CN116625134B - Electric furnace temperature monitoring control method and system based on 5G technology - Google Patents

Abstract

The application discloses an electric furnace temperature monitoring control method and system based on a 5G technology, belonging to the field of intelligent control, wherein the method comprises the following steps: the method comprises the steps of determining pre-control information by interacting information with a target electric furnace, determining a control domain, dividing a step interval and forming a step track; configuring a sensing monitoring device, monitoring a target electric furnace by taking a step track as a standard, and acquiring target monitoring data; calculating control differential, comparing the control differential with a differential threshold, and if the control differential is not satisfied, inputting the monitoring data and the control differential into an adaptive tuning model and outputting tuning control information; and matching the control domain in the step track according to the tuning control information, and compensating to execute the optimization control on the electric furnace temperature controller by the optimization control information so as to realize the phased control and tuning of the electric furnace temperature. The application solves the technical problems of poor real-time performance and low control precision of the electric furnace temperature control in the prior art, and achieves the technical effects of controlling the electric furnace temperature in real time and improving the control precision of the electric furnace temperature.

Description

Electric furnace temperature monitoring control method and system based on 5G technology

Technical Field

The application relates to the field of intelligent control, in particular to an electric furnace temperature monitoring control method and system based on a 5G technology.

Background

With the development of technology and technology, the field of industrial control needs to realize the fine monitoring and real-time control of industrial production processes. The electric furnace temperature control is used as a scene of high temperature and high load, and has high requirements on control precision and real-time performance. However, the existing electric furnace temperature control system adopts the combination of PLC and DCS, and carries out temperature adjustment through a PID control algorithm, but the system response is slow, the control precision is not high, and the intelligent manufacturing requirement of the current industry is difficult to meet.

Disclosure of Invention

The application provides an electric furnace temperature monitoring control method and system based on a 5G technology, and aims to solve the technical problems of poor real-time performance and low control precision of electric furnace temperature control in the prior art.

In view of the above problems, the application provides an electric furnace temperature monitoring control method and system based on 5G technology.

In a first aspect of the present disclosure, there is provided a 5G technology-based electric furnace temperature monitoring control method, the method comprising: the instant information of the target electric furnace is interacted, and pre-control information is determined; determining a control domain based on the instant information and the pre-control information, performing step dissociation and coordinate system conversion, and determining a step track; configuring a sensing monitoring device, determining a target step length node to control and monitor a target electric furnace by taking a step length track as a standard, and acquiring target monitoring data; calculating a control difference based on the target monitoring data, and judging whether the control difference meets a difference threshold; if the target monitoring data and the control difference are not satisfied, inputting the target monitoring data and the control difference into an adaptive tuning model, outputting tuning control information, wherein the adaptive tuning model has capacity expansion and compatibility; based on the tuning control information, matching a control domain of a lower step node in a step track, performing feedback compensation, transmitting to an electric furnace temperature controller to perform optimization control of a lower step interval, and establishing loop correlation between the step track, the self-adaptive tuning model and the electric furnace temperature controller; traversing the step track, and gradually growing the nodes to perform the stepwise control and adjustment of the target electric furnace.

In another aspect of the present disclosure, there is provided an electric furnace temperature monitoring control system based on 5G technology, the system comprising: the pre-control information determining module is used for interacting the instant information of the target electric furnace and determining the pre-control information; the step track determining module is used for determining a control domain based on the instant information and the pre-control information, performing step dissociation and coordinate system conversion, and determining a step track; the target detection data module is used for configuring a sensing monitoring device, determining a target step length node to perform control monitoring of the target electric furnace by taking the step length track as a standard, and obtaining target monitoring data; a control difference determination module that calculates a control difference based on the target monitoring data and determines whether the control difference satisfies a difference threshold; the tuning control information module is used for inputting the target monitoring data and the control difference into the self-adaptive tuning model and outputting tuning control information if the target monitoring data and the control difference are not met, and the self-adaptive tuning model has capacity expansion and compatibility; the step length interval optimizing module is used for matching a control domain of a lower step length node in a step length track based on the tuning control information, performing feedback compensation, transmitting the control domain to the electric furnace temperature controller to execute optimized control of the lower step length interval, and establishing loop correlation between the step length track, the self-adaptive tuning model and the electric furnace temperature controller; and the electric furnace instant control instant adjustment module is used for traversing the step track and gradually growing the nodes to perform the staged instant control instant adjustment of the target electric furnace.

