Multi-stage collaborative boiler combustion optimization control method and device and storage medium

Abstract

The invention discloses a multi-stage collaborative boiler combustion optimization control method and device and a storage medium. The method comprises the steps that multiple types of control parameters related to the operation process of a boiler combustion system are collected; through collaborative optimization of fuel deviation coarse adjustment, key index fine adjustment and wall temperature deviation fine adjustment, the operation state of the combustion system is sensed in real time, various control parameters are analyzed and adjusted, and therefore the operation effect of the boiler combustion system is optimized. Through collaborative optimization of fuel deviation coarse adjustment, key index fine adjustment and wall temperature deviation fine adjustment, the operation state of the combustion system is sensed in real time, various control parameters are rapidly analyzed and accurately adjusted, the problem that in the prior art, a single optimization method is insufficient is solved, multi-stage accurate regulation and control under the complex control environment are achieved, and the control efficiency is improved. And the overall operation effect of the combustion system is optimized.

Description

Technical Field

[0001] The present invention relates to the technical field of power station boilers, and particularly to a multi-level collaborative boiler combustion optimization control method, device, and storage medium. Background Art

[0002] The combustion system of a thermal power plant has a crucial impact on the efficiency, emissions, and safety of the boiler. Traditional combustion optimization technologies usually focus on a specific control parameter, such as intelligent adjustment of powder quantity deviation, automatic adjustment of thermal deviation, or boiler combustion optimization control. With the increasingly strict environmental protection requirements and the complexity of the combustion process, a single optimization control method lacks comprehensive and collaborative optimization of multiple control objectives. Especially when the operating conditions of the boiler change significantly, the existing technologies often cannot fully cope with various interference factors and make precise adjustments in a dynamically changing environment, thus affecting the stability, efficiency, and safety of the combustion process.

[0003] Therefore, how to comprehensively consider multi-level control parameters and optimize the combustion process through intelligent control means remains an urgent problem to be solved in the current field of combustion control technology for thermal power plants. Summary of the Invention

[0004] To solve the above problems, the present invention proposes a multi-level collaborative boiler combustion optimization control method, device, and storage medium. Through the collaborative optimization of rough adjustment of fuel deviation, fine adjustment of key indicators, and precise adjustment of wall temperature deviation, it can real-time sense the operating state of the combustion system, quickly analyze and accurately adjust various control parameters, solve the deficiencies of single optimization methods in the prior art, achieve multi-level precise control in a complex control environment, and optimize the overall operating effect of the combustion system.

[0005] The technical solution adopted by the present invention is as follows:

[0006] A multi-level collaborative boiler combustion optimization control method, comprising:

[0007] Collecting various types of control parameters related to the operation process of the boiler combustion system;

[0008] Through the collaborative optimization of rough adjustment of fuel deviation, fine adjustment of key indicators, and precise adjustment of wall temperature deviation, real-time sense the operating state of the combustion system, analyze and adjust various control parameters, so as to optimize the operating effect of the boiler combustion system.

[0009] Further, the rough adjustment of fuel deviation includes:

[0010] Real-time monitoring and analysis of the operating conditions of the boiler combustion system, and calculating the temperature rise deviation; the operating conditions of the boiler combustion system include the boiler fuel supply conditions, and the wall temperature or temperature rise conditions of the furnace or platen heating surface;

[0011] Adjust the fuel supply at different positions according to the temperature rise deviation to optimize the distribution of fuel in the boiler.

[0012] Furthermore, the fine-tuning of the key indicators includes:

[0013] Construct a prediction model of boiler efficiency and NO concentration at the reactor inlet using a machine learning algorithm, and update the strategy based on real-time data and historical samples to achieve online data update; x Establish an optimization model, obtain the optimal control instructions for relevant control parameters through artificial intelligence optimization methods, set constraint conditions, and verify the solution results using a machine learning model to form a rolling optimization control sequence;

[0014] Transmit the rolling optimization control sequence to the prediction model and the actual combustion system respectively, and compensate and correct the output of the prediction model according to the error feedback between the predicted value and the actual value, so that the prediction model can more accurately reflect the state of the controlled object at future moments.

