Coal mill outlet temperature control method, device and system and coal mill equipment

Abstract

The invention relates to a coal mill outlet temperature control method, device and system and coal mill equipment. The coal mill outlet temperature control method comprises the steps that a reference trajectory and prediction output of the coal mill air duct outlet temperature at the prediction moment are obtained; processing the reference trajectory and the prediction output according to a target proportional integral implicit generalized prediction control model to obtain a target control increment; and an air inlet assembly of the coal mill is controlled according to the target control increment, so that the real-time temperature of an air duct outlet of the coal mill is adjusted to the target temperature, and the air inlet assembly comprises a hot air adjusting valve and a cold air adjusting valve. According to the method, a feedback structure of proportional-integral control is combined with a prediction function of implicit generalized prediction control, so that the influence of uncertain factors such as nonlinearity, time-varying property and hysteresis quality of outlet temperature control of the coal mill can be effectively overcome, and the robustness and the anti-interference capability of the system are remarkably improved.

Description

Technical Field

[0001] The present application relates to the technical field of coal mill control optimization, and particularly to a method, device, system and coal mill equipment for controlling the outlet temperature of a coal mill. Background Art

[0002] The outlet temperature of the coal mill directly affects the combustion efficiency of pulverized coal. An appropriate outlet temperature can ensure that the pulverized coal burns fully in the combustion chamber, improve energy utilization efficiency, and reduce energy waste caused by incomplete combustion. The outlet temperature of the coal mill needs to be maintained within a certain range. If the outlet temperature is too low, it may lead to a relatively high water content in the pulverized coal, which is not conducive to the ignition of the pulverized coal and reduces the combustion efficiency of the boiler. If the outlet temperature is too high, it may cause the coal mill to catch fire, which is adverse to the safe operation of the coal mill.

[0003] In the related art, the control scheme for the outlet temperature of the coal mill has poor control effects in strongly nonlinear, time-varying and uncertain systems and cannot stably adjust the outlet temperature of the coal mill. Summary of the Invention

[0004] Based on this, in view of the above technical problems, it is necessary to provide a method, device, system and coal mill equipment for controlling the outlet temperature of a coal mill, which can effectively improve the robustness and anti-interference ability of the outlet temperature control of the coal mill.

[0005] In a first aspect, the present application provides a method for controlling the outlet temperature of a coal mill air duct, the method comprising: Obtaining a reference trajectory and a predicted output of the outlet temperature of the coal mill air duct at a prediction moment, wherein the reference trajectory is a reference value trend line of the outlet temperature of the coal mill air duct within a preset time period, and the predicted output is a predicted value of the outlet temperature of the coal mill air duct; Processing the reference trajectory and the predicted output according to a target proportional integral implicit generalized predictive control model to obtain a target control increment; Controlling an air inlet assembly of the coal mill according to the target control increment to adjust a real-time temperature at an outlet of the coal mill air duct to a target temperature, wherein the air inlet assembly includes a hot air regulating valve and a cold air regulating valve.

[0006] In one embodiment, the obtaining the reference trajectory of the outlet temperature of the coal mill at the prediction moment includes: Obtaining a real-time outlet temperature and a set outlet temperature at the current moment, wherein the real-time outlet temperature is the real-time temperature at the outlet of the coal mill air duct, and the set outlet temperature is the set temperature at the outlet of the coal mill air duct; Calculating the reference trajectory of the outlet temperature of the coal mill at the prediction moment according to a softening factor at the prediction moment, the real-time outlet temperature and the set outlet temperature at the current moment.

[0007] In one embodiment, the obtaining of the predicted output of the temperature at the outlet of the coal mill air duct at the prediction moment includes: Calculating the predicted output of the temperature at the outlet of the coal mill air duct based on the control increment at the previous moment of the prediction moment, the gain coefficient, the real-time outlet temperature at the current moment, the state coefficient, the control increment at the previous moment of the current moment, and the feed-forward coefficient.

[0008] In one embodiment, the processing of the reference trajectory and the predicted output according to the target proportional integral implicit generalized predictive control model to obtain the target control increment includes: Calculating the difference according to the reference trajectory and the predicted output to obtain the target error value; Processing the target error value according to a preset control performance index function to obtain a prediction performance index; Calculating the target control increment according to the optimal performance index and a preset memory term.

