Intelligent control system and method for separation density of dense medium coal separation

Abstract

The invention provides an intelligent control system and method for dense medium coal separation density. The system comprises a Siemens programmable logic controller, a first computer and a second computer; the Siemens programmable logic controller is used for sending dense medium coal separation data measured in the dense medium process to the first computer and sending preset density data to the second computer; the first computer is used for establishing a mathematical model through the received dense medium coal separation data in combination with commercial mathematical software and a multi-layer feedforward neural network; and the second computer is used for evaluating the performance of the control system by combining the received density data with the mean square error and the error absolute value integral, and adaptively controlling the control system by using the artificial neural network system through the adaptive intelligent controller. By means of the system, the effect of intelligently controlling the dense medium coal separation density can be achieved.

Description

Technical Field

[0001] The present application relates to the field of intelligent heavy medium coal preparation, and more specifically, to an intelligent control system and method for heavy medium coal preparation separation density. Background Art

[0002] As one of the main energy sources, my country's coal resources are among the highest in the world in terms of reserves and distribution, supporting the continuous development of my country's modernization and industrialization. Although the development and utilization of new energy sources have gradually become the focus of national attention, coal still firmly occupies a dominant position in the energy consumption structure.

[0003] The density of heavy medium suspension is the core target of heavy medium separation control. The density control of traditional separation is completely determined by manual experience. There is no mature and reliable data analysis system to guide the operation. The heavy medium density index cannot be accurately adjusted through data analysis, which easily leads to insufficient product quality or excessive product quality. Insufficient product quality directly leads to customer complaints and has a negative impact on coal mines. When the product quality is excessive, it affects the clean coal recovery rate and the direct economic benefits of coal preparation.

[0004] Therefore, how to intelligently control the process of heavy medium coal separation density is a technical problem that needs to be solved. Summary of the invention

[0005] The purpose of the embodiments of the present application is to provide an intelligent control system for the separation density of heavy medium coal preparation. The technical solution of the embodiments of the present application can achieve the effect of intelligently controlling the separation density of heavy medium coal preparation.

[0006] In a first aspect, an embodiment of the present application provides an intelligent control system for heavy medium coal separation density, comprising a Siemens programmable logic controller, a first computer and a second computer; the Siemens programmable logic controller is used to: send heavy medium coal separation data measured in a heavy medium process to the first computer, and send preset density data to the second computer, wherein the heavy medium coal separation data includes a heavy medium coal separation density feedback value and a diverter box valve opening feedback value, and the density data includes a density setting value and a density simulation value; the first computer is used to: establish a mathematical model through the received heavy medium coal separation data in combination with commercial mathematical software and a multi-layer feedforward neural network; the second computer is used to: evaluate the performance of the control system through the received density data in combination with the mean square error and the absolute value integral of the error, and adaptively control the control system using an artificial neural network system through an adaptive intelligent controller.

[0007] In the above system, the present application achieves the effect of intelligently controlling the heavy medium coal separation density by monitoring the heavy medium coal separation data and preset density data of the heavy medium process and using a computer to establish a mathematical model and evaluate and control the control system.

[0008] In some embodiments, the second computer includes:

[0009] Evaluation module, visualization software and adaptive intelligent controller; the evaluation module is used to evaluate density data and determine whether the density data meets the performance index of the control system; the visualization software is used to send the received valve opening given value to the Siemens programmable logic controller when the density data meets the intelligent index of the control system, wherein the valve opening given value is used by the Siemens programmable logic controller to send the valve opening given value to the valve opening signal receiving end of the diverter box to control the valve opening of the diverter box; the adaptive intelligent controller is used to correct the parameters of the adaptive intelligent controller using an artificial neural network system, and send the obtained correction parameters to the first computer.

[0010] In the above system, the evaluation module, visualization software and adaptive intelligent controller of the second computer can send the valve opening set value to the Siemens programmable logic controller according to the density data, so that the Siemens programmable logic controller can control the valve opening of the diversion box to achieve the effect of intelligently controlling the density of heavy medium coal separation.

[0011] In some embodiments, the evaluation module is specifically used to:

[0012] When it is determined that the density data meets the intelligent indicators of the control system, the output valve opening given value is sent to the visualization software; when it is determined that the density data does not meet the intelligent indicators of the control system, the preset second density data is sent to the adaptive intelligent controller, wherein the second density data includes a second density setting value and a second density simulation value.

