Capacity control system and method based on air volume and air pressure of pulverizer system

Abstract

The invention provides a productivity control system and control method based on air volume and air pressure of a pulverizer system, and is applied to the technical field of material pulverizing, the productivity control system comprises an abnormity monitoring module, and the abnormity monitoring module comprises a screen abnormity monitoring unit and a low-efficiency operation monitoring unit; the screen abnormity monitoring unit is used for judging whether the screen has a blocking trend or not, and if the screen has the blocking trend, the blocking trend is fed back to the capacity adjusting module so as to reduce the feeding amount of the crusher; the low-efficiency operation monitoring unit is used for judging whether the pulverizer has a low-efficiency operation condition or not, and if the pulverizer has the low-efficiency operation condition, the low-efficiency operation condition is fed back to the capacity adjusting module to increase the feeding amount of the pulverizer; and the abnormity monitoring module judges whether a screen of the crusher has a blocking trend according to the real-time data acquired by the data acquisition module, on the basis of ensuring that the screen is not blocked, the minimum airflow required by crushing and transportation is kept, a motor of the crusher operates at the maximum load at the moment, and the feeding amount of the crusher is adjusted to realize the maximum productivity.

Description

Technical Field

[0001] The present invention belongs to the technical field of material crushing, and in particular relates to a production capacity control system and a control method based on the air volume and air pressure of a crusher system. Background Art

[0002] like Figure 1 As shown, the current material crushing system includes a buffer bin, a feeder, a hammer mill and a fan. In the material crushing process, grains or coarse granular materials are stored in the buffer bin above the hammer mill, discharged through the feeder, and sent into the air flow and into the hammer mill. The material collides inelastically with the hammer with a speed of up to 110 m / s. The particles hit by the hammer will burst into a cloud of dust and moisture. The impact generates destructive energy and heat. The air will heat up due to energy dissipation. The evaporated moisture will be absorbed by the air. The fine dust and moisture are carried away by the prescribed airflow, while the larger particles rebound from the screen and are hit again.

[0003] During this process, products with high fat content can cause the screen holes to become clogged, which increases resistance, reduces airflow and causes temperatures to rise. The increased temperature causes the product to become more elastic, which reduces grinding efficiency and causes the temperature to rise further.

[0004] In actual production, when the working efficiency of the crusher is low, the operator relies on experience to increase the material entering the crushing chamber. However, due to the different characteristics of the processed materials, relying solely on manual experience has low accuracy, which may cause the screen to be blocked, the crusher to stop abnormally, and cause the entire production line to stagnate. There are problems such as reduced productivity and unstable production capacity, making it difficult to optimize production capacity in real time. Summary of the invention

[0005] In view of the above-mentioned problems in the prior art, the purpose of the present invention is to provide a production capacity control system based on the air volume and pressure of the crusher system. By monitoring the air volume and pressure of the wind network, it is determined whether the screen has a tendency to be blocked. While ensuring that the screen is not blocked, the minimum airflow required for crushing and transportation is maintained, and the motor is operated at the maximum load at this time to maximize production capacity.

[0006] A production capacity control system based on the air volume and air pressure of a pulverizer system, comprising:

[0007] Data acquisition module, used to obtain motor energy consumption data, wind network operation data and material production data in real time during the actual production process;

[0008] The capacity prediction module is used to calculate the predicted value of the real-time optimal capacity of the crusher based on the actual data collected by the data collection module and the capacity prediction model;

[0009] Abnormal monitoring module, including screen abnormality monitoring unit and inefficient operation monitoring unit;

[0010] The screen abnormality monitoring unit is used to determine whether the screen of the pulverizer has a tendency to be blocked according to the collected wind network operation data, and if the screen has a tendency to be blocked, feedback is given to the capacity adjustment module to reduce the feed amount of the pulverizer;

[0011] The inefficient operation monitoring unit is used to determine whether the pulverizer is inefficiently operated according to the collected motor energy consumption data and material production data. If the pulverizer is inefficiently operated, the inefficient operation monitoring unit feeds back to the capacity adjustment module to increase the feed amount of the pulverizer.

