A milling multivariable control system, method, electronic device and storage medium

Abstract

The present application discloses a pulverizing multivariable control system, method, electronic device and storage medium, which relate to the technical field of pulverized coal preparation. The system trains a temperature flow prediction model to predict the primary air flow and the mill outlet temperature, obtains the speed of the coal feeder and the moisture content of the pulverized coal, and calculates the estimated value of the pulverized coal flow at the mill outlet; calculates the primary air flow set value based on the estimated value of the pulverized coal flow at the mill outlet; measures the coal quality parameters to calculate the coal quality correction coefficient, measures the pulverizer current to calculate the pulverizer load correction coefficient, calculates the pulverized coal quality correction coefficient based on the moisture content of the pulverized coal, and calculates the mill outlet temperature set value; constructs a step-by-step prediction controller, takes the pulverizer output instruction, the primary air flow set value and the mill outlet temperature set value as input, takes the cold air door opening, the hot air door opening and the coal feeder speed as output, and designs the objective function and constraint conditions; calculates a control sequence of Nc time steps, outputs the first control action, and realizes coordinated control of the multivariable pulverizing system.

Description

Technical Field

[0001] The present application relates to the technical field of coal powder preparation, and in particular to a coal powder preparation multivariable control system, method, electronic equipment and storage medium. Background Art

[0002] In coal-fired power plants or industrial boilers, pulverized coal preparation is one of the key process links in the fuel supply system. Its main purpose is to process raw coal into pulverized coal with appropriate fineness and moisture content to meet the fuel quality requirements of boiler combustion. The quality of pulverized coal preparation directly affects the boiler's combustion efficiency, thermal parameters, pollutant emissions and other indicators.

[0003] The pulverized coal preparation process usually includes the following steps: raw coal storage and transportation, raw coal screening and crushing, coal grinding, drying, distribution, and slag removal. The traditional pulverized coal preparation system control mainly adopts a combination of single-loop PID control and manual operation, which has problems such as poor control accuracy, strong dependence on personnel, and high energy consumption.

[0004] A Chinese patent with publication number CN103097969A discloses a computer-based method and apparatus for automatically providing control parameters for multiple coal mills that supply coal powder to a factory, the method comprising: (a) obtaining multiple operating variables indicating the load of an individual coal mill for each coal mill by measuring actual parameters indicating the operation of the coal mill; (b) obtaining a demand variable indicating coal demand from the factory; (c) supplying the obtained multiple operating variables and demand variables to a computing system; (d) using a multivariable computing algorithm, specifically a model prediction algorithm, to calculate control parameters based on multiple operating variables and demand variables; (e) providing the calculated control parameters to individually control the operation of each coal mill; and (f) repeating steps (a)-(e).

[0005] The energy-saving optimization control of the existing pulverizing system faces the following challenges: the traditional pulverized coal preparation system control mainly adopts a combination of single-loop PID control and manual operation, which has the problem of poor control accuracy. The traditional PID control belongs to single-loop control and it is difficult to deal with the coupling problem of multivariable systems. Summary of the invention

[0006] The present application aims to solve at least one of the technical problems in the related art to a certain extent. To this end, one purpose of the present application is to propose a multivariable control system, method, electronic device and storage medium for milling, which realizes the coordinated control of the multivariable milling system.

[0007] One aspect of the present application provides a multivariable control method for milling, comprising:

[0008] Step S100: Obtain valve parameters, primary air flow rate and mill outlet temperature at historical time, train to obtain a temperature flow prediction model, predict the current primary air flow rate and mill outlet temperature, obtain the current coal feeder speed and coal powder moisture, and calculate the estimated value of the mill outlet coal powder flow rate;

[0009] Step S200: Compensate and optimize the primary air flow rate according to the estimated value of the pulverized coal flow rate at the mill outlet, and calculate the set value of the primary air flow rate;

[0010] Step S300: Measure the coal quality parameters and calculate the coal quality correction coefficient, determine the current coal mill current, calculate the coal mill load correction coefficient, calculate the coal powder quality correction coefficient according to the current coal powder moisture, and comprehensively calculate the mill outlet temperature setting value based on the current mill outlet temperature;

[0011] Step S400: construct a step-by-step predictive controller, taking the coal mill output command, the primary air flow set value and the mill outlet temperature set value as inputs, and taking the cold air door opening, the hot air door opening and the coal feeder speed as outputs, and designing the objective function and constraint conditions of the step-by-step predictive controller;

[0012] Step S500: Obtain the output command of a single coal mill, input the primary air flow set value, the mill outlet temperature set value and the single coal mill output command into the step predictive controller, calculate the control sequence of Nc time steps, and output the cold air door opening, hot air door opening and coal feeder speed of the first control action in the control sequence.

[0013] Furthermore, the specific method of obtaining the valve parameters, primary air flow rate and mill outlet temperature of the historical time, training the temperature flow prediction model, predicting the current primary air flow rate and mill outlet temperature, obtaining the current coal feeder speed and coal powder moisture, and calculating the estimated value of the mill outlet coal powder flow rate is:

[0014] Step S110: Collect valve parameters, primary air flow and mill outlet temperature in a historical time period, wherein the valve parameters include the hot air valve opening and the cold air valve opening, preset a sliding window length, a sliding step length and a prediction time step length, and divide the valve parameters, primary air flow and mill outlet temperature into N training samples using a sliding time window method;

[0015] Step S120: construct a multi-layer feedforward neural network as the initial network for training the temperature and flow prediction model, wherein the input layer of the multi-layer feedforward neural network includes two nodes: the hot air door opening and the cold air door opening, and the output layer includes two nodes: the primary air flow and the mill outlet temperature;

[0016] Step S130: select mean square error as the loss function of the temperature flow prediction model, take accurate prediction of the primary air flow and mill outlet temperature of each training sample as the prediction target, take minimizing the loss function as the training target, and when the value of the loss function converges to the minimum, the training is completed and the temperature flow prediction model is obtained;

