A dynamic balancing adjustment method for a coal mill

Abstract

The application belongs to the field of coal mills, and particularly discloses a dynamic balance adjusting method for a coal mill, which comprises the following steps: S1, acquiring actual pulverized coal speeds of each powder pipe of the coal mill; S2, determining a target speed under a current coal quantity according to a function model; S3, calculating a speed deviation of each powder pipe; S4, sending a shrink-hole adjusting command to each powder pipe according to the speed deviation, acquiring new actual pulverized coal speeds of each powder pipe of the coal mill, and calculating an average value; and S5, calculating a new speed deviation of each powder pipe according to the average value and the actual pulverized coal speed. The application quantifies the gap between the performance of each powder pipe and the target by establishing a relationship model of the coal quantity and the expected pulverized coal speed, adjusts the shrink hole of the powder pipe according to the gap to achieve the target level, then re-monitors and calculates the new actual pulverized coal speed, updates the actual pulverized coal speed, and makes the actual pulverized coal speed gradually close to the expected value, so that the coal mill can work under the best working condition.

Description

Technical Field

[0001] This invention belongs to the field of coal mills, and specifically relates to a method for dynamic balance adjustment of coal mills. Background Technology

[0002] Coal mills play a crucial role in industrial sectors such as thermal power plants. During the coal pulverization process, the performance of the coal mill directly affects the operating efficiency and economy of the power plant. The uniformity of the coal powder velocity in its pulverizing pipe has a significant impact on combustion efficiency, equipment stability, and other aspects.

[0003] Existing methods for adjusting the pulverized coal speed in coal mill pulverizer tubes mostly rely on experience or fixed parameters, making it difficult to dynamically balance and adjust the speed according to the actual operating conditions of the coal mill in real time. This results in significant differences in the pulverized coal speed in each tube, affecting combustion stability and efficiency, and increasing energy consumption. Summary of the Invention

[0004] The purpose of this invention is to provide a dynamic balance adjustment method for coal mills, in order to solve the problem that the coal powder speed adjustment methods in the coal mill pulverizer tubes mentioned in the background art rely heavily on experience or fixed parameters and cannot adapt to changes in operating conditions in real time.

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

[0006] A method for dynamic balance adjustment of a coal mill, comprising:

[0007] S1. Obtain the actual coal powder velocity of each powder pipe of the coal mill;

[0008] S2. Define a functional model of coal quantity and expected coal powder velocity, and determine the target velocity under the current coal quantity based on the functional model;

[0009] S3. Calculate the speed deviation of each powder tube based on the target speed under the current coal quantity and the actual coal powder speed of each powder tube;

[0010] S4. Send a shrinkage adjustment command to each powder tube according to the speed deviation, obtain the new actual coal powder speed of each powder tube of the coal mill, and calculate the average value.

[0011] S5. Calculate the new speed deviation of each powder tube based on the average value and the actual coal powder speed, and send a shrinkage adjustment command to each powder tube based on the new speed deviation.

[0012] Preferably, the expression for the functional model defining the coal quantity and the expected coal powder velocity is:

[0013] V s =f(m)

[0014] Among them, V sLet f(m) represent the expected coal powder velocity, m represent the coal quantity, and f(m) represent the piecewise linear function.

[0015] Preferably, the expression for calculating the speed deviation of each powder tube based on the target speed under the current coal quantity and the actual coal powder speed of each powder tube is as follows:

[0016] ΔV i =V s -V i

[0017] V i (i = 1, 2, ..., 10)

[0018] Where, ΔV i V represents the speed deviation. s V represents the expected coal powder velocity. i This represents the actual coal powder velocity of each powder tube, where i represents a specific powder tube.

[0019] Preferably, the orifice adjustment command includes adjusting the opening of the powder pipe regulating valve.