One or more technical schemes provided by the application have at least the following technical effects or advantages:

because the interactive information with the target electric furnace is adopted and the pre-control information is determined, the control domain is determined and the step interval is divided, so that a step track is formed; then, configuring a sensing monitoring device, and monitoring a target electric furnace by taking a step track as a standard to obtain target monitoring data; calculating control differential based on the target monitoring data, comparing the control differential with a differential threshold, and if the threshold requirement is not met, inputting the target monitoring data and the control differential into an adaptive tuning model to output tuning control information; finally, matching the control domain in the step track according to the tuning control information, compensating, transmitting the optimizing control information to the electric furnace temperature controller, executing optimizing control, realizing the technical scheme of controlling and tuning the target electric furnace temperature in a staged manner, solving the technical problems of poor real-time performance and low control precision of the electric furnace temperature control in the prior art, achieving the technical effects of controlling the electric furnace temperature in a real-time and refined manner and improving the electric furnace temperature control precision.

The foregoing description is only an overview of the present application, and is intended to be implemented in accordance with the teachings of the present application in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present application more readily apparent.

Drawings

FIG. 1 is a schematic diagram of a possible flow chart of an electric furnace temperature monitoring control method based on a 5G technology according to an embodiment of the application;

FIG. 2 is a schematic diagram of a possible flow chart of determining a step track in an electric furnace temperature monitoring control method based on a 5G technology according to an embodiment of the present application;

FIG. 3 is a schematic diagram of a possible flow chart for correcting tuning control information in an electric furnace temperature monitoring control method based on a 5G technology according to an embodiment of the present application;

fig. 4 is a schematic diagram of a possible structure of an electric furnace temperature monitoring control system based on 5G technology according to an embodiment of the present application.

Reference numerals illustrate: the device comprises a pre-control information determining module 11, a step track determining module 12, a target detection data module 13, a control difference judging module 14, a tuning control information module 15, a step interval optimizing module 16 and an electric furnace control-by-tuning module 17.

Detailed Description

The technical scheme provided by the application has the following overall thought:

the embodiment of the application provides an electric furnace temperature monitoring control method and system based on a 5G technology. Firstly, information interaction with a target electric furnace, pre-control information and a control domain are determined, step intervals are divided, and step tracks are formed; then, configuring a sensing monitoring device, and monitoring a target electric furnace by taking a step track as a standard to obtain target monitoring data; then, calculating control differential according to the target monitoring data, judging the relation between the control differential and a differential threshold, and if the threshold requirement is not met, inputting the target monitoring data and the control differential into an adaptive tuning model, and outputting tuning control information; and finally, matching a control domain in a step track according to the tuning control information, compensating, and transmitting the optimizing control information to an electric furnace temperature controller to realize the phased control and tuning of the target electric furnace temperature.

In a word, the embodiment of the application adopts a 5G communication technology to realize high-speed interaction of electric furnace information, utilizes sensing monitoring to acquire target data, combines an adaptive tuning model to perform online optimization control, and completes refined monitoring and staged control of the electric furnace temperature, thereby achieving the technical effects of high system intellectualization and control precision and good instantaneity, realizing the intellectualization of electric furnace temperature control by combining communication, monitoring and optimization control, and improving the control precision and instantaneity of circuit temperature.

Having described the basic principles of the present application, various non-limiting embodiments of the present application will now be described in detail with reference to the accompanying drawings.

Example 1

As shown in fig. 1, the embodiment of the application provides an electric furnace temperature monitoring control method based on 5G technology, which is applied to an electric furnace temperature control system, and the system is in communication connection with an electric furnace temperature controller.

Specifically, the electric furnace temperature monitoring control method based on the 5G technology is applied to an electric furnace temperature control system, and the electric furnace temperature control system is in communication connection with an electric furnace temperature controller. The electric furnace temperature control system receives the electric furnace real-time information from the electric furnace temperature controller, determines a control range, a control step length and the like according to preset control information, finally determines a step length track and sends optimized control information to the electric furnace temperature controller to control. The electric furnace temperature control system comprises a sensing monitoring device, a data acquisition device, a control device and the like, and is used for receiving real-time information of the electric furnace, determining a control range and a step track and generating optimized control information. The electric furnace temperature controller is arranged on the electric furnace and is used for receiving control information sent by the control system, controlling the electric furnace, and collecting electric furnace information and feeding back the electric furnace information to the control system.

The electric furnace temperature control method comprises the following steps:

step S100: the instant information of the target electric furnace is interacted, and pre-control information is determined;

specifically, the electric furnace temperature control system collects instant information of the target electric furnace through the data collection device, and the control system combines preset control parameters to determine pre-control information of the target electric furnace in the current state, wherein the pre-control information comprises preset temperature change rate, power output value and the like.

