Multi-layer waste coal cinder crushing system based on power generation capacity prediction

Abstract

The invention provides a multi-layer waste coal slag crushing system based on power generation capacity prediction, which relates to the technical field of thermal power generation and comprises a power generation capacity prediction unit, a central control unit and multi-stage crushing equipment, the generating capacity prediction unit is used for predicting the generating capacity of the thermal power station so as to predict the yield and volume of waste coal slag produced by the thermal power station; the central control unit is used for formulating a reasonable crushing treatment strategy according to the predicted yield and volume of the waste coal slag and controlling the multi-stage crushing equipment to perform corresponding crushing treatment on the waste coal slag; the multi-stage crushing equipment comprises a coarse crushing unit, a fine grinding unit and an accurate grinding unit, the coarse crushing unit, the fine grinding unit and the accurate grinding unit are respectively used for performing coarse crushing, fine grinding and accurate grinding treatment on the waste coal slag, and the coarse crushing unit, the fine grinding unit and the accurate grinding unit are further used for realizing step-by-step transfer of the waste coal slag; the waste coal cinder crushing efficiency can be improved, the stability of system operation is guaranteed, and energy is saved.

Description

Technical Field

[0001] The invention relates to the technical field of thermal power generation, and in particular to a multi-layer waste coal slag crushing system based on power generation prediction. Background Art

[0002] With the development of industry, coal is one of the main energy sources. The treatment of waste coal slag produced in industrial places such as power plants has become an urgent problem to be solved. Traditional methods of treating waste coal slag often have problems such as high energy consumption, low efficiency, and serious environmental pollution. Especially today when energy management and environmental protection requirements are becoming increasingly stringent, how to effectively utilize resources and reduce pollution has become the focus of the industry.

[0003] Existing waste coal slag crushing systems often cannot accurately match the dynamic balance between power generation and waste slag processing capacity, resulting in low equipment operation efficiency and even waste of resources. In addition, due to the lack of an effective prediction mechanism, the waste coal slag processing system is difficult to cope with the impact of power generation fluctuations, which in turn affects the stability and economy of the entire production process. Summary of the invention

[0004] The object of the present invention is to provide a multi-layer waste coal slag pulverizing system based on power generation prediction, which can improve the efficiency of waste coal slag pulverizing, ensure the stability of system operation, and save energy.

[0005] The present invention is achieved through the following technical solutions:

[0006] A multi-layer waste coal slag crushing system based on power generation prediction, comprising a power generation prediction unit, a central control unit and a multi-stage crushing device;

[0007] The power generation prediction unit is used to predict the power generation of the thermal power plant, thereby predicting the output and volume of waste coal slag produced by the thermal power plant;

[0008] The central control unit is used to formulate a reasonable crushing treatment strategy according to the predicted waste coal slag output and volume, and control the multi-stage crushing equipment to perform corresponding crushing treatment on the waste coal slag;

[0009] The multi-stage pulverizing equipment includes a coarse pulverizing unit, a fine grinding unit and a fine grinding unit, which are respectively used for coarse pulverizing, fine grinding and fine grinding of waste coal slag, and are also used for realizing the step-by-step transfer of waste coal slag.

[0010] Furthermore, the power generation prediction unit includes a data collection module, a data preprocessing module, a model selection module, a model training and verification module and a model optimization module;

[0011] The data collection module is used to collect historical power generation data, weather data, holidays and special events, economic indicators and demographic data;

[0012] The data preprocessing module is used to clean the data, create new features that are helpful for power generation prediction based on the cleaned data, and standardize the feature data;

[0013] A plurality of power generation prediction models are preset in the model selection module;

[0014] The model training and verification module divides the preprocessed data set into a training set, a verification set and a test set, evaluates the performance of each model based on the training set, the verification set and the test set, and determines the prediction model with the highest performance;

[0015] The model optimization module adjusts the hyperparameters of the corresponding models according to the prediction models determined by the training and verification modules, obtains the optimized prediction models, and substitutes the cleaned data to obtain the predicted power generation of the thermal power plant.