[0020] Preferably, the functional model defining the coal quantity and the expected coal powder velocity includes a long short-term memory model constructed based on the coal quantity and the expected coal powder velocity, comprising:

[0021] A large amount of historical operating data and experimental data of coal mills under different operating conditions are obtained. The historical operating data and experimental data include coal quantity and corresponding expected coal powder speed. The historical operating data and experimental data are divided into training set, validation set and test set.

[0022] A long short-term memory model is constructed, and the constructed long short-term memory model is trained using the training set data. After a certain number of training rounds, the long short-term memory model is validated using the validation set data.

[0023] The trained long short-term memory model is evaluated using the test set data. When the evaluation result of the long short-term memory model shows that the performance meets the requirements, the coal quantity and the expected coal powder speed of the current coal mill are obtained in real time and input into the trained long short-term memory model to calculate the coal quantity and the expected coal powder speed at the next moment.

[0024] By inputting the coal quantity and expected coal powder velocity at the next moment into a piecewise linear function, the dynamically adjusted target velocity is obtained.

[0025] Preferably, training the constructed long short-term memory model using the training set data includes:

[0026] The training set data is input into the long short-term memory model according to a batch size, a predicted value is calculated through forward propagation, a loss value is calculated according to a loss function, and then the parameters of the model are updated through a back propagation algorithm, so that the loss value is continuously reduced.

[0027] Preferably, the loss function is mean square error, and if the validation set loss value does not decrease for consecutive rounds, it is considered that the model may be over-fitted, and the training is stopped.

[0028] Preferably, the using the test set data to evaluate the trained long short-term memory model comprises:

[0029] Calculating whether the mean square error and the mean absolute error index of the long short-term memory model on the test set meet the requirements.

[0030] The application also provides a computer, comprising:

[0031] a storage for storing executable instructions;

[0032] a processor configured to execute the instructions to implement the steps of the coal mill dynamic balance adjustment method.

[0033] The application also provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the steps of the coal mill dynamic balance adjustment method.

[0034] Compared with the prior art, the application has the following beneficial effects:

[0035] The application can quickly calculate the target speed for different coal quantities by establishing a relationship model of coal quantity and expected pulverized coal speed, quantifies the gap between the performance of each powder pipe and the target, adjusts the powder pipe according to the gap to achieve the target level, then re-monitors and calculates a new actual pulverized coal speed, obtains an average value, updates the actual pulverized coal speed, and gradually approaches the expected value, so that the coal mill can work in the best working condition, and through re-calculation and adjustment, the coal mill can maintain dynamic balance and adapt to different working environments and coal types. BRIEF DESCRIPTION OF DRAWINGS

[0036] In order to more clearly illustrate the technical solutions of the embodiments of the application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the application, and other drawings can be obtained by those skilled in the art without creative labor. Among them:

[0037] Figure 1 The method steps of the application are shown in the block diagram. DETAILED DESCRIPTION

[0038] In order to make the above objectives, features and advantages of the present application more clear and comprehensible, specific embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0039] In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application. However, it will be apparent to one skilled in the art that the present application can be practiced without the specific details given herewith. In other instances, well-known methods have not been described in detail in order to avoid obscuring the present application. Therefore, the present application is not intended to be limited by the specific embodiments disclosed below, but is to be accorded the widest scope consistent with the principles and features disclosed herein.

[0040] Secondly, the "one embodiment" or "embodiment" referred to herein means that the specific features, structures or characteristics can be included in at least one implementation of the present application. The "in one embodiment" appearing in different places in the specification does not mean the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments.

[0041] As shown in the accompanying drawings: Figure 1

[0042] Embodiment one: the embodiment provides a coal mill dynamic balance adjustment method, comprising:

[0043] S1, obtaining the actual pulverized coal speed of each powder pipe of the coal mill;

[0044] S2, defining a function model of coal quantity and expected pulverized coal speed, and determining the target speed under the current coal quantity according to the function model;

[0045] S3, calculating the speed deviation of each powder pipe according to the target speed under the current coal quantity and the actual pulverized coal speed of each powder pipe;

[0046] S4, sending the shrink hole adjustment command to each powder pipe according to the speed deviation, and obtaining the new actual pulverized coal speed of each powder pipe of the coal mill, and calculating the average value;

[0047] S5, calculating the new speed deviation of each powder pipe according to the average value and the actual pulverized coal speed, and sending the shrink hole adjustment command to each powder pipe according to the new speed deviation.