[0012] The capacity adjustment module is used to dynamically adjust the feed rate of the crusher according to the feedback information of the abnormal monitoring module;

[0013] The abnormal monitoring module determines whether the screen of the crusher has a tendency to be blocked based on the real-time data collected by the data acquisition module. On the basis of ensuring that the screen is not blocked, it maintains the minimum airflow required for crushing and transportation, and makes the motor of the crusher run at the maximum load at this time, and adjusts the feed amount of the crusher to maximize production capacity.

[0014] Preferably, the motor energy consumption data includes motor current and motor voltage; the wind network operation data includes air volume, wind pressure and time of the test section; and the material production data includes actual material fineness and actual material output.

[0015] Preferably, the screen abnormality monitoring unit compares the actual data of the wind network wind pressure and wind network air volume collected by the data acquisition module with the screen blockage abnormality threshold. If the actual data of the wind network wind pressure and wind network air volume are greater than the screen blockage abnormality threshold, it is judged that the current grinder has an abnormal trend of screen blockage.

[0016] Preferably, the inefficient operation monitoring unit compares the actual motor energy consumption data and actual production capacity data collected by the data acquisition module with the inefficient production abnormality threshold. If the actual motor energy consumption data and actual production capacity data are less than the inefficient production abnormality threshold, it is determined that the current crusher has an inefficient operation abnormality.

[0017] Preferably, it also includes a model optimization module, which is used to record the actual data collected by the data acquisition module and compare the actual material output with the predicted value of the capacity prediction module, and record the difference data; optimize and train the capacity prediction module according to the recorded real-time data to improve the accuracy of the capacity prediction model.

[0018] Preferably, the process of building the capacity prediction model is as follows: constructing the capacity prediction model through the collected sample data; and calibrating the capacity prediction model under no-load conditions; the sample data includes motor current I, wind network wind pressure P, and wind network air volume Q, and the sample data is divided into training set data and verification set data, and the initial prediction model is constructed through the training set data, and the accuracy of the initial prediction model is verified through iterative calculation of the verification set data, thereby obtaining the final capacity prediction model.

[0019] Preferably, the capacity prediction model is constructed by a numerical prediction algorithm, and the specific construction process is as follows:

[0020] The corresponding relationship between the motor current I, the wind network wind pressure P, the wind network air volume Q and the actual material output in the training set data is fitted by a data prediction algorithm to construct an initial prediction model;

[0021] Set the input variables of the capacity forecast model to [X1, X2, X3] = [I, P, Q], and the output variable to the optimal capacity forecast value Y. The optimal capacity forecast value Y is calculated by the ReLU activation function. Among them, ω i is the weight, b is the bias, and the weight and bias are continuously optimized to minimize the error of the fitting result;

[0022] The initial prediction model is iteratively trained using the validation set data to achieve verification, and the difference between the predicted value and the actual value is calculated. If the difference exceeds the set range, the model structure is adjusted or retrained to obtain a verified model until the prediction result of the capacity forecast model meets the error requirements.

[0023] Another object of the present invention is to provide a capacity control method based on the air volume and air pressure of a pulverizer system, which is applicable to a pulverizer control system including a screen, and specifically comprises the following steps:

[0024] Obtain motor energy consumption data, wind network operation data, and material production data during the actual production process;

[0025] According to the actual data obtained, the predicted value of the real-time optimal production capacity of the crusher is calculated based on the production capacity prediction model;

[0026] In the actual production process, determine whether the crusher screen has a tendency to be blocked and whether the crusher is operating inefficiently, and adjust the crusher feed rate based on the judgment results;

[0027] Record the motor energy consumption data, wind network operation data, and material production data during the actual production process, compare the actual material output with the predicted value of the optimal production capacity, record the difference data, and optimize the production capacity prediction module based on the recorded real-time data to improve the accuracy of the production capacity prediction model.

