Multi-model predictive control method and system adopting B / S architecture for coal power unit

Abstract

The invention discloses a multi-model prediction control method and system adopting a B / S architecture for a coal power unit. The system comprises a data acquisition module which is used for acquiring operation data of the coal power unit in real time; the control algorithm module is used for establishing a control algorithm model by adopting a built-in control algorithm and a self-defined algorithm according to the collected data and is used for calculating an optimal control strategy; the predictive control application module combines data with an algorithm model in a visual configuration mode, and accurately controls the coal power unit according to a control strategy output by the algorithm model to realize optimization; and the monitoring and feedback module is used for monitoring the operation state of the coal power unit in real time and feeding back an operation result to the control algorithm model to realize dynamic adjustment of a control strategy. The method is beneficial to improving the operation efficiency of the coal power unit, reducing the coal consumption, reducing the emission, and being beneficial to indexes such as energy conservation and emission reduction.

Description

Technical Field

[0001] The present invention relates to the technical field of coal-fired power generation unit control, and in particular to a multi-model predictive control method and system for coal-fired power generation units using a B / S architecture. Background Art

[0002] With the continuous growth of energy demand and increasingly stringent environmental protection requirements, coal-fired power units, as the main power supply mode, have attracted widespread attention for their operating efficiency and environmental performance. However, the traditional coal-fired power unit control system has deficiencies in coal consumption, emissions, efficiency, etc., and it is difficult to meet the needs of modern power systems. Therefore, the development of a new type of safe and efficient coal-fired power unit control system that can flexibly integrate and implement various optimization control strategies to improve the operating efficiency and environmental performance of coal-fired power units has become an urgent problem to be solved. Summary of the invention

[0003] The purpose of the present invention is to provide a multi-model predictive control method and system for a coal-fired power unit using a B / S architecture to solve the problems raised in the above-mentioned background technology.

[0004] To achieve the above object, the present invention provides the following technical solution: a multi-model predictive control system for a coal-fired power unit adopting a B / S architecture, comprising a data acquisition module: used for real-time acquisition of operating data of the coal-fired power unit;

[0005] Control algorithm module: Based on the collected data, the built-in control algorithm and the custom algorithm are used to build a control algorithm model to calculate the optimal control strategy;

[0006] The predictive control application module combines data with the algorithm model by means of visual configuration, and accurately controls the coal-fired power unit according to the control strategy output by the algorithm model to achieve optimization;

[0007] Monitoring and feedback module: used to monitor the operating status of coal-fired power units in real time, and feed back the operating results to the control algorithm model to achieve dynamic adjustment of the control strategy.

[0008] Preferably, the system adopts a B / S architecture, the server uses a microservice architecture and integrates multiple DCS communication methods, including MQTT, Modbus, OPC_UA, HTTP, and TCP.

[0009] Preferably, the operating data collected by the data acquisition module includes coal consumption, emissions, temperature, and pressure. The data acquisition module integrates multiple communication methods with DCS, including but not limited to MQTT, Modbus, and OPC_UA.

[0010] Preferably, the control algorithm built into the control algorithm module includes neural network and fuzzy control.

[0011] Preferably, the predictive control application module adopts multi-model predictive control and supports custom configuration for freely combining various algorithms to form an algorithm model and realize multi-model comparative analysis.

[0012] Preferably, the monitoring and feedback module is also used to monitor and alarm the system itself. If the system is terminated unexpectedly, data communication is interrupted or abnormal, or the predictive control application times out or stops unexpectedly, the monitoring and feedback module switches to the control link of the coal-fired power unit itself to ensure the normal operation of the coal-fired power unit safely and stably, and at the same time sends alarm information to relevant personnel by email so that system failures can be handled in a timely manner.

[0013] Preferably, the monitoring and feedback module is also used to monitor and alarm the system itself. If the system is terminated unexpectedly, data communication is interrupted or abnormal, or the predictive control application times out or stops unexpectedly, the monitoring and feedback module switches to the control link of the coal-fired power unit itself to ensure the normal operation of the coal-fired power unit safely and stably, and at the same time sends alarm information to relevant personnel by email so that system failures can be handled in a timely manner.