[0048] ​The actual pulverized coal speed of the powder pipe is monitored by the sensor to evaluate the current operation state of the coal mill and the dynamic adjustment requirement. By establishing a model of the relationship between the coal quantity and the expected pulverized coal speed, the target speed can be quickly calculated for different coal quantities. By quantifying the gap between the performance of each powder pipe and the target, a basis is provided for the subsequent adjustment. The opening of the powder pipe adjustment valve is adjusted to achieve the target level. Then, the new actual pulverized coal speed is monitored and calculated again, and the average value is obtained to update the actual pulverized coal speed, so that it gradually approaches the expected value, ensuring that the coal mill works in the best condition. By calculating and adjusting again, it is ensured that the coal mill can maintain a dynamic balance and adapt to different working environments and coal types.

[0049] The expression of the function model defining the coal quantity and the expected pulverized coal speed is:

[0050] V s =f(m)

[0051] wherein V s represents the expected pulverized coal speed, m represents the coal quantity, and f(m) represents a broken line function.

[0052] The expression of the speed deviation of each powder pipe calculated according to the target speed under the current coal quantity and the actual pulverized coal speed of each powder pipe is:

[0053] ΔV i =V s -V i

[0054] V i (i=1,2,…,10)

[0055] wherein ΔV i represents the speed deviation, V s represents the expected pulverized coal speed, V i represents the actual pulverized coal speed of each powder pipe, and i represents a certain powder pipe.

[0056] The shrinkage adjustment command includes adjusting the opening of the powder pipe adjustment valve.

[0057] As can be seen from the above, the corresponding target speed under the current coal quantity is determined by the function relationship between the coal quantity and the expected pulverized coal speed of the coal mill. By comparing the target speed with the actual speed measured by the pulverized coal online detection device, the deviation of each powder pipe is calculated to adjust the pulverized coal adjustment valve, so as to control the speed of each powder pipe.

[0058] On this basis, the average value of the pulverized coal speed of all pipes is calculated in real time as a set value. The measured speed of each powder pipe is compared with the set value, and the deviation of each powder pipe is calculated to adjust the pulverized coal adjustment valve, so as to control the speed of each powder pipe.

[0059] Embodiment two: this embodiment is basically the same as the previous embodiment, the difference is that the function model of defining the coal quantity and the expected coal powder speed includes a long short-term memory model constructed based on the coal quantity and the expected coal powder speed, including:

[0060] A large amount of historical running data and experimental data of the coal mill under different working conditions are obtained, and the historical running data and experimental data include coal quantity and corresponding expected coal powder speed, the historical running data and experimental data are divided into training set, validation set and test set;

[0061] A long short-term memory model is constructed, and the training set data is used to train the constructed long short-term memory model, and the validation set data is used to verify the long short-term memory model after training for a certain number of rounds;

[0062] The trained long short-term memory model is evaluated using test set data, and when the long short-term memory model evaluation result shows that the performance meets the requirements, the current coal quantity and expected coal powder speed of the coal mill are obtained in real time and input into the trained long short-term memory model to calculate the coal quantity and expected coal powder speed at the next moment;

[0063] LSTM prediction:

[0064] In the model, given the past coal quantity data and coal powder speed, the LSTM will output the predicted value at the next moment

[0065]

[0066] Wherein, represents the coal powder speed predicted by the LSTM model, that is, the predicted value at the next moment, LSTM(x t ) represents passing the input data of the current moment x t to the LSTM model for prediction;

[0067] The coal quantity and expected coal powder speed at the next moment are input into the polyline function to obtain the dynamically adjusted target speed;

