CN115138698A - Heating furnace control system, method, device and storage medium - Google Patents
Heating furnace control system, method, device and storage medium Download PDFInfo
- Publication number
- CN115138698A CN115138698A CN202210699444.3A CN202210699444A CN115138698A CN 115138698 A CN115138698 A CN 115138698A CN 202210699444 A CN202210699444 A CN 202210699444A CN 115138698 A CN115138698 A CN 115138698A
- Authority
- CN
- China
- Prior art keywords
- furnace
- working condition
- clustering
- heating
- target
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B21—MECHANICAL METAL-WORKING WITHOUT ESSENTIALLY REMOVING MATERIAL; PUNCHING METAL
- B21B—ROLLING OF METAL
- B21B45/00—Devices for surface or other treatment of work, specially combined with or arranged in, or specially adapted for use in connection with, metal-rolling mills
- B21B45/004—Heating the product
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Control Of Heat Treatment Processes (AREA)
Abstract
The embodiment of the application provides a heating furnace control system, a heating furnace control method, heating furnace control equipment and a storage medium. The central server can provide a working condition classification model of the heating furnace based on strong data processing capacity. The edge end control equipment can identify the working condition of the furnace section according to the working condition classification model and the real-time working condition data, and carry out temperature control according to the identified working condition type. The edge end control equipment is close to the production equipment, so that the calculated heating furnace control parameters can be issued to the heating furnace bottom layer controller in real time, and the requirements of real-time performance and accuracy in the production process are met. Meanwhile, based on the working condition classification model, the control mode of the heating furnace is adjusted according to different working conditions in the actual production situation, the tracking capability of the set value of the furnace temperature is greatly improved, the furnace temperature of the heating furnace meets the preset temperature requirement, and meanwhile, the energy is fully utilized, so that the quality and the energy consumption of the plate blank are better considered.
Description
Technical Field
The present application relates to the field of intelligent industrial technologies, and in particular, to a heating furnace control system, method, device, and storage medium.
Background
In the rolling production process of steel slabs, the furnace temperature distribution in a heating furnace is an important factor influencing the rolling quality. The heating furnace is a main energy consumption device in the slab rolling production process, and the key link for improving the rolling process is how to reduce the energy consumption of the heating furnace and improve the quality of the slab.
In the existing rolling process, the furnace temperature of a heating furnace is usually set according to manual experience, and the actual furnace temperature of the heating furnace can be changed by controlling the heating parameters of the heating furnace according to the set furnace temperature value. However, in the existing furnace temperature control mode, the actual furnace temperature cannot well track the set value, and further the slab quality is influenced. Therefore, a new solution is yet to be proposed.
Disclosure of Invention
Aspects of the present disclosure provide a heating furnace control system, method, device and storage medium for improving the tracking capability of a furnace temperature setting value and reducing the energy consumption of a heating furnace.
The embodiment of the present application further provides a heating furnace control system, including: the system comprises a central server, edge end control equipment and a heating furnace bottom layer controller; wherein the central server is configured to: providing the edge end control equipment with respective working condition classification models of at least one furnace section of the heating furnace; the edge end control device is configured to: acquiring current working condition data of the heating furnace at any furnace section; determining a target working condition type corresponding to the furnace section according to the current working condition data by adopting a working condition classification model corresponding to the furnace section; determining heating control parameters of the furnace section according to the target working condition type and the furnace temperature set value; the heating furnace bottom layer controller is used for: and heating and controlling the furnace section according to the heating and controlling parameters.
The embodiment of the application provides a heating furnace control method, which comprises the following steps: acquiring current working condition data of the heating furnace at any furnace section; determining a target working condition type corresponding to the furnace section according to the current working condition data by adopting a working condition classification model corresponding to the furnace section; and determining heating control parameters of the furnace section according to the target working condition type and the furnace temperature set value so as to perform heating control on the furnace section.
An embodiment of the present application further provides an electronic device, including: a memory and a processor; the memory is to store one or more computer instructions; the processor is to execute the one or more computer instructions to: the steps in the method provided by the embodiments of the present application are performed.
The embodiment of the present application further provides a computer-readable storage medium storing a computer program, and the computer program, when executed by a processor, can implement the heating furnace control method provided in the embodiment of the present application.
In the heating furnace control system provided by the embodiment of the application, in the embodiment, different tasks are split between levels according to the real-time requirement of heating furnace control and the difference of calculated amount, and are respectively deployed at a central server end and an edge end, so that the intelligent optimization of the heating furnace with the cooperation of the center and the edge is realized. The central server can provide a working condition classification model of the heating furnace based on strong data processing capacity. The edge end control equipment can identify the working condition of the furnace section according to the working condition classification model and the real-time working condition data, and carry out temperature control according to the identified working condition type. The edge end control equipment is close to the production equipment, so that the calculated heating furnace control parameters can be issued to the heating furnace bottom layer controller in real time, and the requirements of real-time performance and accuracy in the production process are met. Meanwhile, based on the working condition classification model, the control mode of the heating furnace is adjusted according to different working conditions in the actual production situation, the tracking capability of the set value of the furnace temperature is greatly improved, the furnace temperature of the heating furnace meets the preset temperature requirement, and meanwhile, the energy is fully utilized, so that the quality and the energy consumption of the plate blank are better considered.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
fig. 1 is a schematic structural diagram of a heating furnace control system according to an exemplary embodiment of the present application;
fig. 2 is a schematic processing logic diagram of an edge-side control device according to an exemplary embodiment of the present application;
FIG. 3 is a schematic view of scattered points of sample data in a sample set of historical operating conditions;
FIG. 4-1 is a schematic diagram of evaluation indexes of clustering tasks with different numbers of clustered clusters;
FIG. 4-2 is a schematic diagram of a clustering result when the number of clusters is 8;
FIG. 5 is a schematic diagram of a MPC controller for roll optimization control;
FIG. 6 is a schematic flow chart illustrating a method for controlling a furnace according to an exemplary embodiment of the present application;
fig. 7 is a schematic structural diagram of an electronic device according to an exemplary embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the technical solutions of the present application will be described in detail and completely with reference to the following specific embodiments of the present application and the accompanying drawings. It should be apparent that the described embodiments are only some of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The terminology used in the embodiments of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in the examples of the present invention and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, and "a" and "an" generally include at least two, but do not exclude at least one, unless the context clearly dictates otherwise.
The embodiment of the application provides a solution for the technical problem that the quality of a plate blank and energy consumption cannot be well considered by controlling the furnace temperature of a heating furnace according to manual experience in the prior art. The technical solutions provided by the embodiments of the present application will be described in detail below with reference to the accompanying drawings.
Fig. 1 is a schematic structural diagram of a heating furnace control system according to an exemplary embodiment of the present disclosure. As shown in fig. 1, the heating furnace control system 100 mainly includes: a central server 10, an edge end control device 20, and a heating hearth layer controller 30.
The central server 10 is located at Yun Duance, and the cloud may include, but is not limited to, a public cloud, a private cloud, or a hybrid cloud. Among them, the private cloud may be: the cloud platform is a private and safe cloud platform which is set up for independent use of industrial manufacturers. The central server 10 may be implemented based on a conventional server on the cloud end side, a virtualized data center, an elastic computing instance, or a virtual machine, and the embodiment is not limited.