[0014] Preferably, the B / S architecture uses WebSocket technology to enable real-time data push between the server and the client, and the client can see communication data and calculation data in real time, providing timely monitoring and feedback capabilities.

[0015] The multi-model predictive control method for coal-fired power generation units using a B / S architecture adopts the above-mentioned multi-model predictive control system for coal-fired power generation units using a B / S architecture, including the following steps:

[0016] Users log in to access the control system through a browser. The server adopts microservice communication mode. According to the user's self-designed predictive control method, the required coal-fired power unit operation data is collected in real time. Various custom algorithms are freely combined through user-defined configuration to form an algorithm model. The predictive control application visualizes the configuration combination of equipment operation data and algorithm models, and accurately uses the algorithm model for calculation and analysis, thereby outputting the optimal control strategy of the control logic. The optimized operating parameters are written back to the DCS through data communication, so as to improve the operating efficiency and environmental protection performance of the coal-fired power unit.

[0017] Compared with the prior art, the present invention has the following beneficial effects:

[0018] 1. Improve the operating efficiency of coal-fired power units, reduce coal consumption, reduce emissions, and be beneficial to energy conservation and emission reduction indicators;

[0019] 2. Use advanced control algorithms and optimization strategies to achieve precise control of coal-fired power units and improve the stability and reliability of coal-fired power units;

[0020] 3. Through real-time monitoring and dynamic adjustment, the operating status of coal-fired power units can be optimized, while the overall performance of coal-fired power units can be improved safely and controllably.

[0021] 4. Provide management and configuration of the model. By configuring custom configuration, various algorithms can be freely combined to form an algorithm model, which is convenient for users to modify and define by themselves. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 It is a schematic diagram of the overall architecture of the system of the present invention;

[0023] Figure 2 It is a schematic diagram of the overall operation of the system of the present invention;

[0024] Figure 3 This is a schematic diagram of a data acquisition module of the present invention;

[0025] Figure 4 This is a schematic diagram of the control algorithm module of the present invention;

[0026] Figure 5 This is a schematic diagram of the predictive control application module of the present invention;

[0027] Figure 6 It is the predictive control application module of the present invention;

[0028] Figure 7 This is a schematic diagram of the operation flow of the prediction control application module of the present invention;

[0029] Figure 8 Schematic diagram of the server of the present invention. DETAILED DESCRIPTION

[0030] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0031] like Figure 1-7 As shown, the present invention provides a technical solution for a multi-model predictive control system of a coal-fired power unit using a B / S architecture. The system adopts a B / S architecture, and the server uses a microservice architecture and integrates multiple DCS communication methods. The DCS communication methods include MQTT, Modbus, OPC_UA, HTTP, and TCP.

[0032] Including data acquisition module: used to collect the operation data of coal-fired power units in real time; Figure 3As shown in the figure, the operating data collected by the data acquisition module include coal consumption, emissions, temperature, and pressure, with a maximum time efficiency of 50ms. The data acquisition module integrates multiple communication methods with DCS, including but not limited to MQTT, Modbus, and OPC_UA.

[0033] Control algorithm module: Based on the collected data, the built-in control algorithm and custom algorithm are used to build a control algorithm model to calculate the optimal control strategy; the control algorithms built into the control algorithm module include neural network and fuzzy control. Figure 4 As shown,

[0034] The predictive control application module combines data with algorithm models by means of visual configuration, and accurately controls coal-fired power units according to the control strategy output by the algorithm model to achieve optimization; the predictive control application module adopts multi-model predictive control and supports custom configuration, which is used to freely combine various algorithms to form algorithm models and realize multi-model comparative analysis. Figure 5 as well as Figure 6 As shown, the data is combined with the algorithm model in a visual configuration way, and the coal-fired power unit is precisely controlled according to the control strategy output by the algorithm model to optimize indicators such as coal consumption and emissions. The application also provides functions such as operation cycle, number of operations, timeout time, timeout removal instruction, etc., so as to accurately control the coal-fired power unit safely, efficiently and in real time.

