A method and device for controlling the outlet temperature of a coal mill

By constructing a nonlinear mechanism model based on the law of conservation of energy and an MPC optimization solver, the nonlinear and multivariable coupling problems in the control of coal mill outlet temperature were solved, achieving rapid, accurate and safe temperature regulation, and reducing manual intervention and energy waste.

CN123102484APending Publication Date: 2026-11-17NINGXIA BAOFENG ENERGY GROUP CO LTD +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202611600900.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-10-16
Publication Date
2026-11-17

AI Technical Summary

Technical Problem

Traditional PID control methods are difficult to effectively handle the nonlinearity, multivariable coupling, and large hysteresis characteristics of coal mill outlet temperature, resulting in low control accuracy, slow response speed, and the need for manual intervention when operating conditions change, which poses safety risks.

Method used

A nonlinear mechanism model based on the law of energy conservation is constructed, and combined with the model predictive control (MPC) optimization solver, the optimal operating sequence is optimized by acquiring historical and current operating data, so as to realize multivariate coordinated adjustment and adaptive control of the coal mill outlet temperature.

Benefits of technology

It improves the response speed and accuracy of temperature control, reduces the frequency of manual intervention, enhances the robustness and safety of the control system, and reduces energy consumption and equipment risks.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN123102484A_ABST
    Figure CN123102484A_ABST
Patent Text Reader

Abstract

This application discloses a method and apparatus for controlling the outlet temperature of a coal mill, comprising: acquiring historical operating data of the coal mill under different operating conditions, the historical operating data including the outlet temperature of the coal mill corresponding to different operating cycles and the control variables affecting the outlet temperature of the coal mill; constructing a nonlinear mechanism model according to the law of conservation of energy, the nonlinear mechanism model being used to express the physical relationship between the change of the coal mill outlet temperature and each control variable; constructing a model predictive control (MPC) optimization solver based on the historical operating data and the nonlinear mechanism model; acquiring the current operating data of the coal mill, and using the MPC optimization solver to solve for the optimal sequence of operations corresponding to the current operating data; and controlling the outlet temperature of the coal mill based on the optimal sequence of operations. The above method can significantly improve the accuracy and stability of the coal mill outlet temperature control, overcome the limitations of traditional single-variable control in dealing with multi-variable coupling, and reduce the frequency of manual intervention.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This application generally relates to the field of coal mill industrial control. More specifically, this application relates to a method and apparatus for controlling the outlet temperature of a coal mill. Background Technology

[0002] In industrial applications such as coal processing and methanol production, coal mills are key pieces of equipment. They are used to crush and grind raw coal into pulverized coal for subsequent combustion or gasification processes. The outlet temperature of the coal mill is a crucial parameter for assessing the dryness of the pulverized coal and the mill's operating status; its stability directly impacts the safety of subsequent production processes, product quality, and energy efficiency.

[0003] In related technologies, temperature control of industrial coal mills often employs traditional PID (Proportional-Integral-Derivative) control. This method uses the deviation between the measured and setpoint values ​​of the coal mill outlet temperature as input, and calculates the control output (e.g., adjusting the damper opening or the raw coal feed rate) through a linear combination of fixed proportional, integral, and derivative coefficients, thus providing single-input, single-output feedback regulation of the coal mill outlet temperature. However, the temperature regulation process of a coal mill involves multiple coupled physicochemical processes such as hot air gasification, raw coal drying, and heat transfer, and is influenced by a combination of variables including primary air flow rate, circulating air flow rate, raw coal moisture content, and raw coal feed rate, exhibiting significant nonlinearity, multivariate coupling, and large time lag characteristics. Under such complex operating conditions, traditional PID control methods struggle to fully consider the coupling relationships between these variables.

[0004] Furthermore, in applications such as methanol production, coal mills need to adapt to various operating conditions, including different coal types and loads. When operating conditions change significantly, the fixed parameters of traditional PID control are difficult to adjust adaptively, often requiring operators to manually readjust the control parameters based on experience. This not only increases the intensity of manual labor but also may lead to safety risks due to human error.

[0005] Therefore, there is an urgent need to provide a method for controlling the outlet temperature of a coal mill in order to achieve precise control of the outlet temperature of the coal mill. Summary of the Invention

[0006] In order to at least solve one or more of the technical problems mentioned above, this application proposes a method for controlling the outlet temperature of a coal mill in several aspects.

[0007] In a first aspect, this application provides a method for obtaining historical operating data of a coal mill under different operating conditions, the historical operating data including the coal mill outlet temperature corresponding to different operating cycles and control variables affecting the coal mill outlet temperature; constructing a nonlinear mechanism model according to the law of conservation of energy, the nonlinear mechanism model being used to express the physical relationship between the change in coal mill outlet temperature and each of the control variables; constructing a Model Predictive Control (MPC) optimization solver based on the historical operating data and the nonlinear mechanism model; obtaining the current operating data of the coal mill, and using the MPC optimization solver to solve for the optimal operation sequence corresponding to the current operating data; controlling the coal mill outlet temperature based on the optimal operation sequence; wherein, the nonlinear mechanism model is as follows: ;in, This indicates the outlet temperature of the coal mill. Indicates equivalent heat capacity, Indicates the primary air mass flow rate. Indicates the outlet temperature of the hot blast stove. This indicates the mass flow rate of the circulating air. Indicates the temperature of the circulating air. Indicates the mass flow rate of raw coal. Indicates the inlet temperature of the raw coal. Indicates the moisture content of raw coal. This represents the latent heat of vaporization of water. and This indicates the specific heat of air compared to coal.

[0008] In some embodiments, a Model Predictive Control (MPC) optimization solver is constructed based on the historical operating data and the nonlinear mechanism model, including: linearizing and discretizing the nonlinear mechanism model to obtain a linear discrete difference equation; fitting the temperature deviation weight and control change weight of the MPC optimization solver under different operating conditions based on the historical operating data; constructing a cost function based on the temperature deviation weight and control change weight; wherein the cost function aims to minimize the adjustment amount while minimizing the deviation between the coal mill outlet temperature and the outlet temperature setpoint; and constructing the MPC optimization solver based on the linear discrete difference equation, the cost function, and constraints; wherein the constraints include at least one of the following: operating boundary, allowable fluctuation range of coal mill outlet temperature, and dust ratio.

[0009] In some embodiments, the cost function is as follows: , Where k represents the current time, Indicates the future number step, Indicates the prediction step size. This represents the control step size, where Q is the temperature deviation weight and R is the control change weight. This represents a sequence of changes in the operational quantity. This indicates the magnitude of the change in the operational quantity. This indicates the future temperature deviation.

[0010] In some embodiments, the control variables include at least one of the following: primary air flow rate, circulating air flow rate, hot blast stove outlet temperature, raw coal flow rate, raw coal moisture content, raw coal inlet temperature, and circulating air temperature.

[0011] In some embodiments, controlling the coal mill outlet temperature based on the optimal operation sequence includes: obtaining the optimal operation sequence corresponding to the predicted step size obtained by the MPC optimization solver; controlling the coal mill outlet temperature based on the optimal operation corresponding to the current step in the optimal operation sequence; after entering the next sampling period, obtaining the actual measured value of the coal mill outlet temperature; performing feedback correction on the state variables of the nonlinear mechanism model based on the deviation between the actual measured value and the predicted value of the nonlinear mechanism model; and repeating the prediction and optimization process to achieve rolling time-domain control.

[0012] In some embodiments, the optimal operation sequence corresponding to the current operating data is solved using the MPC optimization solver, including: when the coal mill outlet temperature is lower than the lower limit of the allowable fluctuation range of the coal mill outlet temperature, the optimal operation sequence output by the MPC optimization solver includes a first operation for increasing the primary air flow and a second operation for decreasing the raw coal flow; when the change in the raw coal moisture content reaches a preset threshold, a disturbance feedforward compensation mechanism is triggered, and the optimal operation sequence output by the MPC optimization solver includes a feedforward compensation operation for increasing the primary air flow to compensate for the heat loss caused by the increase in moisture content; when the coal mill outlet temperature is higher than the upper limit of the allowable fluctuation range of the coal mill outlet temperature, the optimal operation sequence output by the MPC optimization solver includes an interlock operation for starting the cooling nitrogen operation device for forced cooling.

[0013] In a second aspect, this application provides a control device for the outlet temperature of a coal mill, comprising: an acquisition module for acquiring historical operating data of the coal mill under different operating conditions, the historical operating data including the outlet temperature of the coal mill corresponding to different operating cycles and control variables affecting the outlet temperature of the coal mill; a nonlinear mechanism model construction module for constructing a nonlinear mechanism model according to the law of conservation of energy, the nonlinear mechanism model being used to express the physical relationship between the change in the outlet temperature of the coal mill and each of the control variables; an MPC optimization solver construction module for constructing a model predictive control MPC optimization solver based on the historical operating data and the nonlinear mechanism model; a solution module for acquiring the current operating data of the coal mill and using the MPC optimization solver to solve for the optimal sequence of operations corresponding to the current operating data; and a control module for controlling the outlet temperature of the coal mill based on the optimal sequence of operations.

[0014] In a third aspect, this application provides a computer-readable storage medium having a computer program stored thereon that, when executed by a processor, implements the method of any of the first aspects.

[0015] In a fourth aspect, this application provides an electronic device comprising: one or more processors; a memory for storing one or more programs; and, when the one or more programs are executed by the one or more processors, causing the one or more processors to implement the method of any one of the first aspects.

[0016] The method for controlling the outlet temperature of a coal mill provided above, in this embodiment, acquires historical operating data containing different operating conditions, constructs a nonlinear mechanism model based on the law of conservation of energy to express the physical relationship between the change in the outlet temperature of the coal mill and various control variables, and then constructs an MPC optimization solver based on the historical operating data and the nonlinear mechanism model. The MPC solver is then used to solve the optimal sequence of operations online based on the current operating data to control the outlet temperature of the coal mill, which can significantly improve the response speed, accuracy and stability of temperature control. Specifically, because this mechanism model accurately describes the dynamic balance between primary air heat (also known as heat in primary air flow rate) input and circulating air heat (also known as heat in circulating air flow rate) input and the heat consumption of coal powder heating and moisture evaporation at the physical level, it provides a reliable predictive basis with interpretability for MPC optimization, which is conducive to improving the accuracy of prediction and control decisions. At the same time, because the MPC optimization solver can coordinate the synergistic effect of multiple operating variables such as primary air flow rate, circulating air flow rate, and raw coal flow rate within a unified framework, it overcomes the inherent limitation of traditional single-variable control in dealing with multi-variable coupling, and realizes precise and rapid multi-variable coordinated adjustment of outlet temperature. In addition, by introducing historical data covering different operating conditions for solver construction, it can automatically adapt when switching operating conditions without manual parameter readjustment, thereby effectively suppressing temperature fluctuations, significantly reducing the frequency of manual intervention and labor intensity, and improving the robustness of the control system and the safety and economy of industrial field operation. Attached Figure Description

[0017] The above and other objects, features, and advantages of exemplary embodiments of this application will become readily understood by reading the following detailed description with reference to the accompanying drawings. In the drawings, several embodiments of this application are illustrated by way of example and not limitation, and the same or corresponding reference numerals denote the same or corresponding parts, wherein: Figure 1 An exemplary flowchart of a method for controlling the outlet temperature of a coal mill according to some embodiments of this application is shown; Figure 2 An exemplary flowchart of the MPC optimization solver control logic of some embodiments of this application is shown; Figure 3 An exemplary flowchart illustrating the logic of a coal mill outlet temperature control method according to some embodiments of this application is shown; Figure 4 An exemplary structural block diagram of a coal mill outlet temperature control device according to some embodiments of this application is shown; Detailed Implementation The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0018] It should be understood that the terms "comprising" and "including" used in the specification and claims of this application indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0019] It should also be understood that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the application. As used in this specification and claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used in this specification and claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes such combinations.

[0020] As used in this specification and claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determined" or "if [described condition or event] is detected" may be interpreted, depending on the context, as "once determined," "in response to determination," "once [described condition or event] is detected," or "in response to detection of [described condition or event]."

[0021] The specific embodiments of this application will now be described in detail with reference to the accompanying drawings.

[0022] In industrial applications such as coal processing and methanol production, coal mills are key pieces of equipment used to crush and grind raw coal into pulverized coal for subsequent combustion or gasification processes. The outlet temperature of the coal mill is a crucial parameter for assessing the dryness of the pulverized coal and the mill's operating status; its stability directly impacts the safety of subsequent production processes, product quality, and energy efficiency.

[0023] The process of preparing pulverized coal using a coal mill mainly includes stages such as raw coal conveying, grinding, drying, separation, and collection. Raw coal is fed into the coal mill at a set flow rate by a coal feeder and is pulverized into fine coal powder by the grinding components. During this process, the moisture content and inlet temperature of the raw coal directly affect the heat consumption required for subsequent drying. Simultaneously, the high-temperature flue gas output from the hot blast stove is conditioned to form hot air. The outlet temperature of the hot blast stove, the temperature of the circulating air, and the ratio of the circulating air flow rate to the primary air flow rate jointly determine the temperature and volume of the desiccant entering the coal mill. The hot air continuously passes through the coal mill to dry the pulverized coal and carries it into the separator. During this process, the outlet temperature of the coal mill, as a core indicator comprehensively reflecting the system's heat balance and safety status, needs to be strictly monitored. After separation, pulverized coal of acceptable fineness is collected by the airflow into the dust collector, while unacceptable coarse powder is returned to the coal mill for regrinding. Throughout the pulverizing process, multiple variables, such as the moisture content of raw coal, the flow rate of raw coal, the outlet temperature of the hot blast stove, the temperature of the circulating air, the flow rate of primary air, the flow rate of circulating air, and the outlet temperature of the coal mill, are coupled together and jointly determine the operational stability and product quality of the pulverizing system.

[0024] Therefore, the temperature regulation process of a coal mill is essentially a complex nonlinear dynamic system involving multiple coupled physicochemical processes such as hot air gasification, raw coal drying, and heat transfer. It is affected by a combination of variables such as primary air flow rate, circulating air flow rate, raw coal moisture content, and raw coal flow rate (i.e., raw coal feed rate).

[0025] Currently, temperature control in industrial coal mills mostly adopts the traditional PID control method. This method is based on simple proportional-integral-derivative adjustment logic, which cannot fully consider the coupling relationship between these variables, resulting in low control accuracy, slow response speed, and often overshooting or excessive fluctuation of outlet temperature.

[0026] This problem of frequent fluctuations and inaccurate adjustments in control has a significant negative impact on production efficiency and energy consumption. On the one hand, drastic temperature fluctuations lead to uneven drying of raw coal, directly affecting the fineness of pulverized coal and combustion stability, which in turn causes a decrease in boiler combustion efficiency, unit load fluctuations, and even unplanned shutdowns, severely restricting the continuity and safety of production. On the other hand, to cope with temperature deviations, the system is often forced to maintain an excessively high hot air margin or frequently and significantly adjust the damper opening, resulting in a surge in hot air consumption and an increase in plant power consumption, causing huge energy waste. In addition, when operating conditions change significantly, the parameters of traditional PID control are difficult to adjust adaptively, requiring manual intervention by operators. This not only increases the intensity of manual labor but may also lead to safety risks due to human error, such as equipment damage caused by excessively high temperatures or the risk of dust explosions.

[0027] For example, the core logic of traditional PID control is to linearly superimpose the deviation between the setpoint and the actual measured value of the controlled variable (such as the outlet temperature of a coal mill) after performing proportional (P), integral (I), and derivative (D) mathematical operations respectively, to generate a control signal to adjust the actuator (such as the damper opening or coal feed rate), thereby making the controlled variable approach the setpoint. The proportional term adjusts in real time according to the magnitude of the current deviation, the integral term is used to eliminate steady-state accumulated error, and the derivative term adjusts proactively according to the trend of deviation changes to suppress fluctuations. In the scenario of coal mill temperature control, PID controllers typically operate in a single-input, single-output manner, that is, adjusting only a single manipulated variable (such as primary air flow) based on the deviation of the outlet temperature. This makes it difficult to consider the coupled effects of other variables (such as circulating air flow, raw coal moisture content, etc.) on temperature. Furthermore, once the control parameters are tuned, they remain fixed, resulting in limited adjustment capabilities when facing changes in operating conditions or external disturbances.

[0028] In view of this, there is an urgent need to provide a method for controlling the outlet temperature of a coal mill. This method utilizes a mechanistic model constructed using the law of conservation of energy to provide a predictive benchmark for the MPC optimization solver, characterizing the physical relationship between hot air heat input, coal powder heating heat consumption, and moisture evaporation heat consumption. This enables the control system to formulate control strategies based on an accurate understanding of the temperature change mechanism, thereby improving the foresight and accuracy of control actions. By leveraging the ability of MPC to coordinate multiple operating variables within a unified optimization framework, the coupling effects between various control channels can be comprehensively considered, overcoming the control deviations caused by the fragmented treatment of variables in traditional PID control. Furthermore, by using historical data covering multiple operating conditions for solver parameter adaptation, the adaptability of the control system under different operating conditions is ensured, maintaining good control quality even in scenarios such as coal type switching and load adjustment. This comprehensively achieves the effects of narrowing temperature fluctuations, reducing manual intervention, and improving operational safety.

[0029] Figure 1 An exemplary flowchart of a method for controlling the outlet temperature of a coal mill according to some embodiments of this application is shown. Figure 2 An exemplary flowchart of the MPC optimization solver control logic of some embodiments of this application is shown.

[0030] like Figure 1 and Figure 2 As shown, the method for controlling the outlet temperature of a coal mill may include the following steps: S101, acquire historical operating data of the coal mill under different operating conditions. The historical operating data includes the coal mill outlet temperature corresponding to different usage cycles and the control variables that affect the coal mill outlet temperature.

[0031] The controlled variables may include at least one of the following: primary air flow rate, circulating air flow rate, hot air furnace outlet temperature, raw coal flow rate, raw coal moisture content, raw coal inlet temperature, and circulating air temperature.

[0032] The collected historical operating data should cover different operating conditions, such as different types of raw coal, different load conditions, and different ambient temperatures, to ensure the sufficiency and generalization ability of the subsequent model (i.e., the MPC solver) parameter identification. In this way, by collecting the above-mentioned multiple variables, the coupling relationship between the variables in the coal mill temperature regulation process can be fully reflected.

[0033] For example, taking the coal mill system of a methanol demonstration plant as an example, its core control objective is to stabilize the coal mill outlet temperature at around 105℃ (with an allowable fluctuation range of 102℃ to 108℃). To this end, historical operating data of the coal mill is first collected, covering key variables such as primary air flow rate, circulating air flow rate, hot air furnace outlet temperature, raw coal flow rate, raw coal moisture content, raw coal inlet temperature, and coal mill outlet temperature. The sampling period for historical operating data can be set to 10 seconds.

[0034] In some embodiments, after acquiring historical operating data of the coal mill under different operating conditions, the historical operating data can be preprocessed.

[0035] For example, preprocessing can remove redundant data that is not related to the temperature control of the coal mill, identify and eliminate outliers caused by sensor failures or communication anomalies, and for missing values ​​in historical operating data, it can be processed by deleting, interpolating or filling the mean / median, etc., according to the type and distribution of the missing values.

[0036] The format, units, and numerical range of the preprocessed historical operating data should be consistent to avoid deviations in subsequent model parameter identification due to data inconsistencies. During data preprocessing, the value ranges or identification benchmarks of key parameters such as equivalent heat capacity required in the mechanistic model can also be preliminarily confirmed.

[0037] S102. A nonlinear mechanism model is constructed according to the law of conservation of energy. The nonlinear mechanism model is used to express the physical relationship between the change of coal mill outlet temperature and various control variables.

[0038] Among them, the mechanism model refers to a mathematical model based on physical and chemical laws (rather than pure data statistics).

[0039] In some embodiments, the nonlinear mechanism model is as follows:

[0040] in, This indicates the outlet temperature of the coal mill (°C). It represents the equivalent heat capacity (J / ℃), including the metal shell, pulverized coal storage, air, etc. It represents the primary air mass flow rate (kg / s), which is obtained by converting the primary air flow rate, and can also be the combustion hot air mass flow rate; This indicates the outlet temperature of the hot air furnace (°C). This represents the circulating air mass flow rate (kg / s), which is obtained by converting the circulating air flow rate. Indicates the temperature of the circulating air (°C); This represents the raw coal mass flow rate (kg / s), obtained by converting the raw coal flow rate. Indicates the inlet temperature of raw coal (°C); This indicates the moisture content of raw coal (absolute mass ratio), which is obtained by converting the moisture content of raw coal. This represents the latent heat of vaporization of water (J / kg). and This represents the specific heat of air compared to coal (J / (kg·℃)).

[0041] This nonlinear mechanism model can be obtained by extending the energy conservation formula, which is as follows:

[0042] in, The heat input for the coal mill system includes the heat carried in by the primary air flow and the circulating air flow. The amount of heat required to heat the pulverized coal and the amount of heat required to evaporate the moisture in the raw coal.

[0043] S103, based on historical operating data and nonlinear mechanism models, constructs a model predictive control (MPC) optimization solver.

[0044] In some embodiments, a model predictive control (MPC) optimization solver can be constructed based on historical operating data and a nonlinear mechanism model, which can be implemented in the following manner: First, the nonlinear mechanism model is linearized and discretized to obtain a linear discrete difference equation. Then, based on historical operating data, the temperature deviation weight and control change weight corresponding to the MPC optimization solver under different operating conditions are fitted. Next, a cost function is constructed based on the temperature deviation weight and control change weight. The cost function aims to minimize the adjustment amount while minimizing the deviation between the coal mill outlet temperature and the outlet temperature setpoint. Finally, the MPC optimization solver is constructed based on the linear discrete difference equation, the cost function, and the constraints.

[0045] The constraints may include at least one of the following: operating boundaries, allowable fluctuation range of coal mill outlet temperature, and dust ratio.

[0046] In some embodiments, the nonlinear mechanism model is linearized and discretized to obtain a linear discrete difference equation. This can be achieved as follows: Taylor expansion is used to perform first-order local linearization on the nonlinear mechanism model at a set operating point, retaining the first-order partial derivative terms (i.e., Jacobian matrices) of each variable and discarding higher-order infinitesimal terms, thereby obtaining a linear state-space equation usable by the MPC optimization solver; then, forward Euler discretization is used to discretize the continuous domain linear model in the time domain, transforming the differential equation into a difference equation with a fixed control sampling period, and finally obtaining a discrete linear prediction model that can be directly called by the digital controller.

[0047] The set operating point refers to the operating condition point in a stable equilibrium state. For example, the steady-state operating point when the coal mill outlet temperature is at the target set temperature (105℃) and the system heat balance is dynamically balanced.

[0048] In some embodiments, the cost function is as follows: , Where k represents the current time, Indicates the future number step, Indicates the prediction step size. Indicates the control step size, Q represents the temperature deviation weight, and R represents the control change weight. This represents a sequence of changes in the operational quantity. This indicates the magnitude of the change in the operational quantity. This indicates the future temperature deviation.

[0049] S104: Obtain the current operating data of the coal mill and use the MPC optimization solver to solve for the optimal sequence of operations corresponding to the current operating data.

[0050] The current operating data refers to a set of data collected in real time during the actual operation of the coal mill, according to a preset sampling period, and used as input to the MPC optimization solver. For example, the current operating data may include the measured value of the coal mill outlet temperature at the current moment and the measured values ​​of the control variables that affect the coal mill outlet temperature at the current moment.

[0051] For example, the control variables affecting the current coal mill outlet temperature may include at least one of the following: primary air flow rate, circulating air flow rate, hot blast stove outlet temperature, raw coal flow rate, raw coal moisture content, raw coal inlet temperature, circulating air temperature, etc.

[0052] In some embodiments, the MPC optimization solver is used to solve for the optimal sequence of operations corresponding to the current running data. The optimal sequence of operations obtained by the MPC optimization solver is different for different situations.

[0053] The first scenario: adjustment strategy when the outlet temperature is too low.

[0054] When the pulverizer outlet temperature is below the lower limit of the allowable fluctuation range, the optimal operation sequence output by the MPC optimizer includes a first operation to increase the primary air flow rate and a second operation to decrease the raw coal flow rate. Continuing with the example of a methanol demonstration plant's pulverizer system, when the pulverizer outlet temperature is below 102℃, the optimal operation sequence output by the MPC optimizer includes a first operation to increase the primary air flow rate and a second operation to decrease the raw coal flow rate. Increasing the primary air flow rate increases heat input, while decreasing the raw coal flow rate reduces heat consumption (including heat loss from pulverized coal heating and moisture evaporation). The combined effect of these two operations allows the outlet temperature to rise back to the normal range.

[0055] By adopting the above scheme, when the outlet temperature is too low, the outlet temperature can be quickly and effectively raised back to the target range through two-way coordinated adjustment of "increasing heat supply and reducing heat consumption", avoiding the problem of slow response when relying on a single operating variable for adjustment in traditional control methods.

[0056] The second scenario: feedforward compensation strategy when the moisture content of raw coal fluctuates.

[0057] When the change in raw coal moisture content reaches a preset threshold, a perturbation feedforward compensation mechanism is triggered. The optimal operation sequence output by the MPC optimization solver includes a feedforward compensation operation to increase the primary air flow rate to compensate for the heat loss caused by the increased moisture content. An increase in raw coal moisture content means that more heat needs to be consumed to evaporate the excess moisture; without compensation, this will lead to a decrease in outlet temperature. Therefore, when solving for the optimal operation, the MPC optimization solver uses the change in raw coal moisture content as known feedforward perturbation information to pre-calculate the compensation amount. Continuing with the example of a methanol demonstration plant's coal mill system, when the raw coal moisture content suddenly increases by 1 percentage point, the perturbation feedforward compensation mechanism increases the primary air flow rate by 0.08 kg / s to offset the inhibitory effect of the increased moisture content on the outlet temperature.

[0058] By adopting the above scheme and integrating the feedforward compensation mechanism for raw coal moisture content fluctuations into the MPC optimization solver, compensation and adjustment can be carried out in advance before the moisture content changes have a substantial impact on the outlet temperature. This achieves "advanced intervention" rather than "lagging response" to disturbances, and significantly improves the ability to resist disturbances.

[0059] The third scenario: safety interlock strategy when the outlet temperature is too high.

[0060] When the coal mill outlet temperature exceeds the upper limit of the allowable fluctuation range, the optimal operation sequence output by the MPC optimization solver includes interlocking operations for activating the cooling nitrogen supply device for forced cooling. Continuing with the example of a methanol demonstration plant's coal mill system, when the MPC predicts the outlet temperature will reach 110℃, a safety interlock mechanism is triggered. First, the cooling nitrogen supply device is activated to inject cooling nitrogen into the coal mill for forced cooling. If the temperature does not drop to a safe range after a predetermined time, a shutdown command is issued to stop the coal mill operation.

[0061] By adopting the above scheme and integrating a high-temperature safety interlock mechanism into the MPC optimization solver, when conventional adjustment methods are insufficient to quickly suppress the temperature rise, cooling nitrogen can be automatically activated for forced cooling or even mill shutdown, avoiding safety accidents such as equipment damage or dust explosions caused by continuous temperature rise, and providing reliable safety redundancy for coal mill operation.

[0062] Through the coordinated operation of the above three scenarios, the control method provided by one or more embodiments of this specification can adaptively output the optimal operating quantity sequence that is adapted to the current operating state under different operating conditions, thereby realizing comprehensive and multi-level intelligent control of the coal mill outlet temperature.

[0063] S105 controls the coal mill outlet temperature based on the optimal operating quantity sequence.

[0064] In some embodiments, controlling the coal mill outlet temperature based on the optimal operation quantity sequence can be achieved in the following manner: first, obtain the optimal operation quantity sequence corresponding to the predicted step size obtained by the MPC optimization solver; then, control the coal mill outlet temperature based on the optimal operation quantity corresponding to the current step in the optimal operation quantity sequence.

[0065] In some embodiments, after entering the next sampling period, the actual measured value of the coal mill outlet temperature is obtained, and the state variables of the MPC optimization solver in the previous sampling period are fed back and corrected based on the deviation between the actual measured value and the predicted value of the nonlinear mechanism model. The prediction and optimization process is repeated to achieve rolling time domain control.

[0066] In this way, through the synergistic effect of the three mechanisms of "model-based advance prediction, rolling optimization global coordination, and feedback correction closed-loop correction", the precise, stable and safe control of the coal mill outlet temperature under multi-variable coupling, large lag and multi-constraint conditions is achieved. It has the characteristics of feedforward, adaptability and robustness, and has more precise and robust dynamic adjustment than traditional PID control.

[0067] The following is a specific example illustrating a method for controlling the outlet temperature of a coal mill provided in this application. Figure 3 As shown, continuing to take the coal mill system of a methanol demonstration plant as an example, the following steps may be included: The first step is data acquisition and preprocessing. Historical operating data of the coal mill under different working conditions is collected, covering key variables such as primary air flow rate, circulating air flow rate, hot air furnace outlet temperature, raw coal flow rate, raw coal moisture content, raw coal inlet temperature, and coal mill outlet temperature. The sampling period for historical operating data is set to 10 seconds. Preprocessing of the historical operating data involves removing redundant data unrelated to coal mill temperature control, identifying and eliminating outliers caused by sensor malfunctions or communication anomalies, and processing missing values ​​in the historical operating data according to their type and distribution, using methods such as deletion, interpolation, or filling with the mean / median, ensuring consistency in format, units, and numerical range.

[0068] The second step is mechanism modeling. A nonlinear mechanism model is constructed based on the law of conservation of energy. This nonlinear mechanism model is used to express the physical relationship between the change in the coal mill outlet temperature and various control variables, specifically characterizing the physical relationship between the hot air heat input, the heat consumption of coal powder heating, and the heat consumption of moisture evaporation.

[0069] The third step is to construct the MPC optimization solver (also known as the MPC model). The nonlinear mechanism model is linearized and discretized to obtain linear discrete difference equations. Specifically, Taylor expansion is used to perform first-order local linearization of the nonlinear mechanism model at a set operating point, retaining the first-order partial derivatives of each variable and discarding higher-order infinitesimal terms to obtain a linear state-space equation. Then, the forward Euler difference method is used to discretize the continuous-domain linear model in the time domain to obtain a discrete linear prediction model. Based on historical operating data, the temperature deviation weights and control change weights corresponding to different operating conditions are fitted to the model predictive control optimization solver, constructing a cost function. This cost function aims to minimize the adjustment amount while minimizing the deviation between the coal mill outlet temperature and the setpoint. Finally, the model predictive control optimization solver is constructed based on the linear discrete difference equations, the cost function, and constraints, including the operating boundary, the allowable fluctuation range of the coal mill outlet temperature, and the dust ratio.

[0070] The fourth step is rolling optimization. Obtain the current operating data of the coal mill, including the measured value of the coal mill outlet temperature at the current moment and the measured values ​​of the control variables affecting the coal mill outlet temperature at the current moment. Use the MPC optimization solver to solve for the optimal sequence of operations corresponding to the current operating data.

[0071] Step 5: Constraint Judgment and Safety Interlock. Determine if the solution meets the constraints. If not, trigger the safety interlock, activate the cooling nitrogen system for forced cooling. If the temperature fails to drop to a safe range after a predetermined time, issue a shutdown command to stop the coal mill.

[0072] Step 6: Execute control. If the constraints are met, control the mill outlet temperature, adjust the air volume, coal volume, and feedforward compensation based on the optimal operating sequence. See step S104 for details; it will not be repeated here.

[0073] Step 7: Real-time monitoring and feedback correction. The outlet temperature is monitored in real time. Upon entering the next sampling cycle, the actual measured value of the coal mill outlet temperature is acquired. Based on the deviation between the actual measured value and the predicted value from the nonlinear mechanism model, the state variables of the model predictive control optimization solver from the previous sampling cycle are corrected using feedback. If the temperature is not within the target range, the prediction and optimization process is repeated to achieve rolling time-domain control; if the temperature is within the target range, operation continues.

[0074] In summary, by utilizing the energy conservation law to construct a mechanistic model, a predictive benchmark is provided for the model predictive control optimization solver, characterizing the physical relationship between hot air heat input, coal powder heating heat consumption, and moisture evaporation heat consumption. This enables the control system to formulate control strategies based on an accurate understanding of the temperature change mechanism, thereby improving the foresight and accuracy of control actions. The ability of model predictive control to coordinate multiple operating variables within a unified optimization framework allows for a comprehensive consideration of the coupling effects between control channels, overcoming the control bias caused by the fragmented handling of variables in traditional proportional-integral-derivative control. Furthermore, the use of historical data covering multiple operating conditions for solver parameter adaptation ensures the adaptability of the control system under different operating conditions, maintaining good control quality even during coal type switching and load adjustments. This comprehensively achieves the effects of narrowing temperature fluctuations, reducing manual intervention, and improving operational safety. Through the synergistic effect of three mechanisms—model-based forward prediction, rolling optimization for global coordination, and feedback correction for closed-loop deviation—precise, stable, and safe control of the coal mill outlet temperature under conditions of multivariate coupling, large lag, and multiple constraints is achieved, combining feedforward, adaptability, and robustness.

[0075] It is understood that the above embodiments are merely examples, and modifications can be made to the above embodiments in actual implementation. Those skilled in the art will understand that any modifications to the above embodiments that do not require creative effort fall within the protection scope of this application, and will not be described in detail in the embodiments.

[0076] Based on the same inventive concept, this application also provides a control device for the outlet temperature of a coal mill, such as... Figure 4As shown, the control device 200 for the coal mill outlet temperature includes: The acquisition module 201 is used to acquire historical operating data of the coal mill under different operating conditions. The historical operating data includes the coal mill outlet temperature corresponding to different usage cycles and the control variables that affect the coal mill outlet temperature. The nonlinear mechanism model construction module 202 is used to construct a nonlinear mechanism model according to the law of conservation of energy. The nonlinear mechanism model is used to express the physical relationship between the change of coal mill outlet temperature and various control variables. MPC optimization solver building module 203 is used to build a model predictive control MPC optimization solver based on historical running data and nonlinear mechanism models; The solver module 204 is used to obtain the current operating data of the coal mill and use the MPC optimization solver to solve for the optimal sequence of operations corresponding to the current operating data. Control module 205 is used to control the outlet temperature of the coal mill based on the optimal operating sequence.

[0077] Based on the same inventive concept, embodiments of this application also provide an electronic device, which may include a processor and a memory. The memory may be used to store computer programs, such as programs / code pre-installed at the time of manufacture, or code for execution by the processor. The processor may be used to call and execute the computer program in the memory to enable the electronic device to implement the coal mill outlet temperature control method described in this application embodiment, such as the one described above. Figure 1 method.

[0078] It should be understood that electronic devices may also include other components, such as displays and transceivers. Displays can be used to show user interfaces, and transceivers can be used to receive various user inputs.

[0079] This electronic device can correspond to the electronic device provided in the above embodiments.

[0080] Since the principle behind the problem solved by the electronic device is similar to the aforementioned method for controlling the outlet temperature of the coal mill, the implementation of the electronic device can be found in the aforementioned method for controlling the outlet temperature of the coal mill, and the repetition will not be repeated.

[0081] The processor in the above embodiments can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this application can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software modules can reside in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. This storage medium is located in memory; the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above methods.

[0082] The memory in the above embodiments can be volatile memory or non-volatile memory, or may include both. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which serves as an external cache. By way of example, but not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous linked dynamic random access memory (SLDRAM), and direct rambus RAM (DR RAM). It should be noted that the memory used in the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0083] Based on the same inventive concept, embodiments of this application also provide a computer-readable storage medium storing a computer program, which, when run on an electronic device, causes the electronic device to implement the methods described in the above method embodiments.

[0084] Those skilled in the art will recognize that the various illustrative logical blocks and steps described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this application.

[0085] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working process of the electronic devices and modules described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0086] In the several embodiments provided in this application, it should be understood that the disclosed electronic devices, modules, and methods can be implemented in other ways. For example, the electronic device embodiments described above are merely illustrative. For instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0087] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0088] In addition, the functional modules in the various embodiments of this application can be integrated into one processing unit, or each module can exist physically separately, or two or more modules can be integrated into one unit.

[0089] If the aforementioned functions are implemented as software functional units 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 this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0090] It should be understood that in the various embodiments of this application, the execution order of each step should be determined by its function and internal logic, and the size of each step number does not mean the order of execution, and does not constitute a limitation on the implementation process of the embodiments.

[0091] The various parts of this specification are described in a progressive manner. Similar or identical parts between the various embodiments can be referred to interchangeably. Each embodiment focuses on the differences from other embodiments. In particular, the embodiments for electronic devices, chip systems, computer-readable storage media, and computer program products are basically similar to the method embodiments, so the descriptions are relatively simple; relevant details can be found in the descriptions within the method embodiments.

[0092] While numerous embodiments of this application have been shown and described herein, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Many modifications, alterations, and alternatives will arise for those skilled in the art without departing from the spirit and intent of this application. It should be understood that various alternatives to the embodiments of this application described herein may be employed in the practice of this application. The appended claims are intended to define the scope of protection of this application and therefore cover equivalents or alternatives within the scope of these claims.

Claims

1. A method for controlling the outlet temperature of a coal mill, characterized in that, The method includes: Acquire historical operating data of the coal mill under different operating conditions. The historical operating data includes the coal mill outlet temperature corresponding to different usage cycles and the control variables that affect the coal mill outlet temperature. A nonlinear mechanism model is constructed based on the law of conservation of energy. This nonlinear mechanism model is used to express the physical relationship between the change in the coal mill outlet temperature and each of the control variables. Based on the historical operating data and the nonlinear mechanism model, a model predictive control (MPC) optimization solver is constructed. The current operating data of the coal mill is obtained, and the optimal operation sequence corresponding to the current operating data is solved using the MPC optimization solver. The coal mill outlet temperature is controlled based on the optimal operating sequence. The nonlinear mechanism model is as follows: ; in, This indicates the outlet temperature of the coal mill. Indicates equivalent heat capacity, Indicates the primary air mass flow rate. Indicates the outlet temperature of the hot blast stove. This indicates the mass flow rate of the circulating air. Indicates the temperature of the circulating air. Indicates the mass flow rate of raw coal. Indicates the inlet temperature of the raw coal. Indicates the moisture content of raw coal. This represents the latent heat of vaporization of water. and This indicates the specific heat of air compared to coal.

2. The method according to claim 1, characterized in that, The construction of a model predictive control (MPC) optimization solver based on the historical operating data and the nonlinear mechanism model includes: The nonlinear mechanism model is linearized and discretized to obtain a linear discrete difference equation; Based on the historical operating data, the temperature deviation weight and control change weight of the MPC optimization solver under different operating conditions are obtained by fitting. Based on the temperature deviation weight and control change weight, a cost function is constructed; wherein, the cost function aims to minimize the adjustment amount while minimizing the deviation between the coal mill outlet temperature and the outlet temperature setpoint. Based on the linear discrete difference equation, the cost function, and the constraints, the MPC optimization solver is constructed; wherein the constraints include at least one of the following: operating boundary, allowable fluctuation range of coal mill outlet temperature, and dust ratio.

3. The method according to claim 2, characterized in that, The cost function is as follows: , Where k represents the current time, Indicates the future number step, Indicates the prediction step size. Indicates the control step size, Q represents the temperature deviation weight, and R represents the control change weight. This represents a sequence of changes in the operational quantity. This indicates the magnitude of the change in the operational quantity. This indicates the future temperature deviation.

4. The method according to claim 1, characterized in that, The controlled variables include at least one of the following: primary air flow rate, circulating air flow rate, hot air furnace outlet temperature, raw coal flow rate, raw coal moisture content, raw coal inlet temperature, and circulating air temperature.

5. The method according to claim 1, characterized in that, Controlling the coal mill outlet temperature based on the optimal operating sequence includes: Obtain the optimal operation sequence corresponding to the prediction step size obtained by the MPC optimization solver; The outlet temperature of the coal mill is controlled based on the optimal operation quantity corresponding to the current step in the optimal operation quantity sequence. After entering the next sampling period, the actual measured value of the coal mill outlet temperature is obtained. Based on the deviation between the actual measured value and the predicted value of the nonlinear mechanism model, the state variables of the MPC optimization solver in the previous sampling period are fed back for correction, and the prediction and optimization process is repeated to achieve rolling time domain control.

6. The method according to claim 1, characterized in that, The optimal sequence of operations corresponding to the current running data is solved using the MPC optimization solver, including: When the outlet temperature of the coal mill is lower than the lower limit of the allowable fluctuation range of the outlet temperature of the coal mill, the optimal operation sequence output by the MPC optimization solver includes a first operation for increasing the primary air flow and a second operation for decreasing the raw coal flow. When the change in the moisture content of raw coal reaches a preset threshold, the disturbance feedforward compensation mechanism is triggered. The optimal operation sequence output by the MPC optimization solver includes feedforward compensation operation to increase the primary air flow rate to compensate for the heat loss caused by the increase in moisture content. When the outlet temperature of the coal mill is higher than the upper limit of the allowable fluctuation range of the coal mill outlet temperature, the optimal operation sequence output by the MPC optimization solver includes interlocking operation quantities for starting the cooling nitrogen operation device for forced cooling.

7. A control device for the outlet temperature of a coal mill, characterized in that, include: The acquisition module is used to acquire historical operating data of the coal mill under different operating conditions. The historical operating data includes the coal mill outlet temperature corresponding to different usage cycles and the control variables that affect the coal mill outlet temperature. A nonlinear mechanism model construction module is used to construct a nonlinear mechanism model according to the law of conservation of energy. This nonlinear mechanism model expresses the physical relationship between the change in the coal mill outlet temperature and the various control variables. The nonlinear mechanism model is as follows: ; in, This indicates the outlet temperature of the coal mill. Indicates equivalent heat capacity, Indicates the primary air mass flow rate. Indicates the outlet temperature of the hot blast stove. This indicates the mass flow rate of the circulating air. Indicates the temperature of the circulating air. Indicates the mass flow rate of raw coal. Indicates the inlet temperature of the raw coal. Indicates the moisture content of raw coal. This represents the latent heat of vaporization of water. and This indicates the specific heat of air compared to that of coal; The MPC optimization solver construction module is used to construct a model predictive control MPC optimization solver based on the historical operating data and the nonlinear mechanism model. The solution module is used to obtain the current operating data of the coal mill and use the MPC optimization solver to solve for the optimal sequence of operations corresponding to the current operating data; The control module is used to control the outlet temperature of the coal mill based on the optimal operating sequence.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the program implements the method described in any one of claims 1-6.

9. An electronic device, characterized in that, include: One or more processors; Memory, used to store one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to implement the method of any one of claims 1-6.