The edge control device 20 is located between the central server 10 and the heating furnace bottom layer controller, and is used for calculating relevant control parameters of the heating furnace on the edge side close to the heating furnace. The edge end control device 20 may be implemented as a server or other computer device on the edge side.
The heating furnace bottom layer controller 30 refers to a device for directly controlling the heating furnace, and includes but is not limited to: a device in which a DCS (Distributed Control System) is operated, a device based on a PLC (Programmable Logic Controller), a device based on an FPGA (Field Programmable Gate Array), and the like. The furnace floor controller 30 is connected to the relevant components of the furnace (e.g., valves, sensors) via an industrial bus.
In a steel processing scene, a factory production planning and scheduling department can set a basic operation target r according to experience of production quality, efficiency and cost in the past day * For example: the upper and lower limits of the heated plate temperature of each slab can be set, i.e. a certain range of the plate temperature interval is set. Wherein, the plate temperature is difficult to be directly measured and can be expressed by the furnace temperature measured in the furnace chamber. Therefore, can be based on the operational target r * A target furnace temperature, i.e. a furnace temperature set point w, is given. In the heating furnace control system, the furnace temperature setting value w may be specified by a factory technician according to experience, or may be determined according to the production requirement of the slab, which is not limited in this embodiment.
In the production process, the edge terminal control deviceThe control parameter u can be adjusted by 20, the heating furnace bottom layer controller 30 can control the real-time temperature y of the heating furnace according to the control parameter u, and the output y tracks the set value w of the furnace temperature, thereby ensuring that the actual operation index r is at the expected operation index r * Nearby.
In this embodiment, based on the central server 10 and the edge control device 20, cloud-edge collaborative heating furnace control can be realized, on one hand, multiplexing of computing resources and computing power can be realized based on the characteristics of elasticity and sharability of the central server, and on the other hand, based on the characteristic that the edge control device is closer to the data source, data transmission delay is reduced, network bandwidth pressure is relieved, and timely issuing of edge control signals is ensured.
As will be exemplified below.
Generally, the furnace sections of a heating furnace are divided into: a preheating section, a heating section and a soaking section. After the slab enters the heating furnace, the slab enters a preheating section to be slowly heated, so that the temperature of the slab gradually rises, then the slab enters a heating section to rapidly raise the temperature of the surface of the steel material to the temperature required by tapping, at the moment, the temperature difference of the section of the slab is large, the slab needs to enter a soaking section with lower temperature to be soaked, the temperature of the surface of the slab keeps balanced and unchanged, the temperature inside and outside the slab gradually tends to be uniform, when the temperature of the whole slab is estimated to meet the temperature requirement of a target slab, the slab is conveyed out of the furnace and rolled into a corresponding product according to the rolling requirement.
In some embodiments, the cloud-side coordinated furnace control system 100 may enable furnace segment-level temperature control.
The central server 10 is mainly used for: and providing the edge control device 20 with a working condition classification model corresponding to each of at least one furnace section of the heating furnace.
In some embodiments, the condition classification model corresponding to each of the at least one furnace section may be run on the central server 10, and the edge-end control device 20 may access the central server 10 and request use of any condition classification model. In this embodiment, the operating condition classification model corresponding to each of the at least one furnace segment may be provided to the edge-side control device 20 as a SaaS (Software as a Service) tool on the central server 10. The operations of constructing, dynamically updating, maintaining, etc. the working condition classification model can be executed by the central server 10 to reduce the computational cost of the edge-side control device 20.
In other embodiments, the central server 10 may issue the operating condition classification model corresponding to each of the at least one furnace segment to the edge-end control device 20, so that the operating condition classification model corresponding to each of the at least one furnace segment runs on the edge-end control device 20. Further, the edge side control device 20 does not need to frequently access the center server 10 through the network. The central server 10 may dynamically update the operating condition classification model, and issue the dynamically updated operating condition classification model to the edge-side control device 20.
The edge-side control device 20 is mainly configured to: acquiring current working condition data of the heating furnace at any furnace section; determining the target working condition type corresponding to the furnace section according to the current working condition data by adopting the working condition classification model corresponding to the furnace section; and determining heating control parameters of the furnace section according to the target working condition type and the furnace temperature set value.
The working condition refers to the working state of the heating furnace under the condition related to the heating action of the heating furnace. In different furnace sections, different operating conditions exist. Wherein, the condition related to the heating action of the heating furnace may include: at least one of the kind of slab, the arrangement and combination of different kinds of slabs, the heat distribution in the heating furnace, the heating target of the slab, the gas flow rate, the combustion air flow rate, and the pressure in the heating furnace. That is, in this embodiment, the operating condition of the heating furnace may be described by using one or more of the above conditions, so as to obtain the operating condition data of the heating furnace.
The current working condition data refers to real-time working condition data of any furnace section of the heating furnace at the current moment.
In some alternative embodiments, a plurality of furnace section corresponding condition classification models are operated at the edge end controller device 20, such as a preheating section condition classification model, a heating section condition classification model and a soaking section condition classification model. The working condition classification models corresponding to the multiple furnace sections can be pre-constructed and issued by the cloud server 10.
After obtaining the current working condition data of any furnace section of the heating furnace, the edge controller 20 may determine the target working condition type corresponding to the furnace section according to the current working condition data of the furnace section by using the working condition classification model of the furnace section. After the target working condition type is determined, the heating control parameters of the furnace section can be determined according to the target working condition type and the furnace temperature set value.
After determining the heating control parameters of the furnace section, the edge controller device 20 may issue the heating control parameters to the heating furnace bottom layer controller 30. Thus, the heating furnace bottom layer controller 30 can control the heating process of the heating furnace in the furnace section according to the received heating control parameters.
In some exemplary embodiments, the central server 10 and the edge-end control device 20 may communicate with each other in a wired communication manner and a wireless communication manner. The wireless communication mode may include a mobile network-based wireless communication mode. When the mobile network is connected through communication, the network system of the mobile network may be any one of 2G (GSM), 2.5G (GPRS), 3G (WCDMA, TD-SCDMA, CDMA2000, UTMS), 4G (LTE), 4G + (LTE +), 5G, 5.5G, wiMax, and the like. When the edge side control device 20 is located on the private cloud, the edge side control device 20 can communicate with the central server 10 on the private cloud through an encrypted communication channel.
The edge end control device 20 and the heating furnace floor controller 30 can communicate with each other in a wired or wireless communication manner. The WIreless mode may include, in addition to the mobile network-based communication connection mode, short-distance communication modes such as bluetooth, zigBee, infrared, wiFi (WIreless-Fidelity, WIreless Fidelity technology), and long-distance WIreless communication modes such as LORA, which is not limited in this embodiment.
In this embodiment, different tasks are split between levels according to the real-time requirement of heating furnace control and the difference of calculated amount, and are respectively deployed at the cloud end and the edge end, so that intelligent optimization of the heating furnace with cloud-edge cooperation is realized. The cloud end can provide a working condition classification model of the heating furnace based on strong data processing capacity. The edge end control equipment can identify the working conditions of the furnace section according to the working condition classification model and the real-time working condition data, and carry out temperature control according to the identified working condition types. The edge end control equipment is close to the production equipment, so that the calculated heating furnace control parameters can be issued to the heating furnace bottom layer controller in real time, and the requirements of real-time performance and accuracy in the production process are met. Meanwhile, based on the working condition classification model, the control mode of the heating furnace is adjusted according to different working conditions in the actual production situation, the tracking capability of the set value of the furnace temperature is greatly improved, the furnace temperature of the heating furnace meets the preset temperature requirement, and meanwhile, the energy is fully utilized, so that the quality and the energy consumption of the plate blank are better considered.