[0035] The predictive control application module combines control algorithms in a visual configuration manner, and accurately controls coal-fired power units according to the control strategy output by the control algorithm module to optimize indicators such as coal consumption and emissions. The predictive control application can also flexibly configure the number of operations, operation intervals, timeouts, timeout removal instructions and other functions to ensure that the coal-fired power units are not affected by the platform and can operate safely and stably in unexpected situations. The predictive control application calculation cycle can reach up to milliseconds, ensuring that the results of the optimized control strategy can reach the coal-fired power units in the most timely manner.

[0036] System predictive control application data flow. The process is divided into the following categories:

[0037] ①The signal generation algorithm data flows to the model prediction and is finally output to the prediction result.

[0038] ② The signal generation algorithm data flow is preprocessed and then enters the model prediction or the signal generation algorithm data flow directly enters the model prediction and finally outputs to the prediction result.

[0039] ③ The signal generation algorithm data flow is preprocessed and then enters the model update and control, or the signal generation algorithm data flow directly enters the control, and finally outputs to the AO variable control instruction, or returns to the model update and control for re-calculation.

[0040] ④ The signal generation algorithm data flow is preprocessed and then enters the model update and control or the signal generation algorithm data flow directly enters the control, and then enters the simulation object model through the control instruction, and finally controls the response or returns to the model control to run again.

[0041] like Figure 7 As shown, the overall architecture design of the present invention. The functions of each part are as follows:

[0042] ①The data source part supports data import including offline data, online data and batch data.

[0043] ②The data modeling part includes data collection, data pre-classification processing and model and algorithm part, which processes and classifies the imported data sources and establishes a prediction model to facilitate subsequent operation control.

[0044] ③The operation control part includes data source configuration management, data governance and calculation, data output, data communication and equipment control. It imports data sources through various methods and selects appropriate advanced algorithms for analysis and parameter adjustment. It stores the output data in various ways, and then controls the equipment operation by configuring control points.

[0045] ④The data storage part supports multiple storage methods for data storage, such as file storage, cache storage, time series database, relational database, etc. Users can easily query the time range of historical data through the system interface, and support flexible time period selection to help users perform data analysis, troubleshooting and performance optimization.

[0046] ⑤ The general component part provides a variety of components and functions, which can present various visual charts to users in the most intuitive way, including scatter charts, line charts, step charts, pie charts, etc. Related chart components support custom data and time dimension filtering, and support flexible binding by dragging and dropping

[0047] Monitoring and feedback module: used to monitor the operating status of coal-fired power units in real time, and feed back the operating results to the control algorithm model to achieve dynamic adjustment of the control strategy: refer to Figure 7 The monitoring and feedback module shown is used to monitor the operating status of the coal-fired power unit in real time, and feed back the operating results to the predictive control application module to achieve dynamic adjustment of the control strategy. At the same time, with the monitoring alarm function, if the system is unexpectedly terminated, data communication is interrupted or abnormal, or the predictive control application is unexpectedly timed out or stopped, it can switch to the control link of the coal-fired power unit itself without disturbance, and ensure the normal operation of the coal-fired power unit safely and stably. At the same time, it can send alarm information to relevant personnel by email or other means to handle system failures in a timely manner.

[0048] The system adopts B / S architecture, logs in and accesses through the browser, and the server adopts microservice communication. Figure 7 As shown in the figure, the microservice infrastructure supports modularization and logical decoupling, and is divided into gateway services, authentication and authorization services, user services, and system services. The business architecture is divided into application services, algorithm services, modeling services, IOT services, and monitoring services. According to the user's own predictive control solution, through a variety of DCS data collection methods with a maximum frequency of 50ms, the required coal-fired power unit operation data is collected in real time, and various custom algorithms are freely combined through user-defined configuration to form an algorithm model. Through the predictive control application visualization configuration combination of equipment operation data and algorithm models, the algorithm model is flexibly and accurately used for calculation and analysis, so as to output the optimal control strategy of the control logic, and the optimized operation parameters are written back to the DCS through data communication, so as to improve the operation efficiency and environmental protection performance of the coal-fired power unit. At the same time, the system also has real-time monitoring and feedback functions. According to the actual operation status of the coal-fired power unit, the control strategy can be dynamically adjusted, and the operation status of the system itself and the predictive control application can be monitored to ensure that the unit operates in a safe and stable optimal state.

[0049] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A multi-model predictive control system for coal-fired power units using a B / S architecture, characterized by: Including data acquisition module: used to collect the operation data of coal-fired power units in real time; Control algorithm module: Based on the collected data, the built-in control algorithm and the custom algorithm are used to build a control algorithm model to calculate the optimal control strategy; The predictive control application module combines data with the algorithm model by means of visual configuration, and accurately controls the coal-fired power unit according to the control strategy output by the algorithm model to achieve optimization; Monitoring and feedback module: used to monitor the operating status of coal-fired power units in real time, and feed back the operating results to the control algorithm model to achieve dynamic adjustment of the control strategy.

2. The multi-model predictive control system for coal-fired power generation units using a B / S architecture according to claim 1 is characterized in that: The system adopts B / S architecture. The server uses microservice architecture and integrates multiple DCS communication methods, including MQTT, Modbus, OPC_UA, HTTP, and TCP.

3. The multi-model predictive control system for coal-fired power generation units using a B / S architecture according to claim 1 is characterized in that: The operating data collected by the data acquisition module include coal consumption, emissions, temperature, and pressure. The data acquisition module integrates multiple communication methods with DCS, including but not limited to MQTT, Modbus, and OPC_UA.

4. The multi-model predictive control system for coal-fired power generation units using a B / S architecture according to claim 1 is characterized in that: The control algorithms built into the control algorithm module include neural network and fuzzy control.

5. The multi-model predictive control system for coal-fired power generation units using a B / S architecture according to claim 4 is characterized in that: The predictive control application module adopts multi-model predictive control and supports custom configuration, which is used to freely combine various algorithms to form an algorithm model and realize multi-model comparative analysis.

6. The multi-model predictive control system for coal-fired power generation units using a B / S architecture according to claim 1 is characterized in that: The monitoring and feedback module is also used to monitor and alarm the system itself. If the system is terminated unexpectedly, data communication is interrupted or abnormal, or the predictive control application times out or stops unexpectedly, the monitoring and feedback module switches to the control link of the coal-fired power unit itself to ensure the normal operation of the coal-fired power unit safely and stably. At the same time, it sends alarm information to relevant personnel by email so that system failures can be handled in a timely manner.

7. The multi-model predictive control system for coal-fired power generation units using a B / S architecture according to claim 1 is characterized in that: The system's microservice infrastructure supports modularization and logical decoupling, and is divided into gateway services, authentication and authorization services, user services, and system services. The business architecture is divided into application services, algorithm services, modeling services, IOT services, and monitoring services.

8. The multi-model predictive control system for coal-fired power generation units using a B / S architecture according to claim 1 is characterized in that: The B / S architecture uses WebSocket technology to enable real-time data push between the server and the client. The client can see communication data and calculation data in real time, providing timely monitoring and feedback capabilities.

9. A multi-model predictive control method for coal-fired power units using a B / S architecture, characterized in that: The multi-model predictive control system for coal-fired power generation units using a B / S architecture as described in any one of claims 1 to 8 comprises the following steps: Users log in to access the control system through a browser. The server adopts microservice communication mode. According to the user's self-designed predictive control method, the required coal-fired power unit operation data is collected in real time. Various custom algorithms are freely combined through user-defined configuration to form an algorithm model. The predictive control application visualizes the configuration combination of equipment operation data and algorithm models, and accurately uses the algorithm model for calculation and analysis, thereby outputting the optimal control strategy of the control logic. The optimized operating parameters are written back to the DCS through data communication, so as to improve the operating efficiency and environmental protection performance of the coal-fired power unit.

Images