Firstly, the control system and the target electric furnace interact instant information through a high-speed communication network to obtain current state data of the electric furnace, such as temperature, power-on time and the like. Then, the control system adopts a data acquisition device to receive and analyze the instant information transmitted on the communication network, and extracts the key state parameters of the electric furnace. Then, the control system combines preset control parameters such as a temperature rising curve, a power control table and the like with the current state of the electric furnace to calculate pre-control information. The pre-control information comprises a preset temperature change rate, a power output reference value, an output signal frequency and amplitude value and the like. For example, comparing the deviation between the current temperature of the electric furnace and a preset temperature curve, and if the deviation is larger, correcting the temperature change rate in the pre-control information by the control system so that the temperature of the electric furnace can return to the preset temperature curve; according to the heating or cooling trend of the electric furnace, the control system corrects the temperature change rate and the power output to match the change state of the electric furnace.

The real-time control of the electric furnace temperature is realized by interacting the real-time information of the target electric furnace and combining the current state of the electric furnace with preset control parameters to quickly judge and correct, determining proper pre-control information and providing a basis for subsequently determining the control range and the step track.

Step S200: determining a control domain based on the instant information and the pre-control information, performing step dissociation and coordinate system conversion, and determining a step track;

specifically, the control range is determined according to the pre-control information and the electric furnace instant information. The control range includes parameters required by the lower step section control, such as a temperature change rate range, a power output range, an output signal frequency range and the like. In addition, the control system also determines a step interval, namely the whole control process is divided into a plurality of step sections, and each step section corresponds to one control range.

Firstly, according to the instant information and the pre-control information of the electric furnace, calculating range values of parameters such as a temperature change rate range, a power output range, an output signal frequency/amplitude range and the like in the heating/cooling process, wherein the range values form a control range, and limiting conditions are provided for the control of each step section. According to the control precision requirement and the complexity of the control process, the whole control process is divided into a plurality of step length sections, each step length section corresponds to the determined control range, the time span of the step length section is set according to the control requirement, and the control precision is higher when the time span is smaller. Then, for each step segment, the control range value is modified according to the electric furnace state, the control sub-range of each step segment is obtained, and an accurate reference target value is provided for the controlled output generated in each step segment. Then, a parameter related to control is selected as a coordinate axis. And marking the control sub-range of each step length section on the coordinate system, connecting all the marking points to form a step length track, and expressing the change trend of the controlled output along with time. And finally, detecting the deviation between the step track and the actual state of the electric furnace, and correcting the step track according to the deviation value, so that the control execution of each step segment can be accurately guided, and the step track is determined.

The control range and the control sub-range of each step length section are determined according to the state of the electric furnace and the preset control requirement, a coordinate system is established by utilizing control variables, the control sub-ranges are subjected to coordinate conversion to form step length tracks, and the total supervision and adjustment of the temperature control of the electric furnace are realized, so that the ordered staging of the temperature control process of the electric furnace is realized, and the control precision and effect are improved.

Step S300: configuring a sensing monitoring device, and determining a target step length node to perform control monitoring of the target electric furnace by taking the step length track as a standard to acquire target monitoring data;

specifically, a sensing device is arranged in the electric furnace to monitor the state of the electric furnace and feed back the control execution result, and a control system selects a control sub-range of a current target step node in a step track as a monitoring reference, so that the sensing device monitors electric furnace parameters according to the reference. The sensing device feeds back the measurement result to the control system in a digital signal format, and the control system demodulates and analyzes the signal to extract target monitoring data of the electric furnace.

First, corresponding sensors, such as thermocouples, hall effect sensors, frequency sensors, etc., are selected according to the electric furnace parameters, such as temperature, power, energizing signals, etc., that are to be monitored. And then, installing the selected sensor in the electric furnace, and constructing a sensing and monitoring device, wherein the installation position of the sensor is kept away from a high-temperature area, and the sensing device is connected with a control system through a high-speed communication network. Then, the control system selects a control sub-range of a target step node as a reference target for monitoring, such as the internal temperature of the electric furnace corresponding to the temperature change rate, according to the current step track. Then, the control system sends out a monitoring start command, and the sensing device starts to measure the parameters of the electric furnace. The sensing device then converts the analog measurement signal to a digital signal, and uploads the monitoring data to the control system via the communication network. The control system decodes and analyzes the signals, and extracts target monitoring data such as temperature change rate, output power and the like.

Real-time monitoring of key parameters of the electric furnace is realized through the precision sensor and the high-speed network, accurate target monitoring data are obtained, and supervision and feedback management of the whole control process are realized, so that control precision and effect are ensured.