[0013] In the above system of the present application, when the density data does not meet the intelligent indicators of the control system, another density data can be resent to the adaptive intelligent controller to realize the intelligent control process of the re-heavy medium coal separation density and achieve the intelligent control effect of accurate heavy medium coal separation density.

[0014] In some embodiments, the first computer is specifically configured to:

[0015] The received correction parameters are simulated through a mathematical model to obtain a corrected target setting value and a density simulation value; the corrected target setting value and the density simulation value are sent to an evaluation module;

[0016] The evaluation module is specifically used for:

[0017] Evaluate the corrected target setting value and density simulation value, and send the obtained second diverter valve opening set value that meets the intelligent index of the control system to the visualization software;

[0018] The visualization software is specifically used to send the second diverter valve opening set value to the Siemens programmable logic controller, so that the Siemens programmable logic controller sends the second diverter valve opening set value to the diverter box valve opening signal receiving end, so as to control the diverter box valve opening.

[0019] In the above system of the present application, the corrected density data can be re-evaluated and transmitted by the first computer to facilitate accurate control of the opening of the diverter box valve.

[0020] In some embodiments, the multi-layer feedforward neural network is a multi-layer structure, the input is the valve opening feedback value, and the output is the density simulation value.

[0021] In the above system of the present application, a mathematical model can be accurately established through a multi-layer feedforward neural network, thereby realizing accurate intelligent control of the separation density of heavy medium coal preparation.

[0022] In the second aspect, an embodiment of the present application provides an intelligent control method for heavy medium coal sorting density, including: obtaining heavy medium coal sorting data measured in the heavy medium process and preset density data; establishing a mathematical model through the heavy medium coal sorting data in combination with commercial mathematical software and a multi-layer feedforward neural network; evaluating the performance of the intelligent control system for heavy medium coal sorting density through preset density data in combination with mean square error and absolute value integral of error, and adaptively controlling the control system using an artificial neural network system through an adaptive intelligent controller.

[0023] In the above embodiments of the present application, by monitoring the heavy medium coal separation data and preset density data of the heavy medium process, and utilizing the relevant data to establish a mathematical model and evaluate and control the control system, the effect of intelligently controlling the heavy medium coal separation density can be achieved.

[0024] In some embodiments, after evaluating the performance of the intelligent control system for heavy medium coal separation density through preset density data in combination with the mean square error and the absolute value integral of the error, and adaptively controlling the control system using an artificial neural network system through an adaptive intelligent controller, it also includes: evaluating the density data to determine whether the density data meets the performance indicators of the control system; when it is determined that the density data meets the intelligent indicators of the control system, sending the output valve opening set value to the visualization software, wherein the valve opening set value is used by the Siemens programmable logic controller to send the valve opening set value to the diverter box valve opening signal receiving end to facilitate the control of the diverter box valve opening.

[0025] In the above embodiment of the present application, the valve opening given value can be sent to the Siemens programmable logic controller according to the density data, so that the Siemens programmable logic controller can control the valve opening of the diversion box to achieve the effect of intelligently controlling the density of heavy medium coal separation.

[0026] In a third aspect, the embodiment of the present application provides an intelligent control device for dense medium coal separation density, comprising:

[0027] An acquisition module is used to acquire the heavy medium coal separation data and preset density data measured in the heavy medium process;

[0028] Establish a module for building a mathematical model using heavy medium coal separation data in combination with commercial mathematical software and a multi-layer feed-forward neural network;

[0029] The control module is used to evaluate the performance of the intelligent control system of the heavy medium coal separation density by using preset density data in combination with the mean square error and the absolute value integral of the error, and to adaptively control the control system using an artificial neural network system through an adaptive intelligent controller.

[0030] Optionally, the device further comprises:

[0031] An evaluation module is used for evaluating the density data to determine whether the density data meets the performance index of the control system after the control module evaluates the performance of the intelligent control system of the heavy medium coal separation density by using preset density data and combining the mean square error and the absolute value integral of the error, and adaptively controls the control system by using the artificial neural network system through the adaptive intelligent controller;

[0032] When it is determined that the density data meets the intelligent indicators of the control system, the output valve opening set value is sent to the visualization software, wherein the valve opening set value is used by the Siemens programmable logic controller to send the valve opening set value to the diverter box valve opening signal receiving end, so as to control the diverter box valve opening.

[0033] In a fourth aspect, an embodiment of the present application provides an electronic device, comprising a processor and a memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the steps in the method provided in the second aspect are executed.

[0034] In a fifth aspect, an embodiment of the present application provides a readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps in the method provided in the second aspect are executed.

[0035] Other features and advantages of the present application will be described in the following description, and partly become apparent from the description, or be understood by practicing the embodiments of the present application. The purpose and other advantages of the present application can be realized and obtained by the structures specifically pointed out in the written description, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0037] Figure 1 A schematic block diagram of an intelligent control system for heavy medium coal separation density provided in an embodiment of the present application;

[0038] Figure 2 A schematic diagram of a PID self-correction control structure of an RBF neural network provided in an embodiment of the present application;

[0039] Figure 3 A flow chart of an intelligent control method for heavy medium coal separation density provided in an embodiment of the present application;

[0040] Figure 4 A schematic block diagram of an intelligent control device for heavy medium coal separation density provided in an embodiment of the present application;

[0041] Figure 5 A schematic block diagram of the structure of an intelligent control device for heavy medium coal separation density provided in an embodiment of the present application. DETAILED DESCRIPTION

[0042] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application usually described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0043] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0044] First, some terms involved in the embodiments of the present application are explained to facilitate understanding by those skilled in the art.

[0045] The Chinese name of PLC is Programmable Logic Controller, which is used as a digital operating electronic system in industrial applications. It uses programmable memory to internally store and execute logic operations, sequential control, arithmetic operations and other operating instructions.

[0046] BP (back propagation) neural network is a multi-layer feedforward neural network trained according to the error back propagation algorithm. It is one of the most widely used neural network models.

[0047] RBF neural network is an artificial neural network, and its name comes from the radial basis function (Radial Basis Function). This network model is often used in pattern recognition, function approximation and nonlinear data modeling. RBF neural network consists of three main layers: input layer, hidden layer and output layer. Among them, the neuron transformation function in the hidden layer is the radial basis function, which has the characteristics of local response, that is, a non-negative nonlinear function that is radially symmetric and attenuated about the center point.

[0048] MATLAB is a commercial mathematical software used in data analysis, wireless communications, deep learning, image processing and computer vision, signal processing, quantitative finance and risk management, robotics, control systems and other fields.

[0049] The OPC protocol is a communication protocol based on Microsoft's OLE (Object Linking and Embedding) technology, developed specifically for the field of industrial automation software.

[0050] WinCC Server software is a high-performance visualization software provided by Siemens, which is used to complete simple and machine-oriented visualization tasks.

[0051] Adaptive PID (controller) control refers to the adaptive PID control or self-correcting PID control technology formed by combining the adaptive control idea with the conventional PID controller, which is collectively referred to as adaptive PID control.

[0052] The separation density of heavy medium coal preparation refers to the efficient separation of coal by adjusting the density of the suspension during the heavy medium coal preparation process. The basic principle of heavy medium coal preparation is based on the Archimedean principle, that is, the buoyancy of particles immersed in liquid is equal to the weight of the same volume of liquid displaced by the particles.

[0053] The present application is applied to the scenario of intelligent heavy medium coal preparation. The specific scenario is to obtain and set relevant data through a Siemens programmable logic controller, and the computer uses the relevant data to establish a mathematical model and control heavy medium coal preparation.

[0054] As one of the main energy sources, my country's coal resources are among the highest in the world in terms of reserves and distribution, supporting the continuous development of my country's modernization and industrialization. Although the development and utilization of new energy sources have gradually become the focus of national attention, coal still firmly occupies a dominant position in the energy consumption structure. The density of heavy medium suspension is the core goal of heavy medium separation control. The density control of traditional separation is completely determined by manual experience. There is no mature and reliable data analysis system to guide the operation. The heavy medium density index cannot be accurately adjusted through data analysis, which easily leads to insufficient product quality or excessive product quality. Insufficient product quality directly leads to customer complaints and has a negative impact on coal mines. When product quality is excessive, it affects the recovery rate of clean coal and the direct economic benefits of coal preparation.