[0015] Furthermore, when fine-tuning the key indicators, set the adjustment priority according to the CO concentration in the flue gas:

[0016] When the CO concentration is lower than the preset lower limit, give priority to adjusting the air distribution to reduce NO emissions, and at the same time increase the weight of reducing NO concentration in multi-objective optimization; the adjustment of the air distribution includes adjusting the air volume and the burnout air damper;

[0017] When the CO concentration exceeds the preset upper limit, start the boiler efficiency optimization process, increase the weight of boiler efficiency in the optimization target, reduce the heat loss due to incomplete chemical combustion by adjusting the air volume and oxygen content, and comprehensively compare with the heat loss of exhaust gas to determine the optimal operating condition, and further adjust the oxygen content and burnout air ratio to optimize NO concentration control. x Emissions, while increasing the weight of reducing NO concentration in multi-objective optimization; the adjustment of the air distribution includes adjusting the air volume and the burnout air damper; x When the CO concentration exceeds the preset upper limit, start the boiler efficiency optimization process, increase the weight of boiler efficiency in the optimization target, reduce the heat loss due to incomplete chemical combustion by adjusting the air volume and oxygen content, and comprehensively compare with the heat loss of exhaust gas to determine the optimal operating condition, and further adjust the oxygen content and burnout air ratio to optimize NO concentration control.

[0018] When the CO concentration exceeds the preset upper limit, start the boiler efficiency optimization process, increase the weight of boiler efficiency in the optimization target, reduce the heat loss due to incomplete chemical combustion by adjusting the air volume and oxygen content, and comprehensively compare with the heat loss of exhaust gas to determine the optimal operating condition, and further adjust the oxygen content and burnout air ratio to optimize NO concentration control. x Concentration control.

[0019] Furthermore, during the operation of the boiler combustion system, automatically check the status of the auxiliary system to ensure that the auxiliary system works normally according to the predetermined cycle, and make a comprehensive judgment based on the key indicators monitored in real time; the auxiliary system includes a fuel preparation system, a control system, and an intelligent soot blowing system.

[0020] Furthermore, the key indicators include fuel data, carbon content in ash and slag, and CO concentration in flue gas; the control parameters related to the fine-tuning of the key indicators include the damper opening, fuel supply, and oxygen content in flue gas.

[0021] Furthermore, the precise adjustment of the wall temperature deviation includes:

[0022] By adjusting the air volume distribution of the burnout air in the furnace width direction, the flue gas temperature distribution is changed, and then the wall temperature of the heating surface is adjusted;

[0023] When the flue gas temperature or the wall temperature in the target area exceeds the preset upper limit, increase the air volume of the burnout air corresponding to the target area;

[0024] When the flue gas temperature or the wall temperature in the target area is lower than the preset lower limit, reduce the air volume of the burnout air corresponding to the target area.

[0025] Furthermore, the adjustment process of the fine adjustment of the wall temperature deviation includes:

[0026] Identify the over-temperature points, that is, the positions where the flue gas temperature or the wall temperature exceeds the preset temperature;

[0027] Determine the burnout air device number corresponding to the over-temperature point;

[0028] Execute the damper adjustment instruction to control the burnout air device corresponding to the over-temperature point to adjust the air volume of the burnout air.

[0029] A computer device includes a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, it implements the above-mentioned multi-level collaborative boiler combustion optimization control method.

[0030] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, it implements the above-mentioned multi-level collaborative boiler combustion optimization control method.

[0031] The beneficial effects of the present invention are as follows:

[0032] 1. Improve the boiler operation efficiency: Through the rough adjustment of fuel deviation, the fine adjustment of key indicators, and the fine adjustment of wall temperature deviation, the present invention improves the steam temperature, realizes the efficient operation of the boiler, reduces fuel consumption and maintenance costs, and thus improves the overall economic benefits.

[0033] 2. Reduce NO x emissions: By dynamically adjusting the oxygen content and air distribution, reduce NO x emissions and reduce the consumption of ammonia removal.

[0034] 3. Enhance the boiler safety: Through the precise adjustment of wall temperature deviation, avoid safety problems such as tube explosion or heating surface cracking caused by local overheating and uneven wall temperature, and significantly improve the operation safety of the boiler.

