Intelligent combustion optimization control system and method for waste incineration

Abstract

The invention relates to the technical field of waste incineration, and provides a waste incineration intelligent combustion optimization control system and method.The intelligent combustion optimization control system is included, the upper and lower limits of physical boundaries of different load working conditions are fully considered in the solving process of a combustion parameter optimal output set Ve, and the optimal output set Ve is optimized. In other words, the combustion parameter optimal output set Ve is subjected to corresponding variation optimization adjustment under the boundary of an existing physical model, the optimized upper and lower limits of the combustion parameter optimal output set Ve change along with the change of the load, and a reasonable and stable optimal value is obtained. An open-loop control mode or a closed-loop control mode can be adopted for regulation and control, the system adaptability is good, the configuration logic of the DCS system comprises interface logic, and a control right switching function and a corresponding safety guarantee function between the DCS system and the intelligent combustion optimization control system can be provided.

Description

Technical Field

[0001] This invention relates to the field of waste incineration technology, and in particular to a smart combustion optimization control system and method for waste incineration. Background Technology

[0002] Because the combustion of waste incineration power generation involves intense and complex physicochemical reactions in a large space, there is a lack of effective means to measure many key parameters. Furthermore, the use of municipal solid waste as the main fuel makes the calorific value unstable. As a result, the level of refined automatic control of boilers is generally low at present.

[0003] Traditional waste incineration systems can assist in incinerating waste, but the current state of the waste incineration field is that the equipment is not highly automated and largely relies on manual operation, which is labor-intensive and inefficient. Faced with the current phenomenon of waste accumulation, it is difficult to quickly incinerate and process the waste. Summary of the Invention

[0004] To address the problems existing in the background technology, the present invention provides a waste incineration system with a reasonable and ingenious structural design, a high degree of automation, reduced manual handling steps, and improved waste incineration efficiency, which can efficiently and quickly solve the current problem of waste accumulation and inability to process waste.

[0005] To address the problems in existing technologies, this invention provides a smart combustion optimization control system for waste incineration, comprising a smart combustion optimization control system. This system employs a BP neural network physical model coupled with a genetic algorithm to derive the optimal output set Ve of combustion parameters under different operating conditions, thereby rationally regulating the intelligent combustion of the waste-to-energy plant boiler. The smart combustion optimization control method utilizes big data analysis theory to search and infer the optimal operating mode under different operating conditions from historical and experimental data of the unit, achieving model self-learning and realizing intelligent combustion in the coal-fired power plant boiler.

[0006] Specifically, the intelligent combustion optimization control system includes a software body that uses a combination of BP neural network and genetic algorithm to obtain the optimal output set V of combustion parameters under different operating conditions. This ensures the rationality and stability of the optimal value, greatly promotes the refined operation of the unit, improves energy saving and emission reduction efficiency and operational safety, and sends combustion optimization control commands after calculating the real-time operating data sent to the optimization algorithm server.

[0007] Specifically, the intelligent combustion optimization control system also includes a hardware unit, which is installed in the control cabinet of the boiler electronic equipment room in the waste-to-energy plant. The hardware unit includes an optimization algorithm server, a PLC controller, a two-way communication link, a two-way communication network, and a power module.

[0008] Specifically, the PLC controller and the DCS system are connected via a bidirectional communication link and exchange data based on the Modbus protocol. The optimization algorithm server and the PLC controller are connected via a bidirectional communication network and exchange data based on the TCP / IP protocol.

[0009] Specifically, the bidirectional communication link and bidirectional communication network collect and send the operating data of the DCS system to the optimization algorithm server in real time, and the combustion optimization control command generated by the optimization algorithm server is output to the DCS system.

[0010] A method for a smart combustion optimization control system for waste incineration, the method comprising the following steps:

[0011] S1: First, the historical operating data of the unit is processed. It goes through the neural network input vector vin and the neural network output vector vout, and then enters the training sample database for storage and experimentation.

[0012] S2: The training sample database will import the data into the boiler combustion system for neural network training. If the data exists in the neural network model N of the boiler combustion system, neural network training will be performed. If it does not exist in the neural network model N of the boiler combustion system, it will return to the training sample database.

[0013] S3: The neural network model N of the boiler combustion system will use a genetic algorithm to calculate the optimal fitness and optimal combustion parameters. After the calculation is completed, the optimal result will be transmitted to the DCS system. If the calculated parameters are not optimal, the original path will be returned.

[0014] S4: The DCS system then transmits the command to the combustion optimization system to put it into operation or shut it down. If it is no longer put into operation or shut down, it will be directed to the open-loop control route, and the staff will provide operation guidance and suggestions. If it is put into operation or shut down, it will be controlled to exit from the closed-loop control line, and then perform intelligent optimization control, and then optimize and modulate the relevant parameters.

