Coal and oil sludge mixing control method and system

Abstract

The invention provides a fire coal and oil sludge mixing control method and system, and belongs to the technical field of oil sludge incineration, and the method comprises the steps: obtaining the historical data of the fire coal consumption rate of a boiler and the historical data of the oil sludge mixing amount, and building the relation between the fuel consumption rate of the boiler and the fire coal consumption rate and the oil sludge mixing amount of the boiler; monitoring data of the coal consumption rate and the oil sludge mixing amount at the current moment in real time, performing iterative optimization on the coal consumption rate and the oil sludge mixing amount until preset conditions are met, obtaining the optimized coal consumption rate and oil sludge mixing amount, and predicting the fuel consumption rate; and according to the optimized coal consumption rate and the oil sludge mixing amount, the oil sludge mixing amount at the preset moment and the coal mixing amount at the preset moment in the boiler are dynamically controlled. The system comprises a data acquisition module, a data processing module and a control module which are mutually connected. The coal consumption rate of the unit and the oil sludge mixing amount are monitored in real time and dynamically controlled, the oil sludge mixing amount is automatically adjusted, and the energy utilization efficiency is improved.

Description

Technical Field

[0001] This invention belongs to the field of oil sludge incineration technology, specifically relating to a method and system for controlling the mixing of coal and oil sludge. Background Technology

[0002] Co-firing oil into coal-fired boilers is an effective way to achieve the harmless disposal and resource utilization of oily sludge, with advantages such as large processing capacity, high efficiency, and strong adaptability. However, after co-firing sludge into coal-fired units, the quality of the mixed fuel entering the furnace decreases, leading to a decrease in boiler efficiency, an increase in plant power consumption, and consequently an increase in the unit's coal consumption rate. In order to improve fuel quality, increase boiler efficiency, and reduce the unit's coal consumption rate, current measures include reducing the moisture content of the oily sludge, for example, by using steam rotary drying technology to dry the sludge to below 40% before grinding and incineration; and calculating the coal consumption rate of coal-fired power plants coupled with sludge.

[0003] However, the calculation of coal consumption rate in existing technologies is not accurate enough, and it is not possible to calculate and monitor the coal consumption rate of the unit in real time. Furthermore, there is a lack of effective means to dynamically control the coal consumption rate and the amount of oil sludge added, which is not conducive to improving energy-saving effects. Summary of the Invention

[0004] To address the aforementioned problems in the prior art, this invention provides a method and system for controlling the blending of coal and oil sludge, aiming to improve energy utilization efficiency by automatically adjusting the amount of oil sludge blended through real-time monitoring and dynamic control of the unit's coal consumption rate and oil sludge blending amount.

[0005] To achieve the above objectives, the present invention provides the following technical solution:

[0006] A method for controlling the mixing of coal and oil sludge includes the following steps:

[0007] Step S1: Obtain historical data on boiler coal consumption rate and oil sludge incorporation amount, and establish the relationship between boiler fuel consumption rate and boiler coal consumption rate and oil sludge incorporation amount.

[0008] Step S2: Monitor the current data of coal consumption rate and oil sludge addition in real time, iteratively optimize the coal consumption rate and oil sludge addition until the preset conditions are met, obtain the optimized coal consumption rate and oil sludge addition, and predict the fuel consumption rate.

[0009] Step S3: Dynamically control the amount of oil sludge added and the amount of coal added at preset times in the boiler based on the optimized coal consumption rate and the amount of oil sludge added.

[0010] Furthermore, step S1 includes:

[0011] Step S101: Using a neural network model, train the model on historical data of boiler coal consumption rate and historical data of oil sludge incorporation amount to obtain boiler combustion efficiency and oil sludge combustion efficiency.

[0012] Step S102: Calculate the boiler's fuel consumption rate.

[0013] Furthermore, the formula for calculating the fuel consumption rate is as follows:

[0014] FR=(CR+SL)×(CE+SCE)

[0015] Wherein, FR is the boiler's fuel consumption rate, representing the actual amount of fuel burned per unit time, in tons per hour;

[0016] CR is the boiler's coal consumption rate, representing the amount of coal input per unit time, in tons per hour;

[0017] SL represents the amount of oil sludge added per unit time, in tons per hour.

