Control method and system for gasification coupling unit to adaptively respond to peak regulation of power grid

Abstract

The invention relates to a control method and system for a gasification coupling unit to adaptively respond to power grid peak regulation. The control method comprises the steps that the feeding amount of solid fuel composed of pulverized coal and biomass charcoal, the feeding amount of biomass gasification synthesis gas, boiler operation parameter data and post-combustion flue gas data are collected in real time; training a neural network based on the collected historical data to obtain a prediction model, wherein the prediction model is used for predicting the boiler load demand in a specific time period in the future; constructing a multi-objective optimization model which takes coal consumption reduction, pollutant emission reduction and boiler stable combustion guarantee as optimization objectives and takes the feeding amount of pulverized coal and biomass gas as key decision variables; and solving the multi-objective optimization model by adopting a swarm intelligent optimization algorithm to obtain an optimal fuel ratio set value under the current working condition. According to the invention, accurate and stable control of the feed amount of the pulverized coal and biomass gasification synthesis gas is realized. According to the method, the peak regulation speed, depth and flexibility of the unit are improved, and multi-target cooperation of economy, environmental protection, stability and the like is achieved.

Description

Control method and system for adaptive response of gasification coupled unit to grid peak shaving Technical Field

[0001] This invention relates to the field of power plant peak shaving control technology, and in particular to a control method and system for adaptive response of gasification coupled power plants to grid peak shaving. Background Technology

[0002] Currently, the technical routes for coal-coated biomass power generation are mainly divided into two categories: direct coupling and indirect coupling. Direct coupling technology is widely used due to its relatively low retrofitting cost; however, existing feeding systems are primarily designed for coal and are difficult to adapt to the characteristics of biomass fuel, easily leading to uneven feeding and incomplete combustion. Furthermore, these systems generally lack real-time intelligent control over the blending ratio, hindering further improvements in combustion efficiency and peak-shaving flexibility. In indirect coupling technology, while parallel coupling schemes can be independently optimized for fuel characteristics, they require the construction of independent combustion and flue gas treatment systems, resulting in high investment costs and system complexity. In contrast, another mainstream indirect coupling method—gasification coupling technology—exhibits unique advantages: this technology first converts biomass into syngas in a gasifier, and then introduces the syngas into a coal-fired boiler to mix and burn with pulverized coal. This method has broad adaptability to biomass feedstocks, and the gasified syngas burns stably, making it easier to achieve efficient co-combustion and precise control with pulverized coal.

[0003] For units using gasification coupling technology, there is currently a lack of effective control schemes that can adaptively respond to grid peak-shaving commands. It is impossible to quickly and accurately adjust the blending ratio of syngas and pulverized coal according to the unit's status, which limits the unit's peak-shaving speed, depth, and flexibility. At the same time, there is a problem that it is difficult to coordinate multiple objectives such as economy, environmental protection, and stability. Summary of the Invention

[0004] To address the shortcomings of existing technologies, this invention provides a control method and system for adaptive response to grid peak shaving in gasification coupled units, which solves the problems of poor fuel adaptability, insufficient peak shaving flexibility, and difficulty in coordinating multiple objectives such as economy, environmental protection and stability in existing units.

[0005] The technical solution adopted in this invention is as follows: This invention provides a control method for adaptive response to grid peak shaving of a gasification coupled unit. The gasification coupled unit includes: a biomass subsystem, which is used to convert biomass feed into biomass gasification syngas and solid biochar, and to transport the biomass gasification syngas to the furnace for combustion; and a pulverized coal preparation subsystem, which is used to prepare solid fuel from raw coal and the solid biochar, and to transport the solid fuel to the furnace for combustion. The control method includes: using a data acquisition unit to collect in real time the solid fuel feed rate, the biomass gasification syngas feed rate, as well as the boiler operating parameter data and the flue gas data after combustion; constructing training data based on the historical data collected by the data acquisition unit; and based on the training data... A predictive model is obtained by training a neural network. This model is used to obtain a predicted value of the boiler load demand for a specific future period based on real-time data collected by the data acquisition unit. Based on the predicted value of the boiler load demand, a multi-objective optimization model is constructed with the optimization objectives of reducing coal consumption, reducing pollutant emissions, and ensuring stable boiler combustion, and with the feed rates of pulverized coal and biomass gas as key decision variables. A swarm intelligence optimization algorithm is used to solve the multi-objective optimization model to obtain the optimal fuel ratio setting value under the current operating conditions, namely the optimal solid fuel feed rate and the optimal biomass gasification syngas feed rate. Based on the optimal fuel ratio setting value, the production control command is used to control the unit to achieve precise and stable control of the feed rates of pulverized coal and biomass gasification syngas.