In some exemplary embodiments, the operating condition classification model of any furnace section may implement operating condition classification based on at least one of a cluster center, an expert knowledge base, and fuzzy rules, as shown in fig. 2.
Wherein the expert knowledge base is used to store and manage knowledge from books and empirical knowledge acquired by experts in the field of steel processing over long-term work practices. And performing keyword matching, rule matching or threshold judgment on the working condition data based on empirical knowledge in the expert knowledge base, and identifying the working condition type corresponding to the working condition data. The fuzzy rule is used for defining a binary fuzzy relation, and the fuzzy relation is used for representing a conclusion under a certain premise. When the working conditions are classified, the working condition data can be used as a premise, and the working condition type can be used as a conclusion on the premise. The clustering center is obtained by clustering the samples in advance. The working condition classification model can cluster the samples into a plurality of cluster clusters (cluster) in advance, and each cluster corresponds to one working condition class. Each cluster has a cluster center whose distance (i.e., similarity) from the other samples in the cluster satisfies a condition for representing a representative sample in the cluster.
An alternative embodiment of the classification of the behavior based on the cluster center will be exemplified below.
When the edge controller device 20 determines the target working condition type corresponding to any furnace section according to the current working condition data of the furnace section, the working condition classification model of the furnace section can be used to calculate the similarity between the current working condition data and the cluster center of each of the preset multiple cluster clusters. And selecting a target cluster to which the current working condition data belongs from the plurality of clusters according to the calculation result of the similarity.
The number of clustering clusters in the working condition classification model and the sample distribution in the clustering clusters are determined when the working condition classification model is constructed in advance. When the working condition classification model is constructed, the central server 10 can set different cluster numbers for clustering, and evaluate the clustering results corresponding to the different cluster numbers by using the cluster evaluation indexes, so as to determine the appropriate cluster number. As will be exemplified below.
Continuing with any furnace segment as an example, the central server 10 may obtain a historical operating condition data set for that furnace segment. The historical working condition data set consists of historical working condition data samples, and the working condition historical data samples are obtained by collecting the working condition data of the furnace section in the historical moment or the historical time range and can be used for describing the real furnace section working conditions.
After obtaining the historical operating condition data of the furnace sections, the central server 10 may create at least one clustering task. And the clustering tasks have different clustering cluster numbers. For example, 5 clustering tasks may be created, and the number of clustering clusters of the 5 clustering tasks is 4, 5, 6, 7, and 8, respectively.
The central server 10 may cluster the historical operating condition data set by using the at least one clustering task based on a preset clustering algorithm to obtain a clustering result of each of the at least one clustering task. The different clustering tasks can cluster the samples in the historical working condition data set into different numbers of clustering clusters. For example, one clustering task clusters the samples in the historical operating condition data set into 5 clustering clusters, and the other clustering task clusters the samples in the historical operating condition data set into 6 clustering clusters.
In this embodiment, the clustering algorithm employed by the central server 10 may include, but is not limited to: one or more of a k-Means algorithm, a bi-kmeans algorithm, a DBSCAN (Density-Based Spatial Clustering of Applications with Noise) algorithm, an OPTICS (Ordering Points to identify Clustering structures) algorithm, and an FCM Clustering algorithm (Fuzzy C-Means).
The FCM clustering algorithm will be exemplified as follows.
In the clustering process, a data set can be divided into different classes or clusters according to a certain criterion (such as distance), so that the similarity of data objects in the same cluster is as large as possible, and the difference of data objects not in the same cluster is also as large as possible. Therefore, after clustering, the data of the same class are gathered together as much as possible, and the data of different classes are separated as much as possible.
It is assumed that the historical operating condition data of a certain furnace section acquired by the central server 10 is as follows: x = { X 1 ,x 2 ,...x j ...,x n }∈R s . Wherein x is j Represents the jth historical operating condition data sample, j is epsilon [0,n]And n is the total number of samples in the historical operating condition data set. Wherein x is j The sample space of (a) is s dimension, s is a positive integer, and the value of s is set according to the number of conditions for describing the working condition. For example, in some embodiments, when two-dimensional data is used to describe the operating condition, s may take a value of 2; when the three-dimensional data is used to describe the working condition, the value of s may be 3, which is not limited in this embodiment.
After the central server 10 creates a clustering task, the number of clustering clusters of the clustering task may be set to c, so that the clustering task divides samples in the historical working condition data set into c categories, where c is an integer greater than 1.
The objective function of the FCM can be described as:
wherein order
In formula 1, m is a fuzzy index used for controlling the fuzzification degree of the membership degree matrix, and m is more than 1. Generally, a more preferred range for m is [1.5,2.5]The range may enable a higher share of sample points between the fuzzy partitioned intervals. In some embodiments, m =2 may be desirable. Wherein U = [ mu ] ij ]Is a fuzzy partition matrix of c x n, mu ij Is the jth sample x j Membership values belonging to class i; v = [ V ] 1 ,v 2 ,...,v c ]Is an s × c matrix composed of c cluster center vectors; d is a radical of ij =||x j -v i I denotes the point x from the sample j Clustering center v to ith class i The distance of (c).
Solving the objective function to obtain the joint membership mu of the sample points ij And a clustering center v i The iterative formula of (1):
in formula 2, r denotes the r-th cluster center. That is, for a certain i, for the ith cluster center, its sample point joint membership μ ij In the formula (2), the numerator is the sample point x j Distance to cluster center of ith class, denominator being sample point x j Distance to the cluster center of the r-th class, r =2,3,4.
In the FCM fuzzy clustering algorithm, the number of classes (i.e., the number of clusters c) needs to be preset, and the cluster center is initialized at the same time. The clustering result has strong dependence on the preset number of the classifications. Therefore, the clustering result can be evaluated to verify the effectiveness of the preset classification number.
In this embodiment, the central server 10 may evaluate the clustering result by using the intra-class compactness Var and the inter-class dispersion Sep.
Wherein the intra-class compactness can be calculated using the following formula 4:
where n (i) represents the number of samples of the ith cluster.
Wherein, it is assumed that the corresponding clustering centers of two different clustering clusters are i respectively a And i b Then the inter-class dispersion can be calculated using the following equation 5:
generally, if the intra-class compactness Var (V, U) of the clustering result is small and Sep (c, U) is large, the characterization clustering result is excellent.
When the central server 10 creates a plurality of clustering tasks, the clustering result of each clustering task can be evaluated, and a better clustering task is selected from the plurality of clustering tasks according to the evaluation results of the inter-class dispersion and the intra-class compactness. The number of clustering clusters corresponding to the better clustering task can be used as the number of working condition categories, and according to the number of the working condition categories and the clustering center, a working condition classification model of the furnace section can be determined.
It should be noted that, when the clustering result is evaluated based on the intra-class compactness and the inter-class dispersion, the clustering validity index V may be further calculated based on the intra-class compactness and the inter-class dispersion w :
In the formula 6, the first and second groups,by V w When the clustering result of the clustering task is evaluated, V of the clustering task w The smaller the clustering result is, the closer the clustering result of the clustering task is to the real sample distribution, so that the more accurate clustering result is obtained.