[0018] CE is the theoretical combustion efficiency of the boiler, representing the ratio of the actual fuel combustion rate to the input fuel rate, in percentage (%). SCE is the sludge combustion efficiency, representing the impact of sludge on combustion efficiency after its introduction, in percentage (%).

[0019] Furthermore, the preset conditions include at least one of the following: the fuel consumption rate reaching a preset value, a preset energy-saving target, a preset economic target, or the minimum value of the fuel consumption rate within a preset time or number of iterations.

[0020] Furthermore, in step S2, the coal consumption rate and the amount of oil sludge added are iteratively optimized using a genetic algorithm. This algorithm treats different amounts of oil sludge added as individuals, and obtains individuals that meet the termination conditions by evaluating the quality of each individual.

[0021] Furthermore, the specific process of iteratively optimizing the coal consumption rate and oil sludge incorporation amount using a genetic algorithm is as follows:

[0022] Define a fitness function: Define a fitness function to evaluate the quality of each individual. The fitness function takes into account energy-saving goals, environmental protection indicators, and actual operational constraints.

[0023] Initialize the population: Based on the range and constraints of coal consumption rate and oil sludge incorporation amount, randomly generate a number of individuals as the initial population;

[0024] Fitness assessment: For each individual, its fitness value is assessed based on the fitness function to evaluate the individual's quality.

[0025] Selection operation: Through the selection operation, a certain number of individuals are selected from the current population to serve as the parents of the next generation.

[0026] Crossover operation: Perform a crossover operation on the parent individual to generate a certain number of child individuals;

[0027] Mutation operation: For offspring individuals, a mutation operation is performed to introduce a certain degree of randomness;

[0028] Population Update: Merge parent and offspring individuals to form an updated population;

[0029] Repeat the fitness assessment, selection, crossover, mutation, and population update operations until the termination condition is met.

[0030] Furthermore, the termination conditions include reaching the maximum number of iterations and the fitness reaching a preset value.

[0031] Furthermore, the fitness function is constructed based on the linear regression equation, and its expression is as follows:

[0032] Fit value = a × fuel consumption rate + b × sludge incorporation amount

[0033] Here, a and b are weighting coefficients used to balance the importance of fuel consumption rate and sludge incorporation.

[0034] Furthermore, the weighting coefficient 'a' is calculated using the following formula:

[0035]

[0036] Among them, w i and c i V represents the weight and actual value of the fuel consumption rate, respectively. i and d i represents the weight and actual value of the amount of oil sludge added, respectively; i is the i-th coal consumption rate data point; j is the j-th sludge addition data point; n is the number of coal consumption rate data points; and m is the number of sludge addition data points.

[0037] Furthermore, the weighting coefficient 'a' is calculated using the following formula:

[0038]

[0039] Furthermore, the calculation process for the weighting coefficient b is as follows:

[0040] The following multiple linear regression equation is established:

[0041] x i =b0+b1y i +ε i

[0042] Where b0 is the intercept, b1 is the coefficient, and ε i It is the error term for the i-th sample, x i y is the fuel consumption rate of the i-th sample. i It is the amount of sludge added to the i-th sample, where i is the sample number;

[0043] Using the least squares method, the sum of squared residuals is calculated. Minimize, and calculate the optimal coefficient b1, where, It is a value estimated by the regression equation;

[0044] The value of the weight coefficient b is calculated using b1, and its expression is as follows:

[0045]

[0046] Where n is the number of sample data.

[0047] Furthermore, in the process of calculating the weight coefficients b based on the multiple linear regression model and the weighted least squares method, a weight matrix W is introduced, the specific process of which is as follows:

[0048] The following multiple linear regression equation is established:

[0049] x i =b0+b1y i +ε i

[0050] Where b0 is the intercept, b1 is the coefficient, and ε i It is the error term for the i-th sample, x i y is the fuel consumption rate of the i-th sample. i It is the amount of sludge added to the i-th sample, where i is the sample number;

[0051] Using the least squares method, the sum of squared residuals is calculated. Minimize, and calculate the optimal coefficient b1, where, The value w is estimated from the regression equation. i Let be the weight of the i-th sample in the weight matrix W;

[0052] The value of the weight coefficient b is calculated using b1, and its expression is as follows:

[0053]

[0054] Where n is the number of sample data.