[0017] The calculation formula of the loss function is: ,in, is the loss function value, N is the total number of training samples, n∈{1,2,...,N}, represents the actual value of the primary wind flow of the nth training sample, It represents the predicted value of primary wind flow. represents the actual value of the mill outlet temperature of the nth training sample, Indicates the predicted value of the mill outlet temperature;

[0018] Step S140: obtaining current valve parameters, using the current valve parameters as input data, inputting the trained temperature and flow prediction model, and obtaining the current primary air flow and mill outlet temperature;

[0019] Step S150: Obtain the current rotation speed of the coal feeder and the moisture content of the pulverized coal, and calculate the estimated flow rate of the pulverized coal at the mill outlet in combination with the current primary air flow rate;

[0020] The calculation formula for the estimated value of the coal powder flow rate at the mill outlet is: ,in, Estimated value of coal powder flow rate at mill outlet, is the current primary wind flow, is the current mill outlet temperature, is the mill inlet temperature, is the coal entering grinding temperature, is the specific heat capacity of coal powder, and MF is the moisture content of coal powder.

[0021] Furthermore, the specific method for compensating and optimizing the primary air flow rate according to the estimated value of the coal powder flow rate at the mill outlet and calculating the set value of the primary air flow rate is:

[0022] Step S210: preset a set value of the coal powder flow rate at the mill outlet, calculate the deviation between the estimated value of the coal powder flow rate at the mill outlet and the set value of the coal powder flow rate at the mill outlet, and calculate the compensation amount of the primary air flow according to the deviation;

[0023] The deviation between the estimated value of the mill outlet coal powder flow rate and the set value of the mill outlet coal powder flow rate The calculation formula is: ,in, The setting value of the coal powder flow rate at the mill outlet;

[0024] The compensation amount of the primary air flow The calculation formula is: ,in, is the compensation coefficient;

[0025] Step S220: Optimize the primary air flow rate according to the compensation amount of the primary air flow rate to obtain the primary air flow rate setting value. ;

[0026] The primary air flow setting value The calculation formula is: ,in, The current primary wind flow rate predicted by the temperature flow prediction model.

[0027] Furthermore, the specific method of measuring the coal quality parameters and calculating the coal quality correction coefficient, determining the current coal mill current, calculating the coal mill load correction coefficient, calculating the coal powder quality correction coefficient according to the current coal powder moisture, and comprehensively calculating the mill outlet temperature setting value based on the current mill outlet temperature is as follows:

[0028] Step S310: directly measuring and obtaining coal quality parameters of the coal using an industrial analyzer, wherein the coal quality parameters include ash content, volatile matter and dry basis moisture, and measuring the current coal mill current;

[0029] Step S320: Obtain the standard values ​​of coal ash, volatile matter and dry basis moisture, calculate the ratio of the measured ash, volatile matter and dry basis moisture to the standard values ​​of the corresponding coal ash, volatile matter and dry basis moisture, and obtain the coal quality correction coefficient by weighted summation. ;

[0030] The calculation formula of the coal quality correction coefficient is: ,in, , , Respectively represent the measured ash, volatile matter and moisture on a dry basis, , , Respectively represent the standard values ​​of coal ash, volatile matter and dry basis moisture, , , represent the weight coefficients of ash, volatile matter and moisture on dry basis respectively;

[0031] Step S330: Obtain the rated coal mill current value, calculate the ratio of the current coal mill current to the rated coal mill current value, and obtain the coal mill load correction coefficient by weighted calculation. ;

[0032] The calculation formula of the coal mill load correction coefficient is: ,in, is the current coal mill current, is the rated coal mill current value, is the empirical coefficient of coal mill current;

[0033] Step S340: Obtain the standard value of coal powder moisture, calculate the ratio of the current coal powder moisture to the standard value of coal powder moisture, and obtain the coal powder quality correction coefficient by weighted calculation. ;

[0034] The calculation formula of the coal powder quality correction coefficient is: ,in, is the standard value of moisture in pulverized coal, is the empirical coefficient of coal powder moisture;

[0035] Step S350: Multiply the coal quality correction factor, the coal mill load correction factor and the coal powder quality correction factor by the current mill outlet temperature to calculate the mill outlet temperature setting value. ;

[0036] The calculation formula of the grinding outlet temperature setting value is: .

[0037] Furthermore, the step-by-step predictive controller is constructed, with the coal mill output command, the primary air flow set value and the mill outlet temperature set value as input, and the cold air door opening, the hot air door opening and the coal feeder speed as output. The specific method for designing the objective function and constraint conditions of the step-by-step predictive controller is as follows:

[0038] Step S410: construct a step predictive controller, and select a nonlinear model predictive controller as the controller type of the step predictive controller;

[0039] Step S420: using the coal mill output command, the primary air flow rate setting value and the mill outlet temperature setting value of the coal mill as inputs of the step-type predictive controller, and using the cold air door opening, the hot air door opening and the coal feeder speed as outputs of the step-type predictive controller;

[0040] Step S430: Preset the prediction time domain and the control time domain, the prediction time domain is greater than or equal to the control time domain, and design the objective function and constraint conditions of the step predictive controller.

[0041] Furthermore, the specific method for designing the objective function and constraint conditions of the step-wise predictive controller is as follows:

[0042] The objective function of the step-wise predictive controller is designed, and the functional expression of the objective function is: ,in, represents the number of time steps in the prediction domain, represents the number of time steps in the control time domain, They represent the weight coefficients of the primary air flow setting value, the mill outlet temperature setting value, and the coal mill output instruction respectively. They represent the weight coefficients of the cold air door opening, hot air door opening and coal feeder speed respectively. They represent the primary air flow, mill outlet temperature and coal mill current at the i-th time step in the prediction domain, respectively. Indicates the coal mill output command. They represent the cold air door opening, hot air door opening and coal feeder speed at the i-th time step in the control time domain respectively;

[0043] Design the constraints of the step predictive controller, the expressions of the constraints include: ,in, are the minimum and maximum values ​​of the cold air door opening, are the minimum and maximum values ​​of the hot air door opening, are the minimum and maximum values ​​of the coal feeder speed respectively.