Except the above clustering validity index V w In addition, the XB index shown in the following formula 7 can be calculated:
the XB index considers the structural characteristics of the data set and can evaluate the clustering task in multiple dimensions. In the XB index, the smaller the numerator and the larger the denominator are, the closer the clustering result is to the real data distribution.
It is worth to say that the fuel saving while controlling the reasonable temperature of the heating furnace is the main purpose of controlling the temperature of the heating furnace. When the combustion reaction is continuously performed in the heating furnace, the ratio of the air flow rate to the fuel gas (theoretical air-fuel ratio) directly determines the energy utilization rate. Under the condition that the ratio of the gas quantity to the air quantity is relatively proper, the gas can be fully combusted, and the temperature of flame can reach a larger value. That is, the heating furnace can achieve high thermal efficiency only when the air-fuel ratio is reasonable. During combustion, if the amount of air added into the heating furnace is insufficient, the fuel is not sufficiently combusted, the heating furnace can emit black smoke, the environment is polluted, and the heating efficiency is reduced. If the air added into the heating furnace is excessive, the excessive combustion can be generated, the surface oxidation area of the plate blank can be increased, the excessive air is discharged through the chimney after being heated to take away a large amount of heat, a large amount of heat loss is caused, and the heat efficiency is reduced.
In an actual environment, since the fuel gas of the heating furnace is a mixed gas of blast furnace gas, converter gas and coke oven gas, and the content is not stable, the measured air-fuel ratio cannot represent the theoretical air-fuel ratio. In consideration of the air flow rate and the generation of residual oxygen after combustion of fuel gas, the residual oxygen content can be used as an important reference index for judging the combustion efficiency in the present embodiment.
Therefore, in the above and following embodiments of the present application, the furnace temperature deviation and the residual oxygen deviation may be used to describe the operating condition data. Namely, the current working condition data of the heating furnace in any furnace section comprises the following steps: furnace temperature deviation and residual oxygen deviation at the current time. Any historical working condition data of the heating furnace in any furnace section comprises the following data: furnace temperature deviation and residual oxygen deviation at any historical time.
The furnace temperature deviation refers to a deviation between a temperature detected in a furnace chamber and a furnace temperature set value. The residual oxygen deviation refers to the deviation between the oxygen content detected at the outlet position of the heating furnace and the oxygen set value.
Furthermore, when the central server 10 constructs the operating condition classification model, the historical operating condition data of any furnace section is concentrated, and the sample data x j Realized as a two-dimensional vector consisting of furnace temperature deviation and residual oxygen deviation of the furnace section. The clustering process of the operating conditions based on the deviation of the furnace temperature and the deviation of the residual oxygen will be described in detail with reference to the accompanying drawings.
Taking a preheating section as an example, the historical working condition data set consists of 30000 groups of data of a certain steel mill, the sampling frequency of each group is 1s, and each sample is described by furnace temperature deviation and residual oxygen deviation. The sample data is represented by scatter distribution, and a scatter diagram as shown in fig. 3 can be presented.
As shown in fig. 3, when the residual oxygen deviation is negative, the larger the negative value is, the lower the air flow rate to the heating furnace is. In this case, the gas and air are not sufficiently combusted, so that the fuel utilization rate is lowered, and the heat loss due to incomplete combustion is increased, thereby lowering the furnace temperature. As shown in fig. 3, as the residual oxygen deviation approaches 0, the furnace temperature tends to increase. That is, as the air flow rate increases, combustion becomes more sufficient. When the residual oxygen deviation is positive and gradually increases, the furnace temperature reaches a peak value at a certain stage, in which case, combustion is relatively sufficient. When the residual oxygen deviation continues to rise, the air input into the furnace is excessive, and when the unburned air is exhausted, excessive heat is carried away, resulting in a decrease in the furnace temperature. When the residual oxygen content is excessive, the oxidation of the plate blank is easy to aggravate, and the quality and yield of the plate blank are reduced.
Based on the FCM algorithm, the central server 10 can cluster the sample set shown in fig. 3 using a plurality of clustering tasks, and use the clustering validity index V w And evaluating the clustering result by the XB index. FIG. 4-1 shows a line graph of the cluster evaluation results, and index 1 shows a cluster validity index V w Index 2 indicates the XB index. As shown in fig. 4-1, according to the clustering validity index V w And the smaller the XB index is, the better the principle is, and the clustering result is more excellent when the number of the clustering centers is determined to be 8. Therefore, the number c of clustering clusters in the condition classification model can be set to 8 so as to be close to the real sample distribution. In the clustering process, a fuzzy weighting index M =2, the particle swarm size is M =20, and the maximum iteration number is J =2. When c =8, the clustering result may be as shown in fig. 4-2.
In fig. 4-2, each cluster represents a corresponding operating condition, and each cluster has a corresponding cluster center.
After the central server 10 constructs the operating condition classification model of each furnace segment based on the above embodiment, the operating condition classification model may be issued to the edge controller device 20. For the edge controller device 20, after receiving the current operating condition data of the furnace section, the operating condition classification model may be used to calculate the distances between the current operating condition data and the c cluster centers, and the cluster center closest to the current operating condition data may be selected from the c cluster centers. And the working condition class corresponding to the cluster center closest to the cluster center can be used as the target working condition class to which the furnace section belongs currently.
It should be noted that, for the central server 10, the operating condition data of the heating furnace in each furnace section may be continuously collected, and the operating condition classification model of each furnace section may be updated according to the collected operating condition data according to a set period. The updated working condition classification model can be timely issued to the edge control device 20 to cope with various working condition changes.
Based on the above embodiments, the edge controller device 20 may perform heating control on each furnace section of the heating furnace according to the target condition type and the furnace temperature set value.
The description is continued with reference to the clustering result shown in fig. 4-2. For example, if the furnace segment currently belongs to the operating condition category corresponding to cluster 1, and both the residual oxygen deviation and the furnace temperature deviation are lower than the set values, which indicates that the air flow rate in the heating furnace is insufficient, the edge controller device 20 may greatly adjust (increase) the air flow rate. If the furnace section currently belongs to the working condition category corresponding to the cluster 2, the residual oxygen deviation is low, the furnace temperature deviation is at a set value, and the situation that the air flow and the coal gas flow are lower than the set value but are balanced mutually is shown. If the furnace section currently belongs to the working condition category corresponding to the cluster 3, the furnace temperature deviation is high, the residual oxygen deviation is normal, and when the residual oxygen set value is not changed, the current state can be kept without adjustment. If the furnace section currently belongs to the working condition type corresponding to the cluster 5, the working condition is the condition of sufficient combustion and the condition of large energy consumption, and the gas flow and the air flow can be reduced simultaneously. If the furnace section currently belongs to the working condition type corresponding to the cluster 6, the air flow is excessive, and the air flow can be greatly reduced. If the furnace section currently belongs to the working condition category corresponding to the cluster 7, the residual oxygen deviation is large at the moment, and the furnace temperature deviation is low, which indicates that the gas flow is insufficient, and the gas flow can be greatly increased. If the furnace section currently belongs to the working condition type corresponding to the cluster 8, the gas flow and the air flow are less, and the gas flow and the air flow can be simultaneously increased.