[0035] 4. Enhance the system adaptability: The present invention can cope with complex operating conditions such as boiler load fluctuations and fuel changes, and the intelligent adjustment system can adapt to different working environments to ensure the stability of the combustion process.

[0036] 5. Reduce the operation complexity: Through the control algorithm of the present invention, reduce manual intervention, optimize the control process, and improve the automation level of boiler operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 This is a flow chart of a multi-stage coordinated boiler combustion optimization control method according to Example 1 of the present invention. DETAILED DESCRIPTION

[0038] In order to have a clearer understanding of the technical features, purposes and effects of the present invention, the specific implementation methods of the present invention are now described. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention, that is, the embodiments described are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative work are within the scope of protection of the present invention.

[0039] Example 1

[0040] like Figure 1 As shown, this embodiment provides a multi-level collaborative boiler combustion optimization control method, including: collecting multiple types of control parameters related to the operation process of the boiler combustion system; through the collaborative optimization of coarse adjustment of fuel deviation, fine adjustment of key indicators and fine adjustment of wall temperature deviation, real-time perception of the operating status of the combustion system, analysis and adjustment of various control parameters, so as to optimize the operation effect of the boiler combustion system.

[0041] Preferably, the fuel deviation rough adjustment includes: real-time monitoring and analysis of the boiler combustion system operation status, calculating the temperature rise deviation; according to the temperature rise deviation, adjusting the fuel supply at different positions, optimizing the distribution of fuel in the boiler, and reducing the negative impact of uneven fuel distribution on wall temperature deviation, combustion efficiency and emissions. Specifically, the boiler combustion system operation status includes the boiler fuel supply status, and the furnace or platen heating surface wall temperature or temperature rise status.

[0042] Preferably, the key indicator fine-tuning includes:

[0043] A machine learning algorithm was used to construct a correlation between boiler efficiency and reactor inlet NO x The concentration prediction model is based on real-time data and historical sample update strategies to achieve online data update;

[0044] Establish an optimization model, obtain the optimal control instructions of relevant control parameters through artificial intelligence optimization methods, set constraints, and use machine learning models to verify the solution results to form a rolling optimization control sequence;

[0045] To achieve closed-loop control, the rolling optimization control sequence is transmitted to the prediction model and the actual combustion system respectively, and the prediction model output is compensated and corrected according to the error feedback between the predicted value and the actual value, so that the prediction model can more accurately reflect the state of the controlled object in the future.

[0046] Preferably, when finely tuning the key indicators, set the adjustment priority according to the CO concentration in the flue gas:

[0047] When the CO concentration is lower than the preset lower limit, give priority to adjusting the air distribution to reduce NO x emissions, and at the same time increase the weight of reducing NO x concentration in multi-objective optimization; among them, adjusting the air distribution includes adjusting the air volume and the burnout air damper;

[0048] When the CO concentration exceeds the preset upper limit, start the boiler efficiency optimization process, increase the weight of the boiler efficiency in the optimization target, reduce the heat loss due to incomplete chemical combustion by adjusting the air volume and oxygen content, and comprehensively compare with the heat loss of exhaust gas to determine the optimal operating condition, and further adjust the oxygen content and the ratio of burnout air to optimize NO x concentration control.

[0049] Preferably, during the operation of the boiler combustion system, automatically check the status of the auxiliary system to ensure that the auxiliary system works normally according to the predetermined cycle, and make a comprehensive judgment based on the key indicators monitored in real time; among them, the auxiliary system includes the fuel preparation system, the control system and the intelligent soot blowing system.

[0050] It should be noted that the control parameters related to the fine tuning of key indicators include the damper opening, the fuel supply and the oxygen content in the flue gas; the key indicators include fuel data, carbon content in ash and CO concentration in flue gas.

[0051] Preferably, the precise adjustment of the wall temperature deviation includes: by adjusting the air volume distribution of the burnout air in the furnace width direction, changing the flue gas temperature distribution, and then adjusting the wall temperature of the heating surface. Specifically, when the flue gas temperature or the wall temperature in the target area exceeds the preset upper limit, increase the air volume of the burnout air corresponding to the target area; when the flue gas temperature or the wall temperature in the target area is lower than the preset lower limit, reduce the air volume of the burnout air corresponding to the target area. This solution is applicable to the wall temperature distribution deviation caused by uneven air distribution or coking, etc., and realizes the leveling of the wall temperature through the optimized adjustment of the burnout air.