[0044] Furthermore, the specific method of obtaining the output command of a single coal mill, inputting the primary air flow set value, the mill outlet temperature set value and the output command of a single coal mill into the step-type predictive controller, calculating the control sequence of Nc time steps, and outputting the cold air door opening, hot air door opening and coal feeder speed of the first control action in the control sequence is as follows:

[0045] Step S510: Obtaining the coal mill output instruction of a single coal mill , get the optimized primary air flow setting value , Grinding outlet temperature setting value , which is input into the step predictive controller as an input variable;

[0046] Step S520: Use the sequential quadratic programming algorithm to calculate the objective function and constraints of the step-wise predictive controller to obtain the control sequence for the next Nc time steps. ,in, represents the control action at the first time step, represents the control action at the Nc-th time step, They represent the cold air door opening, hot air door opening and coal feeder speed of the Nc-th control action respectively;

[0047] Step S530: From the control sequence Extract the control action for the first time step from , the control action of the first time step is output as the optimal control action for actual control of pulverizing, and the cold air door opening, hot air door opening and coal feeder speed are adjusted.

[0048] One aspect of the present application provides a milling multivariable control system, comprising:

[0049] The pulverized coal flow estimation module is used to obtain valve parameters, primary air flow and mill outlet temperature in historical time, train a temperature flow prediction model, predict the current primary air flow and mill outlet temperature, obtain the current coal feeder speed and pulverized coal moisture, and calculate the estimated value of the pulverized coal flow at the mill outlet;

[0050] A primary air flow setting module is used to optimize the primary air flow according to the estimated value of the coal powder flow at the mill outlet, and calculate the primary air flow setting value;

[0051] The temperature setting calculation module is used to measure the coal quality parameters and calculate the coal quality correction coefficient, determine the current coal mill current, calculate the coal mill load correction coefficient, calculate the coal powder quality correction coefficient according to the current coal powder moisture, and comprehensively calculate the mill outlet temperature setting value based on the current mill outlet temperature;

[0052] The controller design module is used to construct a step-by-step predictive controller. It takes the coal mill output command, the primary air flow set value and the mill outlet temperature set value as inputs, and the cold air door opening, hot air door opening and coal feeder speed as outputs to design the objective function and constraints of the step-by-step predictive controller.

[0053] The optimal control output module is used to obtain the output command of a single coal mill, input the primary air flow set value, the mill outlet temperature set value and the single coal mill output command into the step-by-step predictive controller, calculate the control sequence of Nc time steps, and output the cold air door opening, hot air door opening and coal feeder speed of the first control action in the control sequence.

[0054] One aspect of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps in a multivariable control method for milling are implemented.

[0055] One aspect of the present application provides a readable storage medium storing a computer program, wherein the computer program is suitable for loading into a processor to execute steps in a multivariable control method for milling.

[0056] The milling multivariable control system, method, electronic device and storage medium proposed in this application have the following advantages over the prior art:

[0057] By constructing a temperature flow prediction model and combining it with real-time operating parameters, the current primary air flow and mill outlet temperature are predicted, and the primary air flow is compensated and optimized. This solves the problem of inaccurate primary air flow control in traditional methods and achieves precise regulation of the primary air flow.

[0058] Taking into account coal quality parameters, pulverizer load, coal powder quality and other factors, the correction coefficient is introduced to dynamically optimize the mill outlet temperature setting value. Traditional methods often ignore the impact of coal quality and equipment operating conditions on output temperature, resulting in unstable temperature control. The correction coefficient mechanism can dynamically adapt to changes in operating conditions.

[0059] A step-by-step predictive controller is used to integrate multiple subsystems such as coal feeding, air supply and powder exhaust into the control framework, realizing multi-variable collaborative optimization and dealing with the coupling relationship of complex systems. This application can achieve coordination between subsystems through model prediction and overcome coupling interference.

[0060] In the step-wise predictive controller, an objective function including multi-objective optimization is constructed and operable constraints are given. This enables the controller to balance multiple performance indicators such as energy consumption, output, quality, etc. while meeting process constraints, and achieve the best in a global sense. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Figure 1 A method flow chart of a multivariable control method for milling provided in this application;

[0062] Figure 2 A functional module diagram of a milling multivariable control system provided in this application;

[0063] Figure 3 A schematic diagram of the structure of an electronic device provided in this application;

[0064] Figure 4 It is a schematic diagram of the structure of a readable storage medium provided by this application. DETAILED DESCRIPTION

[0065] In order to better understand the present application, various aspects of the present application will be described in more detail with reference to the accompanying drawings. It should be understood that these detailed descriptions are only descriptions of exemplary embodiments of the present application and do not limit the scope of the present application in any way. Throughout the specification, the same reference numerals refer to the same elements. The expression "and / or" includes any and all combinations of one or more of the associated listed items.

[0066] In the accompanying drawings, the size, dimensions and shapes of the elements have been slightly adjusted for ease of illustration. The drawings are for illustration only and are not strictly drawn to scale. As used herein, the terms "substantially", "approximately" and similar terms are used as terms of approximation, not as terms of degree, and are intended to illustrate the inherent deviations in measurements or calculations that will be recognized by those of ordinary skill in the art. In addition, in this application, the order in which the steps are described does not necessarily represent the order in which these processes occur in actual operation, unless otherwise specified or can be derived from the context.

[0067] It should also be understood that expressions such as "including", "comprising", "having", "containing" and / or "comprising" are open rather than closed expressions in this specification, which indicate the presence of the stated features, elements and / or components, but do not exclude the presence of one or more other features, elements, components and / or combinations thereof. In addition, when expressions such as "at least one of..." appear after a list of listed features, they modify the entire list of features rather than just the individual elements in the list. In addition, when describing embodiments of the present application, "may" is used to mean "one or more embodiments of the present application". And, the term "exemplary" is intended to refer to an example or illustration.

[0068] Unless otherwise defined, all words (including engineering terms and scientific and technological terms) used in this article have the same meaning as those commonly understood by ordinary technicians in the field to which this application belongs. It should also be understood that unless there is a clear explanation in this application, words defined in commonly used dictionaries should be interpreted as having the same meaning as their meaning in the context of the relevant technology, and should not be interpreted in an idealized or overly formal sense.

[0069] It should be noted that, in the absence of conflict, the embodiments and features of the embodiments in the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0070] Example 1

[0071] like Figure 1 As shown, a multivariable control method for milling provided by the present application includes:

[0072] Step S100: Obtain valve parameters, primary air flow rate and mill outlet temperature at historical time, train to obtain a temperature flow prediction model, predict the current primary air flow rate and mill outlet temperature, obtain the current coal feeder speed and coal powder moisture, and calculate the estimated value of the mill outlet coal powder flow rate;

[0073] The specific method of obtaining the valve parameters, primary air flow rate and mill outlet temperature at the historical time, training the temperature flow prediction model, predicting the current primary air flow rate and mill outlet temperature, obtaining the current coal feeder speed and coal powder moisture, and calculating the estimated value of the mill outlet coal powder flow rate is as follows:

[0074] Step S110: Collect valve parameters, primary air flow and mill outlet temperature in a historical time period, wherein the valve parameters include the hot air valve opening and the cold air valve opening, preset a sliding window length, a sliding step length and a prediction time step length, and divide the valve parameters, primary air flow and mill outlet temperature into N training samples using a sliding time window method;

[0075] Step S120: construct a multi-layer feedforward neural network as the initial network for training the temperature and flow prediction model, wherein the input layer of the multi-layer feedforward neural network includes two nodes: the hot air door opening and the cold air door opening, and the output layer includes two nodes: the primary air flow and the mill outlet temperature;

[0076] Step S130: select mean square error as the loss function of the temperature flow prediction model, take accurate prediction of the primary air flow and mill outlet temperature of each training sample as the prediction target, take minimizing the loss function as the training target, and when the value of the loss function converges to the minimum, the training is completed and the temperature flow prediction model is obtained;

[0077] The calculation formula of the loss function is: ,in, is the loss function value, N is the total number of training samples, n∈{1,2,...,N}, represents the actual value of the primary wind flow of the nth training sample, It represents the predicted value of primary wind flow. represents the actual value of the mill outlet temperature of the nth training sample, Indicates the predicted value of the mill outlet temperature;

[0078] Step S140: obtaining current valve parameters, using the current valve parameters as input data, inputting the trained temperature and flow prediction model, and obtaining the current primary air flow and mill outlet temperature;

[0079] Step S150: Obtain the current coal feeder speed and coal powder moisture, and calculate the estimated value of the coal powder flow rate at the mill outlet in combination with the current primary air flow rate;

[0080] The calculation formula for the estimated value of the coal powder flow rate at the mill outlet is: ,in, Estimated value of coal powder flow rate at mill outlet, is the current primary wind flow, is the current mill outlet temperature, is the mill inlet temperature, is the coal entering grinding temperature, is the specific heat capacity of coal powder, MF is the moisture content of coal powder;

[0081] The mill inlet temperature refers to: the temperature of the air entering the coal mill, which is assumed to be the ambient temperature;

[0082] The coal entering the pulverizer temperature refers to the temperature of the coal entering the pulverizer, which is obtained by direct measurement;

[0083] The coal powder moisture refers to the moisture content in the coal powder, which is measured in real time by an online moisture meter.

[0084] Step S200: Compensate and optimize the primary air flow rate according to the estimated value of the pulverized coal flow rate at the mill outlet, and calculate the set value of the primary air flow rate;

[0085] The specific method for compensating and optimizing the primary air flow rate according to the estimated value of the coal powder flow rate at the mill outlet and calculating the set value of the primary air flow rate is as follows:

[0086] Step S210: preset a set value of the coal powder flow rate at the mill outlet, calculate the deviation between the estimated value of the coal powder flow rate at the mill outlet and the set value of the coal powder flow rate at the mill outlet, and calculate the compensation amount of the primary air flow according to the deviation;

[0087] The deviation between the estimated value of the mill outlet coal powder flow rate and the set value of the mill outlet coal powder flow rate The calculation formula is: ,in, The setting value of the coal powder flow rate at the mill outlet;

[0088] The compensation amount of the primary air flow The calculation formula is: ,in, is the compensation coefficient;

[0089] The setting value of the coal powder flow rate at the mill outlet is set by those skilled in the art according to the actual production requirements;

[0090] The size of the compensation coefficient is set by those skilled in the art according to actual production requirements;

[0091] Step S220: Optimize the primary air flow rate according to the compensation amount of the primary air flow rate to obtain the primary air flow rate setting value. ;

[0092] The primary air flow setting value The calculation formula is: ,in, is the primary air flow setting value, The current primary wind flow rate predicted by the temperature flow prediction model.

[0093] Step S300: Measure the coal quality parameters and calculate the coal quality correction coefficient, determine the current coal mill current, calculate the coal mill load correction coefficient, calculate the coal powder quality correction coefficient according to the current coal powder moisture, and comprehensively calculate the mill outlet temperature setting value based on the current mill outlet temperature;

[0094] The specific method of measuring the coal quality parameters and calculating the coal quality correction coefficient, determining the current coal mill current, calculating the coal mill load correction coefficient, calculating the coal powder quality correction coefficient according to the current coal powder moisture, and comprehensively calculating the mill outlet temperature setting value based on the current mill outlet temperature is as follows:

[0095] Step S310: directly measuring and obtaining coal quality parameters of the coal using an industrial analyzer, wherein the coal quality parameters include: ash content, volatile matter and moisture content on a dry basis;

[0096] The ash content refers to the mass percentage of ash in coal, which is measured by an industrial analyzer;

[0097] The volatile matter refers to the mass percentage of volatile substances in coal, which is determined by an industrial analyzer;

[0098] The dry basis moisture refers to the mass percentage of moisture in coal, which is measured by an industrial analyzer;

[0099] Step S320: Obtain the standard values ​​of coal ash, volatile matter and dry basis moisture, calculate the ratio of the measured ash, volatile matter and dry basis moisture to the standard values ​​of the corresponding coal ash, volatile matter and dry basis moisture, and obtain the coal quality correction coefficient by weighted summation. ;

[0100] The calculation formula of the coal quality correction coefficient is: ,in, represents the coal quality correction factor, Respectively represent the measured ash, volatile matter and moisture on a dry basis, Respectively represent the standard values ​​of coal ash, volatile matter and dry basis moisture, represent the weight coefficients of ash, volatile matter and moisture on dry basis respectively;

[0101] The weight coefficients of ash, volatile matter and dry basis moisture are set by technicians in this field according to actual needs;

[0102] The coal quality correction coefficient is a coefficient used to correct the influence of coal quality parameters on the mill outlet temperature;

[0103] Step S330: Obtain the rated coal mill current value, calculate the ratio of the current coal mill current to the rated coal mill current value, and obtain the coal mill load correction coefficient by weighted calculation. ;

[0104] The calculation formula of the coal mill load correction coefficient is: ,in, is the current coal mill current, is the rated coal mill current value, is the empirical coefficient of coal mill current;

[0105] Step S340: Obtain the standard value of coal powder moisture, calculate the ratio of the current coal powder moisture to the standard value of coal powder moisture, and obtain the coal powder quality correction coefficient by weighted calculation. ;

[0106] The calculation formula of the coal powder quality correction coefficient is: ,in, is the standard value of moisture in pulverized coal, is the empirical coefficient of coal powder moisture;

[0107] Step S350: Multiply the coal quality correction factor, the coal mill load correction factor and the coal powder quality correction factor by the current mill outlet temperature to calculate the mill outlet temperature setting value. ;

[0108] The calculation formula of the grinding outlet temperature setting value is: ;

[0109] The empirical coefficient of the coal mill current and the empirical coefficient of the coal powder moisture content are set by those skilled in the art based on experience and experiments.

[0110] Step S400: construct a step-by-step predictive controller, taking the coal mill output command, the primary air flow set value and the mill outlet temperature set value as inputs, and taking the cold air door opening, the hot air door opening and the coal feeder speed as outputs, and designing the objective function and constraint conditions of the step-by-step predictive controller;

[0111] The step-by-step prediction controller is constructed, with the coal mill output command, the primary air flow set value and the mill outlet temperature set value as input, and the cold air door opening, the hot air door opening and the coal feeder speed as output. The specific method for designing the objective function and constraint conditions of the step-by-step prediction controller is as follows:

[0112] Step S410: construct a step predictive controller, and select a nonlinear model predictive controller as the controller type of the step predictive controller;

[0113] Step S420: using the coal mill output command, the primary air flow rate setting value and the mill outlet temperature setting value of the coal mill as inputs of the step-type predictive controller, and using the cold air door opening, the hot air door opening and the coal feeder speed as outputs of the step-type predictive controller;

[0114] Step S430: Preset the prediction time domain and the control time domain, the prediction time domain is greater than or equal to the control time domain, and design the objective function and constraint conditions of the step-wise predictive controller;

[0115] The specific method for designing the objective function and constraint conditions of the step-wise predictive controller is as follows:

[0116] The objective function of the step-wise predictive controller is designed, and the functional expression of the objective function is: ,in is the objective function of the step predictive controller, represents the number of time steps in the prediction domain, represents the number of time steps in the control time domain, They represent the weight coefficients of the primary air flow setting value, the mill outlet temperature setting value, and the coal mill output instruction respectively. They represent the weight coefficients of the cold air door opening, hot air door opening and coal feeder speed respectively. They represent the primary air flow, mill outlet temperature and coal mill current at the i-th time step in the prediction domain, respectively. Indicates the coal mill output command. They represent the cold air door opening, hot air door opening and coal feeder speed at the i-th time step in the control time domain respectively;

[0117] Design the constraints of the step predictive controller, the expressions of the constraints include: ,in, are the minimum and maximum values ​​of the cold air door opening, are the minimum and maximum values ​​of the hot air door opening, are the minimum and maximum values ​​of the coal feeder speed respectively.

[0118] The primary air flow setting value, mill outlet temperature setting value, weight coefficient of coal mill output instruction, cold air door opening, hot air door opening and weight coefficient of coal feeder speed are set by technical personnel in this field based on experience and experiments.

[0119] Step S500: Obtain a single coal mill output command, input the primary air flow rate setting value, the mill outlet temperature setting value and the single coal mill output command into the step-by-step predictive controller, calculate a control sequence of Nc time steps, and output the cold air door opening, hot air door opening and coal feeder speed of the first control action in the control sequence;

[0120] The specific method of obtaining the output command of a single coal mill, inputting the primary air flow set value, the mill outlet temperature set value and the output command of a single coal mill into the step-type predictive controller, calculating the control sequence of Nc time steps, and outputting the cold air door opening, hot air door opening and coal feeder speed of the first control action in the control sequence is as follows:

[0121] Step S510: Obtaining the coal mill output instruction of a single coal mill , get the optimized primary air flow setting value , Grinding outlet temperature setting value , which is input into the step predictive controller as an input variable;

[0122] Step S520: Use the sequential quadratic programming algorithm to calculate the objective function and constraints of the step-wise predictive controller to obtain the control sequence for the next Nc time steps. ,in, represents the control action at the first time step, represents the control action at the Ncth time step, They represent the cold air door opening, hot air door opening and coal feeder speed of the Nc-th control action respectively;

[0123] Step S530: From the control sequence Extract the control action of the first time step from , the control action of the first time step is output as the optimal control action for actual control of pulverizing, and the cold air door opening, hot air door opening and coal feeder speed are adjusted.

[0124] Example 2

[0125] like Figure 2 As shown, a milling multivariable control system provided by the present application includes:

[0126] The pulverized coal flow estimation module is used to obtain valve parameters, primary air flow and mill outlet temperature in historical time, train a temperature flow prediction model, predict the current primary air flow and mill outlet temperature, obtain the current coal feeder speed and pulverized coal moisture, and calculate the estimated value of the pulverized coal flow at the mill outlet;

[0127] A primary air flow setting module is used to optimize the primary air flow according to the estimated value of the coal powder flow at the mill outlet, and calculate the primary air flow setting value;

[0128] The temperature setting calculation module is used to measure the coal quality parameters and calculate the coal quality correction coefficient, determine the current coal mill current, calculate the coal mill load correction coefficient, calculate the coal powder quality correction coefficient according to the current coal powder moisture, and comprehensively calculate the mill outlet temperature setting value based on the current mill outlet temperature;

[0129] The controller design module is used to construct a step-by-step predictive controller. It takes the coal mill output command, the primary air flow set value and the mill outlet temperature set value as inputs, and the cold air door opening, hot air door opening and coal feeder speed as outputs to design the objective function and constraints of the step-by-step predictive controller.

[0130] The optimal control output module is used to obtain the output command of a single coal mill, input the primary air flow set value, the mill outlet temperature set value and the single coal mill output command into the step-by-step predictive controller, calculate the control sequence of Nc time steps, and output the cold air door opening, hot air door opening and coal feeder speed of the first control action in the control sequence.

[0131] Example 3

[0132] Figure 3 1 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present application. Figure 3 As shown, according to another aspect of the present application, an electronic device is also provided. The electronic device may include one or more processors and one or more memories. The memories store computer readable codes, and when the computer readable codes are executed by one or more processors, a multivariable control method for milling as described above may be executed.

[0133] The method or system according to the embodiment of the present application can also be used by Figure 3 The electronic device architecture shown in FIG. Figure 3As shown, the electronic device may include a bus, one or more CPUs, a read-only memory (ROM), a random access memory (RAM), a communication port connected to a network, an input / output component, a hard disk, etc. The storage device in the electronic device, such as a ROM or a hard disk, can store a multivariable control method for pulverizing provided in the present application. A multivariable control method for pulverizing may, for example, include: obtaining valve parameters, primary air flow, and mill outlet temperature at historical times, training a temperature flow prediction model, predicting the current primary air flow and mill outlet temperature, obtaining the current coal feeder speed and coal powder moisture, and calculating an estimated value of the coal powder flow at the mill outlet; compensating and optimizing the primary air flow according to the estimated value of the coal powder flow at the mill outlet, and calculating a set value of the primary air flow; measuring the coal quality parameters of the coal and calculating the coal quality correction coefficient, determining the current pulverizer current, calculating the pulverizer load correction coefficient, and calculating the coal powder quality correction coefficient according to the current coal powder moisture; based on the current The mill outlet temperature before is comprehensively calculated to set the mill outlet temperature; a step-by-step predictive controller is constructed, with the mill output command, the primary air flow set value and the mill outlet temperature set value as input, and the cold air door opening, the hot air door opening and the coal feeder speed as output, to design the objective function and constraints of the step-by-step predictive controller; the output command of a single coal mill is obtained, and the primary air flow set value, the mill outlet temperature set value and the single coal mill output command are input into the step-by-step predictive controller, and a control sequence of Nc time steps is calculated, and the cold air door opening, the hot air door opening and the coal feeder speed of the first control action in the control sequence are output. Furthermore, the electronic device may also include a user interface. Of course, Figure 3 The architecture shown is only exemplary and can be omitted according to actual needs when implementing different devices. Figure 3 One or more components of an electronic device are shown.

[0134] Example 4

[0135] Figure 4 Schematic diagram of a readable storage medium structure provided by an embodiment of the present application. Figure 4 As shown, it is a readable storage medium according to an embodiment of the present application. Computer-readable instructions are stored on the computer-readable storage medium. When the computer-readable instructions are executed by the processor, a multivariable control method for milling according to an embodiment of the present application described with reference to the above figures can be executed. The storage medium includes, but is not limited to, for example, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and cache memory (cache). Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc.

[0136] In addition, according to the implementation mode of the present application, the process described in the above reference flow chart can be implemented as a computer software program. For example, the present application provides a non-transitory machine-readable storage medium, which stores machine-readable instructions, and the machine-readable instructions can be executed by a processor to execute instructions corresponding to the method steps provided in the present application, such as: obtaining valve parameters, primary air flow and mill outlet temperature at historical time, training to obtain a temperature flow prediction model, predicting the current primary air flow and mill outlet temperature, obtaining the current coal feeder speed and coal powder moisture, and calculating the estimated value of the mill outlet coal powder flow; compensating and optimizing the primary air flow according to the estimated value of the mill outlet coal powder flow, and calculating the primary air flow set value; measuring the coal quality parameters of the coal and calculating the coal quality correction coefficient, and determining the current mill current, Calculate the coal mill load correction coefficient, calculate the coal powder quality correction coefficient according to the current coal powder moisture, and comprehensively calculate the mill outlet temperature setting value based on the current mill outlet temperature; construct a step-type prediction controller, take the coal mill output instruction, the primary air flow setting value and the mill outlet temperature setting value as input, take the cold air door opening, the hot air door opening and the coal feeder speed as output, and design the objective function and constraint conditions of the step-type prediction controller; obtain the output instruction of a single coal mill, input the primary air flow setting value, the mill outlet temperature setting value and the single coal mill output instruction into the step-type prediction controller, calculate the control sequence of Nc time steps, and output the cold air door opening, the hot air door opening and the coal feeder speed of the first control action in the control sequence. When the computer program is executed by the central processing unit (CPU), the above functions defined in the method of this application are executed.

[0137] The methods, apparatuses, and devices of the present application may be implemented in many ways. For example, the methods, apparatuses, and devices of the present application may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above order of steps for the method is for illustration only, and the steps of the method of the present application are not limited to the order specifically described above unless otherwise specified. In addition, in some embodiments, the present application may also be implemented as programs recorded in a recording medium, which include machine-readable instructions for implementing the method according to the present application. Therefore, the present application also covers recording media storing programs for executing the method according to the present application.

[0138] In addition, the parts of the above-mentioned technical solutions provided in the embodiments of the present application that are consistent with the implementation principles of the corresponding technical solutions in the prior art are not described in detail to avoid excessive redundancy.

[0139] The specific implementation modes as described above further describe the purpose, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation mode of the present invention and is not intended to limit the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A multivariable control method for milling, characterized in that: include: Step S100: Obtain valve parameters, primary air flow rate and mill outlet temperature at historical time, train to obtain a temperature flow prediction model, predict the current primary air flow rate and mill outlet temperature, obtain the current coal feeder speed and coal powder moisture, and calculate the estimated value of the mill outlet coal powder flow rate; Step S200: Compensate and optimize the primary air flow rate according to the estimated value of the pulverized coal flow rate at the mill outlet, and calculate the set value of the primary air flow rate; Step S300: Measure the coal quality parameters and calculate the coal quality correction coefficient, determine the current coal mill current, calculate the coal mill load correction coefficient, calculate the coal powder quality correction coefficient according to the current coal powder moisture, and comprehensively calculate the mill outlet temperature setting value based on the current mill outlet temperature; Step S400: construct a step-by-step predictive controller, taking the coal mill output command, the primary air flow set value and the mill outlet temperature set value as inputs, and taking the cold air door opening, the hot air door opening and the coal feeder speed as outputs, and designing the objective function and constraint conditions of the step-by-step predictive controller; Step S500: Obtain the output command of a single coal mill, input the primary air flow set value, the mill outlet temperature set value and the single coal mill output command into the step predictive controller, calculate the control sequence of Nc time steps, and output the cold air door opening, hot air door opening and coal feeder speed of the first control action in the control sequence.

2. A multivariable control method for milling as claimed in claim 1, characterized in that: The specific method of obtaining the valve parameters, primary air flow rate and mill outlet temperature at the historical time, training the temperature flow prediction model, predicting the current primary air flow rate and mill outlet temperature, obtaining the current coal feeder speed and coal powder moisture, and calculating the estimated value of the mill outlet coal powder flow rate is as follows: Step S110: Collect valve parameters, primary air flow and mill outlet temperature in a historical time period, wherein the valve parameters include the hot air valve opening and the cold air valve opening, preset a sliding window length, a sliding step length and a prediction time step length, and divide the valve parameters, primary air flow and mill outlet temperature into N training samples using a sliding time window method; Step S120: construct a multi-layer feedforward neural network as the initial network for training the temperature and flow prediction model, wherein the input layer of the multi-layer feedforward neural network includes two nodes: the hot air door opening and the cold air door opening, and the output layer includes two nodes: the primary air flow and the mill outlet temperature; Step S130: select mean square error as the loss function of the temperature flow prediction model, take accurate prediction of the primary air flow and mill outlet temperature of each training sample as the prediction target, take minimizing the loss function as the training target, and when the value of the loss function converges to the minimum, the training is completed and the temperature flow prediction model is obtained; The calculation formula of the loss function is: ,in, is the loss function value, N is the total number of training samples, n∈{1,2,...,N}, represents the actual value of the primary wind flow of the nth training sample, It represents the predicted value of primary wind flow. represents the actual value of the mill outlet temperature of the nth training sample, Indicates the predicted value of the mill outlet temperature; Step S140: obtaining current valve parameters, using the current valve parameters as input data, inputting the trained temperature and flow prediction model, and obtaining the current primary air flow and mill outlet temperature; Step S150: Obtain the current coal feeder speed and coal powder moisture, and calculate the estimated value of the coal powder flow rate at the mill outlet in combination with the current primary air flow rate; The calculation formula for the estimated value of the coal powder flow rate at the mill outlet is: ,in, Estimated value of coal powder flow rate at mill outlet, is the current primary wind flow, is the current mill outlet temperature, is the mill inlet temperature, is the coal entering grinding temperature, is the specific heat of coal powder, and MF is the moisture content of coal powder.

3. A multivariable control method for milling as claimed in claim 2, characterized in that: The specific method for compensating and optimizing the primary air flow rate according to the estimated value of the coal powder flow rate at the mill outlet and calculating the set value of the primary air flow rate is as follows: Step S210: preset a set value of the coal powder flow rate at the mill outlet, calculate the deviation between the estimated value of the coal powder flow rate at the mill outlet and the set value of the coal powder flow rate at the mill outlet, and calculate the compensation amount of the primary air flow according to the deviation; The deviation between the estimated value of the mill outlet coal powder flow rate and the set value of the mill outlet coal powder flow rate The calculation formula is: ,in, The setting value of the coal powder flow rate at the mill outlet; The compensation amount of the primary air flow The calculation formula is: ,in, is the compensation coefficient; Step S220: Optimize the primary air flow rate according to the compensation amount of the primary air flow rate to obtain the primary air flow rate setting value. ; The primary air flow setting value The calculation formula is: ,in, The current primary wind flow rate predicted by the temperature flow prediction model.

4. A multivariable control method for milling as claimed in claim 3, characterized in that: The specific method of measuring the coal quality parameters and calculating the coal quality correction coefficient, determining the current coal mill current, calculating the coal mill load correction coefficient, calculating the coal powder quality correction coefficient according to the current coal powder moisture, and comprehensively calculating the mill outlet temperature setting value based on the current mill outlet temperature is as follows: Step S310: directly measuring and obtaining coal quality parameters of the coal using an industrial analyzer, wherein the coal quality parameters include: ash content, volatile matter and moisture content on a dry basis; Step S320: Obtain the standard values ​​of coal ash, volatile matter and dry basis moisture, calculate the ratio of the measured ash, volatile matter and dry basis moisture to the standard values ​​of the corresponding coal ash, volatile matter and dry basis moisture, and obtain the coal quality correction coefficient by weighted summation. ; The calculation formula of the coal quality correction coefficient is: ,in, , , Respectively represent the measured ash, volatile matter and moisture on a dry basis, , , Respectively represent the standard values ​​of coal ash, volatile matter and dry basis moisture, , , represent the weight coefficients of ash, volatile matter and moisture on dry basis respectively; Step S330: Obtain the rated coal mill current value, calculate the ratio of the current coal mill current to the rated coal mill current value, and obtain the coal mill load correction coefficient by weighted calculation. ; The calculation formula of the coal mill load correction coefficient is: ,in, is the current coal mill current, is the rated coal mill current value, is the empirical coefficient of coal mill current; Step S340: Obtain the standard value of coal powder moisture, calculate the ratio of the current coal powder moisture to the standard value of coal powder moisture, and obtain the coal powder quality correction coefficient by weighted calculation. ; The calculation formula of the coal powder quality correction coefficient is: ,in, is the standard value of moisture in pulverized coal, is the empirical coefficient of coal powder moisture; Step S350: Multiply the coal quality correction factor, the coal mill load correction factor and the coal powder quality correction factor by the current mill outlet temperature to calculate the mill outlet temperature setting value. ; The calculation formula of the grinding outlet temperature setting value is: .

5. A multivariable control method for milling as claimed in claim 4, characterized in that: The step-by-step prediction controller is constructed, with the coal mill output command, the primary air flow set value and the mill outlet temperature set value as input, and the cold air door opening, the hot air door opening and the coal feeder speed as output. The specific method for designing the objective function and constraint conditions of the step-by-step prediction controller is as follows: Step S410: construct a step predictive controller, and select a nonlinear model predictive controller as the controller type of the step predictive controller; Step S420: using the coal mill output command, the primary air flow rate setting value and the mill outlet temperature setting value of the coal mill as inputs of the step-type predictive controller, and using the cold air door opening, the hot air door opening and the coal feeder speed as outputs of the step-type predictive controller; Step S430: Preset the prediction time domain and the control time domain, the prediction time domain is greater than or equal to the control time domain, and design the objective function and constraint conditions of the step predictive controller.

6. A multivariable control method for milling as claimed in claim 5, characterized in that: The specific method for designing the objective function and constraint conditions of the step-wise predictive controller is as follows: The objective function of the step-wise predictive controller is designed, and the functional expression of the objective function is: ,in, represents the number of time steps in the prediction domain, represents the number of time steps in the control time domain, , , They represent the weight coefficients of the primary air flow setting value, the mill outlet temperature setting value, and the coal mill output instruction respectively. , , They represent the weight coefficients of the cold air door opening, hot air door opening and coal feeder speed respectively. , , They represent the primary air flow, mill outlet temperature and coal mill current at the i-th time step in the prediction domain, respectively. Indicates the coal mill output command. , , They represent the cold air door opening, hot air door opening and coal feeder speed at the i-th time step in the control time domain respectively; Design the constraints of the step predictive controller, the expressions of the constraints include: , , ,in, , are the minimum and maximum values ​​of the cold air door opening, , are the minimum and maximum values ​​of the hot air door opening, , are the minimum and maximum values ​​of the coal feeder speed respectively.

7. A multivariable control method for milling as claimed in claim 6, characterized in that: The specific method of obtaining the output command of a single coal mill, inputting the primary air flow set value, the mill outlet temperature set value and the output command of a single coal mill into the step-type predictive controller, calculating the control sequence of Nc time steps, and outputting the cold air door opening, hot air door opening and coal feeder speed of the first control action in the control sequence is as follows: Step S510: Obtaining the coal mill output instruction of a single coal mill , get the optimized primary air flow setting value , Grinding outlet temperature setting value , which is input into the step predictive controller as an input variable; Step S520: Use the sequential quadratic programming algorithm to calculate the objective function and constraints of the step-wise predictive controller to obtain the control sequence for the next Nc time steps. ,in, represents the control action at the first time step, represents the control action at the Nc-th time step, , , They represent the cold air door opening, hot air door opening and coal feeder speed of the Nc-th control action respectively; Step S530: From the control sequence Extract the control action of the first time step from , the control action of the first time step is output as the optimal control action for actual control of pulverizing, and the cold air door opening, hot air door opening and coal feeder speed are adjusted.

8. A milling multivariable control system, used to implement a milling multivariable control method according to any one of claims 1 to 7, characterized in that: include: The pulverized coal flow estimation module is used to obtain valve parameters, primary air flow and mill outlet temperature in historical time, train a temperature flow prediction model, predict the current primary air flow and mill outlet temperature, obtain the current coal feeder speed and pulverized coal moisture, and calculate the estimated value of the pulverized coal flow at the mill outlet; A primary air flow setting module is used to optimize the primary air flow according to the estimated value of the coal powder flow at the mill outlet, and calculate the primary air flow setting value; The temperature setting calculation module is used to measure the coal quality parameters and calculate the coal quality correction coefficient, determine the current coal mill current, calculate the coal mill load correction coefficient, calculate the coal powder quality correction coefficient according to the current coal powder moisture, and comprehensively calculate the mill outlet temperature setting value based on the current mill outlet temperature; The controller design module is used to construct a step-by-step predictive controller. It takes the coal mill output command, the primary air flow set value and the mill outlet temperature set value as inputs, and the cold air door opening, hot air door opening and coal feeder speed as outputs to design the objective function and constraints of the step-by-step predictive controller. The optimal control output module is used to obtain the output command of a single coal mill, input the primary air flow set value, the mill outlet temperature set value and the single coal mill output command into the step-by-step predictive controller, calculate the control sequence of Nc time steps, and output the cold air door opening, hot air door opening and coal feeder speed of the first control action in the control sequence.

9. An electronic device, characterized in that: It comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps in a multivariable control method for milling as described in any one of claims 1 to 7 are implemented.

10. A readable storage medium, characterized in that: The readable storage medium stores a computer program, and the computer program is suitable for being loaded by a processor to execute the steps in a multivariable control method for milling as described in any one of claims 1-7.

Images