Intelligent control method for pellet plant vertical grinding process

Abstract

The application discloses an intelligent control method for a vertical grinding process of a pellet plant, and belongs to the technical field of industrial production process control, and the method comprises the following steps: acquiring process parameters in the vertical grinding process of the pellet plant; inputting the process parameters into a hierarchical fuzzy rule control architecture to generate a continuously adjustable control signal and realize production process adjustment; wherein the hierarchical fuzzy rule control architecture comprises a target setting layer, a coordination and distribution layer and an execution and adjustment layer; the target setting layer is used for establishing a multi-target weighted function, and through dynamic adjustment of a weight parameter, optimization switching in different running stages is realized; the coordination and distribution layer is used for actuator priority management and mutual exclusion logic processing; and the execution and adjustment layer generates a continuously adjustable control signal by using a fuzzy rule controller. The method has an abnormality protection and self-recovery function, can keep the system stable operation under complex working conditions, and takes into account energy consumption optimization and production safety.

Description

Technical Field

[0001] This invention relates to the field of industrial production process control technology, and in particular to an intelligent control method for vertical grinding processes in pellet plants. Background Technology

[0002] Pelletizing plants are a crucial production link in the steel industry. Their main function is to process iron ore powder into pellets through pretreatment, pelletizing, and roasting, providing high-quality raw materials with uniform particle size and stable chemical composition for blast furnace ironmaking or direct reduction processes. The pelletizing process is highly continuous and tightly coupled, with the vertical grinding section playing a key role in refining particle size and controlling moisture content. Its operational stability directly affects the quality indicators of the pellets and the energy consumption level of subsequent roasting processes. Therefore, achieving stable operation and optimized energy consumption control of the vertical grinding system is crucial for ensuring safe production, reducing production costs, and improving the level of green manufacturing in pelletizing plants.

[0003] Currently, process control in pelleting plants largely relies on manual settings and real-time intervention. Operators monitor parameters such as return material volume, temperature, and negative pressure through an interface, and manually adjust actuators such as classifier speed, gas valve opening, circulating air valve opening, and main fan frequency based on experience. This model has significant shortcomings: First, manual operation carries the risk of distraction and misoperation, potentially leading to production interruptions or even safety accidents; second, manual adjustments depend on experience, resulting in delayed responses, often correcting parameters only after deviations, causing frequent process oscillations, increasing energy consumption and equipment load; finally, significant differences in operating habits among different operators make it difficult to establish unified control standards, weakening the stability and controllability of the production process. These problems are particularly prominent in large-scale continuous production scenarios, becoming major bottlenecks restricting production efficiency and safety.

[0004] To overcome these problems, researchers and engineers have attempted to employ advanced control methods, such as mechanism-based mathematical modeling and optimization control, and intelligent algorithms based on historical operating data (e.g., data-driven modeling, optimization algorithms, or machine learning). While these methods have improved automation to some extent, they still have limitations: firstly, the pellet production process involves numerous variables, strong nonlinearity, complex coupling relationships, and significant time-varying characteristics, making it difficult to establish and maintain accurate mechanistic models; secondly, methods based on historical data mining often rely on the repeatability of operating conditions, but under actual conditions of frequent fluctuations in raw material properties and complex operating environments, these patterns are difficult to apply stably and may even lead to safety hazards due to accumulated deviations. Therefore, existing control technologies still struggle to balance control accuracy, system stability, and engineering feasibility. Summary of the Invention

[0005] This invention provides an intelligent control method for vertical grinding processes in pellet plants, which solves the technical problem that existing control technologies cannot simultaneously achieve control accuracy, system stability, and engineering feasibility.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0007] On one hand, the present invention provides an intelligent control method for vertical grinding processes in pellet plants, the intelligent control method for vertical grinding processes in pellet plants comprising:

[0008] Obtain process parameters during the vertical grinding process in a pellet plant;

[0009] The acquired process parameters are input into the hierarchical fuzzy rule control architecture;

[0010] The hierarchical fuzzy rule control architecture is used to generate control signals, and the control signals are used to regulate the vertical grinding process of the pellet plant.

[0011] The hierarchical fuzzy rule control architecture comprises, from top to bottom, a target setting layer, a coordination and allocation layer, and an execution adjustment layer. The target setting layer is used to establish a multi-objective weighted function and dynamically adjust the weight parameters in the multi-objective weighted function to achieve the switching of optimization targets at different operating stages. The coordination and allocation layer is used to manage priority and mutual exclusion logic during the adjustment process. The execution adjustment layer is used to generate continuously adjustable control signals through a fuzzy rule controller based on the optimization targets set by the target setting layer, and under the management of the coordination and allocation layer, uses the generated control signals to adjust the vertical grinding process of the pellet plant.

[0012] Furthermore, the process parameters include state parameters, control execution parameters, and process output target parameters; wherein, the state parameters include inlet temperature, combustion chamber negative pressure, and gas flow rate; the control execution parameters include gas valve opening degree, circulating air valve opening degree, classifier speed, and main blower frequency; and the process output target parameters include outlet temperature, bucket elevator current, and belt conveyor current.

[0013] Furthermore, all process parameters are subject to process and safety constraints; among them, the constraints on the state parameters are: ensuring that the inlet temperature, combustion chamber negative pressure, and gas flow rate are within safe ranges; the constraints on the control execution parameters are: ensuring that the gas valve, circulating air valve, classifier, and main blower do not exceed physical limits; and the constraints on the process output target parameters are: ensuring that the outlet temperature and current indicators are within allowable ranges.