Step S400: calculating a control difference based on the target monitoring data, and judging whether the control difference meets a difference threshold;

specifically, the control system analyzes and processes the acquired target monitoring data, and calculates the control difference of the current step node. The control difference is the difference between the target monitoring data and the control sub-range of the target step node, and is a quantization parameter for judging the control execution effect.

Firstly, the control system analyzes target monitoring data, and extracts relevant characteristic parameters such as temperature change rate and output power value. And then, the control system compares and calculates the characteristic parameters with the corresponding control sub-range parameters to obtain control differences such as temperature change rate difference and power output difference. After the control delta is obtained, the control system compares it with a pre-set delta threshold. The difference threshold is a range in which the difference deviation is allowed to be controlled, and exceeding the range affects the control accuracy. If the control difference is lower than the difference threshold, judging that the control execution effect is good; if the difference is higher than the difference threshold, the control deviation is judged, and the optimization control information is required to be generated for correction.

The characteristic parameter difference is calculated based on the target monitoring data, namely the control difference is compared with the difference threshold value, and whether the control execution effect reaches the standard is judged, so that whether the optimization control information is generated or not is determined to be corrected, real-time supervision of step length node control is realized, and the accuracy of the control result of each step length section is ensured.

Step S500: if the target monitoring data and the control difference are not satisfied, inputting the target monitoring data and the control difference into an adaptive tuning model, and outputting tuning control information, wherein the adaptive tuning model has capacity expansion and compatibility;

specifically, if the control difference does not satisfy the difference threshold, the target monitoring data and the control difference are input into the adaptive tuning model, and tuning control information is output.

First, target monitoring data and the calculated control difference are input into the adaptive tuning model. The self-adaptive tuning model is obtained by training and constructing a neural network model through a large amount of sample data, and has the capability of generating optimization control information; meanwhile, the self-adaptive tuning model has the capacity expansion and purchase function, and can automatically expand calculation force according to calculation load so as to ensure real-time performance. And then, the tuning model firstly judges whether the calculation power of the tuning model can meet the calculation requirement, if not, the tuning model starts a capacity expansion and purchase procedure, performs temporary purchase on surrounding idle resources, and expands the calculation power of the tuning model to complete the calculation task. After the capacity expansion and purchase are completed, the self-adaptive optimization model starts an optimization calculation program, and optimal control information such as a corrected temperature change rate, corrected power output and the like is obtained according to the input target monitoring data and control difference and is used for correcting the electric furnace temperature controller, so that the electric furnace state is returned to the control requirement.

By constructing the self-adaptive tuning model, when the control differential quantity does not meet the differential quantity threshold value, corresponding optimization control information is obtained through the self-adaptive tuning model and used for correcting the control differential, so that analysis and reasoning of electric furnace state monitoring data and the control differential quantity are realized, meanwhile, the model can dynamically expand calculation force according to calculation requirements, and the requirement of real-time control on quick feedback is met.

Step S600: based on the tuning control information, matching the control domain of a lower step node in the step track, performing feedback compensation, transmitting to the electric furnace temperature controller to perform optimization control of a lower step interval, and establishing loop correlation between the step track, the self-adaptive tuning model and the electric furnace temperature controller;

specifically, the control system compares and analyzes the optimized control information output by the adaptive tuning model with the step track, matches out that the optimized control information corresponds to a lower step node in the step track, corrects the optimized control information in a control sub-range of the node, and takes the corrected control sub-range as a control target of a lower step interval. And then, the control system transmits the corrected control sub-range to the electric furnace temperature controller, and the controller adjusts output according to the control sub-range to accurately control the temperature change and power output of the electric furnace in a lower step interval. Meanwhile, the control system calculates feedback compensation information based on output feedback of the controller and output of the optimization model, and the feedback compensation information is used for further optimizing a control target of a lower step interval and improving control accuracy.

Wherein, the step track, the self-adaptive tuning model and the electric furnace temperature controller form a closed-loop control association. The control system associates the output of the optimization model with a specific step node through a step track; the controller controls the electric furnace according to the control target of the step length node, and feeds back the execution result to the control system; and the control system generates feedback compensation information according to the feedback result and is used for perfecting an optimization model so as to improve the next control effect.

By realizing closed-loop management of lower step interval control and matching the optimization control information with step nodes, the optimization control can be implemented in a specific step section, fine correction is carried out according to control feedback, a closed-loop mechanism which is mutually related among a step track, an optimization model and a controller is established, and continuous optimization of high-precision control is realized.

Step S700: traversing the step track, and gradually growing the nodes to perform the stepwise control and adjustment of the target electric furnace.

Specifically, the control system traverses the step track, and performs staged control and adjustment on each step node, so as to realize continuous supervision and optimization of the whole electric furnace temperature control process.

The control system decomposes the step track into a plurality of step nodes, and each node corresponds to control parameters such as temperature change rate, power output and the like in a certain time range. The control system selects a control sub-range of the current step node, sends the control sub-range to the electric furnace temperature controller, and the controller precisely controls the working state of the electric furnace in the step interval according to the control sub-range. Meanwhile, the control system starts the sensing monitoring device to monitor parameters such as temperature, power and the like of the electric furnace in the step interval in real time, and target monitoring data are obtained. The control system compares the monitoring data with the control sub-range, judges the difference between the monitoring data and the control sub-range, and accordingly generates optimized control information to correct the output of the controller, and realizes the optimized adjustment of the current step interval control. After the control and optimization adjustment of one step interval are completed, the control system selects the control sub-range of the next step node, repeats the flow, gradually traverses the whole step track, and completes the supervision and management of the whole electric furnace temperature control process.

The complex temperature control process is divided into a plurality of step intervals by decomposing the step track, monitoring, controlling and optimizing adjustment are carried out in each step interval, one-cut control of the whole process is avoided in a step-by-step long interval control mode, each step interval is concerned relatively independently, targeted monitoring and optimizing are carried out in each interval, out runaway is avoided, resources are not excessively consumed, precise control of the whole process is finally realized, real-time refined control of the temperature of the electric furnace is realized, and the temperature control precision of the electric furnace is improved.

Further, as shown in fig. 2, the embodiment of the present application further includes:

step S210: determining a control domain based on the instant information and the pre-control information, wherein the control domain comprises a multi-dimensional control index value: output power, temperature control circuit state, conduction time, heating speed and step interval;

step S220: configuring a preset segmentation step length, dividing the step length interval, and obtaining N step lengths, wherein the N step length time sequences are connected;

step S230: based on the N item step sizes, dissociating the control domain to obtain a target dissociation result, wherein the target dissociation result corresponds to N groups of sub-level control domains, and the N groups of sub-level control domains are in one-to-one correspondence with the N item step sizes;

Step S240: and generating the step track based on the N item step sizes and the N groups of sub-level control fields.

Specifically, first, the pre-control information and the instant information are analyzed, and the dimensional parameters included in the control range are determined as output power, temperature control circuit state, conductor time, heating speed and step length interval. The state of the temperature control circuit is the electrifying state of the electric furnace in the pre-control information and the instant information and is used for judging whether the electric furnace is in a heating or constant temperature state; the on-time is the time span of each step interval, defining the duration of the control output within each step interval; the heating speed is the temperature change rate contained in the pre-control information and the instant information and is used for judging the speed range of heating or cooling of the electric furnace; the step interval refers to the whole temperature control process, and in the time span, the control system needs to control the electric furnace to achieve a relatively stable working state or a temperature change state. Then, the values of the dimension parameters in the pre-control information and the instant information are calculated and analyzed to obtain the range of the parameters in each step interval, such as the temperature change rate range, the power output range and the like, so as to form a control range.

Then, a preset step segmentation number N is configured according to the control precision requirement. Wherein, the larger the value of N, the smaller the time span of each step length, and the higher the control precision. The control system then equally divides the total time span of the step size interval into N shares, each share corresponding to a step size time span. And then, determining the start and stop time of each step in the step interval according to the time span of each step. The starting time of the first step is the starting time of the step interval, and the ending time of the last step is the ending time of the step interval. Subsequently, it is checked whether the individual steps are consecutive to each other in time, there is no overlap or gap of the time spans. If discontinuous step sizes exist, the time span and the start-stop time of each step size are recalculated, and all the step sizes are ensured to be sequential in time. And recording key control parameters of each step length, including step length numbers, time spans, start-stop time and the like, thereby obtaining N step lengths.

Then, selecting the control parameter most relevant to each step length as dissociation basis, such as temperature change rate and power output; splitting each parameter in a control range according to the selected dissociation dimension according to the time proportion, and obtaining a group of control parameters corresponding to each step length, wherein the control parameters have corresponding control ranges in the step length, and forming a sub-level control domain of the step length. Then, according to the determined N step sizes and the sub-level control range corresponding to each step size; selecting control-related parameters, such as temperature and time, as the abscissa axis of the step track; identifying the temperature and time of each sub-level control range on a coordinate system, wherein N sub-level control ranges identify N coordinates; then, each identification area is connected in time sequence, and the first step area is sequentially connected to the last step area to form a step track.

The control range is split and recombined to realize ordered stage of the complex control process, so that each step length obtains an independent sub-level control range, the control targets under different step lengths are clearer and have pertinence, the complex control is simplified, and a foundation is laid for high-precision control.

Further, the embodiment of the application further comprises:

step S241: the step interval comprises a temperature control step interval and a time step interval, and an initialization coordinate system is constructed by taking the temperature control step and the time step as coordinate axes;

step S242: determining N item coordinates based on the N item step sizes;

step S243: in the initialization coordinate system, positioning and distributing the N-item coordinates to be used as a step size coordinate system;

step S244: and based on the N groups of sub-level control domains, carrying out matching identification on the N items of coordinates in the step size coordinate system, and generating the step size track.

Specifically, first, the temperature control step length and the time step length are taken as an ordinate axis and an abscissa axis of a step length track, the temperature control step length on the ordinate axis reflects the temperature variation amplitude of each step length, and the time step length on the abscissa axis reflects the time duration length of each step length, so that an initialized coordinate system is constructed. Then dividing the abscissa according to the time step length of each sub-step long section to determine the abscissa section of each sub-step section; dividing the ordinate according to the temperature control step length of each sub-long section to determine the ordinate section of each sub-long section; and combining the abscissa interval and the total coordinate interval of each sub-long interval to obtain N coordinates, wherein each coordinate comprises 4 coordinate points.

And then, positioning N coordinates one by one in the initialized coordinate system according to the corresponding coordinate points, wherein the coordinates are arranged in time sequence, and the formed new coordinate system is a step-length coordinate system. The temperature change speed range and the time span range of each sub-level control range are then identified on the basis of a step-size coordinate system. Each identification area is connected in sequence through lines, and finally a smooth curve is generated, wherein the curve is the step track.

By constructing an initialized coordinate system with two coordinate axes of a temperature control step length and a time step length, positioning and matching identification are carried out on parameters of each step length on the coordinate system, and finally a smooth step length track curve is generated, the simplified expression of a complex control process is realized, and therefore the control efficiency is improved.

Further, the embodiment of the application further comprises:

step S810: invoking a sample data set, wherein the sample data set comprises sample monitoring data and sample control difference, sample lower step length pre-control information and sample tuning control information;

step S820: dividing the sample data set to determine N groups of sample data;

step S830: training and generating N tuning sub-models based on the N groups of sample data, wherein each tuning sub-model is a three-layer fully-connected neural network model;

Step S840: and integrating the N tuning sub-models to generate the self-adaptive tuning model.

Specifically, an existing sample dataset is invoked for training an adaptive tuning model. The sample data set comprises sample monitoring data, sample control difference, sample lower step length pre-control information and sample tuning control information. The sample monitoring data are actual monitoring data of the target electric furnace at each lower step length node, such as temperature, power and the like; the sample control difference is the difference between the monitoring data of each lower step node and the pre-control information and is used for judging the accuracy of the pre-control information; the sample lower step length pre-control information is a preset control parameter of the target electric furnace at each lower step length node, such as temperature change rate, power output and the like; the sample optimizing control information is an optimized control parameter formulated for correcting the lower step length pre-control information based on sample monitoring data and differences.

Then, the control system divides the sample data set into N groups according to the number of the lower step nodes, and each sample data set corresponds to the data of one lower step node and comprises the monitoring data, the pre-control parameters and the tuning control information of the node. Then, three layers of fully-connected neural network models are selected as structures of the tuning sub-models, the number of input layer nodes is 100-500 of the number of monitoring data and difference parameters in sample data, the number of hidden layer nodes is determined according to the complexity of the sample data, the number of output layer nodes is 1, and tuning control information output by the corresponding models is obtained; based on the selected model structure, N neural network models are constructed as initial models of N tuning sub-models, and the N initial models have the same structure but different sample data used for training. N groups of sample data are selected respectively, N initial models are trained by adopting a supervised learning method, monitoring data and difference parameters of the sample data are used as input and provided for the models, tuning control information of the sample data is used as output and used as a training target of the models, the connection weights among neurons in each sub-model are continuously adjusted by utilizing a back propagation algorithm, and the distance between the output and the training target is minimized until convergence. After training of the N sub-models is finished, the models are tested by using respective sample test data, and whether the generalization capability and the accuracy of the models meet the requirements or not is checked. If the model which does not meet the requirement exists, retraining the model to finally obtain N tuning sub-models. And finally, integrating the N tuning sub-models to obtain a summary model, analyzing the new monitoring data and the pre-control parameters to generate corresponding correction control parameters as tuning control information, and realizing the optimization adjustment of the lower step interval.

And dividing and training the sample data by calling the sample data set, and finally generating a self-adaptive tuning model for optimizing the lower step interval control, thereby providing an optimization basis for obtaining tuning control information of the step.

Further, the embodiment of the application further comprises:

step S510: inputting the target monitoring data and the control difference into a self-adaptive tuning model, and matching the target tuning sub-model;

step S520: judging whether the calculation power of the target tuning sub-model meets the data processing requirement, and if not, generating a capacity expansion and merger instruction;

step S530: based on the capacity expansion and merger instruction, carrying out similarity analysis on the target modem model and the other N-1 modem models, determining N-1 similarity and carrying out positive serialization sequencing;

step S540: determining a to-be-merged sub-model based on the data processing requirements and the similarity;

step S550: and performing temporary fusion on the target tuning sub-model and the sub-model to be merged.

Specifically, first, target monitoring data and control difference are input to be provided to an adaptive tuning model; the self-adaptive tuning model is matched in N tuning sub-models according to the input target monitoring data and control difference, and the sub-model which is most suitable for the current input data is selected as the target tuning sub-model. For example, the sub-model that is trained by data most similar to the current node input data is selected based on the training data.

Secondly, determining the time requirement of the self-adaptive tuning model for processing and optimizing the input data and generating an output result; extracting target sub-model parameters, including the number of neurons, the number of connection weights, the historical calculation time and the like of the model, and judging the calculation force of the model; according to training data of the self-adaptive tuning model, establishing a corresponding relation between model calculation force and input data quantity; based on the corresponding relation, predicting the time required by the target sub-model to finish calculation under the current input data; comparing the time with data processing requirements; if the predicted time for the target sub-model to finish calculation is longer than the data processing requirement time, the calculation power of the target sub-model cannot meet the processing requirement of the current input data, and the control system generates a capacity expansion and fusion instruction to require the self-adaptive tuning model to expand the capacity of the current target tuning sub-model or fuse the current target tuning sub-model with other sub-models, so that the calculation capacity of the model is enhanced, and the data processing requirement is met.

And then, determining a model calculation force capable of meeting the data processing requirement according to the current input data quantity, subtracting the model calculation force of the target tuning sub-model according to the model calculation force, obtaining a missing model calculation force, extracting N-1 tuning sub-models according to the missing model calculation force in a sequence from large to small according to the similarity, and stopping extracting when the total calculation force of the extracted models meets the actual model calculation force, wherein the extracted models are to-be-merged sub-models. And finally, respectively extracting key parameters of the target tuning sub-model and the sub-model to be merged, including parameters such as model structure, training data, connection weight and the like, connecting the sub-models according to a hierarchical sequence by adopting a network cascading method, and setting a conversion layer to realize parameter conversion to generate a temporary fusion model.

Through the merging mechanism, dynamic balance is realized between control continuity and model calculation power improvement, and the merging is carried out on the sub-model which is highly similar to the target sub-model, so that resource consumption caused by capacity expansion is avoided, meanwhile, the model after the merging is ensured to continuously finish accurate optimization calculation aiming at the current node, and guarantee is provided for stable operation of high-precision intelligent control.

Further, as shown in fig. 3, the embodiment of the present application further includes:

step S560: determining control influence factors, wherein the control influence factors comprise natural environment and electric furnace service states;

step S570: based on the control influence factors, acquiring factor index values and analyzing factor index influence coefficients;

step S580: configuring distribution weights, carrying out weighted summation on the factor index influence coefficients, and generating control influence coefficients;

step S590: and correcting the tuning control information based on the control influence coefficient.

Specifically, in actual monitoring control of the circuit temperature, environmental factors and equipment operation states can affect control accuracy except control parameters. Therefore, in order to achieve fine control of the electric furnace temperature, natural environmental factors including environmental temperature, humidity, etc., and electric furnace operation state factors are determined as control influence factors; the operating state factors of the electric furnace comprise equipment aging, part wear and the like. Then, the relevant parameters of control influencing factors, such as the ambient temperature, the humidity, the equipment heat loss rate and the like, are collected in real time through an environmental influence detection sensor and an electric furnace state monitoring device to form factor index values; extracting a data set of control parameters and actual operation parameters of the electric furnace from a large amount of stored historical data; searching a historical subset matched with the current environmental condition in a historical data set based on the currently acquired factor index value; and analyzing the variable quantity of the electric furnace parameters caused by the change of the index value of each factor by one unit as an influence coefficient of each factor index according to the control parameters and the operation parameters of the electric furnace in the current environment.

