An intelligent control method, system and device for heavy medium coal washing

By analyzing the inlet and outlet pressure data and coal flow data, and adjusting the proportional gain coefficient of the PID control system, the response speed and stability problems of the PID control system in heavy medium coal washing are solved, and the accuracy and control effect of the coal washing process are improved.

CN118577383BActive Publication Date: 2024-11-26XINHENG IND AUTOMATION (YINCHUAN) CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410849516.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-06-27
Publication Date
2024-11-26
Estimated Expiration
2044-06-27

AI Technical Summary

Technical Problem

现有的PID控制系统在面对不同介质的洗煤过程中响应速度和稳定性受到干扰,导致重介质洗煤智能控制的精确性降低。

Method used

By acquiring inlet pressure data, outlet pressure data and coal flow data, analyzing the degree of distribution discreteness and expected deviation, and adjusting the proportional gain coefficient of the PID control system to improve the real-time response and accuracy of the control system.

Benefits of technology

The accuracy of the fluctuation difference analysis of pressure data changes during heavy media coal washing is improved, the response speed and stability of different media on the PID control system is reduced, and the accuracy of intelligent control for heavy media coal washing is enhanced.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118577383B_ABST
    Figure CN118577383B_ABST
Patent Text Reader

Abstract

The present invention relates to the field of coal washing equipment control technology, and specifically to an intelligent control method, system and equipment for heavy medium coal washing, including: obtaining the expected deviation of the inlet pressure of the heavy medium cyclone during each coal washing process according to the difference in the number of data of two combined categories, the difference between the pressure data at all times at the inlet and the theoretically set target pressure value; obtaining the real-time response degree of each heavy medium coal washing control system according to the change fluctuation of the outlet coal flow data, the distribution difference between the inlet and outlet pressure data sequences, and the trend difference between the outlet pressure data sequence and the mean envelope pressure data sequence; adjusting the initial proportional gain coefficient according to the expected deviation and real-time response degree, and controlling the heavy medium coal washing according to the adjusted proportional gain coefficient. The present invention reduces the influence of the control system on the responsiveness and improves the accuracy of the intelligent control for heavy medium coal washing.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of coal washing equipment control, and in particular to an intelligent control method, system and equipment for heavy medium coal washing. Background Art

[0002] With the change of supply and demand of coal, users have higher requirements on coal quality in order to improve production efficiency and reduce environmental pollution. At the same time, the fierce competition from oil and natural gas has prompted the coal preparation industry to develop rapidly in the direction of high efficiency, high quality and low cost. Therefore, coal cleaning can reduce coal pollution to the atmosphere and improve economic value.

[0003] Coal washing is to separate non-fuel substances such as impurities and ash from raw coal to improve the quality and economic value of coal. In the process of coal washing, various media are used to clean the coal by controlling the coal washing equipment. Since the density and fluidity of different media are different, the response speed and stability of different media to the PID control system are also different. Therefore, different media will cause the response speed and stability of the PID control system to be disturbed and affected to a certain extent, resulting in a reduction in the accuracy of intelligent control for heavy medium coal washing. Summary of the invention

[0004] The present invention provides an intelligent control method, system and equipment for heavy medium coal washing to solve the existing problems.

[0005] The intelligent control method, system and equipment for heavy medium coal washing of the present invention adopt the following technical solutions:

[0006] An embodiment of the present invention provides an intelligent control method for heavy medium coal washing, the method comprising the following steps:

[0007] Obtain inlet pressure data, outlet pressure data and outlet coal flow data at all times during each coal washing process;

[0008] The same inlet pressure data in each coal washing process is divided into one category to obtain several categories, and all the categories are combined in pairs to obtain several combinations; the distribution discreteness of the inlet pressure data in each coal washing process is obtained according to the difference in the number of data distributions of the two combined categories; the expected deviation of the inlet pressure of the heavy medium cyclone in each coal washing process is obtained through the distribution discreteness and the difference between the pressure data at the inlet of the cyclone at all times in each coal washing process and the theoretically set target pressure value;

[0009] Obtain inlet pressure data sequence, outlet pressure data sequence and outlet mean envelope pressure data sequence; obtain the real-time response degree of each heavy medium coal washing control system according to the fluctuation of outlet coal flow data, the distribution difference between the inlet pressure data sequence and the outlet pressure data sequence, and the trend difference between the outlet pressure data sequence and the outlet mean envelope pressure data sequence;

[0010] The initial proportional gain coefficient of the PID control system for each coal washing is obtained, and the initial proportional gain coefficient of the PID control system for each coal washing is adjusted according to the expected deviation and the real-time response degree to obtain the proportional gain coefficient of the PID control system for each coal washing after adjustment, and the heavy medium coal washing is controlled according to the proportional gain coefficient of the PID control system for each coal washing after adjustment.

[0011] Furthermore, the distribution discreteness of the inlet pressure data in each coal washing process is obtained according to the difference in the number of data distributions of the two combined categories, and the specific steps include the following:

[0012] The ratio of the number of pressure data at all times in one category of each combination to the number of pressure data at all times at the entrance is recorded as the first ratio of each combination; the ratio of the number of pressure data at all times in another category of each combination to the number of pressure data at all times at the entrance is recorded as the second ratio of each combination;

[0013] The difference between the first ratio and the second ratio of each combination is recorded as the first difference of each combination, and the mean of the first differences of all combinations is recorded as the distribution dispersion degree of the inlet pressure data in each coal washing process.

[0014] Furthermore, the expected deviation of the inlet pressure of the heavy medium cyclone in each coal washing process is obtained by the distribution discreteness, the difference between the pressure data at the inlet of the cyclone at all times in each coal washing process and the theoretical set target pressure value, and the specific steps include the following:

[0015] The difference between the pressure data at the inlet at each moment in each coal washing process and the theoretically set target pressure value at the inlet during each coal washing process is recorded as the second pressure difference at each moment in the inlet; the average of the second pressure differences at all moments in the inlet is recorded as the pressure deviation degree at the inlet;

[0016] According to the distribution dispersion and the pressure deviation at the inlet, the expected deviation of the inlet pressure of the heavy medium cyclone in each coal washing process is obtained;

[0017] Among them, the degree of distribution dispersion is positively correlated with the expected deviation of the inlet pressure of the heavy medium cyclone during each coal washing process, and the degree of pressure deviation at the inlet is positively correlated with the expected deviation of the inlet pressure of the heavy medium cyclone during each coal washing process.

[0018] Furthermore, the obtaining of the inlet pressure data sequence, the outlet pressure data sequence and the outlet mean envelope pressure data sequence comprises the following specific steps:

[0019] The inlet pressure data in each coal washing process are sorted in chronological order to form a set of sequences, which are recorded as the inlet pressure data sequence in each coal washing process; the outlet pressure data are sorted in chronological order to form a set of sequences, which are recorded as the outlet pressure data sequence in each coal washing process;

[0020] The data in the outlet pressure data sequence are subjected to moving average calculation to obtain the outlet mean envelope pressure data sequence; the moving average takes each data as the window center, which means taking the average value of the data points within a certain window.

[0021] Furthermore, the real-time response degree of each heavy medium coal washing control system is obtained according to the fluctuation of the outlet coal flow data, the distribution difference between the inlet pressure data sequence and the outlet pressure data sequence, and the trend difference between the outlet pressure data sequence and the outlet mean envelope pressure data sequence, and the specific steps include the following:

[0022] According to the fluctuation of the export coal flow data, the fluctuation degree of the coal flow at the export during each coal washing process is obtained; according to the distribution difference between the inlet pressure data sequence and the outlet pressure data sequence, and the trend difference between the outlet pressure data sequence and the outlet mean envelope pressure data sequence, the feedback strength of the coal washing control system is obtained each time;

[0023] According to the fluctuation degree and the feedback strength, the real-time response degree of each heavy medium coal washing control system is obtained;

[0024] Among them, the fluctuation degree is positively correlated with the real-time response degree of each heavy medium coal washing control system, and the feedback intensity is positively correlated with the real-time response degree of each heavy medium coal washing control system.

[0025] Furthermore, the fluctuation degree of the coal flow at the outlet during each coal washing process is obtained according to the fluctuation of the outlet coal flow data, and the specific steps include the following:

[0026] The difference between the coal flow data at each moment at the outlet and the mean value of the coal flow data at all moments during each coal washing process is recorded as the first coal flow difference at each moment at the outlet; the mean value of the first coal flow difference at all moments at the outlet is recorded as the coal flow fluctuation characteristic at the outlet;

[0027] According to the fluctuation characteristics of coal flow at the outlet and the information entropy of coal flow data at all times at the outlet during each coal washing process, the fluctuation degree of coal flow at the outlet during each coal washing process is obtained;

[0028] Among them, the fluctuation characteristics of the coal flow at the outlet are positively correlated with the fluctuation degree of the coal flow at the outlet during each coal washing process, and the information entropy of the coal flow data at all times is positively correlated with the fluctuation degree of the coal flow at the outlet during each coal washing process.

[0029] Furthermore, the feedback strength of each coal washing control system is obtained according to the distribution difference between the inlet pressure data sequence and the outlet pressure data sequence, and the trend difference between the outlet pressure data sequence and the outlet mean envelope pressure data sequence, and the specific steps include the following:

[0030] The absolute value of the correlation coefficient between the outlet pressure data sequence and the outlet mean envelope pressure data sequence is recorded as the correlation feature between the outlet pressure data sequence and the outlet mean envelope pressure data sequence;

[0031] According to the mean square error between the inlet pressure data sequence and the outlet pressure data sequence, and the correlation characteristics between the outlet pressure data sequence and the outlet mean envelope pressure data sequence, the feedback strength of each coal washing control system is obtained;

[0032] The mean square error is negatively correlated with the feedback strength of each coal washing control system, and the related feature is positively correlated with the feedback strength of each coal washing control system.

[0033] Further, the initial proportional gain coefficient of each coal washing PID control system is adjusted according to the expected deviation and the real-time response degree to obtain the adjusted proportional gain coefficient of each coal washing PID control system, including the following specific steps:

[0034] The product result between the expected deviation and the real-time response degree is recorded as the first product result, the first product result is normalized, the sum of the normalized first product result and 1 is recorded as the adjustment coefficient, and the product result between the adjustment coefficient and the initial proportional gain coefficient of each coal washing PID control system is recorded as the proportional gain coefficient of each coal washing PID control system after adjustment.

[0035] The present invention also provides an intelligent control system for heavy medium coal washing, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the processor implements the steps of any one of the above-mentioned intelligent control methods for heavy medium coal washing.

[0036] The present invention also provides an intelligent control device for heavy medium coal washing, including raw coal processing equipment, washing equipment and coal quality processing equipment, and computer equipment. The intelligent control device for heavy medium coal washing implements the steps of any one of the above-mentioned intelligent control methods for heavy medium coal washing, and the computer equipment implements the above-mentioned intelligent control system for heavy medium coal washing.

[0037] The beneficial effects of the technical solution of the present invention are as follows: the present invention obtains the expected deviation of the inlet pressure of the heavy medium cyclone in each coal washing process according to the difference in the number of data of the two combined categories and the difference between the pressure data at the inlet of the cyclone at all times during each coal washing process and the theoretically set target pressure value, and improves the accuracy of the analysis of the change fluctuation difference of the pressure data through the expected deviation of the inlet pressure; obtains the real-time response degree of each heavy medium coal washing control system according to the change fluctuation of the outlet coal flow data, the distribution difference between the inlet pressure data sequence and the outlet pressure data sequence, and the trend difference between the outlet pressure data sequence and the outlet mean envelope pressure data sequence, and reduces the influence of different media on the response speed and stability of the PID control system through the real-time response degree of each heavy medium coal washing control system; adjusts the initial proportional gain coefficient of each coal washing control system according to the expected deviation and the real-time response degree, obtains the proportional gain coefficient of each coal washing control system after adjustment, and controls the heavy medium coal washing according to the proportional gain coefficient of each coal washing control system after adjustment, thereby improving the accuracy of the intelligent control for heavy medium coal washing. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0039] Figure 1 This is a flow chart of the steps of an intelligent control method for heavy medium coal washing according to the present invention;

[0040] Figure 2 This is the intelligent control flow chart for heavy medium coal washing. DETAILED DESCRIPTION

[0041] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the intelligent control method, system and equipment for heavy medium coal washing proposed by the present invention, its specific implementation method, structure, characteristics and effects in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0042] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0043] The specific scheme of an intelligent control method, system and equipment for heavy medium coal washing provided by the present invention is described in detail below with reference to the accompanying drawings.

[0044] See also Figure 1 , which shows a flowchart of a step of an intelligent control method for heavy medium coal washing provided by an embodiment of the present invention, the method comprising the following steps:

[0045] Step S001: Collect inlet pressure data, outlet pressure data and coal flow data during each coal washing process.

[0046] It should be noted that in order to analyze the control of coal slime content in the coal washing process, it is necessary to collect the pressure data at the cyclone inlet and the pressure data at the coal flow outlet of the coal washing equipment, as well as the coal flow data, and control and adjust the heavy medium coal washing through the changes in the pressure data and coal flow data at the inlet and outlet and the differences between them.

[0047] Specifically, a pressure sensor is installed at the inlet of the cyclone, and a pressure sensor and a flow meter are also installed at the outlet of the coal flow; with a sampling time interval of 1 minute, the pressure data at the inlet, the pressure data at the outlet and the coal flow data at the outlet are collected at all times during each coal washing process.

[0048] At this point, the inlet pressure data, outlet pressure data and coal flow data of each coal washing process are obtained.

[0049] Step S002: The same inlet pressure data in each coal washing process is divided into one category to obtain several categories, and all the categories are combined in pairs to obtain several combinations; according to the difference in the distribution of the number of data of the two combined categories, the distribution discreteness of the inlet pressure data in each coal washing process is obtained; through the distribution discreteness and the difference between the pressure data at the inlet of the cyclone at all times in each coal washing process and the theoretically set target pressure value, the expected deviation of the inlet pressure of the heavy medium cyclone in each coal washing process is obtained.

[0050] It should be noted that, usually, the coal flow inlet of the cyclone is designed to be spacious and smooth enough to ensure that the coal or mixture can enter the coal washing equipment smoothly; and the pressure change at the inlet will not be particularly drastic, so the pressure change at the coal flow inlet is generally relatively small to ensure that the coal cannot affect the operation of the coal washing equipment. However, in addition to being controlled by the operator, the pressure change at the inlet is also affected by the state of the coal entering the coal washing equipment and the flow control. The equipment operator usually adjusts the feeding speed and method to maximize the stable pressure at the inlet to ensure the continuous flow and stable feeding of coal. Therefore, it is also necessary to feed back the changes in the pressure data at the inlet of the cyclone to the coal washing equipment for control and adjustment, so that the coal washing equipment can operate smoothly; therefore, it can be analyzed based on the distribution of pressure data at all times at the coal flow inlet.

[0051] Specifically, the same inlet pressure data in each coal washing process is divided into one category to obtain several categories, and all the categories are combined in pairs to obtain several combination results.

[0052] It should be further explained that in order to analyze whether the equipment is stable during the coal washing process, the stability of the coal washing equipment can be analyzed by the change difference of the pressure data at the entrance at all times during each coal washing process; that is, the distribution of the pressure data at the entrance at all times during each coal washing process is concentrated or dispersed to obtain the change difference of the pressure data. Therefore, according to the difference in the number of data of the two combined categories, the distribution discreteness of the entrance pressure data during each coal washing process is obtained.

[0053] Preferably, as an embodiment, the specific calculation method of the distribution discreteness of the inlet pressure data in each coal washing process is:

[0054] The ratio of the number of pressure data at all times in one category of each combination to the number of pressure data at all times at the entrance is recorded as the first ratio of each combination; the ratio of the number of pressure data at all times in another category of each combination to the number of pressure data at all times at the entrance is recorded as the second ratio of each combination;

[0055] The difference between the first ratio and the second ratio of each combination is recorded as the first difference of each combination, and the mean of the first differences of all combinations is recorded as the distribution dispersion degree of the inlet pressure data in each coal washing process.

[0056] In one embodiment of the present invention, it is specifically expressed by the formula:

[0057]

[0058] In the formula, G represents the number of pressure data at the inlet at all times, g1i Indicates the number of pressure data at all moments in the first category of the i-th combination result, g2 i It represents the number of pressure data at all moments in the second category of the i-th combination result, n represents the total number of combination results of inlet pressure data, || is the absolute value symbol, and F represents the distribution discreteness of inlet pressure data in each coal washing process.

[0059] in, It represents the difference in the proportion of the number of pressure data at all times in each category of each combination to the number of pressure data at all times of the inlet pressure. The larger the difference, the greater the distribution discreteness of the inlet pressure data in each coal washing process; the smaller the difference, the smaller the distribution discreteness of the inlet pressure data in each coal washing process.

[0060] At this point, the distribution discreteness of the inlet pressure data in each coal washing process is obtained.

[0061] It should be noted that in the process of coal washing, in order to ensure the smooth operation of the coal washing equipment, a parameter is generally set to make the coal flow pressure data at the cyclone inlet stable. Therefore, the expected deviation of the inlet pressure of the heavy medium cyclone in each coal washing process can be obtained based on the difference between the pressure data at the inlet of the cyclone at all times during each coal washing process and the theoretically set target pressure value, and the distribution discreteness of the inlet pressure data during each coal washing process. Therefore, the expected deviation of the inlet pressure of the heavy medium cyclone in each coal washing process is obtained by the distribution discreteness, the difference between the pressure data at the inlet of the cyclone at all times during each coal washing process and the theoretically set target pressure value.

[0062] Preferably, as an embodiment, the specific calculation method of the expected deviation of the inlet pressure of the heavy medium cyclone during each coal washing process is:

[0063] The difference between the pressure data at the inlet at each moment in each coal washing process and the theoretically set target pressure value at the inlet during each coal washing process is recorded as the second pressure difference at each moment in the inlet; the average of the second pressure differences at all moments in the inlet is recorded as the pressure deviation degree at the inlet;

[0064] According to the distribution dispersion and the pressure deviation at the inlet, the expected deviation of the inlet pressure of the heavy medium cyclone in each coal washing process is obtained;

[0065] Among them, the degree of distribution dispersion is positively correlated with the expected deviation of the inlet pressure of the heavy medium cyclone during each coal washing process, and the degree of pressure deviation at the inlet is positively correlated with the expected deviation of the inlet pressure of the heavy medium cyclone during each coal washing process.

[0066] In one embodiment of the present invention, it is specifically expressed by the formula:

[0067]

[0068] Where F represents the distribution discreteness of the inlet pressure data during each coal washing process, U k It represents the pressure data at the inlet at the kth moment during each coal washing process, U ′ It represents the theoretical target pressure value at the inlet of each coal washing process, || is the absolute value symbol, m1 represents the number of pressure data collected at the inlet at all times during each coal washing process, and P represents the expected deviation of the inlet pressure of the heavy medium cyclone during each coal washing process.

[0069] Among them, |U k -U ′ | represents the difference between the pressure data at all times of the cyclone inlet during each coal washing process and the theoretically set target pressure value. When the difference is larger, the expected deviation of the inlet pressure of the heavy medium cyclone during each coal washing process is larger; when the difference is smaller, the expected deviation of the inlet pressure of the heavy medium cyclone during each coal washing process is smaller. When the distribution discreteness of the inlet pressure data during each coal washing process is larger, the difference between the pressure data at all times of the cyclone inlet during each coal washing process and the theoretically set target pressure value may be larger, that is, the expected deviation of the inlet pressure of the heavy medium cyclone during each coal washing process is larger; when the distribution discreteness of the inlet pressure data during each coal washing process is smaller, the difference between the pressure data at all times of the cyclone inlet during each coal washing process and the theoretically set target pressure value may be smaller, that is, the expected deviation of the inlet pressure of the heavy medium cyclone during each coal washing process is smaller.

[0070] Thus, the expected deviation of the inlet pressure of the heavy medium cyclone in each coal washing process is obtained.

[0071] Step S003: Obtain the inlet pressure data sequence, the outlet pressure data sequence and the outlet mean envelope pressure data sequence; obtain the real-time response degree of each heavy medium coal washing control system according to the change fluctuation of the outlet coal flow data, the distribution difference between the inlet pressure data sequence and the outlet pressure data sequence, and the trend difference between the outlet pressure data sequence and the outlet mean envelope pressure data sequence.

[0072] It should be noted that in the process of controlling the heavy medium cyclone, in order to analyze whether the operating state of the heavy medium cyclone is stable, the stability of the coal flow at the outlet can be analyzed; when the change of the coal flow at the outlet is smaller, the operating state of the heavy medium cyclone is more stable, so the stability of the operating state of the heavy medium cyclone can be analyzed by the change of the coal flow at the outlet. Because the difference between the pressure data at the inlet and the pressure data at the outlet can also reflect the response degree of the PID control system. Therefore, according to the change fluctuation of the outlet coal flow data, the distribution difference between the inlet pressure data sequence and the outlet pressure data sequence, and the trend difference between the outlet pressure data sequence and the outlet mean envelope pressure data sequence, the real-time response degree of each heavy medium coal washing control system is obtained.

[0073] It should be further explained that the fluctuation of the coal flow at the outlet can reflect the stability of the coal flow, and the stability can also reflect the response of the PID control system. Therefore, according to the fluctuation of the coal flow at the outlet, the fluctuation of the coal flow at the outlet during each coal washing process can be obtained.

[0074] Preferably, as an embodiment, the specific calculation method of the fluctuation degree of the coal flow at the outlet during each coal washing process is:

[0075] The difference between the coal flow data at each moment at the outlet and the mean value of the coal flow data at all moments during each coal washing process is recorded as the first coal flow difference at each moment at the outlet; the mean value of the first coal flow difference at all moments at the outlet is recorded as the coal flow fluctuation characteristic at the outlet;

[0076] According to the fluctuation characteristics of coal flow at the outlet and the information entropy of coal flow data at all times at the outlet during each coal washing process, the fluctuation degree of coal flow at the outlet during each coal washing process is obtained;

[0077] Among them, the fluctuation characteristics of the coal flow at the outlet are positively correlated with the fluctuation degree of the coal flow at the outlet during each coal washing process, and the information entropy of the coal flow data at all times is positively correlated with the fluctuation degree of the coal flow at the outlet during each coal washing process.

[0078] In one embodiment of the present invention, it is specifically expressed by the formula:

[0079]

[0080] Where, L c represents the coal flow data at the outlet at the cth moment in each coal washing process, represents the mean value of the coal flow data at all times at the outlet of each coal washing process, m2 represents the total number of coal flow data at all times at the outlet of each coal washing process, H represents the information entropy of the coal flow data at all times at the outlet of each coal washing process, W represents the fluctuation degree of the coal flow at the outlet of each coal washing process, and || is the absolute value symbol. Among them, the process of obtaining data information entropy is a well-known technology and will not be described in detail here.

[0081] in, It represents the difference between the coal flow data at each moment of the exit during each coal washing process and the mean value of the coal flow data at all moments. When the difference is larger, it means that the fluctuation of the coal flow at the exit is larger, and the fluctuation degree of the exit coal flow at each coal washing process is larger; when the difference is smaller, it means that the fluctuation of the coal flow at the exit is smaller, and the fluctuation degree of the exit coal flow at each coal washing process is smaller. When the information entropy of the coal flow data at all moments of the exit during each coal washing process is smaller, it means that the coal flow data is more stable, and the fluctuation degree of the exit coal flow at each coal washing process is smaller; when the information entropy of the coal flow data at all moments of the exit during each coal washing process is larger, it means that the coal flow data is more unstable, and the fluctuation degree of the exit coal flow at each coal washing process is larger.

[0082] At this point, the fluctuation degree of the export coal flow rate during each coal washing process is obtained.

[0083] It should be noted that, since there is a certain correlation between the distribution trends of the pressure data at the inlet and the outlet, the pressure data sequences corresponding to the inlet and the outlet are obtained for analysis.

[0084] Specifically, the inlet pressure data in each coal washing process are sorted in time order to form a set of sequences, which are recorded as the inlet pressure data sequence in each coal washing process; the outlet pressure data are sorted in time order to form a set of sequences, which are recorded as the outlet pressure data sequence in each coal washing process;

[0085] Perform moving average calculation on the data in the outlet pressure data sequence to obtain the outlet mean envelope pressure data sequence; the moving average takes each data as the window center, which means taking the average value of the data points within a certain window. The size of the window is not specifically limited, and the implementer can determine it according to the specific situation. When the leftmost and rightmost data are the midpoints of the window, if the number of window data is not met, only the mean of the data in the window is calculated.

[0086] It is further explained that the outlet mean envelope pressure data sequence is the time series data sequence corresponding to the mean envelope of the outlet pressure data sequence. The process of obtaining the mean envelope of a set of time series data sequences is a well-known technology and will not be described in detail here.

[0087] It should be noted that when the difference between the pressure data at the inlet and the pressure data at the outlet is greater, it is possible that the control response speed of the coal washing equipment is slow and cannot be adjusted in time. Therefore, the feedback strength of each coal washing control is obtained through the distribution and difference of the pressure data at the inlet and the pressure data at the outlet during each coal washing process. Therefore, the feedback strength of each coal washing control system is obtained according to the distribution difference between the inlet pressure data sequence and the outlet pressure data sequence, and the trend difference between the outlet pressure data sequence and the outlet mean envelope pressure data sequence.

[0088] Preferably, as an embodiment, the specific calculation method of the feedback strength of each coal washing control system is:

[0089] The absolute value of the correlation coefficient between the outlet pressure data sequence and the outlet mean envelope pressure data sequence is recorded as the correlation feature between the outlet pressure data sequence and the outlet mean envelope pressure data sequence;

[0090] According to the mean square error between the inlet pressure data sequence and the outlet pressure data sequence, and the correlation characteristics between the outlet pressure data sequence and the outlet mean envelope pressure data sequence, the feedback strength of each coal washing control system is obtained;

[0091] The mean square error is negatively correlated with the feedback strength of each coal washing control system, and the related feature is positively correlated with the feedback strength of each coal washing control system.

[0092] In one embodiment of the present invention, it is specifically expressed by the formula:

[0093]

[0094] Wherein, MSE represents the mean square error between the inlet pressure data sequence and the outlet pressure data sequence, X represents the correlation coefficient between the outlet pressure data sequence and the outlet mean envelope pressure data sequence, Q represents the feedback strength of each coal washing control system, and || is the absolute value symbol. Among them, the correlation coefficient between the two sequences is obtained by the Pearson correlation coefficient, and the Pearson correlation coefficient is a well-known technology, which will not be described in detail here.

[0095] Among them, when the mean square error between the inlet and outlet pressure data sequences is smaller, it means that the correlation between the two sequences is stronger, that is, when adjusting the control system, a greater feedback force is required to make adjustments, and vice versa, a smaller feedback force is required to make adjustments. When the correlation coefficient between the outlet pressure data sequence and the outlet mean envelope pressure data sequence is closer to 1 or closer to -1, it means that the pressure change at the outlet of the cyclone is increasing or decreasing, and when the inlet pressure regulation force is not good, the outlet pressure of the cyclone may continue to show a stable state different from that during normal operation, that is, the pressure change at the outlet is in a fluctuating and unstable state.

[0096] According to the fluctuation degree of coal flow at the outlet during each coal washing process and the feedback strength of each coal washing control, the real-time response degree of each heavy medium coal washing control system is obtained.

[0097] Preferably, as an embodiment, the specific calculation method of the real-time response degree of each heavy medium coal washing control system is:

[0098] Among them, the fluctuation degree is positively correlated with the real-time response degree of each heavy medium coal washing control system, and the feedback intensity is positively correlated with the real-time response degree of each heavy medium coal washing control system.

[0099] In one embodiment of the present invention, it is specifically expressed by the formula:

[0100]

[0101] Where W represents the fluctuation degree of coal flow at the outlet during each coal washing process, Q represents the feedback strength of the coal washing control system each time, and E represents the real-time response degree of the heavy medium coal washing control system each time.

[0102] Among them, when the fluctuation degree of the coal flow at the outlet during each coal washing process is greater, a greater response degree is required to balance the control system. When the feedback strength of each coal washing control system is greater, the real-time response degree of each heavy medium coal washing control system is greater.

[0103] At this point, the real-time response level of each heavy medium coal washing control system is obtained.

[0104] Step S004: adjusting the initial proportional gain coefficient of each coal washing PID control system according to the expected deviation and the real-time response degree, obtaining the adjusted proportional gain coefficient of each coal washing PID control system, and controlling the heavy medium coal washing according to the adjusted proportional gain coefficient of each coal washing PID control system.

[0105] It should be noted that in the process of using the PID controller to perform closed-loop control on the inlet pressure of the cyclone in the heavy medium coal washing process, the inlet pressure data may be affected by some factors, resulting in the inlet pressure value not being able to quickly reach the set value, which in turn leads to the control system's untimely response and the inlet pressure cannot be stably and accurately controlled. Therefore, according to the expected deviation of the inlet pressure of the heavy medium cyclone in each coal washing process and the real-time response degree of each heavy medium coal washing control system, the proportional gain coefficient corresponding to the proportional control in the PID controller is adjusted to obtain the adjusted proportional gain coefficient of each coal washing control system. Therefore, according to the expected deviation and the real-time response degree, the initial proportional gain coefficient of each coal washing PID control system is adjusted to obtain the adjusted proportional gain coefficient of each coal washing PID control system.

[0106] Preferably, as an embodiment, the specific calculation method of the proportional gain coefficient of each coal washing control system after adjustment is:

[0107] The product result between the expected deviation and the real-time response degree is recorded as the first product result, the first product result is normalized, the sum of the normalized first product result and 1 is recorded as the adjustment coefficient, and the product result between the adjustment coefficient and the initial proportional gain coefficient of each coal washing PID control system is recorded as the proportional gain coefficient of each coal washing PID control system after adjustment.

[0108] In one embodiment of the present invention, it is specifically expressed by the formula:

[0109] B ′ =[1+th(P×E)]×B

[0110] Where P represents the expected deviation of the inlet pressure of the heavy medium cyclone during each coal washing process, E represents the real-time response degree of the heavy medium coal washing control system each time, B represents the initial proportional gain coefficient of the PID control system of each coal washing process, and B ′ It represents the proportional gain coefficient of the coal washing PID control system after adjustment each time, and th() represents the hyperbolic tangent function.

[0111] Among them, the greater the expected deviation of the inlet pressure of the heavy medium cyclone during each coal washing process, the greater the difference between the PID control system and the expectation, and therefore requires greater adjustment, and the corresponding proportional gain coefficient should be larger; the greater the real-time response of the PID control system of each heavy medium coal washing, the greater the corresponding proportional gain coefficient should be.

[0112] The heavy medium coal washing is controlled by adjusting the proportional gain coefficient of the PID control system for each coal washing. The intelligent control flow chart for heavy medium coal washing is shown in the figure. Figure 2 shown.

[0113] This embodiment provides an intelligent control system for heavy medium coal washing, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, an intelligent control method for heavy medium coal washing in steps S001 to S004 is implemented.

[0114] An intelligent control device for heavy medium coal washing, comprising raw coal processing equipment, washing equipment and coal quality processing equipment, and computer equipment. The intelligent control device for heavy medium coal washing implements an intelligent control method for heavy medium coal washing in steps S001 to S004, and the computer equipment implements an intelligent control system for heavy medium coal washing.

[0115] Among them, raw coal processing equipment is used for crushing and screening of raw coal, which is the pretreatment operation before coal cleaning; washing equipment is the key link for separating and cleaning raw coal according to its physical properties; coal quality processing equipment is used for drying and grinding, which is used for subsequent processing operations after coal cleaning.

[0116] At this point, this embodiment is completed.

[0117] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An intelligent control method for heavy medium coal washing, It is characterized in that The method comprises the following steps: Obtain inlet pressure data, outlet pressure data and outlet coal flow data at all times during each coal washing process; The same inlet pressure data in each coal washing process is divided into one category to obtain several categories, and all the categories are combined in pairs to obtain several combinations; the distribution discreteness of the inlet pressure data in each coal washing process is obtained according to the difference in the number of data distributions of the two combined categories; the expected deviation of the inlet pressure of the heavy medium cyclone in each coal washing process is obtained through the distribution discreteness and the difference between the pressure data at the inlet of the cyclone at all times in each coal washing process and the theoretically set target pressure value; Obtain inlet pressure data sequence, outlet pressure data sequence and outlet mean envelope pressure data sequence; obtain the real-time response degree of each heavy medium coal washing control system according to the fluctuation of outlet coal flow data, the distribution difference between the inlet pressure data sequence and the outlet pressure data sequence, and the trend difference between the outlet pressure data sequence and the outlet mean envelope pressure data sequence; Obtaining an initial proportional gain coefficient of each coal washing PID control system, adjusting the initial proportional gain coefficient of each coal washing PID control system according to the expected deviation and the real-time response degree, obtaining the adjusted proportional gain coefficient of each coal washing PID control system, and controlling the heavy medium coal washing according to the adjusted proportional gain coefficient of each coal washing PID control system; The expected deviation of the inlet pressure of the heavy medium cyclone in each coal washing process is obtained by the distribution discreteness, the difference between the pressure data at the inlet of the cyclone at all times in each coal washing process and the theoretical set target pressure value, The specific steps involved are as follows: The difference between the pressure data at the inlet at each moment in each coal washing process and the theoretically set target pressure value at the inlet during each coal washing process is recorded as the second pressure difference at each moment in the inlet; the average of the second pressure differences at all moments in the inlet is recorded as the pressure deviation degree at the inlet; According to the distribution dispersion and the pressure deviation at the inlet, the expected deviation of the inlet pressure of the heavy medium cyclone in each coal washing process is obtained; Among them, the distribution dispersion degree is positively correlated with the expected deviation of the inlet pressure of the heavy medium cyclone during each coal washing process, and the pressure deviation degree at the inlet is positively correlated with the expected deviation of the inlet pressure of the heavy medium cyclone during each coal washing process; The specific steps of obtaining the inlet pressure data sequence, the outlet pressure data sequence and the outlet mean envelope pressure data sequence are as follows: The inlet pressure data in each coal washing process are sorted in chronological order to form a set of sequences, which are recorded as the inlet pressure data sequence in each coal washing process; the outlet pressure data are sorted in chronological order to form a set of sequences, which are recorded as the outlet pressure data sequence in each coal washing process; Perform moving average calculation on the data in the outlet pressure data sequence to obtain the outlet mean envelope pressure data sequence; the moving average takes each data as the window center, which means taking the average value of the data points within a certain window; The real-time response degree of each heavy medium coal washing control system is obtained according to the fluctuation of the export coal flow data, the distribution difference between the inlet pressure data sequence and the outlet pressure data sequence, and the trend difference between the outlet pressure data sequence and the outlet mean envelope pressure data sequence, and the specific steps include the following: According to the fluctuation of the export coal flow data, the fluctuation degree of the coal flow at the export during each coal washing process is obtained; according to the distribution difference between the inlet pressure data sequence and the outlet pressure data sequence, and the trend difference between the outlet pressure data sequence and the outlet mean envelope pressure data sequence, the feedback strength of the coal washing control system is obtained each time; According to the fluctuation degree and the feedback strength, the real-time response degree of each heavy medium coal washing control system is obtained; Among them, the fluctuation degree is positively correlated with the real-time response degree of each heavy medium coal washing control system, and the feedback strength is positively correlated with the real-time response degree of each heavy medium coal washing control system; The adjusting of the initial proportional gain coefficient of each coal washing PID control system according to the expected deviation and the real-time response degree to obtain the adjusted proportional gain coefficient of each coal washing PID control system includes the following specific steps: The product result between the expected deviation and the real-time response degree is recorded as the first product result, the first product result is normalized, the sum of the normalized first product result and 1 is recorded as the adjustment coefficient, and the product result between the adjustment coefficient and the initial proportional gain coefficient of each coal washing PID control system is recorded as the proportional gain coefficient of each coal washing PID control system after adjustment.

2. According to the intelligent control method for heavy medium coal washing according to claim 1, It is characterized in that The specific steps of obtaining the distribution discreteness of the inlet pressure data in each coal washing process according to the difference in the number of data of the two combined categories are as follows: The ratio of the number of pressure data at all times in one category of each combination to the number of pressure data at all times at the entrance is recorded as the first ratio of each combination; the ratio of the number of pressure data at all times in another category of each combination to the number of pressure data at all times at the entrance is recorded as the second ratio of each combination; The difference between the first ratio and the second ratio of each combination is recorded as the first difference of each combination, and the mean of the first differences of all combinations is recorded as the distribution dispersion degree of the inlet pressure data in each coal washing process.

3. According to the intelligent control method for heavy medium coal washing according to claim 1, It is characterized in that The method of obtaining the fluctuation degree of the coal flow at the outlet during each coal washing process according to the fluctuation of the outlet coal flow data includes the following specific steps: The difference between the coal flow data at each moment at the outlet and the mean value of the coal flow data at all moments during each coal washing process is recorded as the first coal flow difference at each moment at the outlet; the mean value of the first coal flow difference at all moments at the outlet is recorded as the coal flow fluctuation characteristic at the outlet; According to the fluctuation characteristics of coal flow at the outlet and the information entropy of coal flow data at all times at the outlet during each coal washing process, the fluctuation degree of coal flow at the outlet during each coal washing process is obtained; Among them, the fluctuation characteristics of the coal flow at the outlet are positively correlated with the fluctuation degree of the coal flow at the outlet during each coal washing process, and the information entropy of the coal flow data at all times is positively correlated with the fluctuation degree of the coal flow at the outlet during each coal washing process.

4. According to the intelligent control method for heavy medium coal washing according to claim 1, It is characterized in that The feedback strength of each coal washing control system is obtained according to the distribution difference between the inlet pressure data sequence and the outlet pressure data sequence, and the trend difference between the outlet pressure data sequence and the outlet mean envelope pressure data sequence, and the specific steps include the following: The absolute value of the correlation coefficient between the outlet pressure data sequence and the outlet mean envelope pressure data sequence is recorded as the correlation feature between the outlet pressure data sequence and the outlet mean envelope pressure data sequence; According to the mean square error between the inlet pressure data sequence and the outlet pressure data sequence, and the correlation characteristics between the outlet pressure data sequence and the outlet mean envelope pressure data sequence, the feedback strength of each coal washing control system is obtained; The mean square error is negatively correlated with the feedback strength of each coal washing control system, and the related feature is positively correlated with the feedback strength of each coal washing control system.

5. An intelligent control system for heavy medium coal washing, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, It is characterized in that When the processor executes the computer program, the steps of an intelligent control method for heavy medium coal washing as described in any one of claims 1 to 4 are implemented.

6. An intelligent control device for heavy medium coal washing, including raw coal processing equipment, washing equipment and coal quality processing equipment, computer equipment, It is characterized in that The intelligent control device for heavy medium coal washing is implemented according to the steps of an intelligent control method for heavy medium coal washing as described in any one of claims 1 to 4, and the computer device implements an intelligent control system for heavy medium coal washing as described in claim 5.