[0028] Preferably, the motor energy consumption data includes motor current and motor voltage; the wind network operation data includes air volume, wind pressure and time of the test section; and the material production data includes actual material fineness and actual material output.

[0029] Preferably, it is determined whether the screen of the pulverizer has a tendency to be blocked according to the collected wind network operation data. If the screen of the pulverizer has a tendency to be blocked, the feed amount of the pulverizer is reduced to avoid the pulverizer feed amount being too large and causing the screen to be actually blocked;

[0030] Based on the collected motor energy consumption data and material production data, it is determined whether the crusher is operating inefficiently. If the crusher is operating inefficiently, the feed amount of the crusher is increased to improve the working efficiency of the crusher.

[0031] The beneficial effects of the present invention are: the production capacity control system and control method based on the air volume and pressure of the pulverizer system are provided with an abnormal monitoring module, so that the abnormal monitoring module determines whether the sieve of the pulverizer has a tendency to be blocked according to the real-time data collected by the data acquisition module, and maintains the minimum airflow required for pulverizing and transportation on the basis of ensuring that the sieve is not blocked, and makes the motor of the pulverizer run at the maximum load at this time, and adjusts the feed amount of the pulverizer to maximize the production capacity.

[0032] By linking the abnormal monitoring module, capacity prediction module, and capacity adjustment module, it is possible to timely detect the tendency of the crusher screen to be blocked, and timely reduce the feed amount to avoid the screen being blocked, ensuring that the crusher can continue to work without abnormal shutdown. In addition, it is possible to timely detect the inefficient operation of the crusher, and timely increase the feed amount to increase the crusher's capacity, which is conducive to improving work efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0034] Figure 1 It is a structural schematic diagram of a material crushing system involved in the present invention;

[0035] Figure 2 is a system block diagram of the present invention;

[0036] Figure 3 It is a flow chart of the method of the present invention. DETAILED DESCRIPTION

[0037] Embodiment 1

[0038] like Figure 2As shown in the figure, a capacity control system based on the air volume and pressure of the pulverizer system is applicable to the pulverizer including the screen. By monitoring the air volume and pressure of the air network, it is judged whether the screen has a tendency to be blocked. While ensuring that the screen is not blocked, the minimum airflow required for crushing and transportation is maintained, and the motor is operated at the maximum load at this time, and the feed amount of the pulverizer is adjusted to maximize the capacity.

[0039] The capacity control system includes a data acquisition module, a capacity prediction module, an abnormality monitoring module, a capacity adjustment module and a model optimization module.

[0040] Data acquisition module: real-time acquisition of motor energy consumption data, wind network operation data, and material production data in the actual production process. Among them, motor energy consumption data includes motor current and motor voltage; wind network operation data includes air volume, air pressure and time of the test section; material production data includes actual material fineness and actual material output.

[0041] Capacity prediction model: According to the actual data collected by the data acquisition module, the predicted value of the real-time optimal capacity of the crusher is calculated based on the capacity prediction model.

[0042] Specifically, the capacity prediction model is built through a numerical prediction algorithm. The specific construction process is as follows:

[0043] Collect sample data: Build a capacity prediction model through sample data. The sample data includes motor current I, wind network wind pressure P, and wind network air volume Q. The sample data is divided into training set data and validation set data. The initial prediction model is built through the training set data, and the accuracy of the initial prediction model is verified through iterative calculation of the validation set data, so as to obtain the final capacity prediction model.

[0044] Firstly, the data prediction algorithm is used to fit the corresponding relationship between the motor current I, wind network pressure P, wind network air volume Q in the training set data and the actual material output, so as to construct the initial prediction model.

[0045] Set the input variables of the capacity forecast model to [X1, X2, X3] = [I, P, Q], and the output variable is the optimal capacity forecast value Y. Specifically, the relationship between input data and output data can be processed by ReLU or LeakyReLU activation function. Taking the ReLU activation function as an example, the output of the optimal capacity forecast value Among them, ω i is the weight, b is the bias, and the value of bias b is related to parameters such as motor voltage, wind network time, and actual material fineness. The weight and bias are continuously optimized to minimize the error of the fitting result.

[0046] Secondly, the initial prediction model is iteratively trained through the validation set data to achieve model verification, and the difference between the predicted value and the actual value is calculated. If the difference exceeds the set range, the model structure is adjusted or retrained to obtain a verified model until the prediction result of the capacity forecasting model meets the error requirements.

[0047] The verified model needs to be calibrated under no-load conditions as a capacity prediction model. Specifically, the standard values ​​of motor current I, wind network pressure P, and wind network air volume Q are collected and recorded when the crusher is running at no-load, and input into the prediction model as standard data. The accuracy of the prediction results of the capacity prediction model can be improved through verification and calibration.

[0048] Abnormal monitoring module: includes screen abnormality monitoring unit and inefficient operation monitoring unit.

[0049] Screen abnormality monitoring unit: judge whether the screen has a tendency to be blocked based on the actual data of wind pressure and air volume collected by the data acquisition module. If so, timely feedback will be given to the crusher to indicate that there is a tendency to be blocked, and adjustments will be made before the screen is blocked to reduce the feed amount of the crusher.

[0050] Specifically, since the wind pressure and air volume of the wind net will increase when the screen is blocked, the actual data of the wind pressure and air volume collected are compared with the abnormal threshold of the screen blockage. If the actual data is greater than the abnormal threshold, it indicates that the crusher has an abnormal trend of screen blockage. The screen abnormality monitoring unit monitors the values ​​of the wind pressure and air volume of the wind net in real time, and compares the actual data with the abnormal threshold of the screen blockage. Feedback is given in time before the screen is blocked, and the capacity adjustment module is driven to reduce the feed amount of the crusher, thereby avoiding continuous feeding that causes the screen to be actually blocked and affecting the normal operation of the crusher.

[0051] Inefficient operation monitoring unit: Determine whether the crusher is inefficiently operating based on the actual motor energy consumption data and actual production capacity data collected by the data acquisition module. If so, timely feedback will be given on the inefficient operation of the crusher, and the production capacity control will be adjusted in time to increase the feed amount of the crusher to improve production capacity.

[0052] Specifically, due to the correlation between the motor operation data and the production capacity data, the collected actual motor energy consumption data and actual production capacity data are compared with the inefficient production abnormality threshold. If the actual production capacity data is less than the inefficient production abnormality threshold, it is fed back that the crusher has an abnormal situation of inefficient operation.

[0053] Capacity adjustment module: dynamically adjust the feed rate of the crusher according to the feedback information from the abnormal monitoring module.

[0054] On the one hand, when the pulverizer has an abnormal tendency to block the screen, the feed rate of the pulverizer is reduced to avoid actual blockage of the screen.

[0055] On the other hand, when the pulverizer has an abnormal situation of inefficient operation, the optimal capacity prediction value is associated with the actual output of the collected materials, and the feed amount of the pulverizer is increased to improve the capacity. It should be noted that when dynamically adjusting the feed amount of the pulverizer to increase the capacity, it is necessary to always pay attention to the abnormal monitoring module to avoid excessive feed amount blocking the screen and affecting the normal operation of the pulverizer.

[0056] Model optimization module: records the motor energy consumption data, wind network operation data and material production data of the crusher under different working conditions, and compares the actual material output obtained with the predicted value of the capacity prediction module, records the deviation data between the two, and optimizes and trains the capacity prediction module based on the recorded real-time data to improve the accuracy of the capacity prediction model. The specific process of the model optimization module is the same as the model optimization process in the prior art, and will not be repeated here. The main purpose of the model optimization module is to improve the accuracy of the prediction results of the capacity prediction model.

[0057] Embodiment 2

[0058] like Figure 3 As shown, the second aspect of the present invention is to propose a capacity control method based on the air volume and air pressure of a pulverizer system, which is applicable to a pulverizer control system including a screen, and specifically includes the following steps:

[0059] Obtain motor energy consumption data, wind network operation data, and material production data during the actual production process. Among them, motor energy consumption data includes motor current and motor voltage; wind network operation data includes air volume, air pressure, and time of the test section; material production data includes actual material fineness and actual material output.

[0060] According to the actual data obtained, the predicted value of the real-time optimal production capacity of the crusher is calculated based on the production capacity prediction model.

[0061] In the actual production process, determine whether the crusher screen has a tendency to be blocked and whether the crusher is operating inefficiently, and adjust the crusher's feed rate based on the judgment results.

[0062] On the one hand, the collected wind network operation data is used to determine whether the crusher screen has a tendency to be blocked. If the crusher screen has a tendency to be blocked, the feed amount of the crusher is reduced to avoid excessive feed amount to the crusher causing the screen to be actually blocked.

[0063] On the other hand, the collected motor energy consumption data and material production data can be used to determine whether the crusher is operating inefficiently. If the crusher is operating inefficiently, the feed amount of the crusher is increased to improve the crusher's working efficiency.

[0064] Record the motor energy consumption data, wind network operation data, and material production data during the actual production process, compare the actual material output with the predicted value of the optimal production capacity, record the difference data, and optimize the production capacity prediction module based on the recorded real-time data to improve the accuracy of the production capacity prediction model.

[0065] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. 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 production capacity control system based on the air volume and pressure of a pulverizer system, characterized in that: include: Data acquisition module, used to obtain motor energy consumption data, wind network operation data and material production data in real time during the actual production process; The capacity prediction module is used to calculate the predicted value of the real-time optimal capacity of the crusher based on the actual data collected by the data collection module and the capacity prediction model; Abnormal monitoring module, including screen abnormality monitoring unit and inefficient operation monitoring unit; The screen abnormality monitoring unit is used to determine whether the screen of the pulverizer has a tendency to be blocked according to the collected wind network operation data. If the screen has a tendency to be blocked, the unit feeds back to the capacity adjustment module to reduce the feed amount of the pulverizer. The inefficient operation monitoring unit is used to determine whether the pulverizer is inefficiently operated according to the collected motor energy consumption data and material production data. If the pulverizer is inefficiently operated, the inefficient operation monitoring unit feeds back to the capacity adjustment module to increase the feed amount of the pulverizer. The capacity adjustment module is used to dynamically adjust the feed rate of the crusher according to the feedback information of the abnormal monitoring module; The abnormal monitoring module determines whether the screen of the crusher has a tendency to be blocked based on the real-time data collected by the data acquisition module. On the basis of ensuring that the screen is not blocked, it maintains the minimum airflow required for crushing and transportation, and makes the motor of the crusher run at the maximum load at this time, and adjusts the feed amount of the crusher to maximize production capacity.

2. The production capacity control system based on the air volume and air pressure of the pulverizer system according to claim 1 is characterized in that: The motor energy consumption data includes motor current and motor voltage; the wind network operation data includes air volume, wind pressure and time of the test section; the material production data includes actual material fineness and actual material output.

3. The production capacity control system based on the air volume and air pressure of the pulverizer system according to claim 1 or 2, characterized in that: The screen abnormality monitoring unit compares the actual data of the wind network wind pressure and wind network air volume collected by the data acquisition module with the screen blockage abnormality threshold. If the actual data of the wind network wind pressure and wind network air volume are greater than the screen blockage abnormality threshold, it is judged that the current grinder has an abnormal trend of screen blockage.

4. The production capacity control system based on the air volume and air pressure of the pulverizer system according to claim 1 or 2, characterized in that: The inefficient operation monitoring unit compares the actual motor energy consumption data and actual production capacity data collected by the data acquisition module with the inefficient production abnormality threshold. If the actual motor energy consumption data and actual production capacity data are less than the inefficient production abnormality threshold, it is determined that the current crusher has an inefficient operation abnormality.

5. The production capacity control system based on the air volume and air pressure of the pulverizer system according to claim 1 is characterized in that: It also includes a model optimization module, which is used to record the actual data collected by the data acquisition module and compare the actual material output with the predicted value of the capacity prediction module, and record the difference data; optimize and train the capacity prediction module according to the recorded real-time data to improve the accuracy of the capacity prediction model.

6. The production capacity control system based on the air volume and air pressure of the pulverizer system according to claim 1 is characterized in that: The process of building the capacity prediction model is as follows: constructing the capacity prediction model through the collected sample data; and calibrating the capacity prediction model under no-load conditions; The sample data includes motor current I, wind network wind pressure P, and wind network air volume Q. The sample data is divided into training set data and verification set data. The initial prediction model is constructed through the training set data, and the accuracy of the initial prediction model is verified through iterative calculation of the verification set data, so as to obtain the final capacity prediction model.

7. The production capacity control system based on the air volume and air pressure of the pulverizer system according to claim 6 is characterized in that: The capacity prediction model is built through a numerical prediction algorithm. The specific construction process is as follows: The corresponding relationship between the motor current I, the wind network wind pressure P, the wind network air volume Q and the actual material output in the training set data is fitted by a data prediction algorithm to construct an initial prediction model; Set the input variables of the capacity forecast model to [X1, X2, X3] = [I, P, Q], and the output variable to the optimal capacity forecast value Y. The optimal capacity forecast value Y is calculated by the ReLU activation function. Among them, ω i is the weight, b is the bias, and the weight and bias are continuously optimized to minimize the error of the fitting result; The initial prediction model is iteratively trained using the validation set data to achieve verification, and the difference between the predicted value and the actual value is calculated. If the difference exceeds the set range, the model structure is adjusted or retrained to obtain a verified model until the prediction result of the capacity forecast model meets the error requirements.

8. A method for controlling the air volume and pressure of a pulverizer system, characterized in that: Applicable to the control system of the pulverizer including the screen, specifically including the following steps: Obtain motor energy consumption data, wind network operation data, and material production data during the actual production process; According to the actual data obtained, the predicted value of the real-time optimal production capacity of the crusher is calculated based on the production capacity prediction model; In the actual production process, determine whether the crusher screen has a tendency to be blocked and whether the crusher is operating inefficiently, and adjust the crusher feed rate based on the judgment results; Record the motor energy consumption data, wind network operation data, and material production data during the actual production process, compare the actual material output with the predicted value of the optimal production capacity, record the difference data, and optimize the production capacity prediction module based on the recorded real-time data to improve the accuracy of the production capacity prediction model.

9. The method for controlling the production capacity based on the air volume and air pressure of the pulverizer system according to claim 8, characterized in that: The motor energy consumption data includes motor current and motor voltage; the wind network operation data includes air volume, wind pressure and time of the test section; the material production data includes actual material fineness and actual material output.

10. The method for controlling the production capacity based on the air volume and air pressure of the pulverizer system according to claim 8, characterized in that: According to the collected wind network operation data, determine whether the crusher screen has a tendency to be blocked. If the crusher screen has a tendency to be blocked, reduce the feed amount of the crusher to avoid excessive feed amount of the crusher causing the screen to be blocked. Based on the collected motor energy consumption data and material production data, it is determined whether the crusher is operating inefficiently. If the crusher is operating inefficiently, the feed amount of the crusher is increased to improve the working efficiency of the crusher.

Images