In some optional embodiments, to further accurately Control the furnace temperature, the edge-end Control device may use an MPC (Model Predictive Control) controller to calculate the Control parameters of the furnace temperature. The MPC controller may be previously constructed by the central server 10. Wherein, different working conditions of different furnace sections correspond to different model parameters so as to realize the heating control of working condition grades for each furnace section.
After determining the target operating condition type based on the foregoing embodiment, the edge-end control device may determine the model parameters in the MPC controller according to the target operating condition type. As shown in fig. 2, after determining the model parameters, the edge-end control device may operate the MPC controller and calculate the heating control parameters of the heating furnace in the furnace section by using the MPC controller, where the heating control parameters at least include: adjusting parameters of gas flow and air flow. According to the adjustment parameters of the gas flow and the air flow, the edge control device can control the heating furnace bottom layer controller 30 to adjust the heating parameters. Alternatively, the hot hearth layer controller 30 may include: a gas valve actuator and an air valve actuator. Furthermore, the edge end control equipment can control the coal gas valve actuator to adjust the coal gas flow, and the air control valve actuator adjusts the flow of the air input into the furnace section.
Models in the MPC controller include an input-output relationship model of the furnace. In the input-output relationship model, the furnace temperature is a Controlled Variable (CV), and the heating control parameter of the heating furnace is a Controlled Variable (MV). The MPC controller may pre-model the relationship between the MV and the controlled variable CV. Based on the relation model, the MPC controller can input control parameters of the heating furnace according to a future time interval, predict the furnace temperature of the future time interval, and determine more reasonable heating control parameters for the current moment according to the error between the predicted furnace temperature and the expected furnace temperature, so as to accurately and quickly control the CV at a specified set value or range.
Alternatively, the MPC controller may further consider the temperature of the slab at the time of entry into the furnace and regard the temperature of the slab at the time of entry as a Disturbance Variable (DV) when constructing the above-described input-output relationship model, and establish a relationship model between MV/DV and CV.
In the MPC controller, a relationship model between the MV and the CV or a relationship model between the MV/DV and the CV is dynamic, and the structure and parameters of the relationship model can be determined according to specific working conditions. The corresponding relationship between the different working condition categories and the model parameters may be determined by the central server 10 in advance according to historical data. After the working condition type of any furnace section is determined based on the method described in each embodiment, the model structure and parameters corresponding to the working condition type can be determined, so that the furnace temperature control requirements under different working conditions can be met.
The description continues with the above example. For example, taking any furnace segment as an example, if the furnace segment belongs to the operating condition class 1 corresponding to the cluster 1 at the t1 th time, the structure and parameters of the input-output relationship model in the MPC controller can be determined according to the model structure and parameters corresponding to the operating condition class 1. Based on the determined configuration and parameters, the input-output relationship model may calculate control parameters for a large increase in air flow to meet the heating demand of condition 1.
For another example, if the furnace segment belongs to the operating condition category 5 corresponding to the cluster 5 at the time t2, the structure and parameters of the input-output relationship model in the MPC controller may be determined according to the model structure and parameters corresponding to the operating condition category 5. Based on the determined configuration and parameters, the input-output relationship model may calculate control parameters for reducing gas flow and air flow to meet the heating requirements of condition 5.
Optionally, after the MPC controller determines the relationship model under any operating condition, the heating parameters may be calculated based on a rolling optimization control mechanism, which will be described in detail below with reference to the accompanying drawings.
During the heating process of the heating furnace, as the input variable (heating control parameter u) and the output variable (real-time furnace temperature y) are stacked on a time scale, the coupling between the variables is enhanced, so that the control deviation is gradually increased. The MPC controller calculates the heating control parameters of the furnace temperature based on a rolling optimization control mechanism, and can effectively reduce the control deviation generated by the stacking effect.
When the MPC controller calculates the control parameters based on the rolling optimization control, the predicted value of the heating control parameters in the future time period can be predicted at any control moment, and the predicted value of the furnace temperature output by the heating furnace in the future time period is predicted according to the predicted value of the heating control parameters and the determined input-output relation model of the heating furnace. In order to verify the rationality of the predicted values of the heating parameters, an optimization objective function can be determined according to the error between the predicted values of the furnace temperature and the set value of the furnace temperature in the future time period, and the predicted values of the heating control parameters are adjusted with the objective of reducing the optimization objective function. And when the optimized objective function converges to the specified range, the adjusted heating control parameters can be output, and the heating control parameters at the control moment are determined from the adjusted heating control parameters.
In the process, the MPC controller converts the prediction process of the control parameters into a furnace temperature prediction problem in a future period of time, and solves the heating control parameter optimization problem in a finite time domain based on the predicted furnace temperature. Based on the solution result of the optimization problem, a control sequence corresponding to the heating control parameter can be obtained, and elements in the control sequence act on a controlled object (namely, the heating furnace), so that the control precision can be effectively improved, and the furnace temperature can better track the furnace temperature set value. At the next control moment, the optimization process is repeated, and the rolling optimization can be realized, as shown in fig. 5.
To further illustrate the above embodiments, the input-output relationship model in an MPC controller can be described as a state space model as shown by the following equation:
wherein x (k) is E.R n Indicating the state of the heating furnace related to the furnace temperature at the time k, including but not limited to the operation amount, the control amount and the like when the heating furnace is operated; u (k) is epsilon to R l Control parameter, y (k) R, representing furnace input at time k 0 The furnace temperature output from the heating furnace at time k is shown. Wherein, f 1 、f 2 Representing the structure and parameters of an input-output relationship model in an MPC controller.
Based on the relationship model shown in equation 8, the MPC controller can predict the furnace temperature output by the furnace in a future period of time, and can obtain:
{y p (k+1|k),y p (k+2|k),…,y p (k + s | k) } equation 9
Where s is the prediction time domain, y p (k + 1|k) represents the furnace temperature output at the time k +1 predicted at the current time k. Wherein the heating control parameters in equations 3-8The method comprises the following steps of (1) predicting heating control parameters input by a heating furnace in a time domain s, namely:
here, u (k + 1|k) represents the heating control parameter input at the predicted k +1 time at the current time k. When the heating control parameter input at the time k +1 is predicted at the time k, the prediction may be performed according to a preset parameter prediction model, or the prediction may be performed in a manner of randomly generating a control parameter, or the prediction may be performed according to a trend curve of a historical control parameter, which is not limited in this embodiment. The predicted heating control parameters can be continuously adjusted in the optimization process until the optimization objective function is converged. Wherein the heating control parameter may be realized as a gas flow or an air flow.
During heating, the real-time furnace temperature y output by the furnace is changed to follow the expected output (i.e. the furnace temperature set value). Within the prediction time domain s, the expected output of the furnace temperature may be represented as:
{y r (k+1),y r (k+2),…,y r (k + s) } formula 11
Wherein, y r (k + 1) represents the desired furnace temperature at time k + 1. The expected furnace temperature in the s prediction time domain may be determined by the central server according to the heating requirement, which is not limited in this embodiment.