[0006] As a preferred technical solution: the mathematical model of the multi-objective optimization model includes: objective function: In the formula, decision variables , , These represent the coal powder feed rate and the biomass gas feed rate, respectively. Represents the objective function value. Represents the amount of pulverized coal fed into the system. The weighted average of emissions of major pollutants. Represents boiler combustion stability deviation; T represents matrix transpose; Constraints: Heat input constraints: ; Stable combustion safety constraints: In the formula, These are the lower heating values ​​of pulverized coal and biomass gas, respectively. The required heat input for the boiler under the target operating conditions; Represents the characteristic flame temperature of the furnace. The set limit.

[0007] The boiler's operating parameters include combustion temperature, internal boiler pressure, and boiler load requirements.

[0008] The data on the flue gas after combustion includes CO and NO in the flue gas. xAnd O2 concentration data.

[0009] The production control command based on the optimal fuel ratio setpoint for controlling the unit includes: a controller using a PID control algorithm receives the optimal fuel ratio setpoint and compares it in real time with the actual feed rates of solid fuel and biomass gasification syngas collected by the data acquisition unit; the obtained error signal is input into the PID algorithm for calculation; and then a control command is generated to automatically adjust the coal powder feed rate and the opening of the regulating valve of the biomass gasification syngas pipeline, thereby achieving precise and stable control of the two fuel feeds.

[0010] The neural network is a long short-term memory network.

[0011] This invention also provides a control system for adaptive response to grid peak shaving in a gasification coupled unit. The system includes: a biomass subsystem for converting biomass feedstock into biomass gasification syngas and solid biochar, and supplying the biomass gasification syngas to the furnace for combustion; a pulverized coal preparation subsystem for preparing solid fuel from raw coal and the solid biochar, and supplying the solid fuel to the furnace for combustion; a data acquisition unit for real-time acquisition of the solid fuel feed rate, biomass gasification syngas feed rate, boiler operating parameter data, and post-combustion flue gas data; and an intelligent prediction unit for constructing training data based on historical data acquired by the data acquisition unit, and training a neural network based on the training data to obtain a prediction model. The prediction model, based on real-time data collected by the data acquisition unit, predicts the boiler load demand for a specific future period. The decision-making unit, based on the predicted boiler load demand, constructs a multi-objective optimization model with the optimization objectives of reducing coal consumption, reducing pollutant emissions, and ensuring stable boiler combustion, using the feed rates of pulverized coal and biomass gas as key decision variables. A swarm intelligence optimization algorithm is used to solve the multi-objective optimization model to obtain the optimal fuel ratio setpoint under the current operating conditions, i.e., the optimal solid fuel feed rate and the optimal biomass gasification syngas feed rate. The execution control unit controls the unit based on the optimal fuel ratio setpoint production control commands, achieving precise and stable control of the pulverized coal and biomass gasification syngas feed rates.

[0012] The mathematical model of the multi-objective optimization model includes: Objective function: In the formula, decision variables , , These represent the coal powder feed rate and the biomass gas feed rate, respectively. Represents the objective function value. Represents the amount of pulverized coal fed into the system. The weighted average of emissions of major pollutants. Represents boiler combustion stability deviation; T represents matrix transpose; Constraints: Heat input constraints: ; Stable combustion safety constraints: In the formula, These are the lower heating values ​​of pulverized coal and biomass gas, respectively. The required heat input for the boiler under the target operating conditions; Represents the characteristic flame temperature of the furnace. The set limit.

[0013] The boiler's operating parameters include combustion temperature, internal boiler pressure, and boiler load requirements.

[0014] The data on the flue gas after combustion includes the concentration data of CO, NOx, and O2 in the flue gas.

[0015] The technical solution of this invention achieves at least the following beneficial effects: Through systematic integration and collaborative work, this invention realizes a complete closed loop from fuel pretreatment, state perception, intelligent decision-making to precise execution. First, through intelligent prediction driven by real-time data, the optimal "gas-solid" fuel blending ratio is dynamically and accurately determined. Finally, through closed-loop control, while ensuring stable combustion of the boiler under low load, it rapidly responds to grid peak-shaving commands, significantly improving the unit's peak-shaving speed, depth, and flexibility. Overall, it achieves the following significant effects: First, it ensures the combustion stability of the boiler under ultra-low load conditions, significantly reducing the minimum stable combustion load; second, it greatly expands the unit's peak-shaving depth and load response rate; third, it provides indispensable flexible adjustment capabilities for the grid to absorb large-scale fluctuating renewable energy. Based on achieving efficient and deep peak-shaving, this invention simultaneously optimizes multiple key performance indicators, achieving the comprehensive optimal benefits of reducing carbon emissions, improving combustion efficiency, and controlling pollutant emissions, realizing the synergistic effect of multiple objectives such as economy, environmental protection, and stability.

[0016] This invention constructs a multi-objective optimization model with the optimization objectives of reducing coal consumption, reducing pollutant emissions, and ensuring stable boiler combustion. The model uses the feed rates of pulverized coal and biomass gas as key decision variables and leverages the zero-carbon characteristics of biomass to effectively reduce the carbon emission intensity of the unit. In terms of economy and energy efficiency, the system creates a clean, efficient, safe, and economical sustainable development path for coal-fired power plants by improving overall combustion efficiency, achieving efficient utilization of all biomass components (syngas and biochar), and participating in deep peak shaving to generate revenue.

[0017] This invention achieves "gas-solid phase-coupled combustion" of biomass and pulverized coal. It fundamentally overcomes the inherent problems of traditional direct-fired coupling technology, such as feed blockage, inaccurate metering, and unstable combustion caused by the high fiber content and uneven density of biomass. This not only significantly improves fuel adaptability and relaxes the quality requirements for biomass feedstock, but also significantly enhances the boiler's operational reliability, especially under load variations.

[0018] Other features and advantages of the invention will be set forth in the following description or may be learned by practicing the invention. Attached Figure Description

[0019] Figure 1 is a flowchart illustrating the control method according to an embodiment of the present invention.

[0020] Figure 2 is a schematic diagram of the structure of the gasification coupling unit according to an embodiment of the present invention.

[0021] Explanation of reference numerals in the attached diagram: 1. Crusher; 2. Gasifier; 3. Coal mill; 4. Boiler; 5. First mass flow sensor; 6. Second mass flow sensor; 7. Temperature sensor and pressure sensor; 8. Flue gas analyzer; 9. Controller. Detailed Implementation

[0022] The specific embodiments of the present invention are described below with reference to the accompanying drawings.

[0023] Example 1 This example provides a control method for adaptive response to grid peak shaving of a gasification coupled unit. The gasification coupled unit includes: a biomass subsystem for converting biomass feedstock into biomass gasification syngas and solid biochar, and transporting the biomass gasification syngas to the furnace for combustion; and a pulverized coal preparation subsystem for preparing raw coal and the solid biochar into solid fuel, and transporting the solid fuel to the furnace for combustion.

[0024] Referring to Figure 2, in one embodiment, the biomass subsystem includes a crusher 1 and a gasifier 2. The crusher 1 is used to crush the biomass raw materials; the gasifier 2 is used to convert the crushed biomass raw materials into biomass gasification syngas and solid biochar. The biomass gasification syngas is transported to the furnace of the boiler 4 for combustion through a biomass gasification gas conveying pipeline. The pulverized coal preparation subsystem mainly includes a coal mill 3, which is mainly used to produce and store pulverized coal, and also to grind the carbonization product biochar from the gasifier 2 together with raw coal to form solid fuel. The solid fuel is sent to the furnace of the boiler 4 for combustion through a pulverized coal conveying pipeline, and the flue gas after boiler combustion is transported to subsequent process stages through the boiler exhaust pipeline.

[0025] Referring to Figure 1, the control method includes: S1. Using a data acquisition unit to collect in real time the solid fuel feed rate, the biomass gasification syngas feed rate, as well as the boiler operating parameter data and the flue gas data after combustion.

[0026] In one implementation, the data acquisition unit includes three acquisition units. As shown in Figure 2, the first acquisition unit includes a first mass flow sensor 5 installed on the pulverized coal conveying pipeline and a second mass flow sensor 6 installed on the biomass gasification gas conveying pipeline, respectively used to acquire real-time data on the feed rates of solid fuel and biomass gasification syngas; the second acquisition unit includes a temperature sensor and a pressure sensor 7 arranged above the boiler 4, used to monitor the combustion temperature and internal pressure of the boiler in real-time; the third acquisition unit includes a flue gas analyzer 8 installed in the boiler exhaust pipe, used to acquire real-time data such as CO, NOx, and O2 concentrations in the flue gas. Preferably, the data acquisition unit also includes a boiler load demand monitoring module, which acquires the boiler load demand in real-time through direct or indirect means.

[0027] S2. Based on the historical data collected by the data acquisition unit, training data is constructed, and a prediction model is obtained by training the neural network based on the training data. This model is used to obtain the predicted value of boiler load demand for a specific future period based on the real-time data collected by the data acquisition unit.

[0028] As a preferred approach, the neural network employs a Long Short-Term Memory (LSTM) network, which is a type of time-recurrent neural network. The LSTM network utilizes historical data uploaded by the data acquisition unit, including the feed rate of the previous period, the biomass gasification syngas feed rate, the combustion temperature and boiler internal pressure, and the CO and NO content in the flue gas. x The prediction model is trained by taking the O2 concentration data sequence as input and the boiler load demand of a later period as output.

[0029] S3. Based on the predicted value of the boiler load demand, construct a multi-objective optimization model with the optimization objectives of reducing coal consumption, reducing pollutant emissions and ensuring stable boiler combustion, and the feed amount of pulverized coal and biomass gas as key decision variables.

[0030] The objective function of the multi-objective optimization model is: In the formula, decision variables , , These represent the coal powder feed rate and the biomass gas feed rate, respectively. Represents the objective function value. Represents the amount of pulverized coal fed into the system. The weighted average of emissions of major pollutants. Represents boiler combustion stability deviation; T represents matrix transpose; where: = ; , , , These represent the emissions of NOx, SO2, and CO2, respectively. , , These are the corresponding weighting coefficients; , Represents the characteristic flame temperature of the furnace; Represents the stable combustion reference temperature; The excess air coefficient, For reference excess air coefficient; This is the weighting coefficient for stable combustion.

[0031] The constraints of the multi-objective optimization model include: thermal input constraints. ; Stable combustion safety constraints: In the formula, These are the lower heating values ​​of pulverized coal and biomass gas, respectively. The required heat input for the boiler under the target operating conditions; This is the limit value for the characteristic flame temperature of the furnace.

[0032] S4. The multi-objective optimization model is solved by a swarm intelligence optimization algorithm to obtain the optimal fuel ratio setting value under the current working conditions, namely the optimal solid fuel feed rate and the optimal biomass gasification syngas feed rate.

[0033] Specifically, the swarm intelligence optimization algorithm is a particle swarm optimization algorithm, and its calculation process includes: constructing the objective function of the particle swarm optimization algorithm: , , , The objective functions are respectively , , Weighting coefficients; S41, defining particles as , Represents the coal powder feed rate (kg / s). S42: Initialize the particle swarm and randomly generate particle positions. This represents the biomass gas feed rate and sets the number of iterations for the particle swarm optimization. and speed S43. For each particle, based on its position... Using the objective function Calculate the fitness value of each particle and evaluate the quality of each particle; S44. For each particle, compare its fitness value with the fitness value of its current best position. If the current particle has a better fitness, then take the current position as the new best position.

[0034] S45. For each particle, compare its fitness value with the fitness value of the global best position. If the current particle has a better fitness, then the current position is taken as the new global best position.

[0035] S46. Calculate the new velocity of each particle based on the current velocity and position update formula. and new position The particle update formula is as follows:

[0036]

[0037] in: Inertial weights; , Here is the acceleration constant; , The random coefficients are in the range [0,1]. Let be the individual optimal solution for particle i in generation t; To find the global optimal solution S47, determine if the maximum number of iterations has been reached. If yes, stop the algorithm and output the global optimal solution; otherwise, continue iterating.

[0038] S5. Based on the optimal fuel ratio setting value, the production control command is used to control the unit to achieve precise and stable control of the feed amount of pulverized coal and biomass gasification syngas.

[0039] Specifically, the production control command based on the optimal fuel ratio setting value for controlling the unit includes: the controller 9 (as shown in Figure 2) using a PID control algorithm receives the optimal fuel ratio setting value and compares it in real time with the actual feed amounts of solid fuel and biomass gasification syngas collected by the data acquisition unit. The obtained error signal is input into the PID algorithm for calculation, and then a control command is generated to automatically adjust the coal powder feed rate and the opening of the biomass gasification syngas pipeline regulating valve, thereby achieving precise and stable control of the two fuel feeds.

[0040] The control method of this embodiment will be further verified by specific examples below.

[0041] This example uses a 660MW ultra-supercritical gasification coupled unit system model built on the Aspen Plus platform as the object. The system structure of this ultra-supercritical gasification coupled unit is shown in Figure 2. The selected gasifier is a circulating fluidized bed gasifier. The control method includes: using a data acquisition unit to collect real-time data on solid fuel feed rate, biomass gasification syngas feed rate, boiler operating parameters, and post-combustion flue gas data. Real-time data of unit operation is collected through the data acquisition unit to construct a training set. A prediction model is obtained by training this training set to predict the unit state under preset operating conditions and obtain the predicted boiler load demand. A multi-objective optimization model is then constructed. , , , The objective functions are respectively , , The weighting coefficients.

[0042] The multi-objective optimization model is solved using the particle swarm optimization algorithm, where particles are defined as... , Represents the coal powder feed rate (kg / s). This represents the biomass gas feed rate and sets the number of iterations for the particle swarm optimization; each particle is evaluated based on its position. Using the objective function Calculate the fitness value of each particle to evaluate its quality. For each particle, compare its fitness value with the fitness value of its current best position. If the current particle has a better fitness, then set the current position as the new best position. Compare the fitness value of each particle with the fitness value of the global best position to find the current position as the new global best position. Calculate the new velocity of each particle based on the current velocity and position update formula. and new position The particle update formula is as follows: , , Inertial weights; , Here is the acceleration constant; , The random coefficients are in the range [0,1]. Let be the individual optimal solution for particle i in generation t; The solution is globally optimal. Based on the solution results, PID control is used to control the unit. Data verification shows that stable and accurate control of the unit's peak-shaving response is achieved.

[0043] An economic analysis was then conducted. The benefits mainly came from the electricity cost savings due to biomass gasification replacing coal consumption and peak-shaving savings. The costs primarily consisted of the annual biomass fuel cost. A single boiler coupled with biomass gasification can increase peak-shaving capacity by approximately 10%. Assuming a deep-shaving period of 1000 hours, a grid-connected electricity price of -0.08 yuan / kWh, and a power generation cost of 0.30 yuan / kWh, the cost savings per kWh would be 0.08 + 0.30 = 0.38 yuan / kWh. The electricity cost savings from peak-shaving would be 660 MW × 10% × 1000 h × 0.38 yuan / kWh ÷ 10,000 = 25.08 million yuan. Assuming a 1:3 ratio of biomass power generation to coal-fired power generation, with a grid connection price of 0.49932 yuan / kWh and a marginal profit of 0.05958 yuan / kWh, the estimated annual grid connection electricity generated by biomass gasification is 74 million kWh. The estimated electricity cost savings from biomass gasification are approximately 74 million × 0.49932 + 3 × 74 million × 0.05958 ≈ 50.18 million yuan. The annual straw processing volume is approximately 60,000 tons. At a price of 400 yuan per ton of straw, the annual biomass fuel cost is approximately 60,000 × 400 ≈ 24 million yuan. Therefore, the annual revenue is 25.08 + 50.18 - 24 million = 51.26 million yuan. In summary, without considering initial investment costs such as equipment upgrades and operation, the annual revenue is 51.26 million yuan.

[0044] Based on the calculation results of the above examples, it can be seen that the control method of this embodiment achieves the coordinated effect of multiple objectives such as economy, environmental protection and stability on the basis of stable and accurate control of the unit's peak-shaving response.

[0045] Example 2 This example provides a control system for an adaptive response to grid peak shaving in a gasification coupled unit. The system includes: a biomass subsystem for converting biomass feedstock into biomass gasification syngas and solid biochar, and delivering the biomass gasification syngas to the furnace for combustion; a pulverized coal preparation subsystem for preparing solid fuel from raw coal and the solid biochar, and delivering the solid fuel to the furnace for combustion; a data acquisition unit for real-time acquisition of the solid fuel feed rate, biomass gasification syngas feed rate, boiler operating parameter data, and flue gas data after combustion; and an intelligent prediction unit for constructing training data based on historical data acquired by the data acquisition unit, and training a neural network based on the training data to obtain a prediction model. The prediction model, based on real-time data collected by the data acquisition unit, predicts the boiler load demand for a specific future period. The decision-making unit, based on the predicted boiler load demand, constructs a multi-objective optimization model with the optimization objectives of reducing coal consumption, reducing pollutant emissions, and ensuring stable boiler combustion, using the feed rates of pulverized coal and biomass gas as key decision variables. A swarm intelligence optimization algorithm is used to solve the multi-objective optimization model to obtain the optimal fuel ratio setting value under the current operating conditions, i.e., the optimal solid fuel feed rate and the optimal biomass gasification syngas feed rate. The execution control unit controls the unit based on the optimal fuel ratio setting value production control commands, achieving precise and stable control of the pulverized coal and biomass gasification syngas feed rates.

[0046] In summary, this invention, through real-time monitoring of boiler operating status and grid demand, utilizes advanced optimization algorithms to dynamically and accurately predict and solve for the optimal blending ratio of syngas and pulverized coal. Through this intelligent collaborative mechanism, the system can precisely leverage the stable combustion and regulation characteristics of high-calorific-value biomass gas. Its significant benefits include: 1. Ensuring boiler combustion stability under ultra-low load conditions, significantly reducing the minimum stable combustion load; 2. Greatly expanding the unit's peak-shaving depth and load response rate; 3. Providing indispensable flexible regulation capabilities for the grid to absorb fluctuating renewable energy on a large scale.

[0047] It will be understood by those skilled in the art that the above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A control method for adaptive response of a gasification coupled unit to grid peak shaving, characterized in that, The gasification coupling unit includes: a biomass subsystem for converting biomass feedstock into biomass gasification syngas and solid biochar, and supplying the biomass gasification syngas to the furnace for combustion; and a pulverized coal preparation subsystem for preparing solid fuel from raw coal and the solid biochar, and supplying the solid fuel to the furnace for combustion. The control method includes: using a data acquisition unit to collect real-time data on solid fuel feed rate, biomass gasification syngas feed rate, boiler operating parameters, and post-combustion flue gas data; constructing training data based on historical data collected by the data acquisition unit; and training a neural network based on the training data to obtain a prediction model, which is used for... The data acquisition unit collects real-time data to obtain a predicted value of boiler load demand for a specific future period. Based on the predicted value of boiler load demand, a multi-objective optimization model is constructed with the optimization objectives of reducing coal consumption, reducing pollutant emissions, and ensuring stable boiler combustion, and with the feed rates of pulverized coal and biomass gas as key decision variables. The multi-objective optimization model is solved using a swarm intelligence optimization algorithm to obtain the optimal fuel ratio setting value under the current operating conditions, namely the optimal solid fuel feed rate and the optimal biomass gasification syngas feed rate. Based on the optimal fuel ratio setting value, the unit is controlled by production control commands to achieve precise and stable control of the feed rates of pulverized coal and biomass gasification syngas.

2. The method according to claim 1, characterized in that, The mathematical model of the multi-objective optimization model includes: Objective function: In the formula, decision variables ， ， These represent the coal powder feed rate and the biomass gas feed rate, respectively. Represents the objective function value. Represents the amount of pulverized coal fed into the system. The weighted average of emissions of major pollutants. Represents boiler combustion stability deviation; T represents matrix transpose; Constraints: Heat input constraints: ; Stable combustion safety constraints: In the formula, These are the lower heating values ​​of pulverized coal and biomass gas, respectively. The required heat input for the boiler under the target operating conditions; Represents the characteristic flame temperature of the furnace. The set limit.

3. The method according to claim 1, characterized in that, The boiler's operating parameters include combustion temperature, internal boiler pressure, and boiler load requirements.

4. The method according to claim 1, characterized in that, The data on the flue gas after combustion includes CO and NO in the flue gas. x And O2 concentration data.

5. The method according to claim 1, characterized in that, The production control command based on the optimal fuel ratio setpoint for controlling the unit includes: a controller using a PID control algorithm receives the optimal fuel ratio setpoint and compares it in real time with the actual feed rates of solid fuel and biomass gasification syngas collected by the data acquisition unit; the obtained error signal is input into the PID algorithm for calculation; and then a control command is generated to automatically adjust the coal powder feed rate and the opening of the regulating valve of the biomass gasification syngas pipeline, thereby achieving precise and stable control of the two fuel feeds.

6. The method according to claim 1, characterized in that, The neural network is a long short-term memory network.

7. A control system for adaptive response to grid peak shaving of a gasification coupled unit, characterized in that, The system includes: a biomass subsystem for converting biomass feedstock into biomass gasification syngas and solid biochar, and supplying the biomass gasification syngas to the furnace for combustion; a pulverized coal preparation subsystem for preparing solid fuel from raw coal and the solid biochar, and supplying the solid fuel to the furnace for combustion; a data acquisition unit for real-time acquisition of the solid fuel feed rate, biomass gasification syngas feed rate, boiler operating parameter data, and post-combustion flue gas data; and an intelligent prediction unit for constructing training data based on historical data acquired by the data acquisition unit, training a neural network based on the training data to obtain a prediction model, and the prediction model is based on the data acquisition unit. The system collects real-time data to predict the boiler load demand for a specific future period. A decision-making unit, based on this predicted load demand, constructs a multi-objective optimization model with the optimization objectives of reducing coal consumption, reducing pollutant emissions, and ensuring stable boiler combustion, using the feed rates of pulverized coal and biomass gas as key decision variables. A swarm intelligence optimization algorithm is used to solve the multi-objective optimization model to obtain the optimal fuel ratio setpoint under the current operating conditions, i.e., the optimal solid fuel feed rate and the optimal biomass gasification syngas feed rate. An execution control unit, based on the optimal fuel ratio setpoint, controls the unit using production control commands to achieve precise and stable control of the pulverized coal and biomass gasification syngas feed rates.

8. The control system according to claim 1, characterized in that, The mathematical model of the multi-objective optimization model includes: Objective function: In the formula, decision variables ， ， These represent the coal powder feed rate and the biomass gas feed rate, respectively. Represents the objective function value. Represents the amount of pulverized coal fed into the system. The weighted average of emissions of major pollutants. Represents boiler combustion stability deviation; T represents matrix transpose; Constraints: Heat input constraints: ; Stable combustion safety constraints: In the formula, These are the lower heating values ​​of pulverized coal and biomass gas, respectively. The required heat input for the boiler under the target operating conditions; Represents the characteristic flame temperature of the furnace. The set limit.

9. The control system according to claim 1, characterized in that, The boiler's operating parameters include combustion temperature, internal boiler pressure, and boiler load requirements.

10. The control system according to claim 1, characterized in that, The data on the flue gas after combustion includes the concentrations of CO, NOx, and O2 in the flue gas.

Images