A method for optimizing control of ash conveying in a thermal power plant

Abstract

The application provides a method for optimizing ash conveying in a thermal power plant, comprising: laying a special gas accompanying pipeline along an ash conveying pipeline, and installing an intelligent concentration stabilizer on the ash conveying pipeline at a preset distance; calculating real-time moisture of coal quality by using a heat balance principle of a direct-fired coal mill; predicting a heat value of coal quality based on a BP neural network; calculating an ash content of coal quality according to the real-time moisture of coal quality and the heat value of coal quality; calculating a real-time total ash amount according to the ash content of coal quality and real-time coal feeding amounts of each coal mill; determining a pneumatic conveying ratio according to the real-time total ash amount; and determining an ash conveying interval according to the pneumatic conveying ratio. The application solves the problems of high ash conveying cost and inability to optimize ash conveying frequency and selection in the prior art.

Description

Technical Field

[0001] This invention relates to the field of thermal power generation technology, and in particular to an optimized control method for ash conveying in thermal power plants. Background Technology

[0002] The power system is a key sector for carbon emissions and a pioneering sector in carbon market trading. The power industry faces enormous pressure to conserve energy and reduce emissions, but it also presents an opportunity to achieve a green transformation.

[0003] Pneumatic ash conveying systems are important auxiliary systems in power plants. Compressed air consumes a lot of energy and has low utilization efficiency. By using intelligent analysis to achieve linkage between the air-consuming side and the air source side of ash conveying, energy consumption and carbon emissions can be reduced while ensuring system safety.

[0004] For ash conveying in thermal power plants, existing technologies disclose intelligent transformation schemes for ash conveying systems, including hardware modifications to process pipelines, hardware modifications to control systems, optimization of control programs, and intelligent detection and automatic ash removal systems for ash blockage locations. The invention patent application document CN114476690A, entitled "Automatic Unblocking Device for Ash Conveying Systems in Thermal Power Plants," discloses an automatic unblocking device for ash conveying systems in thermal power plants, including an unblocking ash storage tank and ash conveying pipelines, with several identical pressure sensors installed on the conveying pipelines. All of the above methods involve modifying and optimizing pneumatic ash conveying systems; however, these methods primarily focus on solving the blockage problem of pneumatic ash conveying systems and do not address optimization of ash conveying frequency or ash selection. Summary of the Invention

[0005] In order to overcome the shortcomings of the prior art, the purpose of this invention is to provide an optimized control method for ash conveying in thermal power plants. This invention solves the problems of high ash conveying costs and the inability to optimize ash conveying frequency and ash conveying selection in the prior art.

[0006] To achieve the above objectives, the present invention provides the following solution:

[0007] A method for optimizing ash conveying control in a thermal power plant includes:

[0008] A dedicated gas-tracing pipeline is laid along the ash conveying pipeline, and intelligent concentration stabilizers are installed on the ash conveying pipeline at preset intervals.

[0009] Real-time moisture content of coal is calculated using the heat balance principle of a direct-fired coal mill.

[0010] Predicting the calorific value of coal based on a BP neural network;

[0011] The ash content of the coal is calculated based on the real-time moisture content and calorific value of the coal.

[0012] The real-time total ash content is calculated based on the coal ash content and the real-time coal feed rate of each coal mill.

[0013] The pneumatic conveying ratio is determined based on the real-time total ash volume.

[0014] The ash conveying interval is determined based on the pneumatic conveying ratio.

[0015] Preferably, the intelligent concentration stabilizer is used to control the ash plugs below a preset length value.

[0016] Preferably, the calculation of real-time coal moisture content using the heat balance principle of a direct-fired coal mill includes:

[0017] Collect historical operating data of direct-fired coal mills;

[0018] Based on the historical operating data of the direct-fired coal mill, a moisture measurement formula is constructed using the energy conservation principle formula.

[0019] The real-time moisture content of coal is calculated using the aforementioned moisture measurement formula.

[0020] Preferably, the energy conservation principle formula is:

[0021] q gz +q lf +q nm +q r =q z +q jc +q2+q5;

[0022]

[0023]

[0024]

[0025]

[0026] q z =ΔM(2491+1884t2-419t) r );

[0027]

[0028]

[0029]

[0030] Among them, M m The coal feed rate of the coal feeder is expressed in tons per hour (t / h); M ft1 is the primary air volume at the coal mill inlet, t / h; t2 is the primary air temperature at the coal mill inlet, ℃; t3 is the temperature of the air-coal mixture at the coal mill outlet, ℃; W is the coal mill power, KW; C1 is the specific heat of the desiccant at the coal mill inlet, KJ / kg*℃; C2 is the specific heat of the desiccant at the coal mill outlet, KJ / kg*℃; C lk Specific heat of cold air, kJ / kg*℃; C rd Specific heat of coal dryer, KJ / kg*℃; t lk The temperature of the leaking cold air, in °C; t r The temperature at which coal enters the system, in °C; K. lf R is the air leakage coefficient of the coal mill. 90 Q5 represents the fineness of the pulverized coal, in %; Q5 represents the heat loss of the subsystem, in KW; K nm The coefficient by which the input power of the coal mill is converted into heat.

[0031] Preferably, the moisture measurement formula is:

[0032]

[0033] Preferably, the formula for calculating the real-time total ash content is:

[0034] G = F × W ar(A) ×k×0.9;

[0035] Where G is the real-time total ash content, F is the amount of coal fed into the furnace, War(A) is the received ash content, and k is the ash-to-slag ratio.

[0036] Preferably, the method of predicting the calorific value of coal based on a BP neural network includes:

[0037] A real-time calorific value prediction model for coal quality in the first direct-fired coal mill was established based on a BP neural network.

[0038] The real-time calorific value prediction model of coal quality for the first direct-fired coal mill is trained and updated to obtain the real-time calorific value prediction model of coal quality for the second direct-fired coal mill.

[0039] The calorific value of coal is predicted using the real-time calorific value prediction model of the second direct-fired coal mill.

[0040] According to specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0041] This invention provides an optimized control method for ash conveying in thermal power plants, comprising: laying a dedicated gas-tracing pipeline along the ash conveying pipeline; installing intelligent concentration stabilizers at preset intervals along the ash conveying pipeline; calculating the real-time moisture content of the coal using the heat balance principle of a direct-fired coal mill; predicting the calorific value of the coal based on a BP neural network; calculating the ash content of the coal based on the real-time moisture content and the calorific value; calculating the real-time total ash content based on the ash content and the real-time coal feed rate of each coal mill; determining the pneumatic conveying ratio based on the real-time total ash content; and determining the ash conveying interval based on the pneumatic conveying ratio. The ash conveying frequency and ash conveying selection are optimized. Attached Figure Description

[0042] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0043] Figure 1 This is a schematic diagram of a method for optimizing ash conveying control in a thermal power plant, provided by an embodiment of the present invention.

[0044] Figure 2 This is a schematic diagram of the concentration stabilizer principle provided in an embodiment of the present invention. Detailed Implementation

[0045] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0046] The purpose of this invention is to provide an optimized control method for ash conveying in thermal power plants. This invention solves the problems in the prior art.

[0047] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0048] like Figure 1 As shown, this invention provides an optimized control method for ash conveying in thermal power plants. This invention solves the problems of high ash conveying costs and the inability to optimize ash conveying frequency and selection in the prior art.

[0049] A method for optimizing ash conveying control in a thermal power plant includes:

[0050] Step 100: Lay a dedicated gas tracing pipeline along the ash conveying pipeline, and install intelligent concentration stabilizers on the ash conveying pipeline at preset intervals;

[0051] Step 200: Calculate the real-time moisture content of the coal using the heat balance principle of a direct-fired coal mill;

[0052] Step 300: Predict the calorific value of coal based on a BP neural network;

[0053] Step 400: Calculate the ash content of the coal based on the real-time moisture content and calorific value of the coal;

[0054] Step 500: Calculate the real-time total ash content based on the coal ash content and the real-time coal feed rate of each coal mill;

[0055] Step 600: Determine the pneumatic conveying ratio based on the real-time total ash content;

[0056] Step 700: Determine the ash conveying interval based on the pneumatic conveying ratio.

[0057] Specifically, S1, a dedicated gas-tracing pipeline is laid along the ash conveying pipeline. Intelligent concentration stabilizers are installed on the ash conveying pipeline at intervals of approximately 3-8 meters. The intelligent concentration stabilizers draw air from the dedicated gas-tracing pipeline. When the flow velocity at a certain point in the ash conveying pipeline falls below the critical velocity, causing ash settling and blockage, the pressure at that point rises. Once the pressure exceeds the preset pressure of the intelligent concentration stabilizer, the stabilizer activates to replenish air. The replenished airflow disturbs the ash plug at that point. After the pressure returns to normal, the intelligent concentration stabilizer shuts off.

[0058] S2. Estimate the real-time ash content in the ash hopper of the electrostatic precipitator based on the coal feed rate and coal quality of the coal-fired boiler.

[0059] S3. Set the compressed air volume according to the ash-to-air ratio (the mass of compressed air required to transport a unit mass of fly ash) for ash conveying:

[0060] The mathematical model of this invention establishes calculation models for ash accumulation in four electric fields, and monitors the amount of ash accumulation in each electric field in real time.

[0061] A dedicated gas-tracing pipeline is laid along the ash conveying pipeline on the equipment. An intelligent concentration stabilizer is installed on the ash conveying pipeline, and the intelligent concentration stabilizer draws gas from the dedicated gas-tracing pipeline.

[0062] In a more specific technical solution, in step S1, the gas distribution system of the ash conveying system retains only the main air intake of the original conveying system. A regulating valve is installed on the main air intake and the dedicated tracing gas pipe to stabilize the conveying gas source pressure at approximately 0.25-0.3 MPa (adjustable). All fluidizing gas, secondary gas, anti-clogging gas, etc., are shut off, and fluidizing gas is replenished in real time by intelligent concentration stabilizers along the ash conveying pipe.

[0063] Its working principle is as follows:

[0064] Intelligent concentration stabilizers can control ash plugs below a specific length, ensuring that the length of ash plugs during operation is less than the critical length (L) of granular materials, thus improving system reliability. For example... Figure 2 As shown.

[0065] Furthermore, the calculation of real-time coal moisture content using the heat balance principle of a direct-fired coal mill includes:

[0066] Collect historical operating data of direct-fired coal mills;

[0067] Based on the historical operating data of the direct-fired coal mill, a moisture measurement formula is constructed using the energy conservation principle formula.

[0068] The real-time moisture content of coal is calculated using the aforementioned moisture measurement formula.

[0069] Specifically, the historical operating data of the direct-fired coal mill includes: current (A), coal feed rate (t / h), inlet air pressure (KPa), mill differential pressure (KPa), inlet air temperature (°C), outlet air temperature (°C), inlet air volume (t / h), load (MW), air velocity in duct 1 (m / s), air velocity in duct 2 (m / s), air velocity in duct 3 (m / s), and air velocity in duct 4 (m / s). After adding the coal feeding records of the coal mill and the historical time corresponding to the coal quality industrial analysis data to the historical operating data, a training dataset is established.

[0070] Specifically, the formula for the principle of energy conservation is:

[0071] q gz +q lf +q nm +q r =q z +q jc +q2+q5;

[0072]

[0073]

[0074]

[0075]

[0076] q z =ΔM(2491+1884t2-419t) r );

[0077]

[0078]

[0079]

[0080] Among them, M m The coal feed rate of the coal feeder is expressed in tons per hour (t / h); M f t1 is the primary air volume at the coal mill inlet, t / h; t2 is the primary air temperature at the coal mill inlet, ℃; t3 is the temperature of the air-coal mixture at the coal mill outlet, ℃; W is the coal mill power, KW; C1 is the specific heat of the desiccant at the coal mill inlet, KJ / kg*℃; C2 is the specific heat of the desiccant at the coal mill outlet, KJ / kg*℃; C lk Specific heat of cold air, kJ / kg*℃; C rd Specific heat of coal dryer, KJ / kg*℃; t lk The temperature of the leaking cold air, in °C; t r The temperature at which coal enters the system, in °C; K. lf R is the air leakage coefficient of the coal mill. 90 Q5 represents the fineness of the pulverized coal, in %; Q5 represents the heat loss of the subsystem, in KW; K nm The coefficient by which the input power of the coal mill is converted into heat.

[0081] The heat q consumed in evaporating water z It is related to the amount of water ΔM that evaporates per kg of raw coal in the coal mill:

[0082]

[0083] Where: M ar To receive the base moisture content; M mf This refers to the moisture content of pulverized coal.

[0084]

[0085] Moisture content of pulverized coal (M) mf Generally, it is roughly equal to the moisture content of an air dryer, usually lower, around 15%.

[0086] Specifically, the moisture measurement formula is as follows:

[0087]

[0088] The method for predicting the calorific value of coal based on a BP neural network includes:

[0089] A real-time calorific value prediction model for coal quality in the first direct-fired coal mill was established based on a BP neural network.

[0090] The real-time calorific value prediction model of coal quality for the first direct-fired coal mill is trained and updated to obtain the real-time calorific value prediction model of coal quality for the second direct-fired coal mill.

[0091] The calorific value of coal is predicted using the real-time calorific value prediction model of the second direct-fired coal mill.

[0092] Specifically, a real-time calorific value prediction model for coal in a direct-fired coal mill is established based on a backpropagation neural network:

[0093] The collected historical data of coal mills were used as the input of the BPNN model, and the calorific value of coal from the direct-fired coal mill was used as the predicted output. An input matrix was established, where M represents the number of samples and M represents the number of input variables.

[0094] (1) Randomly initialize the weight matrix = [Mq], = [1q], where q is the number of nodes in the first hidden layer, z [1] = sigmod(a [1] The sigmod function is shown below:

[0095] (2) Obtain the output z of the f-th hidden layer [4] The output variable is 1, with z as the variable. [4] Step ii is repeated, using the input variable, to calculate the predicted value of the target variable output by the output layer. The L2 norm loss function is used to calculate the loss between the output vector and the actual value of the target variable y. The calculation formula is as follows:

[0096] (3) Update each hidden layer w according to the loss value S. [i] b [i] ,

[0097]

[0098]

[0099] Where α is the hyperparameter learning rate, which is defined manually. After the update is completed, iterate (1)-(3) n times to calculate the predicted value of the target variable, coal moisture content. The root mean square error (MSE)

[0100]

[0101] Based on the trained BP neural network, the calorific value of coal in a direct-fired coal mill is predicted.

[0102] The output z of the first hidden layer [1] The hidden layers consist of f layers, which serve as the input parameters for the second hidden layer.

[0103] The ash content of coal is calculated based on its moisture content and calorific value.

[0104] Based on the predicted real-time ash content of each coal mill, the real-time coal feed rate of each coal mill, and the real-time total ash content, the following calculation is performed:

[0105] G = F × W ar(A) ×k×0.9;

[0106] G represents the real-time total ash content, F represents the amount of coal fed into the furnace, War(A) represents the received ash content, and k represents the ash-to-slag ratio.

[0107] Based on the ash storage status of each electric field ash hopper, the total ash storage is determined, the interval between two conveying operations of the conveying unit is determined in real time, and historical data is intelligently learned to accurately match the ash conveying cycle. At the same time, based on conveying parameters such as conveying pressure rise time, conveying pressure maintenance time, and purging pressure drop time, the full hopper conveying status is quantitatively evaluated in real time, and disturbances caused by factors such as ash particle size and fluidization state are intelligently identified, providing a basis for cycle parameter optimization. This ensures that each conveying operation is carried out when the hopper pump is full, thereby reducing the number of conveying operations and improving conveying efficiency.

[0108] The beneficial effects of this invention are as follows:

[0109] This invention provides an optimized control method for ash conveying in thermal power plants, which reduces the number of conveying operations, improves conveying efficiency, and lowers ash conveying costs.

[0110] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0111] This document uses specific examples to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. Furthermore, those skilled in the art will recognize that, based on the ideas of the present invention, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A method for optimizing ash conveying control in a thermal power plant, characterized in that, include: A dedicated gas-tracing pipeline is laid along the ash conveying pipeline, and intelligent concentration stabilizers are installed on the ash conveying pipeline at preset intervals. Real-time moisture content of coal is calculated using the heat balance principle of a direct-fired coal mill. Predicting the calorific value of coal based on a BP neural network; The ash content of the coal is calculated based on the real-time moisture content and calorific value of the coal. The real-time total ash content is calculated based on the coal ash content and the real-time coal feed rate of each coal mill. The pneumatic conveying ratio is determined based on the real-time total ash volume. The ash conveying interval is determined based on the pneumatic conveying ratio.

2. The optimized control method for ash conveying in a thermal power plant according to claim 1, characterized in that, The intelligent concentration stabilizer is used to control the ash plugs below a preset length value.

3. The optimized control method for ash conveying in a thermal power plant according to claim 1, characterized in that, The calculation of real-time coal moisture content using the heat balance principle of a direct-fired coal mill includes: Collect historical operating data of direct-fired coal mills; Based on the historical operating data of the direct-fired coal mill, a moisture measurement formula is constructed using the energy conservation principle formula. The real-time moisture content of coal is calculated using the aforementioned moisture measurement formula.

4. The optimized control method for ash conveying in a thermal power plant according to claim 3, characterized in that, The formula for the principle of energy conservation is: ； ； ； ； ； ； ； ； ； in, This refers to the coal feed rate of the coal feeder. This refers to the primary air volume at the inlet of the coal mill. This refers to the primary air temperature at the inlet of the coal mill. The temperature of the air-coal mixture at the coal mill outlet; W is the power of the coal mill, in KW. The specific heat of the desiccant at the coal mill inlet; The specific heat of the desiccant at the coal mill outlet; The specific heat of cold air; The specific heat of the coal dryer; The temperature of the leaking cold air; The temperature at which the coal enters the system; The air leakage coefficient of the coal mill; For coal powder fineness; This is due to the heat loss of the subsystem; ΔM is the coefficient by which the input power of the coal mill is converted into heat, and ΔM is the amount of water evaporated per kilogram of raw coal in the coal mill. To receive the base moisture.

5. The optimized control method for ash conveying in a thermal power plant according to claim 4, characterized in that, The moisture measurement formula is as follows: 。 6. The optimized control method for ash conveying in a thermal power plant according to claim 4, characterized in that, The formula for calculating the real-time total ash volume is: ； Where G is the real-time total ash content, F is the amount of coal fed into the furnace, War(A) is the received ash content, and k is the ash-to-slag ratio.

7. The optimized control method for ash conveying in a thermal power plant according to claim 1, characterized in that, The method for predicting the calorific value of coal based on a BP neural network includes: A real-time calorific value prediction model for coal quality in the first direct-fired coal mill was established based on a BP neural network. The real-time calorific value prediction model of coal quality for the first direct-fired coal mill is trained and updated to obtain the real-time calorific value prediction model of coal quality for the second direct-fired coal mill. The calorific value of coal is predicted using the real-time calorific value prediction model of the second direct-fired coal mill.

Images