The heating control parameters that the MPC controller makes are used to control the furnace so that the predicted output of the furnace is as close as possible to the desired output of the system. Thus, in this embodiment, the cumulative error between the predicted output and the desired output may be used to define the optimization objective function of the MPC controller:
the MPC may adjust the heating control parameters with the goal of minimizing the optimal objective function, as shown by the following equation:
based on the optimized objective function, the predicted heating control parameters can be continuously adjusted until the optimized objective function converges to a specified range, the adjusted heating control parameters are output, and the heating furnace is controlled by adopting the heating control parameters.
In general, the adjusted heating control parameter may be a heating control parameter sequence within the prediction time domain s, and a first parameter in the heating control parameter sequence may be used as the heating control parameter at the time k + 1. At time k + 1, the foregoing steps may be repeated to determine the heating control parameter at time k + 2, and so on. Through the rolling calculation process, errors generated in the control process can be reduced, and accurate furnace temperature control is realized.
In the heating furnace process, the control purposes of the furnace temperature control loop and the waste oxygen control loop are respectively to control the gas flow and the air flow so as to enable the furnace temperature to gradually approach the furnace temperature set value. The MPC controller can respectively calculate the heating control parameters of the furnace temperature control loop based on the calculation process, and can also be suitable for calculating the heating control parameters of the waste oxygen control loop. When the method is used for calculating the heating control parameter of the furnace temperature control loop, the heating control parameter u is realized as the gas flow. When the method is used for calculating the heating control parameter of the waste oxygen control loop, the heating control parameter u is realized as the air flow, and the description is omitted.
Based on the above embodiment, the MPC controller can determine the heating control parameters of the heating furnace and perform heating control on the heating furnace according to the heating control parameters. In the process of heating control, the MPC controller can also acquire real-time feedback data of the heating furnace and adjust the heating control process. As shown in FIG. 2, the real-time updated monitoring data of the furnace under the control of the furnace floor controller can be input to the MPC controller as feedback data generated by the control. Wherein the real-time monitoring data comprises: the temperature of the furnace inlet plate, the real-time gas flow, the real-time air flow and the real-time furnace temperature. The MPC controller can continuously adjust the gas flow and the air flow according to the fed back data so that the real-time furnace temperature of the heating furnace can better track the furnace temperature set value, thereby realizing the production operation target.
It should also be noted that in some embodiments, the MPC controllers for each of the three furnace sections may be used to calculate the heating control parameters for each of the three furnace sections. In other embodiments, the same MPC controller may be used to calculate the heating control parameters for three furnace sections, taking into account the coupling between the different furnace sections, and this embodiment is not limited thereto. When the same MPC controller is adopted, the furnace temperatures and the heating control parameters sampled by the three furnace sections can be input into the same MPC control loop so as to respectively calculate the heating control parameters of the three furnace sections, which is not described again.
In addition to the cloud-edge cooperative heating furnace control system provided in the foregoing embodiment, an embodiment of the present application also provides a heating furnace control method, which will be described below with reference to the accompanying drawings.
Fig. 6 is a schematic flowchart of a cloud-edge collaborative heating furnace control method according to an exemplary embodiment of the present application, and as shown in fig. 6, when executed on the side of an edge controller device, the method includes:
And 603, determining heating control parameters of the furnace section according to the target working condition type and the furnace temperature set value so as to control the heating of the furnace section.
Optionally, determining a target working condition category corresponding to the furnace section according to the current working condition data by using the working condition classification model corresponding to the furnace section, where the determining includes: calculating the similarity between the current working condition data and the clustering centers of the preset clustering clusters by adopting the working condition classification model; the plurality of clustering clusters correspond to a plurality of working condition categories; selecting a target cluster to which the current working condition data belongs from the plurality of clusters according to the calculation result of the similarity; and taking the working condition category corresponding to the target clustering cluster as the target working condition category.
Optionally, in some embodiments, the edge-end controller device may perform the operation of building the behavior classification model. Accordingly, the edge end director may also be operable to: acquiring a historical working condition data set of the furnace section; determining at least one clustering task; the clustering tasks have different clustering cluster numbers; clustering the historical working condition data set by adopting the at least one clustering task based on a preset clustering algorithm to obtain a clustering result of each clustering task; evaluating the clustering result of each clustering task by adopting a clustering evaluation index; selecting a target clustering task meeting set conditions from the at least one clustering task according to an evaluation result; and determining the working condition classification model according to the clustering cluster and the clustering center corresponding to the target clustering task.
Optionally, the current operating condition data includes: the furnace temperature deviation and the residual oxygen deviation of the furnace section at the current moment. Any historical operating condition data used for constructing the operating condition classification model comprises the following steps: the furnace temperature deviation and residual oxygen deviation of the furnace section at any historical moment.
Optionally, the cluster evaluation index is calculated according to the intra-class compactness and/or the inter-class dispersion, and reference may be specifically made to the descriptions in the foregoing embodiments.
Optionally, when the edge-end control device determines the heating control parameter of the furnace section according to the target working condition type and the furnace temperature set value, the edge-end control device may determine a model parameter in the MPC controller according to the target working condition type; calculating heating control parameters of the heating furnace in the furnace section according to the furnace temperature set value by adopting an MPC controller, wherein the heating control parameters at least comprise: adjusting parameters of gas flow and air flow; and controlling a coal gas valve actuator and an air valve actuator to carry out flow adjustment according to the adjustment parameter of the coal gas flow and the adjustment parameter of the air flow.
In this embodiment, the edge control device may identify the operating conditions of the furnace section according to the operating condition classification model and the real-time operating condition data, and perform temperature control according to the identified operating condition type. The edge end control equipment is close to the production equipment, so that the calculated heating furnace control parameters can be issued to the heating furnace bottom layer controller in real time, and the requirements of real-time performance and accuracy in the production process are met. Meanwhile, based on the working condition classification model, the control mode of the heating furnace is adjusted according to different working conditions in the actual production situation, the tracking capability of the set value of the furnace temperature is greatly improved, the furnace temperature of the heating furnace meets the preset temperature requirement, and meanwhile, the energy is fully utilized, so that the quality and the energy consumption of the plate blank are better considered.
It should be noted that the execution subjects of the steps of the methods provided in the above embodiments may be the same device, or different devices may be used as the execution subjects of the methods. For example, the execution subject of steps 601 to 604 may be device a; for another example, the execution subject of steps 601 and 602 may be device a, and the execution subject of step 603 may be device B; and so on.
In addition, in some of the flows described in the above embodiments and the drawings, a plurality of operations are included in a specific order, but it should be clearly understood that the operations may be executed out of the order presented herein or concurrently, and the sequence numbers of the operations, such as 601, 602, etc., are used only for distinguishing between different operations, and the sequence numbers themselves do not represent any execution order. Additionally, the flows may include more or fewer operations, and the operations may be performed sequentially or concurrently.
It should be understood that the term "and/or" as used herein is merely one type of association that describes an associated object, meaning that three relationships may exist, e.g., a and/or B may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" herein generally indicates that the former and latter related objects are in an "or" relationship.
It should be noted that, the descriptions of "first", "second", etc. in this document are used for distinguishing different messages, devices, modules, etc., and do not represent a sequential order, nor do they limit the types of "first" and "second".
It is also noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a good or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such good or system. Without further limitation, an element defined by the phrase "comprising a … …" does not exclude the presence of additional like elements in a commodity or system comprising the element.
Fig. 7 is a schematic structural diagram of an electronic device according to an exemplary embodiment of the present application, where the electronic device is suitable for the cloud-edge-coordinated heating furnace control method according to the foregoing embodiment. As shown in fig. 7, the electronic apparatus includes: a memory 701 and a processor 702.