[0015] S5: Finally, the adjusted data is matched with the data in the sample library and the performance index parameters are compared. If the final comparison result is that jout-reai is greater than jout, new samples are generated and re-entered into the training sample database for processing. If the result is that jout-reai is less than or equal to jout, the processing ends.

[0016] The beneficial effects of this invention are as follows: The optimal combustion parameter output set Ve in this invention fully considers the upper and lower limits of the physical boundaries under different load conditions during the solution process. That is, the optimal combustion parameter output set Ve is adjusted by variation within the boundaries of the existing physical model, and its optimization upper and lower limits change with the load, resulting in reasonable and stable optimal values. It can be controlled using either open-loop or closed-loop control methods, exhibiting excellent system adaptability. Furthermore, the configuration logic of the DCS system includes interface logic, providing control switching functionality and corresponding safety assurance functions between the DCS system and the intelligent combustion optimization control system. Attached Figure Description

[0017] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0018] Figure 1 This is a flowchart of the system operation of the present invention. Detailed Implementation

[0019] To make the technical methods, creative features, objectives, and effects of this invention easier to understand, the invention will be further described below in conjunction with specific embodiments.

[0020] like Figure 1 As shown, a smart combustion optimization control system for waste incineration includes a smart combustion optimization control system. The smart combustion optimization control system uses a BP neural network physical model coupled with a genetic algorithm to obtain the optimal output set Ve of combustion parameters under different operating conditions, and rationally regulates the smart combustion of the waste-to-energy plant boiler. The smart combustion optimization control method applies big data analysis theory to find and infer the optimal operating mode under different operating conditions from the unit's historical operating data and experimental data, realizes model self-learning, and achieves smart combustion of the coal-fired power plant boiler.

[0021] Preferably, the intelligent combustion optimization control system includes a software core that uses a combination of BP neural network and genetic algorithm to obtain the optimal output set V of combustion parameters under different operating conditions. This ensures the rationality and stability of the optimal values, greatly promotes the refined operation of the unit, improves energy saving and emission reduction efficiency, and enhances operational safety. After calculating the real-time operating data sent to the optimization algorithm server, the system sends combustion optimization control commands. The intelligent combustion optimization control system also includes a hardware core installed in the control cabinet of the boiler electronic equipment room in the waste-to-energy plant. The hardware core includes an optimization algorithm server, a PLC controller, a two-way communication link, a two-way communication network, and a power supply module.

[0022] Preferably, the PLC controller and the DCS system are connected via a bidirectional communication link and exchange data based on the Modbus protocol. The optimization algorithm server and the PLC controller are connected via a bidirectional communication network and exchange data based on the TCP / IP protocol. The bidirectional communication link and the bidirectional communication network collect and send the operating data of the DCS system to the optimization algorithm server in real time. The combustion optimization control command generated by the optimization algorithm server is output to the DCS system. The optimization control system adopts a smart combustion optimization control method, as described in the first aspect for the smart combustion optimization control system used in waste-to-energy power plant boilers. The optimization control system uses a smart combustion optimization control method to process massive amounts of historical unit operating data, fully considering the unit's economic, environmental, and safety requirements. Based on boiler efficiency, boiler heating surface safety coefficient, and normalized performance indicators of flue gas parameters such as NOx, SOx, and HCl generated at the boiler outlet, an evaluation index J and a fitness function F are established. Operators can achieve optimized combustion control based on the optimal output set V of combustion parameters.

[0023] (1) In the process of solving the optimal output set of combustion parameters Ve in this invention, the upper and lower limits of the physical boundary under different load conditions are fully considered. That is, the optimal output set of combustion parameters Ve is adjusted by corresponding variation optimization under the boundary of the existing physical model. The upper and lower limits of its optimization change with the load, and a reasonable and stable optimal value is obtained. It can be controlled by open-loop control or closed-loop control, which has good system adaptability.

[0024] (2) The configuration logic of the DCS system of the present invention includes interface logic, which can provide the control switching function between the DCS system and the intelligent combustion optimization control system and the corresponding safety protection function. Based on the real-time collected flue gas temperature measurement data of the furnace, the safety coefficient α of the boiler heating surface is calculated. The safety coefficient α of the boiler heating surface is used to evaluate the safety of the boiler heating surface. This not only ensures the economy and environmental protection of the unit, but also considers the safety of the unit operation. The structural design is reasonable and ingenious, with a high degree of automation, reducing the manual handling links, improving the efficiency of waste incineration, and can efficiently and quickly solve the current phenomenon of waste accumulation and inability to process.

[0025] Historical data from the database:

[0026] S1: First, the historical operating data of the unit is processed. It goes through the neural network input vector vin and the neural network output vector vout, and then enters the training sample database for storage and experimentation.

[0027] S2: The training sample database will import the data into the boiler combustion system for neural network training. If the data exists in the neural network model N of the boiler combustion system, neural network training will be performed. If it does not exist in the neural network model N of the boiler combustion system, it will return to the training sample database.