[0068] Polyline function adjustment output:

[0069]

[0070] Wherein, V s , final represents the final adjusted coal powder speed, the result after modification of the polyline function, represents the current real-time coal quantity value, which is input into the polyline function and updated according to the real-time data, V s represents the expected coal powder speed under the current coal quantity, m represents the current coal quantity, which is input into the polyline function, m1, m2, m3 represent the segment threshold of the polyline function, which represents different coal quantity ranges, and Vs1 , V s2 , V s3 The target coal powder speed under m1, m2 and m3 respectively corresponding to the speed value of each segment.

[0071] Specifically, training the constructed long short-term memory model using the training set data includes:

[0072] The training set data is input into the long short-term memory model according to a certain batch size, the predicted value is calculated through forward propagation, the loss value is calculated according to the loss function, and then the parameters of the model are updated through the back propagation algorithm, so that the loss value is continuously reduced.

[0073] Specifically, the loss function is mean square error, and when the loss value of the validation set no longer decreases for a plurality of consecutive rounds, it is considered that the model may be over-fitted, and the training is stopped.

[0074] Specifically, evaluating the trained long short-term memory model using the test set data includes:

[0075] Whether the mean square error and the mean absolute error index of the long short-term memory model on the test set meet the requirements is calculated.

[0076] As can be seen from the above, by combining the prediction ability of the broken line function and the LSTM model, the ability of the LSTM to process time series data ensures the prediction accuracy of the model and captures the dynamic changes in the time series, adapts to the rapidly changing working conditions, while the flexibility of the broken line function allows the model output to be adjusted at any time in practical application, which can well adapt to the changing demand of coal quantity and coal powder speed, realizes efficient dynamic adjustment of coal powder speed, and makes the dynamic adjustment of the coal mill more efficient and accurate.

[0077] The integrated model can better balance the running state of the coal mill, optimize the coal powder speed, improve the work efficiency, and reduce the energy consumption.

[0078] In order to achieve the above purpose, the present application also provides a computer, which comprises:

[0079] A storage for storing executable instructions;

[0080] A processor configured to execute the instructions to implement the steps of the above-mentioned coal mill dynamic balance adjustment method.

[0081] In order to achieve the above purpose, the present application also provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the steps of the above-mentioned coal mill dynamic balance adjustment method.

[0082] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a computer-readable storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a terminal device to enter the methods described in the various embodiments of the present invention.

[0083] It is important to note that the constructions and arrangements of this application shown in several different exemplary embodiments are merely illustrative. Although only a few embodiments are described in detail in this disclosure, those who consult this disclosure will readily understand that many modifications are possible (e.g., changes in the size, dimensions, structure, shape, and proportions of various elements, as well as parameter values ​​(e.g., temperature, pressure, etc.), mounting arrangements, use of materials, color, orientation, etc.) without substantially departing from the novel teachings and advantages of the subject matter described in this application). For example, an element shown as integrally formed may be composed of multiple parts or elements, the position of elements may be inverted or otherwise altered, and the nature or number or position of discrete elements may be changed or altered. Therefore, all such modifications are intended to be included within the scope of the invention. The order or sequence of any process or method steps may be changed or rearranged according to alternative embodiments. In the claims, any "device plus function" clause is intended to cover the structure performing the function described herein, and not only structural equivalents but also equivalent structures. Other substitutions, modifications, alterations, and omissions may be made in the design, operation, and arrangement of the exemplary embodiments without departing from the scope of the invention. Therefore, the present invention is not limited to the specific embodiments, but extends to various modifications that still fall within the scope of the appended claims.

[0084] Furthermore, in order to provide a concise description of exemplary embodiments, not all features of actual embodiments (i.e., those features that are not relevant to the best mode of carrying out the invention as currently considered, or those features that are not relevant to implementing the invention) may be omitted.