[0014] Furthermore, multi-objective weighted function Represented as:

[0015]

[0016] in, , , , All are weighted parameters; The outlet temperature; This refers to the current of the bucket elevator. The current of the belt conveyor; To create a negative pressure in the combustion chamber; This represents the ideal value for negative pressure in the combustion chamber. This is the ideal value for the outlet temperature; This represents the ideal value for the bucket elevator current. This represents the ideal value for the belt conveyor current.

[0017] Furthermore, the control signals include the adjustment amount of the gas valve opening, the adjustment amount of the circulating air valve opening, the adjustment amount of the classifier speed, and the adjustment amount of the main blower frequency.

[0018] Furthermore, the coordination and allocation layer is specifically used for:

[0019] Assign priorities to the actuators corresponding to each control signal as follows:

[0020]

[0021] in, This refers to the opening degree of the gas valve; This refers to the opening degree of the circulating air valve; The rotational speed of the air classifier; Main fan frequency; This represents the deviation of the outlet temperature from the ideal value. This is the deviation between the negative pressure in the combustion chamber and the ideal value. This represents the deviation between the bucket elevator current and the ideal value. This refers to the deviation between the conveyor belt current and the ideal value. for The corresponding weight parameters; for The corresponding weight parameters; It is a non-negative real scalar used to measure the urgency of adjustment of a certain actuator at the current moment; It is a mapping function used to convert the deviation into the corresponding priority level value; This is a preset minimum amount, used to ensure that the main fan is adjusted last;

[0022] Based on the priority of each actuator, the adjustment and allocation logic is set; among which...

[0023] The priority allocation logic for return material loops is as follows:

[0024]

[0025] The priority allocation logic for negative pressure circuits is as follows:

[0026]

[0027] The priority allocation logic for the outlet temperature loop is as follows:

[0028]

[0029] in, , , All are preset deviation thresholds; This is a feasibility function, indicating whether the actuator is within the allowed operating range; This is a Boolean variable used to activate the actuator to participate in regulation;

[0030] The mutual exclusion logic constraints are set as follows:

[0031]

[0032] in, This represents the logical XOR operation.

[0033] Furthermore, the calculation process of the mapping function is expressed as follows:

[0034]

[0035] in, The priority level value corresponding to the input parameter X; exp is an exponential function with the natural constant e as its base. The slope parameter; This is a preset threshold.

[0036] Furthermore, the execution adjustment layer is specifically used for:

[0037] The deviation of the outlet temperature from the ideal value The deviation between the negative pressure in the combustion chamber and the ideal value Deviation between bucket elevator current and ideal value and the deviation of the belt conveyor current from the ideal value As input variables, based on the optimization target set by the target setting layer, combined with the preset membership function and fuzzy rule base, a continuously adjustable control signal is generated through fuzzy inference and defuzzification; and based on the adjustment allocation logic and mutual exclusion logic constraints set by the coordination allocation layer, the generated control signal is used to adjust the gas valve opening, circulating air valve opening, classifier speed and main fan frequency in the vertical grinding process of the pellet plant.

[0038] Furthermore, the membership function is expressed as:

[0039]

[0040] in, For the first i Input variables The L Membership degree; exp is an exponential function with the natural constant e as its base; For the first The center of the item; The total dimension of the input variables; This is the bandwidth parameter.

[0041] Furthermore, the fuzzy rules in the fuzzy rule base include:

[0042] ;in, This refers to the speed adjustment of the air classifier; , , These represent negative large, negative small, zero, small positive, and large positive, respectively. These respectively represent a significant increase, an increase, a remainder, a decrease, and a significant reduction;

[0043] ;in, This is a feasibility function; Main fan frequency regulation; ;

[0044] ;in, , ; This refers to the adjustment amount of the gas valve opening.

[0045] ;in, This represents the change in gas flow rate; The threshold for gas flow rate jump; This represents the change in inlet temperature. The threshold for inlet temperature change; The observation buffer time set for the system; This indicates that the gas valve adjustment is temporarily suspended. Second;

[0046] ;in, t This is the current system uptime, in seconds. The time of the last adjustment action of the gas valve, in seconds; resume (.) is a control instruction that indicates the resumption of execution of a suspended set of control rules;

[0047] ;in, , ; This refers to the opening degree of the circulating air valve; This refers to the adjustment amount of the circulating air valve; For the feasible operating space of an actuator;

[0048] ;in, , ; This refers to the frequency adjustment of the main fan.

[0049] In another aspect, the present invention also provides an electronic device comprising a processor and a memory; wherein the memory stores at least one instruction, which is loaded and executed by the processor to implement the above-described method.

[0050] In another aspect, the present invention also provides a computer-readable storage medium storing at least one instruction, which is loaded and executed by a processor to implement the above method.

[0051] The beneficial effects of the technical solution provided by this invention include at least the following:

[0052] This invention provides an intelligent control method for vertical grinding processes in pellet plants. Based on a hierarchical control architecture, it combines global target setting, actuator coordination, and low-level fuzzy control to achieve coordinated optimization of return material stability, outlet temperature regulation, and combustion chamber negative pressure control. The upper layer is responsible for multi-objective setting and weight adjustment, the middle layer is responsible for actuator priority management and mutual exclusion logic processing, and the bottom layer uses fuzzy rule control and a dual closed-loop mechanism to achieve real-time adjustment of the classifier, gas valve, circulating air valve, and main blower. This invention's method can fully utilize expert experience and process knowledge without relying on precise mathematical models. Through hierarchical coordination and fuzzy rule reasoning, it achieves multi-objective, real-time, and stable control of key process parameters such as return material quantity, temperature, and negative pressure. Simultaneously, this invention's method possesses the capabilities of actuator priority scheduling, mutual exclusion logic coordination, and self-recovery from abnormal operating conditions, enhancing the system's intelligence, adaptability, and safety under complex operating conditions. Attached Figure Description