[0028] S3: The neural network model N of the boiler combustion system will use a genetic algorithm to calculate the optimal fitness and optimal combustion parameters. After the calculation is completed, the optimal result will be transmitted to the DCS system. If the calculated parameters are not optimal, the original path will be returned.

[0029] S4: The DCS system then transmits the command to the combustion optimization system to put it into operation or shut it down. If it is no longer put into operation or shut down, it will be directed to the open-loop control route, and the staff will provide operation guidance and suggestions. If it is put into operation or shut down, it will be controlled to exit from the closed-loop control line, and then perform intelligent optimization control, and then optimize and modulate the relevant parameters.

[0030] S5: Finally, the adjusted data is matched with the data in the sample library and the performance index parameters are compared. If the final comparison result is that jout-reai is greater than jout, new samples are generated and re-entered into the training sample database for processing. If the result is that jout-reai is less than or equal to jout, the processing ends.

[0031] Real-time running data:

[0032] S1: First, process the real-time running data, then input the vector vin-real, and use the genetic algorithm to calculate the optimal fitness and optimal combustion parameters. After the calculation is completed, the optimal result is transmitted to the DCS system. If the calculated parameters are not optimal, return to the original path.

[0033] S2: The DCS system then transmits the command to the combustion optimization system to put it into operation or shut it down. If it is no longer put into operation or shut down, it will be directed to the open-loop control route, and the staff will provide operation guidance and suggestions. If it is put into operation or shut down, it will be controlled to exit from the closed-loop control line, and then perform intelligent optimization control, and then optimize and modulate the relevant parameters.

[0034] S3: Finally, the adjusted data is matched with the data in the sample library and the performance index parameters are compared. If the final comparison result is that jout-reai is greater than jout, new samples are generated and re-entered into the training sample database for processing. If the result is that jout-reai is less than or equal to jout, the processing ends.

[0035] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely illustrative of the principles of the invention. Various changes and modifications can be made to the present invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of protection claimed by the present invention. Scope of Protection of the Present Invention.

Claims

1. A smart combustion optimization control system for waste incineration, characterized in that: Including intelligent combustion optimization control system, The intelligent combustion optimization control system uses a BP neural network physical model coupled with a genetic algorithm to obtain the optimal output set of combustion parameters Ve under different operating conditions, and to reasonably regulate the intelligent combustion of the waste-to-energy plant boiler. It also includes a software body, which uses a combination of BP neural network and genetic algorithm to obtain the optimal output set V of combustion parameters under different operating conditions. After calculating the real-time running data sent to the optimization algorithm server, it sends combustion optimization control commands.

2. The intelligent combustion optimization control system for waste incineration according to claim 1, characterized in that: The intelligent combustion optimization control system also includes a hardware unit, which is installed in the control cabinet of the boiler electronic equipment room of the waste-to-energy plant. The hardware unit includes an optimization algorithm server, a PLC controller, a two-way communication link, a two-way communication network, and a power module.

3. The intelligent combustion optimization control system for waste incineration according to claim 2, characterized in that: The PLC controller is connected to the DCS system via a bidirectional communication link and exchanges data based on the Modbus protocol. The optimization algorithm server and the PLC controller are connected via a bidirectional communication network and exchange data based on the TCP / IP protocol.

4. The intelligent combustion optimization control system for waste incineration according to claim 2, characterized in that: The bidirectional communication link and bidirectional communication network collect and send the DCS system's operating data to the optimization algorithm server in real time, and the combustion optimization control command generated by the optimization algorithm server is output to the DCS system.

5. A method for a smart combustion optimization control system for waste incineration according to any one of claims 1-4, characterized in that: The method includes the following steps: S1: First, the historical operating data of the unit is processed. It goes through the neural network input vector vin and the neural network output vector vout, and then enters the training sample database for storage and experimentation. S2: The training sample database will import the data into the boiler combustion system for neural network training. If the data exists in the neural network model N of the boiler combustion system, neural network training will be performed. If it does not exist in the neural network model N of the boiler combustion system, it will return to the training sample database. S3: The neural network model N of the boiler combustion system will use a genetic algorithm to calculate the optimal fitness and optimal combustion parameters. After the calculation is completed, the optimal result will be transmitted to the DCS system. If the calculated parameters are not optimal, the original path will be returned. S4: The DCS system then transmits the command to the combustion optimization system to put it into operation or shut it down. If it is no longer put into operation or shut down, it will be directed to the open-loop control route, and the staff will provide operation guidance and suggestions. If it is put into operation or shut down, it will be controlled to exit from the closed-loop control line, and then perform intelligent optimization control, and then optimize and modulate the relevant parameters. S5: Finally, the adjusted data is matched with the data in the sample library and the performance index parameters are compared. If the final comparison result is that jout-reai is greater than jout, new samples are generated and re-entered into the training sample database for processing. If the result is that jout-reai is less than or equal to jout, the processing ends.

Images