The memory 701 is used for storing a computer program and may be configured to store other various data to support operations on the electronic device. Examples of such data include instructions for any application or method operating on the electronic device.
The memory 701 may be implemented, among other things, by any type or combination of volatile and non-volatile memory devices, such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disks.
A processor 702, coupled to the memory 701, for executing the computer program in the memory 701 for: acquiring current working condition data of the heating furnace at any furnace section; determining a target working condition type corresponding to the furnace section according to the current working condition data by adopting a working condition classification model corresponding to the furnace section; and determining heating control parameters of the furnace section according to the target working condition type and the furnace temperature set value so as to perform heating control on the furnace section.
Optionally, when the processor 702 determines the target operating condition category corresponding to the furnace section according to the current operating condition data by using the operating condition classification model corresponding to the furnace section, the processor is specifically configured to: calculating the similarity between the current working condition data and the clustering centers of the preset clustering clusters by adopting the working condition classification model; the plurality of clustering clusters correspond to a plurality of working condition categories; selecting a target cluster to which the current working condition data belongs from the plurality of clusters according to the calculation result of the similarity; and taking the working condition category corresponding to the target clustering cluster as the target working condition category.
Optionally, in some embodiments, the edge-end controller device may perform a building operation of the condition classification model. Accordingly, the processor 702 may also be configured to: acquiring a historical working condition data set of the furnace section; determining at least one clustering task; the clustering tasks have different clustering cluster numbers; clustering the historical working condition data set by adopting the at least one clustering task based on a preset clustering algorithm to obtain a clustering result of the at least one clustering task; evaluating the clustering result of each clustering task by adopting a clustering evaluation index; selecting a target clustering task meeting a set condition from the at least one clustering task according to an evaluation result; and determining the working condition classification model according to the clustering cluster and the clustering center corresponding to the target clustering task.
Optionally, the current operating condition data includes: the furnace temperature deviation and the residual oxygen deviation of the furnace section at the current moment. Any historical operating condition data used for constructing the operating condition classification model comprises the following steps: the furnace temperature deviation and residual oxygen deviation of the furnace section at any historical moment.
Optionally, the cluster evaluation index is calculated according to the intra-class compactness and/or the inter-class dispersion, and reference may be made to the descriptions in the foregoing embodiments.
Optionally, when determining the heating control parameter of the furnace section according to the target working condition type and the furnace temperature set value, the processor 702 may determine the model parameter in the MPC controller according to the target working condition type; calculating heating control parameters of the heating furnace in the furnace section according to the furnace temperature set value by adopting an MPC controller, wherein the heating control parameters at least comprise: adjusting parameters of gas flow and air flow; and controlling a gas valve actuator and an air valve actuator to adjust the flow according to the adjustment parameter of the gas flow and the adjustment parameter of the air flow.
Further, as shown in fig. 7, the electronic device further includes: communications components 703 and power components 704. Only some of the components are schematically shown in fig. 7, and the electronic device is not meant to include only the components shown in fig. 7.
The communication component 703 is configured to facilitate communication between the device in which the communication component is located and other devices in a wired or wireless manner. The device in which the communication component is located may access a wireless network based on a communication standard, such as WiFi,2G, 3G, 4G, or 5G, or a combination thereof. In an exemplary embodiment, the communication component receives a broadcast signal or broadcast related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, the communication component may be implemented based on Near Field Communication (NFC) technology, radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, ultra Wideband (UWB) technology, bluetooth (BT) technology, and other technologies.
The power supply module 704 provides power to various components of the device in which the power supply module is located. The power components may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the device in which the power component is located.
In this embodiment, the edge control device may identify the operating condition of the furnace section according to the operating condition classification model and the real-time operating condition data, and perform temperature control according to the identified operating condition type. The edge end control equipment is close to the production equipment, so that the calculated control parameters of the heating furnace can be issued to the bottom layer controller of the heating furnace in real time, and the requirements on instantaneity and accuracy in the production process are met. Meanwhile, based on the working condition classification model, the control mode of the heating furnace is adjusted according to different working conditions in the actual production situation, the tracking capability of the set value of the furnace temperature is greatly improved, the furnace temperature of the heating furnace meets the preset temperature requirement, and meanwhile, the energy is fully utilized, so that the quality and the energy consumption of the plate blank are better considered.
Accordingly, the present application further provides a computer-readable storage medium storing a computer program, where the computer program is capable of implementing the steps that can be executed by the electronic device in the foregoing method embodiments when executed.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.
Computer-readable media, including both permanent and non-permanent, removable and non-removable media, may implement the information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising a … …" does not exclude the presence of another identical element in a process, method, article, or apparatus that comprises the element.
The above description is only an example of the present application and is not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (14)
1. A heating furnace control system, comprising:
the system comprises a central server, edge end control equipment and a heating furnace bottom layer controller;
wherein the central server is configured to: providing a working condition classification model of each furnace section of the heating furnace for the edge end control equipment;
the edge end control device is configured to: acquiring current working condition data of the heating furnace at any furnace section; determining a target working condition type corresponding to the furnace section according to the current working condition data by adopting a working condition classification model corresponding to the furnace section; determining heating control parameters of the furnace section according to the target working condition type and the furnace temperature set value;
the heating furnace bottom layer controller is used for: and heating and controlling the furnace section according to the heating control parameters.
2. The system of claim 1, wherein the edge-side control device, when determining the target operating condition category corresponding to the furnace section according to the current operating condition data by using the operating condition classification model corresponding to the furnace section, is specifically configured to:
calculating the similarity between the current working condition data and the clustering centers of the preset clustering clusters by adopting the working condition classification model; the plurality of clustering clusters correspond to a plurality of working condition categories;
selecting a target cluster to which the current working condition data belongs from the plurality of clusters according to the calculation result of the similarity;
and taking the working condition category corresponding to the target clustering cluster as the target working condition category.
3. The system of claim 2, wherein the central server is further configured to: according to the historical working condition data set of the furnace section, constructing a working condition classification model of the furnace section; and issuing the working condition classification model to the edge terminal control equipment.
4. The system of claim 3, wherein the central server, when constructing the operating condition classification model based on the historical operating condition dataset of the furnace section, is specifically configured to:
determining at least one clustering task; the clustering tasks have different clustering cluster numbers;
clustering the historical working condition data set by adopting the at least one clustering task based on a preset clustering algorithm to obtain a clustering result of each clustering task;
evaluating the clustering result of each clustering task by adopting a clustering evaluation index;
selecting a target clustering task meeting set conditions from the at least one clustering task according to an evaluation result;
and determining the working condition classification model according to the clustering cluster and the clustering center corresponding to the target clustering task.
5. The system of claim 4, wherein the current operating condition data comprises: the furnace temperature deviation and the residual oxygen deviation of the furnace section at the current moment; any historical operating condition data includes: the furnace temperature deviation and residual oxygen deviation of the furnace section at any historical moment.