[0052] Preferably, the adjustment process of the precise adjustment of the wall temperature deviation includes:

[0053] Identify the over-temperature points, that is, the positions where the flue gas temperature or the wall temperature exceeds the preset temperature;

[0054] Determine the burnout air device number corresponding to the over-temperature point;

[0055] Execute the damper adjustment instruction to control the burnout air device corresponding to the over-temperature point to adjust the air volume of the burnout air.

[0056] Preferably, in order to achieve precise control, an electric actuator is installed on the burnout air device to upgrade the manual adjustment to an automatic adjustment to ensure timely response when the wall temperature exceeds the limit.

[0057] In this embodiment, by combining the above-mentioned rough fuel deviation adjustment, fine adjustment of key indicators, and precise adjustment of wall temperature deviation into a collaborative optimization system, and through a multi-level optimization algorithm, the coordination and balance between different control objectives are achieved, ensuring that the boiler reaches the optimal state under complex operating conditions.

[0058] Specifically, taking the pulverized coal boiler of a certain thermal power plant as an example, by installing sensors such as temperature, air-powder flow rate, and NO x concentration, various parameters of the boiler are monitored in real time. By roughly adjusting the fuel supply, it is ensured that the air-powder distribution of each burner of each coal mill is uniform; by precisely adjusting key indicators such as NO x concentration and boiler efficiency, while optimizing the combustion process, the wall temperature deviation fine adjustment technology is used to identify the over-temperature points and adjust the air volume distribution of the over-fire air in the furnace width direction in real time to ensure the uniform distribution of the temperature on the boiler wall surface. Through multi-level collaborative optimization, the comprehensive goals of high-efficiency operation, low emissions, and high safety of the boiler are achieved.

[0059] In summary, the multi-level collaborative boiler combustion optimization control method of this embodiment has the following characteristics:

[0060] 1. The collaborative optimization of rough fuel deviation adjustment, fine adjustment of key indicators, and precise adjustment of wall temperature deviation. This technology combines the three control methods to optimize the overall interaction of various parameters in the boiler, solving the problem that a single optimization method cannot meet multi-level requirements and is original.

[0061] 2. Intelligent wall temperature regulation: By adjusting the distribution of the over-fire air along the furnace width direction to adjust the wall temperature deviation, combined with the automatic adjustment of the over-fire air device by the electric actuator, the uniform distribution of the wall temperature is realized, avoiding the problem of untimely response of traditional manual adjustment, and greatly improving the safety and accuracy of boiler operation.

[0062] 3. Machine learning is adopted for the fine adjustment of key indicators: A closed-loop optimization control system is constructed. Through the model predictive control algorithm, multi-objective optimization of the boiler efficiency and the NOx concentration at the reactor inlet is carried out to determine the key control parameters. At the same time, the system monitors key indicators such as coal quality parameters, carbon content in ash and slag, and CO concentration in flue gas in real time, and sets the priority of the control strategy according to expert experience to achieve precise control of the combustion process.

[0063] Embodiment 2

[0064] This embodiment is based on Embodiment 1:

[0065] This embodiment provides a computer device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, it implements a multi-level collaborative boiler combustion optimization control method of Embodiment 1. Among them, the computer program can be in the form of source code, object code, executable file, or some intermediate form, etc.

[0066] Embodiment 3

[0067] This embodiment is based on Embodiment 1:

[0068] This embodiment provides a computer-readable storage medium storing a computer program, which when executed by a processor implements a multi-level collaborative boiler combustion optimization control method according to Embodiment 1. Among them, the computer program can be in the form of source code, object code, executable file or some intermediate form, etc. The storage medium includes: any entity or device capable of carrying the computer program code, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc. It should be noted that the content included in the storage medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the storage medium does not include electrical carrier signals and telecommunication signals.