[0055] To this end, the present application adopts an intelligent control system for the density of heavy medium coal separation, including a Siemens programmable logic controller, a first computer and a second computer; the Siemens programmable logic controller is used to: send the heavy medium coal separation data measured in the heavy medium process to the first computer, and send the preset density data to the second computer, wherein the heavy medium coal separation data includes the feedback value of the heavy medium coal separation density and the feedback value of the valve opening of the diverter box, and the density data includes the density setting value and the density simulation value; the first computer is used to: establish a mathematical model by combining the received heavy medium coal separation data with commercial mathematical software and a multi-layer feedforward neural network; the second computer is used to: evaluate the performance of the control system by combining the received density data with the mean square error and the absolute value integral of the error, and adaptively control the control system using an artificial neural network system through an adaptive intelligent controller. By monitoring the heavy medium coal separation data and the preset density data of the heavy medium process, using a computer to realize the establishment of a mathematical model and the evaluation and control of the control system, the effect of intelligently controlling the density of heavy medium coal separation can be achieved.

[0056] In the embodiment of the present application, the execution entity may be a heavy medium coal separation density device in a heavy medium coal separation density system. In actual applications, the heavy medium coal separation density device may be electronic devices such as terminal devices and servers, which are not limited here.

[0057] Combine the following Figure 1 The intelligent control system of the heavy medium coal separation density in the embodiment of the present application is described in detail.

[0058] Please see Figure 1 , Figure 1 A schematic block diagram of an intelligent control system for heavy medium coal separation density provided in an embodiment of the present application, such as Figure 1 The intelligent control system of heavy medium coal separation density shown includes:

[0059] Siemens programmable logic controller 110, first computer 120 and second computer 130; Siemens programmable logic controller 110 is used to: send the heavy medium coal separation data measured in the heavy medium process to the first computer 120, and send the preset density data to the second computer 130, wherein the heavy medium coal separation data includes the heavy medium coal separation density feedback value and the diverter box valve opening feedback value, and the density data includes the density setting value and the density simulation value; the first computer 120 is used to: establish a mathematical model through the received heavy medium coal separation data in combination with commercial mathematical software and a multi-layer feedforward neural network; the second computer 130 is used to: evaluate the performance of the control system through the received density data in combination with the mean square error and the absolute value integral of the error, and use the artificial neural network system to adaptively control the control system (PID) through the adaptive intelligent controller 1303.

[0060] The first computer 120 and the second computer 130 may be one or more, respectively, and the above process may be implemented multiple times. The first computer includes visualization software 1201 and commercial mathematical software 1202. The visualization software 1201 is used to store and send mathematical models, density-related data and valve opening given values, and the density-related data includes density actual value and set value, etc. The commercial mathematical software 1202 is used to establish a mathematical model. The Siemens programmable logic controller belongs to the Siemens PLC system, and the model can be selected according to demand, such as CPU 315-2PN / DP. The commercial mathematical software exchanges density data and mathematical models with the visualization software 1201 through the OPC protocol.

[0061] Specifically, the input signal of the mathematical model is u(k), i.e., the feedback value of the valve opening of the diverter box at the kth moment, and the output signal is y(k), i.e., the density simulation value of the heavy medium at the kth moment. The commercial mathematical software of the first computer outputs the density setting value yr(k) and the density simulation value y(k) to the second computer. The second computer uses the evaluation system to evaluate the control performance of the heavy medium suspension density control process by using the performance evaluation indicators mean squared error (MSE) and integrated absolute error (IAE) for the first density setting value yr(k) and the density simulation value y(k). After the evaluation system evaluates the density setting value and the density given value, if the system control performance indicators are not met, the visualization software 1302 in the second computer will evaluate the density setting value yr(k) given by the evaluation system. r The adaptive intelligent controller uses the RBF neural network system to identify the corrected PID parameters, and gives the parameters to the simulation model in the first computer for further simulation calculation, and outputs the corrected density setting value y r(k) and density simulation value y(k) are sent to the evaluation system of the second computer for evaluation. If the diverter box valve opening meets the performance index after correction, the diverter valve opening given value is output to the visualization software 1302, and then the visualization software 1302 gives the diverter valve opening given value to the Siemens PLC control system, and then the Siemens PLC control system gives the diverter valve opening given value to the diverter box valve opening signal receiving end, thereby completing the control of the diverter box valve opening; if the performance is still not met after correction, this step is performed again until the performance index is met.