6. The system of any one of claims 1 to 5, wherein the edge-end control device, when determining the heating control parameters of the furnace section based on the target operating condition class and the furnace temperature set point, is specifically configured to:
determining model parameters in the MPC controller according to the target working condition type;
calculating the heating control parameters of the heating furnace in the furnace section according to the furnace temperature set value by adopting the MPC controller; the heating control parameters include: adjusting parameters of gas flow and air flow;
and controlling a gas valve actuator and an air valve actuator to adjust the flow according to the adjustment parameter of the gas flow and the adjustment parameter of the air flow.
7. A heating furnace control method is characterized by comprising the following steps:
acquiring current working condition data of the heating furnace at any furnace section;
determining a target working condition type corresponding to the furnace section according to the current working condition data by adopting a working condition classification model corresponding to the furnace section;
and determining heating control parameters of the furnace section according to the target working condition type furnace temperature set value so as to control the heating of the furnace section.
8. The method of claim 7, wherein determining the target operating condition category corresponding to the furnace section according to the current operating condition data using the operating condition classification model corresponding to the furnace section comprises:
calculating the similarity between the current working condition data and the clustering centers of the preset clustering clusters by adopting the working condition classification model; the plurality of clustering clusters correspond to a plurality of working condition categories;
selecting a target cluster to which the current working condition data belongs from the plurality of clusters according to the calculation result of the similarity;
and taking the working condition category corresponding to the target clustering cluster as the target working condition category.
9. The method of claim 8, further comprising:
acquiring a historical working condition data set of the furnace section;
determining at least one clustering task; the clustering tasks have different clustering cluster numbers;
clustering the historical working condition data set by adopting the at least one clustering task based on a preset clustering algorithm to obtain a clustering result of each clustering task;
evaluating the clustering result of each clustering task by adopting a clustering evaluation index;
selecting a target clustering task meeting a set condition from the at least one clustering task according to an evaluation result;
and determining the working condition classification model according to the clustering cluster and the clustering center corresponding to the target clustering task.
10. The method of claim 9, wherein determining heating control parameters for the furnace section based on the target operating condition class and a furnace temperature setpoint to provide heating control for the furnace section comprises:
determining model parameters in the MPC controller according to the target working condition category;
calculating the heating control parameters of the heating furnace in the furnace section according to the furnace temperature set value by adopting the MPC controller; the heating control parameters include: adjusting parameters of gas flow and air flow;
and controlling a gas valve actuator and an air valve actuator to adjust the flow according to the adjustment parameter of the gas flow and the adjustment parameter of the air flow.
11. The method of claim 10, wherein calculating the heating control parameters of the furnace at the furnace section based on the furnace temperature setpoint using the MPC controller comprises:
predicting a predicted value of the heating control parameter in a future time period at any control moment by using the MPC controller;
predicting a furnace temperature predicted value output by the heating furnace in the future time period according to the predicted value of the heating control parameter and the input-output relation model of the heating furnace;
determining an optimization objective function according to the error between the furnace temperature predicted value and the furnace temperature set value in the future time period;
adjusting the predicted value of the heating control parameter with the objective of reducing the optimized objective function as the objective until the optimized objective function converges to the specified range, and outputting the adjusted heating control parameter;
and determining the heating control parameter at the control moment from the adjusted heating control parameters.
12. The method of claim 11, wherein the optimization objective function is determined based on cumulative errors of predicted furnace temperature values and furnace temperature set points at a plurality of future times over the future time period; the adjusted heating control parameters include: a heating control parameter corresponding to each of the plurality of future times.
13. An electronic device, comprising: a memory and a processor;
the memory is to store one or more computer instructions;
the processor is to execute the one or more computer instructions to: performing the steps of the method of any one of claims 7-12.
14. A computer-readable storage medium storing a computer program, wherein the computer program is capable of implementing the furnace control method according to any one of claims 7 to 12 when executed by a processor.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210699444.3A CN115138698A (en) | 2022-06-20 | 2022-06-20 | Heating furnace control system, method, device and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210699444.3A CN115138698A (en) | 2022-06-20 | 2022-06-20 | Heating furnace control system, method, device and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115138698A true CN115138698A (en) | 2022-10-04 |
Family
ID=83408529
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210699444.3A Pending CN115138698A (en) | 2022-06-20 | 2022-06-20 | Heating furnace control system, method, device and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115138698A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117268126A (en) * | 2023-10-18 | 2023-12-22 | 和和能源(北京)有限公司 | Heating furnace control system |
CN117862403A (en) * | 2024-03-11 | 2024-04-12 | 溧阳市金昆锻压有限公司 | Gear forging and pressing feeding equipment |
-
2022
- 2022-06-20 CN CN202210699444.3A patent/CN115138698A/en active Pending
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117268126A (en) * | 2023-10-18 | 2023-12-22 | 和和能源(北京)有限公司 | Heating furnace control system |
CN117862403A (en) * | 2024-03-11 | 2024-04-12 | 溧阳市金昆锻压有限公司 | Gear forging and pressing feeding equipment |
CN117862403B (en) * | 2024-03-11 | 2024-06-04 | 溧阳市金昆锻压有限公司 | Gear forging and pressing feeding equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN115138698A (en) | Heating furnace control system, method, device and storage medium | |
CN115095907B (en) | Intelligent heat supply energy-saving regulation and control method and system based on deep learning and storage medium | |
Pinto et al. | Data-driven district energy management with surrogate models and deep reinforcement learning | |
CN111795484B (en) | Intelligent air conditioner control method and system | |
RU2747281C2 (en) | Hierarchical implicit controller for a shielded system in a power grid | |
CN107203687B (en) | Multi-target cooperative intelligent optimization control method for desulfurization process of absorption tower | |
Goudarzi et al. | Predictive modelling of building energy consumption based on a hybrid nature-inspired optimization algorithm | |
Sala-Cardoso et al. | Predictive chiller operation: A data-driven loading and scheduling approach | |
Ali et al. | Optimized power control methodology using genetic algorithm | |
Gao et al. | Comparative study of model-based and model-free reinforcement learning control performance in HVAC systems | |
CN114219212A (en) | Flexible scheduling method for demand side resources considering ubiquitous power internet of things and edge calculation | |
Hadjiski et al. | Intelligent hybrid control of thermal treatment processes of wood | |
CN113191086A (en) | Genetic algorithm-based electric heating heat load demand optimization method and system | |
CN109492335A (en) | A kind of annealing furnace furnace temperature prediction technique and system | |
CN117150677A (en) | Method and device for determining type selection parameters of electric dust collector | |
Maier et al. | Assessing mixed-integer-based heat pump modeling approaches for model predictive control applications in buildings | |
Kurte et al. | Comparative analysis of model-free and model-based HVAC control for residential demand response | |
Tungom et al. | Hierarchical framework for demand prediction and iterative optimization of EV charging network infrastructure under uncertainty with cost and quality-of-service consideration | |
Zhang et al. | Building energy performance optimization: a new multi-objective particle swarm method | |
CN116187514A (en) | Method, device, terminal and storage medium for predicting building energy efficiency | |
CN110210642A (en) | A kind of city electric energy substitution amount prediction technique and device | |
CN113701232B (en) | Heat supply system building-level regulation and control method and system based on temperature diversity analysis | |
CN114936529A (en) | Temperature control load group aggregation model, modeling method and temperature control load group adjustable potential evaluation method | |
Ma et al. | Control and Communication for Demand Response with Thermostatically Controlled Loads | |
CN109598643A (en) | A kind of annealing furnace subregion gas flow distribution method, equipment and storage equipment |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |