response curve to obtain the dynamic characteristics of a single control loop. The construction unit is used to construct a causal relationship network among multiple variables according to a preset time-series causal algorithm, so as to determine the global coupling relationship among at least one key parameter in the process control data that meets the preset key requirements through the causal relationship network, and construct the multivariate prediction model based on the global coupling relationship and the dynamic characteristics.
7. The apparatus according to claim 6, characterized in that, The prediction module includes: An analysis unit is used to input the global coupling relationship, the dynamic characteristics, and the process control data into the multivariate prediction model in each control cycle, so as to output the predicted nitrogen oxide concentration data for the target time period. The solving unit is used to solve the target control command on a rolling basis based on the predicted nitrogen oxide concentration data, so as to control the nitrogen oxide concentration to meet the preset smoothing requirements according to the target control command, and track the preset value of nitrogen oxide concentration, wherein the target control command includes the opening degree of the urea valve and the dilution water valve.
8. An electronic device, characterized in that, include: The memory, the processor, and the computer program stored in the memory and executable on the processor, the processor executing the program to implement the intelligent control method for nitrogen oxides based on multivariate model prediction as described in any one of claims 1-4.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to implement the intelligent control method for nitrogen oxides based on multivariate model prediction as described in any one of claims 1-4.
10. A computer program product, comprising a computer program, characterized in that, The computer program is executed to implement the intelligent control method for nitrogen oxides based on multivariate model prediction as described in any one of claims 1-4.