[0053] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0054] Figure 1This is a schematic diagram of the execution flow of the intelligent control method for the vertical grinding process in a pellet plant provided in an embodiment of the present invention;

[0055] Figure 2 This is a schematic diagram illustrating the principle of the hierarchical fuzzy rule control architecture provided in this embodiment of the invention;

[0056] Figure 3 This is an outlet temperature response curve provided in an embodiment of the present invention;

[0057] Figure 4 This is a current response curve of a belt conveyor provided in an embodiment of the present invention;

[0058] Figure 5 This is a current response curve of a bucket elevator provided in an embodiment of the present invention;

[0059] Figure 6 This is a combustion chamber negative pressure response curve provided in an embodiment of the present invention;

[0060] Figure 7 This is a curve showing the change in the opening degree of the gas valve provided in an embodiment of the present invention;

[0061] Figure 8 This is a curve showing the change in the opening of the circulating damper provided in an embodiment of the present invention;

[0062] Figure 9 This is a graph showing the change in the rotational speed of the air classifier provided in an embodiment of the present invention;

[0063] Figure 10 This is a graph showing the frequency variation of the main fan provided in an embodiment of the present invention;

[0064] Figure 11 This is a system block diagram of the electronic device provided in the embodiments of the present invention. Detailed Implementation

[0065] To make the objectives, technical solutions, and advantages of the present invention clearer, the embodiments of the present invention will be described in further detail below with reference to the accompanying drawings.

[0066] First, it should be noted that in the embodiments of the present invention, the words "exemplarily," "for example," etc., are used to indicate that they are examples, illustrations, or descriptions. Any embodiment or design scheme described as "exemplary" in the present invention should not be construed as being more preferred or advantageous than other embodiments or design schemes. Specifically, the use of the term "exemplarily" is intended to present the concept in a specific manner. Furthermore, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or it can be either one or the other.

[0067] First Embodiment

[0068] This embodiment provides an intelligent control method for the vertical grinding process in a pellet plant, used for intelligent regulation and control of the vertical grinding process. This method can be implemented by an electronic device, which can be a terminal or a server. The execution flow of this method is as follows: Figure 1 As shown, it includes the following steps:

[0069] S1, obtain the process parameters during the vertical grinding process of the pellet plant;

[0070] It should be noted that in the vertical grinding process of a pellet plant, the process parameters during system operation involve multiple coupled physical quantities. To facilitate subsequent hierarchical control and fuzzy rule design, it is necessary to classify and abstractly model the main variables of the system. These can typically be divided into a set of state parameters, a set of control execution parameters, and a set of process output targets. The parameters included in each parameter set are as follows:

[0071] State parameter set: ;in, The inlet temperature reflects the thermal state of the material and gas entering the mill and is an important prerequisite affecting the subsequent outlet temperature. The negative pressure in the combustion chamber is used to characterize the operating conditions of the combustion and ventilation systems and is a key indicator for maintaining safe and stable operation inside the furnace. The gas flow rate is a direct reflection of combustion energy supply; too high a flow rate will lead to increased energy consumption, while too low a flow rate may result in insufficient temperature or unstable combustion. These state parameters do not directly reflect the final product quality, but they exert fundamental constraints and influences on the dynamic behavior of the entire grinding-roasting process.

[0072] Control execution parameter set: ;in, The opening degree of the gas valve directly regulates the gas flow rate, which is the main means of temperature control; The opening degree of the circulating air valve is used to regulate the air volume and furnace pressure, affecting the negative pressure in the combustion chamber and the material flow characteristics. The rotational speed of the classifier determines the return material ratio and the particle size distribution of the finished product, and is a key variable affecting grinding efficiency and current load. The main fan frequency controls the overall ventilation volume of the system, which is related to the stability of negative pressure and also plays an auxiliary regulatory role.

[0073] Control parameters are the means by which operators or control systems can directly intervene, and there are strong couplings and certain mutual exclusions among them. For example, adjusting the gas valve and the circulating air valve may have opposite effects on the negative pressure; the classifier and the main blower may also have priority conflicts when adjusting the return current. Therefore, it is necessary to allocate control rights through a reasonable coordination and priority mechanism (detailed below).

[0074] Process output target set: ;in, The outlet temperature is a direct indicator of the stability of the thermal regime; too high or too low a temperature will affect the quality of the pellets. The current of the bucket elevator is related to the amount of returned material and the mill load. Excessive current will cause overload shutdown. The current of the belt conveyor also reflects the dynamic fluctuations of material flow and return ratio, and is a supplementary indicator for stabilizing return.

[0075] These output targets are directly related to product quality and equipment safety, and are the core adjustment objects of the control system. In particular, the outlet temperature reflects both the combustion and heat exchange effect and directly determines the yield of pellet roasting, making it the most critical of all target variables.

[0076] Furthermore, it should be noted that in actual operation, all parameters are subject to process and safety constraints. State constraints: It is necessary to ensure that the inlet temperature, combustion chamber negative pressure, and gas flow rate are within safe ranges to avoid unstable combustion due to excessively low temperatures or cold air intake due to excessively high negative pressures. Execution constraints: Ensure that gas valves, circulating air valves, classifiers, and main fans do not exceed their physical limits to prevent equipment damage. Output constraints: Ensure that outlet temperature and current parameters are within allowable ranges to guarantee pellet quality and safe equipment operation.