[0016] Furthermore, the training set, validation set and test set account for 70%, 15% and 15% respectively.

[0017] Furthermore, the model optimization module uses a grid search or a random search method to find the optimal hyperparameters of the prediction model determined in the model training and verification module.

[0018] Furthermore, the power prediction unit also includes a deployment and monitoring module, which is used to deploy the optimized prediction model to actual applications and regularly check the deviation between the prediction results of the prediction model and the actual situation.

[0019] Furthermore, the central control unit includes a data receiving module, a CPU and a crushing processing strategy generating module;

[0020] The data receiving module is used to receive the power generation prediction value output by the power generation prediction unit;

[0021] The CPU has multiple thresholds preset in it, and is used to compare the power generation prediction value with the thresholds;

[0022] The pulverizing strategy generation module is used to generate a corresponding pulverizing strategy according to the comparison result between the power generation prediction value and the threshold value, wherein the pulverizing strategy is used to control the working states of the coarse pulverizing unit, the fine grinding unit and the fine grinding unit.

[0023] Furthermore, the coarse crushing unit includes a first material chute, a first gantry and a crushing hammer;

[0024] The feeding end of the first feeding chute is used to receive the waste coal slag, the first feeding chute is fixedly provided with a first gantry, the top of the first gantry is fixedly provided with a telescopic driving member, and the telescopic driving member is fixedly connected to the top of the leg;

[0025] The bottom of the supporting leg passes through the top of the first gantry frame and is connected to the crushing hammer, which is located above the trough surface of the first material trough.

[0026] Furthermore, the crushing hammer is configured to be columnar, and a plurality of protrusions are evenly arranged on the surface of the columnar crushing hammer.

[0027] Furthermore, the fine grinding unit includes a second feed chute, a diverter block, a grinding roller, a second gantry, a limit block and a spring, the feed end of the second feed chute is used to receive the coarsely crushed waste coal slag output by the first feed chute, and the second feed chute is fixedly provided with a second gantry;

[0028] The diverter block is used to guide the waste coal slag in the feeding trough to the two sides of the diverter block. A bidirectional motor is installed in the diverter block. The two driving shafts of the bidirectional motor are respectively connected to a grinding roller drive. A guide rod is fixedly provided on the top surface of the diverter block. The head end of the guide rod passes through the second gantry frame and is fixedly connected to the limit block.

[0029] The rod body of the guide rod is sleeved with a spring, and two ends of the spring are respectively fixedly connected with the second door-shaped frame and the diverter block.

[0030] Furthermore, the fine grinding unit is a grinding disc structure.

[0031] The technical solution of the present invention has at least the following advantages and beneficial effects:

[0032] The present invention provides a multi-layer waste coal slag pulverizing system based on power generation prediction. By predicting the amount of waste coal slag, the operation strategy of subsequent multi-stage pulverizing equipment can be better planned, thereby ensuring the stability of waste coal slag pulverizing processing when the amount of waste coal slag changes;

[0033] Secondly, the use of multi-stage crushing equipment can carry out fine and targeted crushing of waste coal slag, effectively improving the efficiency of waste coal slag crushing and saving energy. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0035] Figure 1A structural schematic diagram provided for the present invention;

[0036] Figure 2 A schematic diagram of the structure of the multi-stage crushing equipment provided by the present invention;

[0037] Figure 3 A schematic structural diagram of a coarse crushing unit provided by the present invention;

[0038] Figure 4 This is a schematic structural diagram of the fine grinding unit provided by the present invention.