[0009] In one embodiment, the controlling of the air inlet assembly of the coal mill according to the target control increment to adjust the real-time temperature at the outlet of the coal mill air duct to the target temperature includes: Calculating the sum value according to the control amount at the previous moment of the current moment and the target control increment to obtain the target control amount; Controlling the air inlet assembly of the coal mill according to the target control amount to adjust the real-time temperature at the outlet of the coal mill air duct to the target temperature.

[0010] In one embodiment, the method further includes: Estimating the control parameters of the air inlet assembly by using the fading memory recursive least squares algorithm; Adjusting the memory factor of the preset memory term according to the control parameters.

[0011] In one embodiment, the obtaining of the real-time outlet temperature at the current moment includes: Collecting the real-time temperature at the outlet of the coal mill air duct through an infrared monitoring module to obtain the real-time outlet temperature.

[0012] In a second aspect, the present application further provides a control device for the temperature at the outlet of the coal mill air duct, and the device includes: An obtaining module, configured to obtain the reference trajectory and the predicted output of the temperature at the outlet of the coal mill air duct at the prediction moment; A calculating module, configured to process the reference trajectory and the predicted output according to the target proportional integral implicit generalized predictive control model to obtain the target control increment; A control module, configured to control an air inlet component of the coal mill according to the target control increment so as to adjust the real-time temperature at the air duct outlet of the coal mill to a target temperature, wherein the air inlet component includes a hot air regulating valve and a cold air regulating valve.

[0013] In a third aspect, the present application further provides a real-time temperature control system for the air duct outlet of a coal mill, including a control module, an infrared monitoring module, and an air inlet component. The control module is respectively connected to the infrared monitoring module and the air inlet component. The air inlet component includes a hot air regulating valve and a cold air regulating valve; The infrared monitoring module is configured to obtain the real-time temperature at the air duct outlet of the coal mill and send the real-time temperature to the control module; The control module includes a proportional-integral implicit generalized predictive controller; the control module is configured to execute the real-time temperature control method for the air duct outlet of the coal mill described in the first aspect.

[0014] In a fourth aspect, the present application further provides a coal mill device, including the real-time temperature control system for the air duct outlet of the coal mill described in the third aspect.

[0015] In summary, the present application proposes a real-time temperature control method, device, system, and coal mill device for the coal mill outlet, including: obtaining a reference trajectory and a predicted output of the real-time temperature at the air duct outlet of the coal mill at a prediction moment; processing the reference trajectory and the predicted output according to a target proportional-integral implicit generalized predictive control model to obtain a target control increment; controlling the air inlet component of the coal mill according to the target control increment so as to adjust the real-time temperature at the air duct outlet of the coal mill to a target temperature, wherein the air inlet component includes a hot air regulating valve and a cold air regulating valve. The present application combines the feedback structure of proportional-integral control with the prediction function of implicit generalized predictive control, can effectively overcome the influence of uncertain factors such as nonlinearity, time-variation, and hysteresis in the real-time temperature control of the coal mill outlet, and significantly improves the robustness and anti-interference ability of the system. Description of the Drawings

[0016] Figure 1 It is a structural block diagram of a real-time temperature control system for the air duct outlet of a coal mill in an embodiment; Figure 2 It is an algorithm schematic diagram of a target proportional-integral implicit generalized predictive control model in an embodiment; Figure 3 It is a flowchart of a real-time temperature control method for the air duct outlet of a coal mill in an embodiment; Figure 4 It is a schematic diagram of the principle of a real-time temperature control method for the air duct outlet of a coal mill in an embodiment; Figure 5 It is a structural block diagram of a real-time temperature control device for the air duct outlet of a coal mill in an embodiment; Figure 6 Internal structure diagram of a computer device in an embodiment.

[0017] Summary of reference numerals: Control module - 110; Infrared monitoring module - 120; Air inlet assembly - 130; Hot air regulating valve - 131; Cold air regulating valve - 132. Detailed implementation manners

[0018] In order to make the objectives, technical solutions and advantages of the present application clearer and more understandable, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0019] In one embodiment, as Figure 1 shown, a temperature control system for the outlet of the coal mill air duct is provided, including a control module 110, an infrared monitoring module 120 and an air inlet assembly 130. The control module 110 is respectively connected to the infrared monitoring module 120 and the air inlet assembly 130. The air inlet assembly 130 includes a hot air regulating valve 131 and a cold air regulating valve 132.

[0020] The infrared monitoring module 120 is used to obtain the real-time temperature at the outlet of the coal mill air duct and send the real-time temperature to the control module 110.

[0021] In this embodiment, the infrared monitoring module 120 can adopt a high-resolution infrared sensor. The infrared monitoring module 120 can be arranged inside or outside the air duct of the coal mill and is used to monitor the real-time temperature at the outlet of the coal mill air duct in real time. After collecting the temperature data, the temperature data is converted into a digital signal and transmitted to the control module 110. The specific types of the infrared sensor and the analog-to-digital conversion circuit in the infrared monitoring module 120 are not specifically limited in this embodiment, and appropriate infrared sensors and analog-to-digital conversion circuits or chips can be selected according to the needs of the actual application scenario. And the infrared monitoring module 120 in this embodiment can be installed inside the coal mill according to the needs of the actual application scenario, and can be installed at any position that can realize the function of monitoring the temperature at the outlet of the coal mill air duct.

[0022] The control module 110 includes a proportional-integral implicit generalized predictive controller. In this embodiment, the model structure of the proportional-integral (Proportional-Integral, abbreviated as PI) implicit generalized predictive control (Implicit Generalized Predictive Control, abbreviated as IGPC) controller is as Figure 2 shown, and at least includes a PI implicit generalized predictive module and a parameter estimation module. Among them, the controlled object is the air inlet assembly 130, represents the observed output value of the controlled object, that is, the temperature at the outlet of the coal mill air duct, Represents the preset temperature value at the outlet of the coal mill air duct, i.e., the reference temperature value.

[0023] Among them, the PI implicit generalized prediction module is used to calculate the target control quantity for the controlled object according to the target proportional-integral implicit generalized prediction control model. The target control quantity acts on the controlled object to make the air inlet assembly 130 open according to the target opening value, and make the hot air regulating valve 131 and the cold air regulating valve 132 open according to the corresponding target opening values, so as to adjust the air inlet parameters at the inlet of the coal mill air duct, and then adjust the temperature value at the outlet of the coal mill air duct. In this embodiment, the PI implicit generalized prediction module combines the prediction function of IGPC and the feedback regulation function of PI, and can adapt to various complex working conditions, such as the working scenarios of coal mills with characteristics of uncertainty, time-varying, large time delay, large inertia and nonlinearity.

[0024] In this embodiment, the PI controller responds quickly to the error change through the proportional term, eliminates the steady-state error through the integral term, and directly deals with the local nonlinearity of the system. Automatically adjusts the proportional gain and the integral gain to make the controller adapt to the time-varying working conditions. The integral term in PI can continuously eliminate the residual error caused by the lag.

[0025] The rolling optimization and multi-step prediction in GPC can ensure that the control strategy adapts to nonlinearity, hysteresis and time-variation.

[0026] The parameter estimation module is used to estimate the control parameters according to the Fading Memory Recursive Least Squares (FM-RLS) algorithm, and adjust the memory factor of the preset memory item according to the control parameters. The memory factor of the FR-RLS algorithm is the forgetting factor. By gradually reducing the weight of historical data, the parameter estimation depends more on the latest data and quickly tracks the time-varying characteristics of the system. In the actual application scenario, the FM-RLS algorithm is used as the identification link in the PI feedback process. By adding the forgetting factor in the recursive process and reducing the weight of historical data, the correction effect of new data is enhanced, making the parameter estimation more adaptable to the time-varying system, and thus effectively strengthening the robustness and adaptability of the PI implicit generalized prediction module.

[0027] In one embodiment, as Figure 3 shown, a method for controlling the temperature at the outlet of the coal mill air duct is provided, including: S301, obtaining the reference trajectory and the predicted output of the temperature at the outlet of the coal mill air duct at the prediction moment, where the reference trajectory is the reference value trend line of the temperature at the outlet of the coal mill air duct within a preset time period, and the predicted output is the predicted value of the temperature at the outlet of the coal mill air duct.

[0028] In this embodiment, the prediction moment is any future moment compared with the current moment. For example, The moment is the prediction moment, where is the current moment, is the difference between the future moment and the current moment.

[0029] The predicted output of the temperature at the outlet of the coal mill air duct at the prediction moment is the predicted value of the temperature at the outlet of the coal mill air duct at the prediction moment.

[0030] The reference trajectory of the temperature at the outlet of the coal mill air duct at the prediction moment is the temperature reference value trend line within the preset time period corresponding to the outlet of the coal mill air duct at the prediction moment. The preset time period in this embodiment can be custom-set according to the needs of actual applications. The reference value can be determined according to the actual application requirements of the coal mill, and the reference values of the coal mill are different under different working conditions.

[0031] S302. Process the reference trajectory and the predicted output according to the target proportional-integral implicit generalized predictive control model to obtain the target control increment.

[0032] In this embodiment, the target proportional-integral implicit generalized predictive control model is used to calculate the target control increment. By combining the PI feedback structure with the predictive function of IGPC, a control performance index function with a PI structure is constructed, and then according to the optimal performance index function, the target control increment is solved. The target control increment acts on the air inlet assembly 130 of the coal mill to adjust the opening degree of the air inlet assembly 130 of the coal mill, so as to realize the dynamic control of the temperature at the outlet of the coal mill air duct.

[0033] In this embodiment, the specific structure of the target proportional-integral implicit generalized predictive control model can refer to the structure of the proportional-integral implicit generalized predictive controller as described in the foregoing embodiment such as Figure 2 shown.

[0034] During the actual operation process, as Figure 4 shown, the working principle of the target proportional-integral implicit generalized predictive control model can be: First, through the smooth processing of the temperature set value and the real-time temperature value , the reference trajectory of the temperature at the outlet of the coal mill air duct at the prediction moment is obtained. The predicted output of the temperature at the outlet of the coal mill air duct at the prediction moment is predicted by using the predictive function of the PI-IGPC controller. The actual output at the outlet of the air duct of the coal mill system is detected by the infrared monitoring module 120, that is, the real-time temperature value .

[0035] Second, combine the reference trajectory and the predicted output Perform rolling optimization, multi-step prediction, and feedback correction processing, and finally obtain the control quantity for the air inlet component 130 in the coal mill system. , and apply the control quantity to the coal mill system so that the outlet temperature of the coal mill is controlled within a preset range. Among them, during the rolling optimization process, the control quantity calculated in real time will be input into the PI-IGPC controller multiple times to update the predicted output , and then based on the updated predicted output and the reference trajectory perform multiple predictions within the control period (control length and prediction length), and finally achieve the dynamic control of the air inlet component 130 of the coal mill system.

[0036] S303, control the air inlet component 130 of the coal mill according to the target control increment to adjust the real-time temperature at the outlet of the coal mill air duct to the target temperature, where the air inlet component 130 includes a hot air regulating valve 131 and a cold air regulating valve 132.

[0037] In this embodiment, by combining the target control increment with the control quantity at the previous moment of the current moment, the control quantity at the current moment can be obtained. Based on the control quantity at the current moment, control the air inlet component 130 of the coal mill to control the opening degree of the air inlet component 130 within the preset opening degree range, and the real-time temperature at the outlet of the coal mill air duct can be adjusted to the target temperature.

[0038] In this embodiment, both the target control increment and the control quantity are control parameters of the corresponding control object, that is, the opening degree increment and the opening degree value of the air inlet component 130. It should be noted that the air inlet component 130 includes a hot air regulating valve 131 and a cold air regulating valve 132. The control quantity in this embodiment can indicate that the hot air regulating valve 131 opens according to the first opening degree and the cold air regulating valve 132 opens according to the second opening degree. The specific forms of the control quantity and the control increment in this embodiment are determined according to the number of control objects. When the number of control objects is 2, both the control quantity and the control increment include two control parameters for different control objects.

[0039] Based on the above steps, this embodiment provides a method for controlling the outlet temperature of the coal mill air duct by combining PI feedback and IGPC predictive control functions, which overcomes the problems of complex conventional PID cascade control tuning methods and poor adaptability to operating conditions. Through multi-step prediction, rolling optimization, and feedback correction control strategies, it can effectively overcome the influence of uncertain factors such as nonlinearity, time-variation, and hysteresis in the control of the outlet temperature of the coal mill air duct, and significantly improve the robustness and anti-interference ability of the system.

[0040] In one of the embodiments, obtaining the reference trajectory of the outlet temperature of the coal mill at the prediction moment includes: Obtain the real-time outlet temperature and the set outlet temperature at the current moment, where the real-time outlet temperature is the real-time temperature at the outlet of the coal mill air duct, and the set outlet temperature is the set temperature at the outlet of the coal mill air duct.

[0041] According to the softening factor at the prediction moment, the real-time outlet temperature and the set outlet temperature at the current moment, calculate the reference trajectory of the outlet temperature of the coal mill at the prediction moment.

[0042] In this embodiment, the calculation formula of the reference trajectory includes: Wherein, is the softening factor at the prediction moment, , decays with the increase of the time step so that the weight of gradually decreases, the weight of gradually increases, is the real-time outlet temperature at the current moment,

[0043] is the set outlet temperature at the current moment,

[0044] is the reference trajectory. Collect the real-time temperature at the outlet of the coal mill air duct through the infrared monitoring module 120 to obtain the real-time outlet temperature.

[0045] In this embodiment, by collecting the real-time temperature at the outlet of the coal mill air duct through a high-resolution infrared sensor, the real-time temperature can be collected more quickly, and based on the real-time temperature and the reference temperature to construct the reference trajectory, it can realize smooth tracking while achieving more timely temperature tracking, avoiding the lag effect of the coal mill outlet temperature control.

[0046] In one of the embodiments, obtaining the predicted output of the outlet temperature of the coal mill air duct at the prediction moment includes: According to the control increment at the previous moment of the prediction moment, the gain coefficient, the real-time outlet temperature at the current moment, the state coefficient, the control increment at the previous moment of the current moment, and the feedforward coefficient, calculate the predicted output of the outlet temperature of the coal mill air duct.

[0047] In this embodiment, the calculation formula of the predicted output includes: Simplify the above formula through the following formula: The calculation formula for the simplified predicted output can be obtained as follows: Where, is the predicted temperature at the future time , is the control increment at the previous moment of the time, is the gain matrix,

[0048] is the temperature at the current time , is the state coefficient, indicating the influence of the current state on the future output, is the feedforward coefficient, indicating the influence of the previous control input increment on the future output, is the control increment at the previous moment of the current time .

[0049] In this embodiment, a PI-IGPC control module is used to calculate the predicted output of the pulverizer air duct outlet temperature. In the actual application process, an Autoregressive Integrated Moving Average Model (abbreviated as CARIMA model) is used to construct the function of the PI-IGPC control module. The expression of the CARIMA model is: Where, is the disturbance sequence; is the backward shift operator; represents the difference operator; is an n-th order polynomial, is an m-th order polynomial, is an n-th order polynomial.

[0050] Specifically in this embodiment, it can be embodied as: Where, is an n-th order polynomial. is order polynomial, where, . is an n-th order polynomial.

[0051] In the actual application process, users of the FR-RLS algorithm update the parameters of the CARIMA model online. For example 、 the coefficients of 、 and .

[0052] In one of the embodiments, the reference trajectory and the predicted output are processed according to the target proportional-integral implicit generalized predictive control model to obtain the target control increment, including: Calculating the difference according to the reference trajectory and the predicted output to obtain the target error value.

[0053] Processing the target error value according to the preset control performance index function to obtain the predicted performance index.

[0054] Calculating the target control increment according to the optimal performance index and the preset memory term.

[0055] In this embodiment, the calculation formula of the target error value is: where is the target error value, is the reference trajectory at the prediction time , is the predicted output at the prediction time.

[0056] In this embodiment, the calculation formula of the preset control performance index function is: where is the proportionality factor, is the integral factor, , , is the prediction length, that is, the predicted range of the mill outlet temperature, is the control length, that is, the control range of the opening of the air inlet component 130, is the control weighting coefficient, is the control increment at the prediction time , is the target error value, is the target error value increment, is the current time, is the interval time between the prediction time and the current time. represents the calculation result of the preset control performance index function, that is, the predicted performance index . Specifically, Represents the weighted sum of squares of the proportional error term and the integral error term. Among them, the proportional error term is used to penalize the change in error and encourage the system to respond quickly to changes in the set value. The integral error term is used to penalize the accumulation of error and encourage the system to eliminate the steady-state error. Represents the weighted sum of squares of the control increment term, which is used to penalize the change in control input and encourage the system to use a smooth control strategy.

[0057] In this embodiment, the prediction performance index Can be used to adjust the proportional and integral gains, optimize the dynamic response and steady-state accuracy of the system. During the IGPC prediction process, the prediction performance index Is used to optimize the control input over a future period of time to minimize the performance index. In this embodiment, the optimal performance index is the minimum prediction performance index .

[0058] In this embodiment, the calculation formula for the target control increment includes: Among them, Is a preset memory term, Is a memory factor, Is an identity matrix, Is the proportional gain, Is The transpose of, Is the integral gain, Is The transpose of, Is the change in the reference trajectory, The change in the predicted output, Is the reference trajectory, Is the predicted output, Is the prediction length, Is the control length.

[0059] In the actual application process, by simplifying the calculation formula for the target control increment and letting The simplified calculation formula for the target control increment can be obtained: Among them, Based on the above steps, during the calculation of the target control increment, the predictive performance index in IGPC control is integrated, and the PI feedback characteristic and the predictive characteristic of IGPC control are fully combined, which can accurately track the control parameters that dynamically change of the target object. While achieving high-precision control, the anti-interference ability of the system is greatly improved.

[0060] In one embodiment, the method for controlling the temperature at the outlet of the coal mill air duct further includes: Using the fading memory recursive least squares algorithm to estimate the control parameters of the air inlet component 130. Adjust the memory factor of the preset memory term according to the control parameters.

[0061] In this embodiment, the FM-RLS algorithm is used as the identification link in the PI feedback process. A forgetting factor is added during the recursion process. By reducing the weight of historical data and enhancing the correction effect of new data, the parameter estimation better adapts to the time-varying system.

[0062] In one embodiment, controlling the air inlet component 130 of the coal mill according to the target control increment to adjust the real-time temperature at the outlet of the coal mill air duct to the target temperature includes: Calculating the sum value based on the control quantity at the previous moment of the current moment and the target control increment to obtain the target control quantity.

[0063] Controlling the air inlet component 130 of the coal mill according to the target control quantity to adjust the real-time temperature at the outlet of the coal mill air duct to the target temperature.

[0064] In this embodiment, the calculation formula of the target control quantity includes: Wherein, is the control quantity of the air inlet component 130 at the previous moment of the current moment, is the target control increment.

[0065] To sum up, this embodiment provides a method for controlling the temperature at the outlet of the coal mill air duct. By effectively combining the PI feedback function and the IGPC predictive control function, it overcomes problems such as the complicated tuning method of conventional PID cascade control and poor adaptability to operating conditions. Through multi-step prediction, rolling optimization and feedback correction control strategies, it can effectively overcome the influence of uncertain factors such as nonlinearity, time-variance and hysteresis in the control of the temperature at the outlet of the coal mill air duct, and significantly improve the robustness and anti-interference ability of the system.

[0066] It should be understood that although the steps in the flowcharts involved in the above-described embodiments are sequentially shown in the direction of the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear indication in this document, the execution of these steps has no strict order limitation, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-described embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same moment, but can be executed at different moments, and the execution order of these steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or steps or stages in other steps.

[0067] Based on the same inventive concept, an embodiment of the present application further provides a pulverizer air duct outlet temperature control device for implementing the pulverizer air duct outlet temperature control method described above. The solution provided by this device to solve the problem is similar to the solution described in the above method. Therefore, the specific limitations in one or more embodiments of the pulverizer air duct outlet temperature control device provided below can refer to the limitations on the pulverizer air duct outlet temperature control method in the above text, and will not be repeated here.

[0068] In one embodiment, as Figure 5 shown, a pulverizer air duct outlet temperature control device 500 is provided, including: an acquisition module 510, a calculation module 520, and a control module 530, where: The acquisition module 510 is configured to acquire a reference trajectory and a predicted output of the pulverizer air duct outlet temperature at a prediction moment.

[0069] The calculation module 520 is configured to process the reference trajectory and the predicted output according to a target proportional integral implicit generalized predictive control model to obtain a target control increment.

[0070] The control module 530 is configured to control the air inlet assembly of the pulverizer according to the target control increment to adjust the real-time temperature at the pulverizer air duct outlet to a target temperature, where the air inlet assembly includes a hot air regulating valve and a cold air regulating valve.

[0071] In one of the embodiments, the acquisition module 510 is specifically configured to acquire the real-time outlet temperature and the set outlet temperature at the current moment, where the real-time outlet temperature is the real-time temperature at the pulverizer air duct outlet, and the set outlet temperature is the set temperature at the pulverizer air duct outlet; and calculate the reference trajectory of the outlet temperature of the pulverizer at the prediction moment according to the softening factor at the prediction moment, the real-time outlet temperature, and the set outlet temperature at the current moment.

[0072] In one embodiment, the acquisition module 510 is specifically configured to calculate the predicted output of the outlet temperature of the pulverizer air duct according to the control increment at the previous moment of the prediction moment, the gain coefficient, the real-time outlet temperature at the current moment, the state coefficient, the control increment at the previous moment of the current moment, and the feedforward coefficient.

[0073] In one embodiment, the calculation module 520 is specifically configured to calculate the difference according to the reference trajectory and the predicted output to obtain the target error value; process the target error value according to the preset control performance index function to obtain the predicted performance index; calculate the target control increment according to the optimal performance index and the preset memory term.

[0074] In one embodiment, the control module 530 is specifically configured to calculate the sum value according to the control amount at the previous moment of the current moment and the target control increment to obtain the target control amount; control the air inlet assembly of the pulverizer according to the target control amount to adjust the real-time temperature at the outlet of the pulverizer air duct to the target temperature.

[0075] In one embodiment, the calculation module 520 is specifically configured to estimate the control parameters of the air inlet assembly by using the fading memory recursive least squares algorithm; adjust the memory factor of the preset memory term according to the control parameters.

[0076] In one embodiment, the acquisition module 510 is specifically configured to collect the real-time temperature at the outlet of the pulverizer air duct through the infrared monitoring module group to obtain the real-time outlet temperature.

[0077] In summary, this embodiment provides a control device for the outlet temperature of the pulverizer air duct, which effectively combines the PI feedback function and the IGPC predictive control function, overcomes the problems of complicated tuning methods of conventional PID cascade control and poor adaptability to operating conditions, and can effectively overcome the influence of uncertain factors such as nonlinearity, time-variation, and hysteresis of the control of the outlet temperature of the pulverizer air duct through multi-step prediction, rolling optimization, and feedback correction control strategies, significantly improving the robustness and anti-interference ability of the system.

[0078] Each module in the above control device for the outlet temperature of the pulverizer air duct can be implemented in whole or in part by software, hardware, and their combination. The above modules can be embedded in the processor in the computer device in the form of hardware or be independent of it, or can be stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0079] In one embodiment, a pulverizer device is provided, including the control system for the outlet temperature of the pulverizer air duct in the foregoing embodiment.

[0080] In one embodiment, a computer device is provided. The computer device can be a terminal, and its internal structure diagram can be as Figure 6As shown in the figure. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit, and an input device. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface, the display unit, and the input device are connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a method for controlling the outlet temperature of the coal mill air duct. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covering the display screen, or a button, a trackball, or a touchpad provided on the computer device housing, or an external keyboard, touchpad, or mouse, etc.

[0081] Those skilled in the art can understand that Figure 6 the structure shown in the figure is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0082] In one embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory. When the processor executes the computer program, the following steps are implemented: Obtain the reference trajectory and predicted output of the outlet temperature of the coal mill air duct at the prediction moment.

[0083] Process the reference trajectory and predicted output according to the target proportional-integral implicit generalized predictive control model to obtain the target control increment.

[0084] Control the air inlet component of the coal mill according to the target control increment to adjust the real-time temperature at the outlet of the coal mill air duct to the target temperature, where the air inlet component includes a hot air regulating valve and a cold air regulating valve.

[0085] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by the processor, the following steps are implemented: Obtain the reference trajectory and predicted output of the outlet temperature of the coal mill air duct at the prediction moment.

[0086] Process the reference trajectory and predicted output according to the target proportional-integral implicit generalized predictive control model to obtain the target control increment.

[0087] Control the air inlet component of the coal mill according to the target control increment to adjust the real-time temperature at the outlet of the coal mill air duct to the target temperature, where the air inlet component includes a hot air regulating valve and a cold air regulating valve.

[0088] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the following steps: Obtain the reference trajectory and predicted output of the outlet temperature of the coal mill air duct at the prediction moment.

[0089] Process the reference trajectory and predicted output according to the target proportional-integral implicit generalized predictive control model to obtain the target control increment.

[0090] Control the air inlet component of the coal mill according to the target control increment to adjust the real-time temperature at the outlet of the coal mill air duct to the target temperature, where the air inlet component includes a hot air regulating valve and a cold air regulating valve.

[0091] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memories. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in the present application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in the present application can be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, etc., without limitation.

[0092] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0093] The above-described embodiments merely represent several implementation manners of the present application. The description thereof is relatively specific and detailed, but it should not be construed as a limitation on the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A method for controlling the outlet temperature of a coal mill air duct, characterized in that: The method comprises: Obtaining a reference trajectory and a prediction output of the coal mill air duct outlet temperature at the prediction moment, wherein the reference trajectory is a reference value trend line of the coal mill air duct outlet temperature within a preset time period, and the prediction output is a predicted value of the coal mill air duct outlet temperature; Processing the reference trajectory and the predicted output according to a target proportional-integral implicit generalized predictive control model to obtain a target control increment; The air inlet assembly of the coal mill is controlled according to the target control increment to adjust the real-time temperature at the air duct outlet of the coal mill to the target temperature, wherein the air inlet assembly includes a hot air regulating valve and a cold air regulating valve.

2. The method according to claim 1, characterized in that The step of obtaining a reference trajectory of the outlet temperature of the coal mill at the prediction time includes: Obtaining the real-time outlet temperature and the set outlet temperature at the current moment, wherein the real-time outlet temperature is the real-time temperature of the coal mill air duct outlet, and the set outlet temperature is the set temperature of the coal mill air duct outlet; According to the softening factor at the prediction moment, the real-time outlet temperature at the current moment and the set outlet temperature, a reference trajectory of the outlet temperature of the coal mill at the prediction moment is calculated.

3. The method according to claim 1, characterized in that The predicted output of the coal mill air duct outlet temperature at the predicted time is obtained, including: The predicted output of the coal mill air duct outlet temperature is calculated based on the control increment at the moment before the prediction moment, the gain coefficient, the real-time outlet temperature at the current moment, the state coefficient, the control increment at the moment before the current moment and the feedforward coefficient.

4. The method according to claim 1, characterized in that The step of processing the reference trajectory and the predicted output according to the target proportional-integral implicit generalized predictive control model to obtain a target control increment includes: Calculate a difference between the reference trajectory and the predicted output to obtain a target error value; Processing the target error value according to a preset control performance index function to obtain a predicted performance index; The target control increment is calculated based on the optimal performance index and the preset memory item.

5. The method according to claim 4, characterized in that The step of controlling the air inlet assembly of the coal mill according to the target control increment to adjust the real-time temperature at the air duct outlet of the coal mill to the target temperature includes: Calculate the sum of the control amount at the previous moment and the target control increment to obtain the target control amount; The air inlet assembly of the coal mill is controlled according to the target control amount to adjust the real-time temperature at the air duct outlet of the coal mill to the target temperature.

6. The method according to claim 5, characterized in that The method further comprises: Using a fading memory recursive least squares algorithm to estimate the control parameters of the air inlet component; The memory factor of the preset memory item is adjusted according to the control parameter.

7. The method according to claim 2, characterized in that The step of obtaining the real-time outlet temperature at the current moment includes: The real-time temperature of the coal mill air duct outlet is collected by an infrared monitoring module to obtain the real-time outlet temperature.

8. A coal mill air duct outlet temperature control device, characterized in that: The device comprises: An acquisition module, used to acquire a reference trajectory and a predicted output of the coal mill air duct outlet temperature at the prediction moment; A calculation module, used for processing the reference trajectory and the predicted output according to a target proportional-integral implicit generalized predictive control model to obtain a target control increment; A control module is used to control the air inlet component of the coal mill according to the target control increment to adjust the real-time temperature at the air duct outlet of the coal mill to the target temperature, wherein the air inlet component includes a hot air regulating valve and a cold air regulating valve.

9. A coal mill air duct outlet temperature control system, characterized in that: It includes a control module, an infrared monitoring module and an air inlet component, wherein the control module is connected to the infrared monitoring module and the air inlet component respectively, and the air inlet component includes a hot air regulating valve and a cold air regulating valve; The infrared monitoring module is used to obtain the real-time temperature of the coal mill air duct outlet and send the real-time temperature to the control module; The control module includes a proportional-integral implicit generalized predictive controller; the control module is used to execute the coal mill air duct outlet temperature control method described in any one of claims 1-7.

10. A coal mill equipment, characterized in that: It includes the coal mill air duct outlet temperature control system as described in claim 9.

Images