[0069] It should be noted that for the foregoing method embodiments, for the sake of simple description, they are expressed as a series of action combinations. However, those skilled in the art should know that this application is not limited by the described action sequence, because according to this application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

Claims

1. A multi - level collaborative boiler combustion optimization control method, characterized in that, Including: Collecting various control parameters related to the operation process of the boiler combustion system; Through the collaborative optimization of rough fuel deviation adjustment, fine adjustment of key indicators, and precise adjustment of wall temperature deviation, the operation state of the combustion system is perceived in real time, various control parameters are analyzed and adjusted, so as to optimize the operation effect of the boiler combustion system.

2. The multi - level collaborative boiler combustion optimization control method according to claim 1, wherein, The rough fuel deviation adjustment includes: Real-time monitoring and analysis of the operation status of the boiler combustion system, calculating the temperature rise deviation; the operation status of the boiler combustion system includes the boiler fuel supply status, and the wall temperature or temperature rise status of the furnace or the platen heating surface; According to the temperature rise deviation, adjust the fuel supply at different positions to optimize the distribution of fuel in the boiler.

3. A multi - level collaborative boiler combustion optimization control method according to claim 1, characterized in that, The fine adjustment of key indicators includes: Build a prediction model for boiler efficiency and NO concentration at the reactor inlet using machine learning algorithms, and realize online data update based on real-time data and historical sample update strategies; x ​ Establish an optimization model, obtain the optimal control instructions of relevant control parameters through artificial intelligence optimization methods, set constraint conditions, and use a machine learning model to verify the solution results to form a rolling optimization control sequence; Transmit the rolling optimization control sequence to the prediction model and the actual combustion system respectively, and compensate and correct the output of the prediction model according to the error feedback between the predicted value and the actual value, so that the prediction model can more accurately reflect the state of the controlled object at future moments.

4. A multi-level collaborative boiler combustion optimization control method according to claim 1, characterized in that When fine-tuning the key indicators, set the adjustment priority according to the CO concentration in the flue gas: When the CO concentration is lower than the preset lower limit, the air distribution is preferentially adjusted to reduce NO x emissions. Meanwhile, in the multi-objective optimization, the weight of reducing NO x concentration is increased; the adjustment of the air distribution includes adjusting the air volume and the overfire air damper; When the CO concentration exceeds the preset upper limit, start the boiler efficiency optimization process, increase the weight of the boiler efficiency in the optimization target, reduce the heat loss due to incomplete chemical combustion by adjusting the air volume and oxygen content, and determine the optimal operating condition through comprehensive comparison with the heat loss of flue gas. Further adjust the oxygen content and the ratio of overfire air to optimize the NO x concentration control.

5. A multi-level collaborative boiler combustion optimization control method according to claim 1, characterized in that During the operation of the boiler combustion system, automatically check the status of the auxiliary system to ensure that the auxiliary system works normally according to the predetermined cycle, and make a comprehensive judgment based on the key indicators monitored in real time; the auxiliary system includes a fuel preparation system, a control system, and an intelligent soot blowing system.

6. A multi-level collaborative boiler combustion optimization control method according to claim 1, characterized in that The key indicators include fuel data, carbon content in ash and slag, and CO concentration in flue gas; the control parameters related to the fine adjustment of key indicators include damper opening, fuel supply amount, and oxygen content in flue gas.

7. A multi-level collaborative boiler combustion optimization control method according to claim 1, characterized in that The precise adjustment of wall temperature deviation includes: By adjusting the air volume distribution of the overfire air in the furnace width direction, changing the flue gas temperature distribution, and then adjusting the wall temperature of the heating surface; When the flue gas temperature or wall temperature in the target area exceeds the preset upper limit, increase the air volume of the overfire air corresponding to the target area; When the flue gas temperature or wall temperature in the target area is lower than the preset lower limit, reduce the air volume of the overfire air corresponding to the target area.

8. A multi - level collaborative boiler combustion optimization control method according to claim 1, characterized in that, The adjustment process of the precise adjustment of wall temperature deviation includes: Identifying the over-temperature points, that is, the positions where the flue gas temperature or wall temperature exceeds the preset temperature; Determining the overfire air device number corresponding to the over-temperature point; Executing the damper adjustment instruction to control the overfire air device corresponding to the over-temperature point to adjust the air volume of the overfire air.

9. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, it implements the multi-level collaborative boiler combustion optimization control method described in any one of claims 1-8.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the multi-level collaborative boiler combustion optimization control method described in any one of claims 1-8.

Images