[0077] Based on the above, the system's operational constraints can be expressed as follows: ;in, ; ;in, The minimum inlet temperature set for the site; This is the minimum negative pressure setting for the combustion chamber at the site. The minimum gas flow rate set at the site; This represents the lower limit of the feasible operating space for the gas valve opening. This represents the lower limit of the feasible operating space for the opening of the circulating air valve; This represents the lower limit of the feasible operating range for the air classifier's rotational speed. This is the lower limit of the feasible operating space for the main fan frequency. Set the lower limit of the outlet temperature; This is the lower limit of the bucket elevator current setting value. This is the lower limit of the belt conveyor current setting value. The maximum inlet temperature set for the site; This refers to the maximum negative pressure value set for the combustion chamber on-site. This refers to the maximum gas flow rate set at the site. This represents the upper limit of the feasible operating space for the gas valve opening. This represents the upper limit of the feasible operating space for the opening of the circulating air valve; This represents the upper limit of the feasible operating range for the air classifier's rotational speed. The upper limit of the feasible operating space for the main fan frequency; Set an upper limit for the outlet temperature; The upper limit of the bucket elevator current setting; This is the upper limit of the current setting for the belt conveyor.

[0078] S2, input the acquired process parameters into the hierarchical fuzzy rule control architecture;

[0079] S3. The hierarchical fuzzy rule control architecture is used to generate control signals, and the control signals are used to regulate the vertical grinding process of the pellet plant.

[0080] It should be noted that vertical grinding processes involve numerous operating variables and complex coupling relationships. Furthermore, constrained by safety and energy consumption limits, single-level fuzzy control struggles to simultaneously address multi-objective coordination and actuator conflict resolution. Direct adjustment relying solely on the bottom-level fuzzy controller often leads to issues such as inconsistencies between local optimization and global objectives, conflicting control signals, or actuator overruns. Therefore, it is necessary to introduce a hierarchical control architecture, dividing the tasks of global objective setting, actuator coordination, and local fuzzy adjustment to form a top-down hierarchical control system. This ensures system stability and controllability under complex operating conditions. Therefore, this embodiment proposes a Hierarchical Fuzzy Rule-based Control (HFRC) architecture.

[0081] The principle of this hierarchical fuzzy rule control architecture is as follows: Figure 2 As shown. Specifically, this hierarchical fuzzy rule control architecture consists of three layers: the target setting layer, the coordination and allocation layer, and the execution and adjustment layer. The target setting layer is located at the top, and its core task is to establish a multi-objective weighted function based on the production plan and process requirements, combined with key process parameters such as temperature, return material, and negative pressure, and to achieve the switching of optimization targets at different operating stages by dynamically adjusting the weights. It is responsible for determining the global multi-objective weighted function. for:

[0082] (1)

[0083] in, , , , These are all weighted parameters, and the values ​​of each weighted parameter are adjusted according to production conditions. This represents the ideal value for negative pressure in the combustion chamber. This is the ideal value for the outlet temperature; This represents the ideal value for the bucket elevator current. This represents the ideal value for the belt conveyor current.

[0084] Therefore, the optimization objective model can be summarized as follows:

[0085] (2)

[0086] in, T The number of prediction steps within the control cycle is determined based on the control cycle set on-site. for A vector composed of the minimum values ​​of all elements in the vector; ,express t A vector composed of the elements within the set at any given time. for t Constant inlet temperature, for t The combustion chamber is under constant negative pressure. for t Real-time gas flow rate; for A vector composed of the maximum values ​​of all elements in the vector; for A vector composed of the lower bounds of the feasible operation space of each element in the vector; ,express t A vector composed of the elements within the set at any given time. for t The opening degree of the gas valve at all times. for t The opening of the air valve is constantly being circulated. for t The rotation speed of the powder classifier is constantly monitored. for t Main fan frequency at all times; for A vector consisting of the upper limit of the feasible operation space of each element in the vector; for A vector composed of the minimum values ​​of all elements in the vector; ,express t A vector composed of the elements within the set at any given time. for t Constant outlet temperature for t The current of the bucket elevator at all times, for t Constantly monitor the conveyor belt current; for A vector composed of elements with set maximum values.

[0087] Under the guidance of the target setting layer, the coordination and allocation layer is responsible for actuator priority management and mutual exclusion logic processing. Because the gas valve, circulating air valve, classifier, and main fan have significant coupling during regulation, interference between control signals can easily occur without coordination. The coordination and allocation layer establishes priority strategies and limiting functions to ensure that each actuator can function effectively during regulation without compromising system stability due to boundary violations or conflicts. Specifically, the priorities of each actuator are defined as follows:

[0088] (3)

[0089] in, This represents the deviation of the outlet temperature from the ideal value. This is the deviation between the negative pressure in the combustion chamber and the ideal value. This represents the deviation between the bucket elevator current and the ideal value. This refers to the deviation between the conveyor belt current and the ideal value. for The corresponding weight parameters, for The corresponding weighting parameters are set in this embodiment because the current deviation of the bucket elevator is almost 10 times that of the belt conveyor. , ; It is a non-negative real scalar used to measure the urgency of adjustment of a certain actuator at the current moment, i.e. ; It is a mapping function used to convert the deviation into the corresponding priority level value; This is a preset minimum value used to ensure that the main fan is adjusted last; further, the calculation process of the mapping function is expressed as:

[0090] (4)

[0091] in, The priority level value corresponding to the input parameter X; exp is an exponential function with the natural constant e as its base. This is the slope parameter, typically taken as 1 to 2; The preset threshold needs to be determined based on the error magnitude of each parameter.

[0092] According to equations (3) and (4), the control allocation logic is as follows: First, the priority allocation of the return circuit is performed:

[0093] (5)

[0094] Negative pressure circuit priority allocation:

[0095] (6)

[0096] Outlet temperature loop priority allocation:

[0097] (7)

[0098] in, , , All of these are preset deviation thresholds, which determine whether to trigger an action; This is a feasibility function, indicating whether the actuator is within the allowed operating range; This is a Boolean variable used to activate the actuator to participate in regulation;

[0099] The mutual exclusion logic constraints are as follows:

[0100] (8)

[0101] in, This represents the logical XOR operation.

[0102] The lowest-level execution and regulation layer consists of a series of fuzzy rule controllers used to achieve real-time correction of temperature, return material, and negative pressure. Based on process experience, this layer uses outlet temperature, current deviation, and negative pressure deviation as input variables. Combining membership functions and a fuzzy rule base, it generates continuously adjustable control signals (such as gas valve opening adjustment, circulating air valve opening adjustment, classifier speed adjustment, and main fan frequency adjustment) through fuzzy inference and defuzzification. This allows for precise adjustment of the gas valve opening, circulating air valve opening, classifier speed, and main fan frequency. Compared to traditional manual adjustment, the fuzzy controller can continuously, quickly, and smoothly respond to changes in operating conditions, effectively reducing system oscillation amplitude and the frequency of manual intervention.

[0103] Furthermore, due to the complexity of the process requiring a higher level of control intelligence, this embodiment constructs a fuzzy rule base under multi-dimensional, multi-objective constraints. Its core idea is to transform expert experience and process logic into a set of condition-action (IF-THEN) rules, and achieve dynamic coordination between variables through composite reasoning. Unlike traditional fuzzy controllers, this rule base not only focuses on the correspondence between a single input and output, but also emphasizes cross-condition triggering and multi-output coordination, ensuring global optimization control can still be achieved under multiple operating condition disturbances. To achieve global constraints and fine-grained local control over complex operating conditions, this embodiment constructs a multi-dimensional fuzzy rule base that establishes a nonlinear mapping relationship between the fuzzy set of process variables and the actuator action space.

[0104] First, fuzzify the input:

[0105] (9)

[0106] in, Indicates the first i An input variable, that is, the deviation value of a certain parameter. i =1,2,3,…, m , Each deviation is divided into several fuzzy sets, for example: , representing "negative large, negative small, zero, small positive, and large positive", respectively. Provide the corresponding indices. , put the first The center of the term is denoted as In order to achieve the mapping from numerical deviation to fuzzy language, in order to calculate the first... i Input variables The L Given membership degrees, the Gaussian membership function is defined as follows:

[0107] (10)

[0108] in, For the first i Input variables The L Membership degree; exp is an exponential function with the natural constant e as its base; The total dimension of the input variables; The membership function is centered, and the key threshold method is used for tuning, taking it at the edge of a clear error band. For the bandwidth parameter, the nearest-center method is used for tuning. To ensure that adjacent terms have the specified overlap characteristics, Determined using the nearest-middle method:

[0109] For internal items ( )have:

[0110] (11)

[0111] in, N =5, which represents the total number of language variables; For the first The center of a membership degree; For the first The center of a membership degree is essentially that the parameters in the formula have no explicit meaning, and their values ​​can be taken at the edge of a defined error band.

[0112] And for boundary terms ( or ,For example or Since there are no bilateral neighboring centers, a boundary extrapolation strategy can be adopted, which can be used... and The value of . Where, and For bandwidth parameters; parameters k This is a width adjustment factor used to control the degree of overlap of fuzzy sets (it can be selected based on experience or cross-validation as needed), and can generally be set to 1.

[0113] Define the set of output actions:

[0114]

[0115] in, This refers to the adjustment amount of the gas valve opening. This refers to the adjustment amount of the recirculating air valve opening. This refers to the speed adjustment of the air classifier. This refers to the frequency regulation of the main fan. The corresponding output set is divided into:

[0116]

[0117] These respectively represent "a significant decrease", "a reduction", "maintaining", "an increase", and "a significant increase".

[0118] Establish a fuzzy rule base. The fuzzy reasoning process can be formally represented as:

[0119]

[0120] in, Indicates the outlet temperature deviation. Indicates the negative pressure deviation in the combustion chamber. Indicates the current deviation of the belt conveyor. This indicates the current deviation of the bucket elevator. Each deviation Divided into several fuzzy sets: ;

[0121] That is, the Cartesian product of the input fuzzy sets maps to the Cartesian product of the output fuzzy sets. In other words, each rule is:

[0122]

[0123] in, and Let them represent the fuzzy sets of input and output, respectively. i =1,2,…, m ; j =1,2,…, n ; Indicates the first q One adjustment amount, q =1,2,…, n ; n This represents the total number of adjustment quantities.

[0124] To represent the rule base more intuitively, this embodiment organizes it as a fuzzy rule tensor:

[0125]

[0126] in, The set of fuzzy languages ​​representing the deviation of outlet temperature, combustion chamber negative pressure, belt conveyor current, and bucket elevator current, respectively. These represent the fuzzy output languages ​​corresponding to the gas valve opening adjustment, circulating damper opening adjustment, classifier speed adjustment, and main blower frequency adjustment, respectively.

[0127] Each element of this tensor corresponds to a fuzzy rule. This rule base is organized according to three subsystems: return material control, temperature control, and negative pressure control. Each subsystem adopts a structure of input deviation fuzzification → condition matching → hierarchical action output. The following is an example rule definition:

[0128] Rule 1:

[0129] (12)

[0130] in, , There is a one-to-one correspondence between the two.

[0131] Rule 2:

[0132] (13)

[0133] in, This is a feasibility function; .

[0134] Rule 3:

[0135] (14)

[0136] in, , There is a one-to-one correspondence between the two.

[0137] Rule 4, 5:

[0138] (15)

[0139] (16)

[0140] in, This represents the change in gas flow rate; The threshold for gas flow rate jump; This represents the change in inlet temperature. The threshold for inlet temperature change; The observation buffer time set for the system; This indicates that the gas valve adjustment is temporarily suspended. Second; t This is the current system uptime, in seconds. The time of the last adjustment action of the gas valve, in seconds; resume (.) is a control instruction that indicates "resume execution" of a suspended set of control rules.

[0141] Rule 6:

[0142] (17)

[0143] in, , There is a one-to-one correspondence between the two. This represents the feasible operating space of an actuator.

[0144] Rule 7:

[0145] (18)

[0146] in, , There is a one-to-one correspondence between the two.

[0147] After fuzzy inference using the fuzzy rule base, the defuzzification process is performed using a single-point defuzzification method. In the single-point defuzzification method, each output linguistic item... Pre-allocate a fixed numerical control quantity. The format is as follows:

[0148] (19)

[0149] in, For the corresponding Fixed numerical control values ​​for fuzzy output language; For the corresponding Fixed numerical control values ​​for fuzzy output language; =0; For the corresponding Fixed numerical control values ​​for fuzzy output language; For the corresponding Fixed numerical control values ​​for fuzzy output language;

[0150] Through this three-tiered collaborative architecture, the system establishes an organic connection between global goal setting, actuator coordination, and real-time control. This avoids the limitations of single-level control while ensuring stable operation under complex working conditions and multi-objective constraints. This layered architecture not only enhances the robustness and adaptability of the control system but also provides an feasible engineering solution for the intelligent operation of vertical grinding processes.

[0151] Based on the above, the algorithm implementation process is as follows:

[0152]

[0153] Furthermore, to verify the effectiveness of the proposed method, numerical simulations were performed on the MATLAB / Simulink platform in this embodiment. The simulation model covers key aspects such as the main fan, combustion chamber, and actuator dynamics, and the system's response performance was examined under typical disturbance conditions. Specific parameter settings are as follows:

[0154] The total simulation duration was 100 seconds, with a sampling period of 1 second. During the simulation, burr noise was superimposed on the outlet temperature, belt conveyor current, bucket elevator current, and combustion chamber negative pressure. Different perturbations were applied at 20 seconds, 50 seconds, and 70 seconds to verify the robustness and reliability of the proposed method.

[0155] The reasonable ranges for control and process parameters are set as follows: outlet temperature 98~102 ℃, belt conveyor current 12.8~13.5 A, bucket elevator current 55~65 A, combustion chamber negative pressure -200 to -80 Pa. The actuator ranges are: gas valve opening 0~90°, circulating damper opening 0~90°, classifier speed 200~400 rpm, main fan frequency 38~42 Hz.

[0156] Due to the complexity of on-site adjustment rules and the significant coupling and nonlinear relationships between actuators such as gas valves, classifiers, main fans, and circulating air valves and process parameters, it is difficult to establish an accurate mechanistic model for simulation. Therefore, this embodiment designs a simplified fuzzy control rule for numerical simulation, the specific form of which is shown in Table 1.

[0157] Table 1 Fuzzy Control Rules

[0158]

[0159] Numerical simulation results are as follows Figures 3 to 6As shown in the figure, under the designed control strategy, even when the system experienced step disturbances at 20s, 50s, and 70s, accompanied by superimposed noise from the outlet temperature, conveyor current, bucket elevator current, and combustion chamber negative pressure, the key parameters were able to recover and stabilize within a reasonable operating range relatively quickly. Furthermore, the outlet temperature, conveyor current, bucket elevator current, and combustion chamber negative pressure did not exhibit overshoot or prolonged deviation, demonstrating good steady-state accuracy and dynamic response performance. This fully demonstrates the effectiveness and feasibility of the proposed method in suppressing external disturbances and enhancing system robustness.

[0160] Depend on Figures 7 to 10 It can be seen that the opening degree of the gas valve, the opening degree of the circulating air damper, the speed of the air classifier, and the frequency of the main blower can all be adjusted in real time according to the system disturbance and control requirements.

[0161] In summary, this embodiment proposes an intelligent control algorithm based on hierarchical fuzzy rule control (HFRC) for the vertical grinding process in a pellet plant. In terms of the control flow, the algorithm first constructs a multi-objective function at the global target setting layer, comprehensively considering factors such as temperature stability, energy consumption level, and equipment safety to quantify the process objectives. Subsequently, at the coordination and allocation layer, the priority of each control task is calculated based on real-time deviations, and mutual exclusion constraints are introduced to ensure coordination between actuators. Finally, a fuzzy control mechanism is introduced at the execution adjustment layer: the deviation is fuzzified using a membership function, fuzzy control quantities are obtained through fuzzy rule base reasoning, and further transformed into specific actuator adjustment signals using a defuzzification method. The proposed hierarchical control strategy, through the organic integration of multi-objective optimization and fuzzy control, achieves dynamic and flexible adjustment of the vertical grinding black-box process, effectively overcoming the lag and non-standardization problems existing in manual control. This improves control accuracy while ensuring process stability, providing a feasible path for the intelligent upgrading of complex processes in pellet plants.

[0162] Second Embodiment

[0163] This embodiment provides an electronic device, such as... Figure 11 As shown, the electronic device includes a processor and a memory; wherein the processor and the memory can be connected via a communication bus; the memory stores at least one instruction, which is loaded and executed by the processor to implement the method of the first embodiment described above. Furthermore, the electronic device may also include a transceiver, the processor and the transceiver can be connected via a communication bus, and the transceiver is used to communicate with other devices.

[0164] Below, in conjunction with Figure 11 A detailed introduction to each component of this electronic device is provided below:

[0165] The processor is the control center of the electronic device. The electronic device may include multiple processors, each of which can be a single-core processor (single-CPU) or a multi-core processor (multi-CPU). The term "processor" can refer to a single processor or a collective term for multiple processing elements. For example, a processor can be one or more central processing units (CPUs), other general-purpose processors, application-specific integrated circuits (ASICs), or one or more integrated circuits configured to implement embodiments of the present invention, such as one or more digital signal processors (DSPs), one or more field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor. The processor can perform various functions of the electronic device by running or executing software programs stored in memory and by calling data stored in memory.

[0166] In a specific implementation, as one example, the processor may include one or more CPUs, for example... Figure 11 CPU0 and CPU1 shown are, of course, merely illustrative examples.

[0167] The memory is used to store the software program that executes the solution of the present invention, and the processor controls its execution. For specific implementation methods, please refer to the above method embodiments, which will not be repeated here.

[0168] Optionally, the memory may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto. The memory may be integrated with the processor or exist independently, and may be accessed through the interface circuit of the electronic device ( Figure 11 (Not shown in the image) is coupled to the processor; however, this embodiment of the invention does not impose specific limitations on this.

[0169] The transceiver may include a receiver and a transmitter. Figure 11 (Not shown separately). The receiver is used to implement the receiving function, and the transmitter is used to implement the transmitting function. The transceiver can be integrated with the processor or exist independently, and can be connected through the interface circuit of the electronic device (…). Figure 11 (Not shown in the image) is coupled to the processor, and this embodiment of the invention does not specifically limit this.

[0170] In addition, it should be noted that, Figure 11 The structure of the electronic device shown is not intended to limit the device. Actual devices may include more or fewer components than shown, or combine certain components, or have different component arrangements. Furthermore, the technical effects achieved by this electronic device when performing the method of the first embodiment described above can be referenced to the technical effects described in the first embodiment; therefore, they will not be repeated here.

[0171] Third Embodiment

[0172] This embodiment provides a computer-readable storage medium storing at least one instruction, which is loaded and executed by a processor to implement the method of the first embodiment described above. The computer-readable storage medium may be a ROM, random access memory, CD-ROM, magnetic tape, floppy disk, or optical data storage device, etc. The instruction stored therein can be loaded and executed by a processor in a terminal.

[0173] Furthermore, it should be noted that the present invention can be provided as a method, apparatus, or computer program product. Therefore, embodiments of the present invention can take the form of a completely or partially hardware embodiment, a completely or partially software embodiment, or an embodiment combining software and hardware aspects. Moreover, when implemented in software, embodiments of the present invention can take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program code. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any usable medium accessible to a computer or a data storage device such as a server or data center containing one or more sets of usable media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive (SSD).

[0174] Embodiments of the present invention are described with reference to flowchart illustrations and / or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0175] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing terminal device to operate in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1The functions specified in one or more boxes. These computer program instructions may also be loaded onto a computer or other programmable data processing terminal equipment to cause a series of operational steps to be performed on the computer or other programmable terminal equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable terminal equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0176] It should also be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. The terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal device. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal device that includes said element. Furthermore, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, and B alone, where A and B can be singular or plural. Additionally, the character " / " in this text generally indicates an "or" relationship between the preceding and following objects, but it can also indicate an "AND / OR" relationship. Please refer to the context for specific interpretations. "At least one" refers to one or more items, while "more than" refers to two or more items. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or multiple items. For example, at least one of a, b, or c can be represented as: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0177] Furthermore, it is understood that in various embodiments of the present invention, the order of the above-mentioned process numbers does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0178] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. 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 invention.

[0179] In the several embodiments provided by this invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of functional modules / units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the shown or discussed mutual couplings or direct couplings or communication connections may be through some interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms. Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, i.e., 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. Additionally, the functional units in the various embodiments of this invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0180] If the method is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part 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 the present invention. 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.

[0181] Finally, it should be noted that the above description is merely a preferred embodiment of the present invention. It should be pointed out that although preferred embodiments of the present invention have been described, those skilled in the art, once they understand the basic inventive concept of the present invention, can make several improvements and modifications without departing from the principles described herein. These improvements and modifications should also be considered within the scope of protection of the present invention. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the embodiments of the present invention.

Claims

1. An intelligent control method for vertical grinding processes in pellet plants, characterized in that, include: Obtain process parameters during the vertical grinding process in a pellet plant; The acquired process parameters are input into the hierarchical fuzzy rule control architecture; The hierarchical fuzzy rule control architecture is used to generate control signals, and the control signals are used to regulate the vertical grinding process of the pellet plant. The hierarchical fuzzy rule control architecture comprises, from top to bottom, a target setting layer, a coordination and allocation layer, and an execution adjustment layer. The target setting layer is used to establish a multi-objective weighted function and dynamically adjust the weight parameters in the multi-objective weighted function to achieve the switching of optimization targets at different operating stages. The coordination and allocation layer is used to manage priority and mutual exclusion logic during the adjustment process. The execution adjustment layer is used to generate continuously adjustable control signals through a fuzzy rule controller based on the optimization targets set by the target setting layer, and under the management of the coordination and allocation layer, uses the generated control signals to adjust the vertical grinding process of the pellet plant. The coordination and allocation layer is specifically used for: Assign priorities to the actuators corresponding to each control signal as follows: ； in, This refers to the opening degree of the gas valve; This refers to the opening degree of the circulating air valve; The rotational speed of the air classifier; Main fan frequency; This represents the deviation of the outlet temperature from the ideal value. This is the deviation between the negative pressure in the combustion chamber and the ideal value. This represents the deviation between the bucket elevator current and the ideal value. This refers to the deviation between the conveyor belt current and the ideal value. for The corresponding weight parameters; for The corresponding weight parameters; It is a non-negative real scalar used to measure the urgency of adjustment of a certain actuator at the current moment; It is a mapping function used to convert the deviation into the corresponding priority level value; This is a preset minimum amount, used to ensure that the main fan is adjusted last.