[0055] A coal and oil sludge blending control system includes a data acquisition module, a data processing module, and a control module connected in sequence. The data acquisition module acquires and monitors in real time the coal consumption rate and oil sludge blending amount of the boiler, and transmits the data to the data processing module. The data processing module processes the data input from the data acquisition module in real time, and iteratively optimizes the coal consumption rate and oil sludge blending amount to obtain an oil sludge blending amount and coal consumption rate that meet preset conditions, and outputs the results to the control module. The control module controls the oil sludge blending amount and coal consumption rate at preset times based on the oil sludge blending amount and coal consumption rate input from the data processing module.

[0056] Furthermore, the data processing module incorporates a control algorithm, which includes a neural network model and a genetic algorithm. The neural network model is trained on the boiler's coal consumption rate data and oil sludge addition data to obtain the calculated boiler's fuel consumption rate. The genetic algorithm iteratively optimizes the coal consumption rate and oil sludge addition to obtain oil sludge addition and coal consumption rate that meet preset conditions.

[0057] Furthermore, the genetic designation sets different weighting coefficients for fuel consumption rate and sludge incorporation amount.

[0058] Compared with the prior art, the present invention has at least the following beneficial effects:

[0059] 1. This invention improves energy utilization efficiency by real-time monitoring and dynamic control of boiler coal consumption rate and oil sludge addition amount, and automatically adjusting the oil sludge addition amount.

[0060] 2. This invention, through the built-in control algorithm of the control system, can automatically adjust the amount of oil sludge added based on data analysis results to achieve the best energy-saving and environmental protection effects;

[0061] 3. This invention takes into account the relationship between the amount of oil sludge added and the fuel consumption rate to construct a fitness function, and uses different weighting methods for the two to obtain a reasonable blending ratio of oil sludge and coal. Attached Figure Description

[0062] Figure 1 This is a schematic diagram of a coal and oil sludge blending control system according to an embodiment of the present invention;

[0063] Figure 2 This is a technical roadmap of a method for controlling the blending of coal and oil sludge according to an embodiment of the present invention. Detailed Implementation

[0064] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, 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, 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.

[0065] Therefore, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the invention without inventive effort are within the scope of protection of the invention.

[0066] To better understand the purpose, process, and function of this invention, the following detailed description of a method and system for controlling the blending of coal and oil sludge, in conjunction with the accompanying drawings, is provided.

[0067] Example 1

[0068] like Figure 1 As shown, the present invention provides the following technical solution:

[0069] A coal and oil sludge blending control system includes a data acquisition module, a data processing module, and a control module connected in sequence. The data acquisition module acquires and monitors in real time the coal consumption rate and oil sludge blending amount of the boiler, and transmits the data to the data processing module. The data processing module processes the data input from the data acquisition module in real time, and iteratively optimizes the coal consumption rate and oil sludge blending amount to obtain an oil sludge blending amount and coal consumption rate that meet preset conditions, and outputs the results to the control module. The control module controls the oil sludge blending amount and coal consumption rate at preset times based on the oil sludge blending amount and coal consumption rate input from the data processing module.

[0070] Furthermore, the data processing module incorporates a control algorithm, which includes a neural network model and a genetic algorithm. The neural network model is used to train historical data to establish the relationship between fuel consumption rate and sludge blending amount. The genetic algorithm applies different weights to sludge blending amount and coal consumption rate to calculate a reasonable blending ratio of sludge and coal.

[0071] It should be noted that the particle swarm optimization algorithm can also be used to calculate the blending ratio of oil sludge and coal.

[0072] In some preferred embodiments of the present invention, the data acquisition module includes a coal combustion sensor and an oil sludge sensor respectively installed on the silo and the scraper conveyor, which monitor the coal consumption rate and the amount of oil sludge added in real time in advance.

[0073] Example 2

[0074] like Figure 2 As shown, the present invention provides a method for controlling the blending of coal and oil sludge, comprising the following steps:

[0075] Step S1: Obtain historical data on boiler coal consumption rate and oil sludge incorporation amount, and establish the relationship between boiler fuel consumption rate and boiler coal consumption rate and oil sludge incorporation amount.

[0076] Step S2: Monitor the current data of coal consumption rate and oil sludge addition in real time, iteratively optimize the coal consumption rate and oil sludge addition until the preset conditions are met, obtain the optimized coal consumption rate and oil sludge addition, and predict the fuel consumption rate.

[0077] Step S3: Dynamically control the amount of oil sludge added and the amount of coal added at preset times in the boiler based on the optimized coal consumption rate and the amount of oil sludge added.

[0078] Furthermore, step S1 includes:

[0079] Step S101: Using a neural network model, train the model on historical data of boiler coal consumption rate and historical data of oil sludge incorporation amount to obtain boiler combustion efficiency and oil sludge combustion efficiency.

[0080] Step S102: Calculate the boiler's fuel consumption rate.

[0081] Furthermore, the formula for calculating the fuel consumption rate is as follows:

[0082] FR=(CR+SL)×(CE+SCE)

[0083] Wherein, FR is the boiler's fuel consumption rate, representing the actual amount of fuel burned per unit time, in tons per hour;

[0084] CR is the boiler's coal consumption rate, representing the amount of coal input per unit time, in tons per hour;

[0085] SL represents the amount of oil sludge added per unit time, in tons per hour.

[0086] CE is the theoretical combustion efficiency of the boiler, which represents the ratio of the actual amount of fuel burned to the amount of fuel added, in percentage (%). SCE is the sludge combustion efficiency, which represents the impact of adding sludge on the combustion efficiency. This indicator is a difference; for example, if the original CE is 80%, and the overall efficiency becomes 75% after adding sludge, then SCE is -5%, and its unit is also 5%.

[0087] Furthermore, the preset conditions include at least one of the following: the fuel consumption rate reaching a preset value, a preset energy-saving target, a preset economic target, or the minimum value of the fuel consumption rate within a preset time or number of iterations.

[0088] Furthermore, in step S2, the coal consumption rate and the amount of oil sludge added are iteratively optimized using a genetic algorithm. This algorithm treats different amounts of oil sludge added as individuals, and obtains individuals that meet the termination conditions by evaluating the quality of each individual.

[0089] Furthermore, the termination conditions include reaching the maximum number of iterations and the fitness reaching a preset value.

[0090] Example 3

[0091] The difference from Example 2 is that, in this example, the fitness function is constructed based on a linear regression equation, and its expression is:

[0092] Fit value = a × fuel consumption rate + b × sludge incorporation amount

[0093] Here, a and b are weighting coefficients used to balance the importance of fuel consumption rate and sludge incorporation.

[0094] The above formula can be adjusted according to actual conditions to reflect the impact of sludge incorporation on energy-saving effects. Through the iterative process of a genetic algorithm, the amount of sludge incorporation that maximizes the fitness value is found, thereby achieving the optimal energy-saving effect.

[0095] In practical engineering applications, determining the specific formula for the weight coefficient 'a' usually requires in-depth analysis and experimental research. A common method is to use multi-objective optimization techniques. This optimization algorithm can help find the optimal weight coefficient, enabling the best overall effect when considering multiple objectives. By training and validating on real-world data, a specific formula for the weight coefficient 'a' suitable for the specific situation can be obtained. Therefore, determining the specific formula for the weight coefficient 'a' is a complex engineering problem that requires in-depth research and analysis considering the specific system characteristics, objectives, and constraints. Based on the results of the multi-objective optimization algorithm, a specific formula for the weight coefficient 'a' suitable for the specific situation is obtained.

[0096] Furthermore, in some preferred embodiments of this example, the weighting coefficient 'a' is calculated using the following formula:

[0097]

[0098] Where w and c represent the weight and actual value of fuel consumption rate, respectively; v and d represent the weight and actual value of sludge incorporation, respectively; i is the i-th coal consumption rate data point; j is the j-th sludge incorporation data point; n is the number of coal consumption rate data points; and m is the number of sludge incorporation data points.

[0099] Example 4

[0100] The difference from Example 3 is that in this example, logarithmic operations are used to amplify or reduce the change in fuel consumption rate, and square root operations are used to adjust the influence of sludge admixture. The weighting coefficient 'a' is calculated using the following formula:

[0101]

[0102] Among them, w i and v j This indicates the weights of fuel consumption rate and sludge incorporation. These weights can be set according to actual conditions and objectives. For example, the weight of coal consumption rate can be determined based on the importance of energy consumption, and the weight of sludge incorporation can be determined based on its degree of influence.

[0103] c i and d j This represents the actual values ​​of fuel consumption rate and sludge incorporation. These values ​​can be obtained through actual monitoring and recording, for example, by determining the actual consumption or mass of fuel and sludge.

[0104] i represents the i-th coal consumption rate data point, j represents the j-th sludge incorporation data point, n represents the number of coal consumption rate data points, and m represents the number of sludge incorporation data points.

[0105] This implementation plan can more accurately reflect the actual system characteristics, objectives, and constraints.

[0106] In some preferred embodiments of this example, a unit with a fuel consumption rate of 1000 tons / day has an oil sludge incorporation amount of 50 tons / day. Meanwhile, the weights for the fuel consumption rate and the oil sludge incorporation amount are given as 0.7 and 0.3, respectively. Therefore, according to the above formula, the specific value of the weighting coefficient 'a' can be calculated.

[0107]

[0108] Through such calculation examples, a specific weighting coefficient 'a' can be obtained, which can then be used to evaluate the energy-saving / energy-consuming effects of co-firing oil sludge in the unit. It should be noted that in practical applications, more factors and constraints may need to be considered, therefore the complexity of the formula will vary depending on the specific circumstances.

[0109] Example 5

[0110] The difference from Examples 3-4 is that the calculation process for the weighting coefficient b is as follows:

[0111] The following multiple linear regression equation is established:

[0112] x i =b0+b1y i +ε i

[0113] Where b0 is the intercept, b1 is the coefficient, and ε i It is the error term, x i It is the fuel consumption rate, y i This represents the amount of sludge added, where i is the sample number.

[0114] Using the least squares method, the sum of squared residuals is calculated. Minimize, and calculate the optimal coefficient b1, where, It is a value estimated by the regression equation;

[0115] The value of the weight coefficient b is calculated using b1, and its expression is as follows:

[0116]

[0117] Where n is the number of sample data.

[0118] The formula can be used to calculate the weighting coefficient b, reflecting the impact of sludge incorporation on energy-saving performance. It should be noted that in practical applications, more factors and constraints may need to be considered, therefore the complexity of the formula will vary depending on the specific circumstances.

[0119] Furthermore, in some preferred embodiments of this example, in the process of calculating the weight coefficient b based on the multiple linear regression model and the weighted least squares method, a weight matrix W is introduced to adjust the weights of different samples in order to estimate the regression equation more accurately. The specific process is as follows:

[0120] The following multiple linear regression equation is established:

[0121] x i =b0+b1y i +ε i

[0122] Where b0 is the intercept, b1 is the coefficient, and ε i It is the error term, x i It is the fuel consumption rate, y i This represents the amount of sludge added, where i is the sample number;

[0123] Using the least squares method, the sum of squared residuals is calculated. Minimize, and calculate the optimal coefficient b1, where, The value w is estimated from the regression equation. i Let be the weight of the i-th sample;

[0124] The value of the weight coefficient b is calculated using b1, and its expression is as follows:

[0125]

[0126] Where n is the number of sample data.

[0127] This formula can be used to calculate the weighting coefficient b, reflecting the impact of sludge incorporation on energy-saving performance, and it considers the weights of different samples. It is important to note that in practical applications, choosing an appropriate weighting matrix W is crucial, as different weighting matrices may lead to different results. Therefore, the complexity of the formula will vary depending on the specific circumstances and the chosen weighting matrix. The weighting coefficient b can be calculated using the aforementioned multiple linear regression model and weighted least squares method to reflect the impact of sludge incorporation on energy-saving performance.

[0128] After calculating the weighting coefficient b, practical applications can be implemented. For example, when adjusting the amount of oil sludge added, the weighting coefficient b can be used to evaluate the impact of different addition amounts on energy-saving effects. This allows for more accurate control of the amount of oil sludge added, thereby achieving the goals of energy saving and reducing coal consumption.

[0129] This method also allows for real-time monitoring of the relationship between fuel consumption rate and sludge incorporation amount, enabling timely adjustments to the sludge incorporation amount to maximize energy savings.

[0130] Furthermore, this invention allows for a better study of the impact of sludge incorporation on energy-saving effects and can guide practical operations, thereby achieving the goal of energy conservation and emission reduction.

[0131] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention are included within the scope of protection of the present invention.

Claims

1. A method of coal and sludge blending control, characterized by, The method comprises the following steps: Step S1: obtaining historical data of coal consumption rate of the boiler and historical data of oil sludge mixing amount, and establishing a relationship between fuel consumption rate of the boiler and coal consumption rate of the boiler and oil sludge mixing amount; Step S2: real-time monitoring current time data of the coal consumption rate and the oil sludge mixing amount, and iteratively optimizing the coal consumption rate and the oil sludge mixing amount until a preset condition is met, to obtain optimized coal consumption rate, oil sludge mixing amount, and predicted fuel consumption rate; Step S3: dynamically controlling the oil sludge mixing amount at a preset time and the coal mixing amount at the preset time in the boiler according to the optimized coal consumption rate and the oil sludge mixing amount.

2. The coal and oil sludge blending control method of claim 1, wherein, The step S1 comprises: Step S101: training the historical data of the coal consumption rate of the boiler and the historical data of the oil sludge mixing amount by using a neural network model, to obtain boiler combustion efficiency and oil sludge combustion efficiency; Step S102: calculating the fuel consumption rate of the boiler.

3. The coal and oil sludge blending control method of claim 2, wherein, The calculation expression of the fuel consumption rate is: FR=(CR+SL)×(CE+SCE) Wherein, FR is the fuel consumption rate of the boiler, indicating the actual combustion fuel per unit time, unit: ton / hour; CR is the coal consumption rate of the boiler, indicating the input coal quantity per unit time, unit: ton / hour; SL is the oil sludge mixing amount, indicating the input oil sludge quantity per unit time, unit: ton / hour; CE is the theoretical combustion efficiency of the boiler, indicating the ratio of actual combustion quantity to input quantity, unit: %; and SCE is the oil sludge combustion efficiency, indicating the part of the influence value on the combustion efficiency after the oil sludge is input, unit: %.

4. The coal and oil sludge blending control method of claim 3, wherein, The preset condition comprises at least one of the fuel consumption rate reaching a preset value, a preset energy-saving target, a preset economic target, a preset time, or a minimum value of the fuel consumption rate within a preset number of iterations.

5. The coal and oil sludge blending control method of claim 3, wherein, In the step S2, the coal consumption rate and the oil sludge mixing amount are iteratively optimized by using a genetic algorithm, which takes different oil sludge mixing amounts as individuals, and obtains an individual meeting a termination condition by evaluating the advantages and disadvantages of each individual.

6. The coal and oil sludge blending control method of claim 5, wherein, The specific process of iteratively optimizing the coal consumption rate and the oil sludge mixing amount by using the genetic algorithm is as follows: Defining a fitness function for evaluating the advantages and disadvantages of each individual, which considers the energy-saving target, the environmental protection index, and the limitation conditions of actual operation; Initializing a population by randomly generating a number of individuals as an initial population according to the range and constraint conditions of the coal consumption rate and the oil sludge mixing amount; Evaluating the fitness of each individual according to the fitness function to evaluate the advantages and disadvantages of the individual; Selecting a number of individuals from the current population as the parents of the next generation population by selection operation; Crossing the parent individuals to generate a number of child individuals; Mutating the child individuals to introduce randomness; Updating the population by combining the parent and child individuals to form an updated population; Repeating the evaluation of the fitness, the selection operation, the crossing operation, the mutation operation, and the updating of the population until the termination condition is met.

7. The coal and oil sludge blending control method of claim 6, wherein, The termination condition comprises reaching a maximum number of iterations and the fitness reaching a preset value.

8. The coal and oil sludge blending control method of claim 6, wherein, The fitness function is constructed based on a linear regression equation, which is expressed as: Fitness value = a x fuel consumption rate + b x oil sludge incorporation amount Wherein, a and b are weight coefficients for balancing the importance of fuel consumption rate and oil sludge incorporation amount.

9. The coal and oil sludge blending control method of claim 8, wherein, The weight coefficient a is calculated by the following formula: where w i and c i represent the weight and actual value of fuel consumption rate, respectively, v i and d i represent the weight and actual value of sludge incorporation amount, respectively, i is the i-th data point of coal-fired power plant consumption rate, j is the j-th data point of sludge incorporation amount, n is the number of data points of coal-fired power plant consumption rate, and m is the number of data points of sludge incorporation amount.

10. The coal and oil sludge blending control method of claim 9, wherein, The weight coefficient a is calculated by the following formula:

11. The coal and oil sludge blending control method of claim 8, wherein, The calculation process of the weight coefficient b is as follows: The following multiple linear regression equation is established: x i = b0+ b1y i + ε i where b0 is an intercept, b1 is a coefficient, ε i is an error term for the i-th sample, x i is the fuel consumption rate for the i-th sample, y i is the amount of sludge incorporation for the i-th sample, i is the sample number; Using the least squares method, the sum of squared residuals is calculated. Minimize, and calculate the optimal coefficient b1, where, It is a value estimated from the regression equation; The value of the weight coefficient b is calculated by b1, which is expressed as: Wherein, n is the number of sample data.

12. The coal and oil sludge blending control method of claim 11, wherein, In the process of calculating the weight coefficient b based on the multiple linear regression model and the weighted least squares method, a weight matrix W is introduced, and the specific process is as follows: The following multiple linear regression equation is established: x i = b0+ b1y i + ε i where b0 is an intercept, b1 is a coefficient, ε i is an error term for the i-th sample, x i is the fuel consumption rate for the i-th sample, y i is the amount of sludge incorporation for the i-th sample, i is the sample number; Using the least squares method, the sum of squared residuals is calculated. Minimize, and calculate the optimal coefficient b1, where, The value w is estimated from the regression equation. i Let be the weight of the i-th sample in the weight matrix W; The value of the weight coefficient b is calculated by b1, which is expressed as: Wherein, n is the number of sample data.

13. A coal and sludge blending control system for implementing the coal and sludge blending control method as claimed in claims 1-12, characterized by: The data acquisition module, the data processing module and the control module are connected in sequence, the data acquisition module acquires and real-time monitors the coal consumption rate data and the oil sludge incorporation amount data of the boiler, and transmits the data to the data processing module; the data processing module real-time processes the data input by the data acquisition module, and iteratively optimizes the coal consumption rate and the oil sludge incorporation amount, obtains the oil sludge incorporation amount and the coal consumption rate meeting the preset condition, and outputs to the control module; The control module controls the oil sludge incorporation amount and the coal consumption rate at the preset time according to the oil sludge incorporation amount and the coal consumption rate input by the data processing module.

14. The coal and sludge blending control system of claim 13, wherein: The data processing module is built-in control algorithm, the control algorithm includes neural network model and genetic algorithm, neural network model trains the coal consumption rate data and the oil sludge incorporation amount data of the boiler, obtains the calculation of the fuel consumption rate of the boiler; genetic algorithm iteratively optimizes the coal consumption rate and the oil sludge incorporation amount, and obtains the oil sludge incorporation amount and the coal consumption rate meeting the preset condition.

15. The coal and sludge blending control system of claim 13, wherein: The genetic algorithm sets different weight coefficients for the fuel consumption rate and the oil sludge incorporation amount.

Images