[0039] Icons: 1. Power generation prediction unit; 2. Central control unit; 3. Multi-stage crushing equipment; 31. Coarse crushing unit; 311. First feed chute; 312. First gantry; 313. Crushing hammer; 314. Telescopic drive member; 315. Leg; 316. Bump; 32. Fine grinding unit; 321. Second feed chute; 322. Diverter block; 323. Grinding roller; 324. Second gantry; 325. Guide rod; 326. Limit block; 327. Spring; 328. Bidirectional motor; 33. Fine grinding unit. DETAILED DESCRIPTION

[0040] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0041] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0042] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0043] In the description of the present invention, it should be noted that if the terms "center", "up", "down", "left", "right", "vertical", "horizontal", "inside", "outside" and the like appear, the orientation or position relationship indicated is based on the orientation or position relationship shown in the accompanying drawings, or is the orientation or position relationship in which the product of the application is usually placed when used. It is only for the convenience of describing the present invention and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention.

[0044] In the description of the present invention, it is also necessary to explain that, unless otherwise clearly specified and limited, the terms "set", "install", "connect", and "connect" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0045] Example 1

[0046] Combined with Figure 1-2 The multi-layer waste coal slag pulverizing system based on power generation prediction comprises a power generation prediction unit 1, a central control unit 2 and a multi-stage pulverizing device 3;

[0047] The power generation prediction unit 1 is used to predict the power generation of the thermal power plant, thereby predicting the output and volume of waste coal slag produced by the thermal power plant;

[0048] By predicting the power generation of a thermal power plant, we can get the operating conditions of the power generation equipment in the thermal power plant, including the operating time, coal addition and coal consumption. In a thermal power plant, when the power demand is large, in order to meet this demand, the coal input is usually increased to increase the power generation capacity, which will lead to an increase in the amount and volume of waste coal slag generated during the combustion process. This is because more coal is consumed to generate more steam, which in turn drives the generator to generate more electricity.

[0049] On the contrary, when the demand for electricity is small, the power plant can reduce the amount of coal input, which means that the coal in the combustion process can be burned more fully, and under more optimized combustion conditions, the coal combustion efficiency will be higher, and the waste coal slag produced will be relatively small, and its volume will be correspondingly reduced;

[0050] Therefore, by predicting the power generation of a thermal power plant, it is possible to determine whether the final amount of waste coal slag produced is large or small, and whether the volume of waste coal is large or small.

[0051] The central control unit 2 is used to formulate a reasonable crushing treatment strategy according to the predicted waste coal slag output and volume, and control the multi-stage crushing equipment 3 to perform corresponding crushing treatment on the waste coal slag;

[0052] That is, when the power generation of the thermal power station is large, resulting in a large output and volume of waste coal, the corresponding pulverization treatment strategy is: start each level of the multi-stage pulverization equipment 3, and pulverize the non-coal in sequence through the steps of coarse pulverization, fine grinding and fine grinding;

[0053] When the power generation of the thermal power station is stable and moderate, resulting in the production and volume of waste coal being at a medium level, the corresponding pulverization treatment strategy is: start the fine grinding unit 32 and the fine grinding unit 33 in the multi-stage pulverization equipment 3, and pulverize the non-coal in turn through the fine grinding and fine grinding steps;

[0054] When the power generation of the thermal power station is small, resulting in a small output and volume of waste coal, the corresponding crushing treatment strategy is: start the fine grinding unit 33 in the multi-stage crushing equipment 3 to crush the non-coal;

[0055] By formulating this processing strategy, each unit in the multi-stage crushing equipment 3 can be reasonably used for waste coal of different outputs, which not only ensures that the waste coal slag is fully crushed and processed, but also reduces energy waste accordingly.