[0085] It should be understood that numerous specific implementation decisions can be made during the development of any practical implementation, such as in any engineering or design project. Such development efforts may be complex and time-consuming, but for those skilled in the art who benefit from this disclosure, the development effort will be a routine work of design, manufacturing, and production without requiring much experimentation.

[0086] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for dynamic balance adjustment of a coal mill, characterized in that, include: S1. Obtain the actual coal powder velocity of each powder pipe of the coal mill; S2. Define a functional model of coal quantity and expected coal powder velocity, and determine the target velocity under the current coal quantity based on the functional model; S3. Calculate the speed deviation of each powder tube based on the target speed under the current coal quantity and the actual coal powder speed of each powder tube; S4. Send a shrinkage adjustment command to each powder tube according to the speed deviation, obtain the new actual coal powder speed of each powder tube of the coal mill, and calculate the average value. S5. Calculate the new speed deviation of each powder tube based on the average value and the actual coal powder speed, and send a shrinkage adjustment command to each powder tube based on the new speed deviation; The expression for the functional model defining the coal quantity and the expected coal powder velocity is as follows: ； in, Indicates the expected coal powder speed. Indicates the amount of coal. This represents a piecewise linear function.

2. The method for dynamic balance adjustment of a coal mill according to claim 1, characterized in that, The expression for calculating the speed deviation of each pulverizer tube based on the target speed under the current coal quantity and the actual coal powder speed of each pulverizer tube is as follows: ； ； in, Indicates speed deviation, Indicates the expected coal powder speed. This represents the actual coal powder velocity of each powder tube, where i represents a specific powder tube.

3. The method for dynamic balance adjustment of a coal mill according to claim 1, characterized in that, The orifice reduction adjustment command includes adjusting the opening degree of the powder pipe regulating valve.

4. The method for dynamic balance adjustment of a coal mill according to claim 1, characterized in that, The functional model defining the coal quantity and expected coal powder velocity includes a long short-term memory model based on the coal quantity and expected coal powder velocity, comprising: A large amount of historical operating data and experimental data of coal mills under different operating conditions are obtained. The historical operating data and experimental data include coal quantity and corresponding expected coal powder speed. The historical operating data and experimental data are divided into training set, validation set and test set. A long short-term memory model is constructed, and the constructed long short-term memory model is trained using the training set data. After a certain number of training rounds, the long short-term memory model is validated using the validation set data. The trained long short-term memory model is evaluated using the test set data. When the evaluation result of the long short-term memory model shows that the performance meets the requirements, the coal quantity and the expected coal powder speed of the current coal mill are obtained in real time and input into the trained long short-term memory model to calculate the coal quantity and the expected coal powder speed at the next moment. By inputting the coal quantity and expected coal powder velocity at the next moment into a piecewise linear function, the dynamically adjusted target velocity is obtained.

5. The method for dynamic balance adjustment of a coal mill according to claim 4, characterized in that, The step of training the constructed long short-term memory model using the training set data includes: The training set data is input into the long short-term memory model according to a certain batch size. The predicted value is calculated through forward propagation, and the loss value is calculated according to the loss function. Then, the parameters of the model are updated through the backpropagation algorithm, so that the loss value is continuously reduced.

6. The method for dynamic balance adjustment of a coal mill according to claim 5, characterized in that, The loss function is the mean squared error. If the loss value on the validation set no longer decreases after several consecutive rounds, the model is considered to be overfitting, and training is stopped.

7. The method for dynamic balance adjustment of a coal mill according to claim 6, characterized in that, The evaluation of the trained Long Short-Term Memory model using the test set data includes: Calculate whether the mean squared error and mean absolute error of the long short-term memory model on the test set meet the requirements.

8. A computer, characterized in that, The computer includes: Storage, used to store executable instructions; The processor is configured to execute the instructions to implement the steps of a dynamic balance adjustment method for a coal mill as described in any one of claims 1-7.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of a dynamic balance adjustment method for a coal mill as described in any one of claims 1-7.

Images