2. The intelligent control method for vertical grinding processes in pellet plants as described in claim 1, characterized in that, The process parameters include state parameters, control execution parameters, and process output target parameters; wherein... The state parameters include inlet temperature, combustion chamber negative pressure, and gas flow rate; The control execution parameters include the opening degree of the gas valve, the opening degree of the circulating air valve, the speed of the air classifier, and the frequency of the main air fan; The process output target parameters include outlet temperature, bucket elevator current, and belt conveyor current.

3. The intelligent control method for vertical grinding processes in pellet plants as described in claim 2, characterized in that, All process parameters are subject to process and safety constraints; the constraints on the state parameters are: ensuring that the inlet temperature, combustion chamber negative pressure, and gas flow rate are within safe ranges; the constraints on the control execution parameters are: ensuring that the gas valve, circulating air valve, classifier, and main blower do not exceed physical limits; and the constraints on the process output target parameters are: ensuring that the outlet temperature and current indicators are within allowable ranges.

4. The intelligent control method for vertical grinding processes in pellet plants as described in claim 1, characterized in that, Multi-objective weighted function Represented as: ； in, , , , All are weighted parameters; The outlet temperature; This refers to the current of the bucket elevator. The current of the belt conveyor; To create a negative pressure in the combustion chamber; This represents the ideal value for negative pressure in the combustion chamber. This represents the ideal value for the outlet temperature. This represents the ideal value for the bucket elevator current. This is the ideal value for the belt conveyor current.

5. The intelligent control method for vertical grinding processes in pellet plants as described in claim 1, characterized in that, The control signals include the adjustment amount of the gas valve opening, the adjustment amount of the circulating air valve opening, the adjustment amount of the classifier speed, and the adjustment amount of the main blower frequency.

6. The intelligent control method for vertical grinding processes in pellet plants as described in claim 5, characterized in that, The coordination and allocation layer is also specifically used for: Based on the priority of each actuator, the adjustment and allocation logic is set; among which... The priority allocation logic for return material loops is as follows: ； The priority allocation logic for negative pressure circuits is as follows: ； The priority allocation logic for the outlet temperature loop is as follows: ； in, , , All are preset deviation thresholds; This is a feasibility function, indicating whether the actuator is within the allowed operating range; This is a Boolean variable used to activate the actuator to participate in regulation; The mutual exclusion logic constraints are set as follows: ； in, This represents the logical XOR operation.

7. The intelligent control method for vertical grinding processes in pellet plants as described in claim 6, characterized in that, The calculation process of the mapping function is expressed as follows: ； in, The priority level value corresponding to the input parameter X; exp is an exponential function with the natural constant e as its base. This is the slope parameter; This is a preset threshold.

8. The intelligent control method for vertical grinding processes in pellet plants as described in claim 6, characterized in that, The execution adjustment layer is specifically used for: The deviation of the outlet temperature from the ideal value The deviation between the negative pressure in the combustion chamber and the ideal value Deviation between bucket elevator current and ideal value and the deviation of the belt conveyor current from the ideal value As input variables, based on the optimization target set by the target setting layer, combined with the preset membership function and fuzzy rule base, a continuously adjustable control signal is generated through fuzzy inference and defuzzification; and based on the adjustment allocation logic and mutual exclusion logic constraints set by the coordination allocation layer, the generated control signal is used to adjust the gas valve opening, circulating air valve opening, classifier speed and main fan frequency in the vertical grinding process of the pellet plant.

9. The intelligent control method for vertical grinding processes in pellet plants as described in claim 8, characterized in that, The membership function is expressed as follows: ； in, For the first i Input variables The L Membership degree; exp is an exponential function with the natural constant e as its base; For the first The center of the item; The total dimension of the input variables; This is the bandwidth parameter.

10. The intelligent control method for vertical grinding processes in pellet plants as described in claim 8, characterized in that, The fuzzy rules in the fuzzy rule base include: ;in, This refers to the speed adjustment of the air classifier; , , These represent negative large, negative small, zero, small positive, and large positive, respectively. These respectively represent a significant increase, an increase, a remainder, a decrease, and a significant reduction; ;in, This is a feasibility function; Main fan frequency regulation; ; ;in, , ; This refers to the adjustment amount of the gas valve opening. ;in, This represents the change in gas flow rate; The threshold for gas flow rate jump; This represents the change in inlet temperature. The threshold for inlet temperature change; The observation buffer time set for the system; This indicates that the gas valve adjustment is temporarily suspended. Second; ;in, t This is the current system uptime. This refers to the moment when the gas valve last performed a regulating action. resume (.) is a control instruction that indicates the resumption of execution of a suspended set of control rules; ;in, , ; This refers to the opening degree of the circulating air valve; This refers to the adjustment amount of the circulating air valve; For the feasible operating space of an actuator; ;in, , ; This refers to the frequency adjustment of the main fan.

Images