[0062] In addition, the BP neural network takes the input signal u(k), that is, the feedback value of the diverter box valve opening, and the output is y(k), that is, the density simulation value. A three-layer BP neural network is used, that is, the input is {y(k-1), u(k-1), u(k-2)}, the number of hidden layer nodes is 6, and the momentum factor α=0.05. Then, the incremental PID algorithm is used to correct the diverter box valve opening. After determining that the diverter box valve opening meets the performance index after correction, the specific correction method is as follows:

[0063] △u(k)=K p (k-1)x c1 (k)+K i (k-1)x c1 (k)+K d (k-1)x c1 (k);

[0064] In the formula, Kp, Ki, Kd are PID adjustment parameters, and

[0065]

[0066] The control law is u(k)=u(k-1)+Δu(k);

[0067] Among them, the RBF neural network uses the density setting value y r (k) and the actual value of density y(k) are calculated by the above formula to obtain the RBF system input signal u1(k). A 6-10-1 structure RBF neural network is adopted, with the input being {y(k-1), y(k-2); u(k), u(k-1), u(k-2), u(k-3)}, the output being ym(k), and the number of hidden nodes being 10. The network training learning rate η is taken as 0.5, and the momentum term factor α is taken as 0.05. The initial values ​​of the PID parameters are all taken as 0, the PID parameter learning rate ηc is taken as 1, and the momentum term factor α is taken as 0.1. u ​​represents the input or output related density data signal.

[0068] Specifically, the PID self-correction control structure based on the RBF neural network can correct the valve opening of the diverter box by Figure 2The PID self-tuning control structure of the RBF neural network is implemented as shown.

[0069] Please see Figure 2 , Figure 2 A schematic diagram of a PID self-correction control structure of an RBF neural network provided in this application includes:

[0070] The visualization software 1302 in the second computer 130 converts the density setting value y given by the evaluation module 1301 into r The adaptive intelligent controller 1303 uses the RBF neural network system to identify the corrected PID parameters, and gives the parameters to the simulation model in the first computer 120 for further simulation calculation, and outputs the corrected density setting value y r The first computer 120 uses a BP neural network based on a global error and corrected PID parameter identification to establish a system mathematical model.

[0071] also, Figure 2 The specific methods and steps shown can be found in Figure 1 The system shown will not be described in detail here.

[0072] Optionally, evaluating the performance of the control system by receiving the density data and combining the mean square error and the absolute value integral of the error can be achieved by the following formula:

[0073] Mean squared error (MSE);

[0074]

[0075] Integrated absolute error (IAE);

[0076]

[0077] Where N is a natural number, the actual density value y(k), and the simulated density value y sp( k), k is a positive integer greater than or equal to 2.

[0078] In some embodiments of the present application, the second computer 130 includes:

[0079] Evaluation module 1301, visualization software 1302 and adaptive intelligent controller 1303; evaluation module 1301 is used to: evaluate density data and determine whether the density data meets the performance indicators of the control system; visualization software 1302 is used to: when the density data meets the intelligent indicators of the control system, send the received valve opening given value to the Siemens programmable logic controller 110, wherein the valve opening given value is used for the Siemens programmable logic controller 110 to send the valve opening given value to the valve opening signal receiving end of the diverter box, so as to control the diverter box valve opening; adaptive intelligent controller 1303 is used to: use an artificial neural network system to correct the parameters of the adaptive intelligent controller 1303, and send the obtained correction parameters to the first computer 120.

[0080] In the above process, the evaluation module 1301, visualization software 1302 and adaptive intelligent controller 1303 of the second computer 130 can send the valve opening set value to the Siemens programmable logic controller 110 according to the density data, so that the Siemens programmable logic controller 110 can control the valve opening of the diversion box to achieve the effect of intelligently controlling the separation density of heavy medium coal separation.

[0081] The visualization software 1201 and the visualization software 1302 may be the same software or different software respectively installed on different computers.

[0082] In some embodiments of the present application, the evaluation module 1301 is specifically used to:

[0083] When it is determined that the density data meets the intelligent indicators of the control system, the output valve opening given value is sent to the visualization software 1302; when it is determined that the density data does not meet the intelligent indicators of the control system, the preset second density data is sent to the adaptive intelligent controller 1303, wherein the second density data includes a second density setting value and a second density simulation value.

[0084] In the above process, when the density data does not meet the intelligent index of the control system, the present application can resend another density data to the adaptive intelligent controller 1303 to realize the intelligent control process of the heavy medium coal separation density and achieve the intelligent control effect of accurate heavy medium coal separation density.

[0085] In some embodiments of the present application, the first computer 120 is specifically used for:

[0086] The received correction parameters are simulated through a mathematical model to obtain a corrected target setting value and a density simulation value; the corrected target setting value and the density simulation value are sent to the evaluation module 1301;

[0087] The evaluation module 1301 is specifically used for:

[0088] Evaluate the corrected target setting value and density simulation value, and send the obtained second diverter valve opening set value that meets the intelligent index of the control system to the visualization software 1302;

[0089] The visualization software 1302 is specifically used to send the second diverter valve opening set value to the Siemens programmable logic controller 110, so that the Siemens programmable logic controller 110 sends the second diverter valve opening set value to the diverter box valve opening signal receiving end to control the diverter box valve opening.

[0090] In the above process, the first computer 120 can re-evaluate and transmit the corrected density data to facilitate accurate control of the opening of the diverter box valve.

[0091] In some embodiments of the present application, the multi-layer feedforward neural network is a multi-layer structure, the input is the valve opening feedback value, and the output is the density simulation value.

[0092] In the above process, the present application can accurately establish a mathematical model through a multi-layer feedforward neural network, thereby realizing accurate intelligent control of the heavy medium coal separation density.

[0093] In the above Figure 1 In the process shown, the present application uses an intelligent control system for the separation density of heavy medium coal preparation, including a Siemens programmable logic controller, a first computer and a second computer; the Siemens programmable logic controller is used to: send the heavy medium coal preparation separation data measured in the heavy medium process to the first computer, and send the preset density data to the second computer, wherein the heavy medium coal preparation separation data includes the feedback value of the heavy medium coal preparation separation density and the feedback value of the valve opening of the diverter box, and the density data includes the density setting value and the density simulation value; the first computer is used to: establish a mathematical model by combining the received heavy medium coal preparation separation data with commercial mathematical software and a multi-layer feedforward neural network; the second computer is used to: evaluate the performance of the control system by combining the received density data with the mean square error and the absolute value integral of the error, and adaptively control the control system using an artificial neural network system through an adaptive intelligent controller. By monitoring the heavy medium coal preparation separation data and the preset density data of the heavy medium process, using a computer to realize the establishment of a mathematical model and the evaluation and control of the control system, the effect of intelligently controlling the separation density of heavy medium coal preparation can be achieved.

[0094] Combine the following Figure 3 The intelligent control method of the heavy medium coal separation density in the embodiment of the present application is described in detail.

[0095] Please see Figure 3 , Figure 3A flowchart of an intelligent control method for the separation density of heavy medium coal separation provided in an embodiment of the present application is shown in FIG. Figure 3 The intelligent control method of the heavy medium coal separation density shown includes:

[0096] Step 310: Obtaining the heavy medium coal separation data and preset density data measured in the heavy medium process.

[0097] Step 320: Establish a mathematical model by using the heavy medium coal separation data in combination with commercial mathematical software and a multi-layer feedforward neural network.

[0098] Step 330: Evaluate the performance of the intelligent control system for the density of heavy medium coal separation by using preset density data combined with mean square error and absolute value integral of error, and adaptively control the control system using an artificial neural network system through an adaptive intelligent controller.

[0099] In some embodiments of the present application, after evaluating the performance of the intelligent control system for dense medium coal separation density by using preset density data and combining mean square error and absolute value integral of error, and adaptively controlling the control system by using an artificial neural network system through an adaptive intelligent controller, Figure 3 The method shown also includes: evaluating the density data to determine whether the density data meets the performance indicators of the control system; when it is determined that the density data meets the intelligent indicators of the control system, sending the output valve opening set value to the visualization software, wherein the valve opening set value is used by the Siemens programmable logic controller to send the valve opening set value to the diverter box valve opening signal receiving end to facilitate the control of the diverter box valve opening.

[0100] In the above process, the present application can send the valve opening given value to the Siemens programmable logic controller according to the density data, so that the Siemens programmable logic controller can control the valve opening of the diverter box to achieve the effect of intelligently controlling the density of heavy medium coal separation.

[0101] also, Figure 3 The specific methods and steps shown can be found in Figure 1 The method shown will not be described in detail here.

[0102] Previous article Figure 3 Describes the intelligent control method of the separation density of heavy medium coal separation. Figure 4-Figure 5 Describe the intelligent control device for the separation density of heavy medium coal preparation.

[0103] Please refer to Figure 4 , is a schematic block diagram of an intelligent control device 400 for dense medium coal separation density provided in an embodiment of the present application, and the device 400 may be a module, program segment or code on an electronic device. The device 400 is similar to the above Figure 3The method embodiment corresponds to and can be executed Figure 3 The various steps involved in the method embodiment and the specific functions of the device 400 can be found in the description below. To avoid repetition, the detailed description is appropriately omitted here.

[0104] Optionally, the device 400 includes:

[0105] An acquisition module 410 is used to acquire the heavy medium coal separation data and preset density data measured in the heavy medium process;

[0106] Establishing module 420, for establishing a mathematical model by using heavy medium coal separation data and combining commercial mathematical software and a multi-layer feedforward neural network;

[0107] The control module 430 is used to evaluate the performance of the intelligent control system of the heavy medium coal separation density by using preset density data in combination with the mean square error and the absolute value integral of the error, and to adaptively control the control system using an artificial neural network system through an adaptive intelligent controller.

[0108] Optionally, the device further comprises:

[0109] An evaluation module is used for evaluating the density data after the control module evaluates the performance of the intelligent control system for the density of heavy medium coal separation through preset density data combined with the mean square error and the integral of the absolute value of the error, and adaptively controls the control system using an artificial neural network system through an adaptive intelligent controller, to determine whether the density data meets the performance indicators of the control system; when it is determined that the density data meets the intelligent indicators of the control system, the output valve opening given value is sent to the visualization software, wherein the valve opening given value is used by the Siemens programmable logic controller to send the valve opening given value to the valve opening signal receiving end of the diverter box to facilitate the control of the diverter box valve opening.

[0110] Please refer to Figure 5 5 is a block diagram showing the structure of an intelligent control device for dense medium coal separation density provided in an embodiment of the present application. The device may include a memory 510 and a processor 520. Optionally, the device may also include: a communication interface 530 and a communication bus 540. The device is connected to the above Figure 3 The method embodiment corresponds to and can be executed Figure 3 The various steps involved in the method embodiment and the specific functions of the device can be found in the description below.

[0111] Specifically, the memory 510 is used to store computer-readable instructions.

[0112] Processor 520, configured to process readable instructions stored in the memory, capable of executing Figure 3 The steps in the method.

[0113] The communication interface 530 is used for signaling or data communication with other node devices, for example, for communication with a server or a terminal, or for communication with other device nodes, but the embodiments of the present application are not limited thereto.

[0114] The communication bus 540 is used to realize direct connection and communication among the above components.

[0115] The communication interface 530 of the device in the embodiment of the present application is used to communicate signals or data with other node devices. The memory 510 can be a high-speed RAM memory or a non-volatile memory, such as at least one disk memory. The memory 510 can also be at least one storage device located away from the aforementioned processor. The memory 510 stores computer-readable instructions. When the computer-readable instructions are executed by the processor 520, the electronic device executes the aforementioned Figure 3 The method process shown. The processor 520 can be used on the device 400 and used to perform the functions in the present application. Exemplarily, the above-mentioned processor 520 can be a general-purpose processor, a digital signal processor (Digital Signal Processor, DSP), an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), a field programmable gate array (Field Programmable Gate Array, FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, and the embodiments of the present application are not limited thereto.

[0116] The embodiment of the present application also provides a readable storage medium, when the computer program is executed by a processor, Figure 3 The method process in the method embodiment shown is executed by the electronic device.

[0117] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the device described above can refer to the corresponding process in the aforementioned method, and will not be described in detail here.

[0118] In summary, the embodiment of the present application provides an intelligent control system and method for the density of heavy medium coal separation, the system includes a Siemens programmable logic controller, a first computer and a second computer; the Siemens programmable logic controller is used to send the heavy medium coal separation data measured in the heavy medium process to the first computer, and send the preset density data to the second computer, wherein the heavy medium coal separation data includes the feedback value of the density of heavy medium coal separation and the feedback value of the valve opening of the diverter box, and the density data includes the density setting value and the density simulation value; the first computer is used to establish a mathematical model by combining the received heavy medium coal separation data with commercial mathematical software and a multi-layer feedforward neural network; the second computer is used to evaluate the performance of the control system by combining the received density data with the mean square error and the absolute value integral of the error, and adaptively control the control system using an artificial neural network system through an adaptive intelligent controller. The system can achieve the effect of intelligently controlling the density of heavy medium coal separation.

[0119] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of a code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0120] In addition, the functional modules in the various embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

[0121] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0122] The above description is only an embodiment of the present application and is not intended to limit the scope of protection of the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application. It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings.

[0123] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0124] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

Claims

1. An intelligent control system for the separation density of heavy medium coal preparation, characterized in that: include: Siemens programmable logic controller, first computer and second computer; The Siemens programmable logic controller is used to: send the heavy medium coal separation data measured in the heavy medium process to the first computer, and send the preset density data to the second computer, wherein the heavy medium coal separation data includes the heavy medium coal separation density feedback value and the diverter box valve opening feedback value, and the density data includes the density setting value and the density simulation value; The first computer is used to: establish a mathematical model by combining the received heavy medium coal separation data with commercial mathematical software and a multi-layer feedforward neural network; The second computer is used to: evaluate the performance of the control system by receiving density data in combination with mean square error and absolute value integral of error, and adaptively control the control system by using an artificial neural network system through an adaptive intelligent controller.

2. The system according to claim 1, characterized in that The second computer comprises: evaluation modules, visualization software, and adaptive intelligent controllers; The evaluation module is used to: evaluate the density data to determine whether the density data meets the performance index of the control system; The visualization software is used to: when the density data meets the intelligent index of the control system, send the received valve opening given value to the Siemens programmable logic controller, wherein the valve opening given value is used for the Siemens programmable logic controller to send the valve opening given value to the diverter box valve opening signal receiving end, so as to control the diverter box valve opening; The adaptive intelligent controller is used to correct the parameters of the adaptive intelligent controller using an artificial neural network system, and send the obtained corrected parameters to the first computer.

3. The system according to claim 2, characterized in that The evaluation module is specifically used for: When it is determined that the density data meets the intelligent index of the control system, the output valve opening given value is sent to the visualization software; When it is determined that the density data does not meet the intelligent index of the control system, the preset second density data is sent to the adaptive intelligent controller, wherein the second density data includes a second density setting value and a second density simulation value.

4. The system according to claim 2, characterized in that The first computer is specifically used for: The received correction parameters are simulated through the mathematical model to obtain the corrected target setting value and density simulation value; Sending the corrected target setting value and density simulation value to the evaluation module; The evaluation module is specifically used for: Evaluate the corrected target setting value and density simulation value, and send the obtained second diverter valve opening given value that meets the intelligent index of the control system to the visualization software; The visualization software is specifically used to send the second diverter valve opening set value to the Siemens programmable logic controller, so that the Siemens programmable logic controller sends the second diverter valve opening set value to the diverter box valve opening signal receiving end, so as to control the diverter box valve opening.

5. The system according to any one of claims 1 to 4, characterized in that: The multi-layer feedforward neural network is a multi-layer structure, the input is the valve opening feedback value, and the output is the density simulation value.

6. An intelligent control method for dense medium coal separation density, characterized in that: include: Obtaining the heavy medium coal separation data and preset density data measured in the heavy medium process; A mathematical model is established by using the heavy medium coal separation data in combination with commercial mathematical software and a multi-layer feedforward neural network; The performance of the intelligent control system for dense medium coal separation density is evaluated by combining the preset density data with the mean square error and the absolute value integral of the error, and the control system is adaptively controlled by an adaptive intelligent controller using an artificial neural network system.

7. The method according to claim 6, characterized in that After evaluating the performance of the intelligent control system for dense medium coal separation density by using the preset density data in combination with the mean square error and the absolute value integral of the error, and adaptively controlling the control system by using an artificial neural network system through an adaptive intelligent controller, the method further includes: Evaluating the density data to determine whether the density data meets the performance index of the control system; When it is determined that the density data meets the intelligent indicators of the control system, the output valve opening set value is sent to the visualization software, wherein the valve opening set value is used by the Siemens programmable logic controller to send the valve opening set value to the diverter box valve opening signal receiving end to facilitate the control of the diverter box valve opening.

8. An intelligent control device for the separation density of heavy medium coal separation, characterized in that: include: An acquisition module is used to acquire the heavy medium coal separation data and preset density data measured in the heavy medium process; Establishing a module for establishing a mathematical model through the heavy medium coal separation data combined with commercial mathematical software and a multi-layer feedforward neural network; The control module is used to evaluate the performance of the intelligent control system of the heavy medium coal separation density through the preset density data combined with the mean square error and the absolute value integral of the error, and to adaptively control the control system using an artificial neural network system through an adaptive intelligent controller.

9. An electronic device, characterized in that: include: A memory and a processor, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the steps in the method according to any one of claims 6 to 7 are executed.

10. A computer-readable storage medium, characterized in that: include: A computer program, when the computer program is run on a computer, causes the computer to execute the method according to any one of claims 6 to 7.

Images