[0056] The multi-stage pulverizing device 3 includes a coarse pulverizing unit 31, a fine grinding unit 32 and a fine grinding unit 33, wherein the coarse pulverizing unit 31, the fine grinding unit 32 and the fine grinding unit 33 are respectively used to perform coarse pulverization, fine grinding and fine grinding on the waste coal slag, and the coarse pulverizing unit 31, the fine grinding unit 32 and the fine grinding unit 33 are also used to realize the step-by-step transfer of the waste coal slag;

[0057] Among them, the process of step-by-step transfer of waste coal slag between the coarse crushing unit 31, the fine grinding unit 32 and the fine grinding unit 33 is as follows: the waste coal slag after passing through the coarse crushing unit 31 can directly enter the fine grinding unit 32, and the waste coal slag after passing through the fine grinding unit 32 can directly enter the fine grinding unit 33;

[0058] It should be noted that if the coarse pulverization step is not required in the pulverization treatment strategy, that is, the coarse pulverization unit 31 is not started, then the waste coal slag will still enter the coarse pulverization unit 31 after being sent out from the thermal power plant, but the coarse pulverization step is not required, and the waste coal slag will directly enter the fine grinding unit 32 after passing through the coarse pulverization unit 31;

[0059] If the pulverizing treatment strategy does not require a fine grinding step, the waste coal slag directly enters the fine grinding unit 32 after passing through the coarse pulverizing unit 31, and then enters the fine grinding unit 33 through the fine grinding unit 32;

[0060] Although the waste coal slag always needs to pass through the coarse crushing unit 31, the fine grinding unit 32 and the fine grinding unit 33, the crushing treatment strategy can determine whether a specific crushing treatment unit is started, thereby achieving the purpose of energy saving and emission reduction.

[0061] Example 2

[0062] The power generation prediction unit 1 includes a data collection module, a data preprocessing module, a model selection module, a model training and verification module and a model optimization module;

[0063] The data collection module is used to collect historical power generation data, weather data, holidays and special events, economic indicators and demographic data;

[0064] The historical power generation data includes: collecting hourly or daily power generation over the past 3-5 years;

[0065] Weather data, including temperature, humidity, wind speed, etc., can be obtained from weather stations;

[0066] Holidays and special events include recording the dates of annual statutory holidays, major events, etc.

[0067] Economic indicators include GDP growth rate, industrial production index, etc.;

[0068] Demographic data includes understanding the population size and distribution of the service area;

[0069] The above data covers the factors that can have a major impact on the power generation of thermal power plants; and these factors can constitute a data set;

[0070] The data preprocessing module is used to clean the data, create new features that are helpful for power generation prediction based on the cleaned data, and standardize the feature data;

[0071] The preprocessing process is aimed at the data set, and data cleaning is to remove or fill missing values, such as filling with the value of the previous moment or the average value;

[0072] The creation of new features is to generate new features by transforming and processing the original data to better capture the information in the data. The goal is to make it easier for subsequent mathematical models to learn patterns and laws in the data.

[0073] Standardization refers to converting the data set containing new features into a form with zero mean and unit variance so that the scales of different features are consistent.

[0074] Among them, Z-score standardization is generally used in processing;

[0075]

[0076] x is the target data, which can be feature data, μ is the mean value of the data set, and σ is the standard deviation of all data points in the entire data set;

[0077] or Mini-Max scaling,

[0078]

[0079] x is the data point in the data set that needs to be scaled, max(x) and min(x) are the minimum and maximum values ​​of the data set, respectively.

[0080] A plurality of power generation prediction models are preset in the model selection module;

[0081] These include the linear regression model, which is suitable for simple linear relationships; the support vector machine (SVM) model, which is suitable for nonlinear relationships; the random forest model, which is suitable for processing complex data sets and can automatically select important features; the gradient boosted tree (GBDT) model, an enhancement algorithm, which is suitable for large-scale data sets; and the long short-term memory network (LSTM) model, which is suitable for time series prediction and can capture temporal dependencies.

[0082] The model training and verification module divides the preprocessed data set into a training set, a verification set and a test set, evaluates the performance of each model based on the training set, the verification set and the test set, and determines the prediction model with the highest performance;

[0083] The training set is used to train the model so that the model can learn the mapping relationship between input data and output results. The validation set can evaluate the performance of the model during the training process and is used to adjust the model's hyperparameters and select the best model. The test set is used to finally evaluate the performance of the model after the model training and tuning are completed.

[0084] In particular, the training set, validation set and test set account for 70%, 15% and 15% respectively;

[0085] In addition, when evaluating the performance of each model, the cross-validation method is first used to verify the error of each model, where the K-fold cross-validation formula is:

[0086]

[0087] k is the number of cross-validation folds, that is, the data set is divided into k subsets, E i is the validation error of the i-th fold;

[0088] The mean square error and mean absolute error are then used to evaluate the performance of the model.

[0089] The model optimization module adjusts the hyperparameters of the corresponding models according to the prediction models determined by the training and verification modules, obtains the optimized prediction models, and substitutes the cleaned data to obtain the predicted power generation of the thermal power plant;

[0090] Among them, hyperparameters are those parameters that are not learned by the model during the training process and need to be set manually, so that the model can achieve the best performance on the validation set by adjusting the hyperparameters. In addition, the model optimization module uses a grid search or random search method to find the optimal hyperparameters of the prediction model determined in the model training and validation module.

[0091] As needed, the power prediction unit also includes a deployment and monitoring module, which is used to deploy the optimized prediction model into actual applications and regularly check the deviation between the prediction results of the prediction model and the actual situation; and is used to feedback and verify the accuracy of the calculation results in the prediction model. If the accuracy decreases, the prediction model will be modified in a timely manner.

[0092] Example 3

[0093] The central control unit includes a data receiving module, a CPU and a crushing processing strategy generating module;

[0094] The data receiving module is used to receive the power generation prediction value output by the power generation prediction unit 1;

[0095] The CPU has multiple thresholds preset in it, and is used to compare the power generation prediction value with the thresholds;

[0096] The threshold setting includes: setting multiple thresholds, such as low load threshold, medium load threshold and high load threshold, based on historical data and experience; then comparing the power generation forecast value and the threshold through simple logical judgment such as if-else statement to determine the current power load situation;

[0097] The pulverizing strategy generation module is used to generate a corresponding pulverizing strategy according to the comparison result between the power generation prediction value and the threshold value, wherein the pulverizing strategy is used to control the working states of the coarse pulverizing unit 31 , the fine grinding unit 32 and the fine grinding unit 33 .

[0098] Example 4

[0099] Combined with Figure 3 The coarse crushing unit 31 includes a first material chute 311, a first gantry 312 and a crushing hammer 313;

[0100] The feeding end of the first feeding chute 311 is used to receive the waste coal slag. The first feeding chute 311 is fixedly provided with a first gantry 312. A telescopic driving member 314 is fixedly installed on the top of the first gantry 312. The telescopic driving member 314 is fixedly connected to the top of the support leg 315.

[0101] After the bottom of the support leg 315 passes through the top of the first gantry 312, the waste coal slag is connected to the crushing hammer 313, which is located above the trough surface of the material trough;

[0102] The telescopic driving member 314 is telescopically driven to synchronously drive the legs 315 and the crushing hammer 313 to perform upward and downward movements, so that the crushing hammer 313 pound and crush the waste coal slag in the first feeding chute 311; it should be noted that the legs 315 are also door-shaped structures, and the cross bars of the legs 315 are fixedly connected to the telescopic driving member 314, and the two vertical bars of the legs 315 are located on both sides of the telescopic driving member 314, and after passing through the top of the first door-shaped bracket, they are correspondingly connected to the two ends of the crushing hammer 313;

[0103] In addition, combined with Figure 4 The crushing hammer 313 is configured to be columnar, and a plurality of protrusions 316 are evenly arranged on the surface of the columnar crushing hammer 313. Based on this structure, a through hole is provided at the bottom of the two vertical rods of the support leg 315, so that the connecting columns at both ends of the columnar crushing hammer 313 can cooperate with the through hole, so that the columnar crushing hammer 313 can rotate freely; then when the crushing hammer 313 moves up and down to crush the waste coal slag, it can also rotate randomly, so that the surface of different parts of the crushing hammer 313 is used to crush the waste coal slag, thereby improving the overall service life of the crushing hammer 313; in addition, the protrusions 316 on the surface of the columnar crushing hammer 313 can improve the efficiency of the primary crushing of the waste coal slag.

[0104] As required, the fine grinding unit 32 includes a second feed chute 321, a diverter block 322, a grinding roller 323, a second gantry 324, a stopper 326 and a spring 327. The feed end of the second feed chute 321 is used to receive the coarsely crushed waste coal slag output by the first feed chute 311. The second feed chute 321 is fixedly provided with a second gantry 324.

[0105] The diverter block 322 is used to guide the waste coal slag in the feeding trough to the two sides of the diverter block 322. A bidirectional motor 328 is installed in the diverter block 322. The two driving shafts of the bidirectional motor 328 are respectively connected to a grinding roller 323. A guide rod 325 is fixedly provided on the top surface of the diverter block 322. The head end of the guide rod 325 passes through the second door frame 324 and is fixedly connected to the limit block 326.

[0106] The rod body of the guide rod 325 is sleeved with a spring 327, and the two ends of the spring 327 are respectively fixedly connected to the second door frame 324 and the diverter block 322;

[0107] The diverter block 322 has one end face facing the feed end of the second feed trough 321 in a triangular shape, and one of the corners of the triangle is used to separate the waste coal slag flowing toward the diverter block 322, thereby leading it to the two sides of the diverter block 322, namely, the two grinding rollers 323. The grinding rollers 323 are driven to rotate by a bidirectional motor 328 to achieve secondary fine grinding of the waste coal slag. At the same time, the diverter block 322 and the grinding roller 323 can have a higher downward pressure under the action of the spring 327, thereby having a certain crushing effect on the waste coal slag and improving the effect of fine grinding.

[0108] In addition, the fine grinding unit 33 is a grinding disc structure, which, as a three-stage fine grinding step, can grind the waste coal slag into extremely small particles.

[0109] It should be noted that the first feeding chute 311 and the second feeding chute 321 are right-angled U-shaped plate structures, that is, the cross-sections of the two feeding chutes are right-angled U-shaped, and the two feeding chutes are parallel and inclined to each other, so that the waste coal slag can automatically move along the feeding chute under the action of gravity, and be subjected to primary crushing or secondary fine grinding by the crushing hammer 313 or the grinding roller 323 during the movement.

[0110] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A multi-layer waste coal slag crushing system based on power generation prediction, characterized in that: It comprises a power generation prediction unit (1), a central control unit (2) and a multi-stage crushing device (3); The power generation prediction unit (1) is used to predict the power generation of the thermal power plant, thereby predicting the output and volume of waste coal slag produced by the thermal power plant; The central control unit (2) is used to formulate a reasonable crushing treatment strategy according to the predicted output and volume of the waste coal slag, and control the multi-stage crushing equipment (3) to perform corresponding crushing treatment on the waste coal slag; The multi-stage pulverizing device (3) comprises a coarse pulverizing unit (31), a fine grinding unit (32) and a fine grinding unit (33), wherein the coarse pulverizing unit (31), the fine grinding unit (32) and the fine grinding unit (33) are respectively used to perform coarse pulverizing, fine grinding and fine grinding treatments on the waste coal slag, and the coarse pulverizing unit (31), the fine grinding unit (32) and the fine grinding unit (33) are also used to realize the step-by-step transfer of the waste coal slag.

2. The multi-layer waste coal slag crushing system based on power generation prediction according to claim 1, characterized in that: The power generation prediction unit (1) comprises a data collection module, a data preprocessing module, a model selection module, a model training and verification module and a model optimization module; The data collection module is used to collect historical power generation data, weather data, holidays and special events, economic indicators and demographic data; The data preprocessing module is used to clean the data, create new features that are helpful for power generation prediction based on the cleaned data, and standardize the feature data; A plurality of power generation prediction models are preset in the model selection module; The model training and verification module divides the preprocessed data set into a training set, a verification set and a test set, evaluates the performance of each model based on the training set, the verification set and the test set, and determines the prediction model with the highest performance; The model optimization module adjusts the hyperparameters of the corresponding models according to the prediction models determined by the training and verification modules, obtains the optimized prediction models, and substitutes the cleaned data to obtain the predicted power generation of the thermal power plant.

3. The multi-layer waste coal slag crushing system based on power generation prediction according to claim 2, characterized in that: The training set, validation set and test set account for 70%, 15% and 15% respectively.

4. The multi-layer waste coal slag crushing system based on power generation prediction according to claim 2, characterized in that: The model optimization module uses a grid search or random search method to find the optimal hyperparameters of the prediction model determined in the model training and validation module.

5. The multi-layer waste coal slag crushing system based on power generation prediction according to claim 2, characterized in that: The power generation prediction unit (1) also includes a deployment and monitoring module, which is used to deploy the optimized prediction model to actual applications and regularly check the deviation between the prediction results of the prediction model and the actual situation.

6. The multi-layer waste coal slag crushing system based on power generation prediction according to claim 1, characterized in that: The central control unit (2) comprises a data receiving module, a CPU and a crushing processing strategy generating module; The data receiving module is used to receive the power generation prediction value output by the power generation prediction unit (1); The CPU has multiple thresholds preset in it, and is used to compare the power generation prediction value with the thresholds; The pulverizing process strategy generation module is used to generate a corresponding pulverizing process strategy according to a comparison result between the power generation prediction value and a threshold value, wherein the pulverizing process strategy is used to control the working states of the coarse pulverizing unit (31), the fine grinding unit (32) and the fine grinding unit (33).

7. The multi-layer waste coal slag crushing system based on power generation prediction according to claim 1, characterized in that: The coarse crushing unit (31) comprises a first material chute (311), a first gantry (312) and a crushing hammer (313); The feeding end of the first feeding chute (311) is used to receive waste coal slag, the first feeding chute (311) is fixedly provided with a first door-shaped frame (312), the top of the first door-shaped frame (312) is fixedly installed with a telescopic driving member (314), and the telescopic driving member (314) is fixedly connected to the top of the support leg (315); The bottom of the supporting leg (315) passes through the top of the first door frame (312) and is connected to the crushing hammer (313) respectively. The crushing hammer (313) is located above the trough surface of the first material trough (311).

8. The multi-layer waste coal slag crushing system based on power generation prediction according to claim 7, characterized in that: The crushing hammer (313) is configured to be columnar, and a plurality of protrusions (316) are evenly arranged on the surface of the columnar crushing hammer (313).

9. The multi-layer waste coal slag crushing system based on power generation prediction according to claim 7, characterized in that: The fine grinding unit (32) comprises a second feeding chute (321), a diverter block (322), a grinding roller (323), a second gantry (324), a limit block (326) and a spring (327); the feeding end of the second feeding chute (321) is used to receive the coarsely crushed waste coal slag output by the first feeding chute (311); the second feeding chute (321) is fixedly provided with the second gantry (324); The diverter block (322) is used to guide the waste coal slag in the material trough to the two sides of the diverter block (322). A bidirectional motor (328) is installed in the diverter block (322). The two driving shafts of the bidirectional motor (328) are respectively connected to a grinding roller (323). A guide rod (325) is fixedly provided on the top surface of the diverter block (322). The head end of the guide rod (325) passes through the second door frame (324) and is fixedly connected to the limit block (326). The rod body of the guide rod (325) is sleeved with a spring (327), and the two ends of the spring (327) are respectively fixedly connected to the second door-shaped frame (324) and the diverter block (322).

10. The multi-layer waste coal slag crushing system based on power generation prediction according to claim 1, characterized in that: The fine grinding unit (33) is a grinding disc structure.

Images