Then, providing the relevant information of the control influencing factors and the factor indexes thereof to an expert, and requesting the expert to give a weight configuration scheme of each factor index according to the understanding and judgment of the expert on the control task; and carrying out weighted summation on the index weights of the factors and the corresponding influence coefficients to generate control influence coefficients, wherein the control influence coefficients represent the comprehensive influence quantity of all the control influence factor changes on the operation parameters of the electric furnace in the current environment. Finally, judging the influence direction of the environmental change on the operation parameters of the electric furnace according to the positive and negative control influence coefficients, and if the coefficients are positive, indicating that the environmental change can cause the increase of the operation parameters; if the coefficient is negative, it indicates that the environmental change causes a decrease in the operating parameter; calculating a correction amount for correcting the control information based on the value of the control influence coefficient so as to offset the change of the operation parameter of the electric furnace caused by the environmental change; and adding or subtracting the obtained correction quantity and the correction control information of the adjustment control information to generate new corrected control information after correction, thereby minimizing environmental influence and improving control precision.

The control influence factors are acquired and analyzed to obtain the control influence coefficients, and the optimized control parameters are corrected based on the control influence coefficients, so that the effective compensation of external factors is realized, the robustness of the control parameters generated by the self-adaptive tuning model is enhanced, and the guarantee is provided for the stable operation of high-precision intelligent control.

Further, the embodiment of the application further comprises:

step S581: configuring an excavating period, calling the control difference of step length nodes in the period, performing deviation analysis, and determining periodic deviation information;

step S582: if the periodic deviation information meets the deviation condition, a deviation tracing instruction is generated;

step S583: and calling the target monitoring data of the step-length nodes in the period, tracing the source of the deviation incentive and executing the weight increasing process.

Specifically, to improve the accuracy of the influence of the control influencing factors on the temperature control, a preferred configuration distribution weighting scheme is provided. Firstly, a time period containing a plurality of step nodes is configured as an excavating period according to the number of lower step nodes and a control period, and a plurality of step intervals of the electric furnace in a relatively stable running state are covered, so that stable data are obtained for analysis.

And secondly, calling the control differences of the step length nodes in the mining period, extracting characteristic parameters of the control differences, including difference values, increasing/decreasing rates, increasing/decreasing amplitudes and the like, and checking whether corresponding relations exist between the control differences of adjacent step length nodes in the mining period or not, wherein the corresponding relations are such as continuous increasing or decreasing of the difference values, large change amplitude of the increasing/decreasing rates and the like. If no obvious corresponding relation exists, the pre-control information is basically matched with the actual control requirement in the excavating period, and the control is relatively accurate. When the corresponding relation between the step node control differences exists, judging whether the corresponding relation presents periodic characteristics in the mining period or not, if so, the corresponding relation is reduced after the differences are increased, and then the cyclic variation is increased. If the corresponding relation shows obvious periodic change, the periodic deviation exists between the pre-control information and the actual control requirement, and the periodic deviation information is generated.

Then, a condition for judging the severity of the periodic deviation information is set based on the analysis of the history control data, and as the deviation condition, there are included a deviation increase rate exceeding a threshold value, a large deviation change amplitude, a short and frequent deviation period, and the like. And judging whether the characteristic parameter value in the information meets a preset deviation condition according to the periodic deviation information. If the characteristics of the deviation information are basically matched with the deviation conditions, which indicates that the deviation is serious, tracing analysis and correction are needed, the control system generates a deviation tracing instruction to carry out tracing analysis on the information in the step interval generating the deviation, including monitoring data, operating environment and the like, so as to find out the main inducement of the deviation.

And then, according to the deviation tracing instruction, calling target monitoring data of each step length node in the step length interval designated by the instruction, extracting key characteristic parameters from the target monitoring data, correspondingly analyzing data characteristics of adjacent step length nodes according to actual temperature, power, environmental humidity and the like, and judging whether corresponding changes exist between the characteristic parameters, wherein the corresponding relation corresponds to the changes of the control difference. If the correspondence is strong, it indicates that the change of the data characteristic is a main cause of the deviation generation. After the main cause of the deviation is confirmed, the control influence factors related to the data characteristics corresponding to the cause are increased in weight value in weight configuration, so that the influence of the control influence factors on the control correction parameters is increased, and the current deviation is corrected.

By configuring the mining period and analyzing the control difference of each step node in the period, judging whether deviation information exists or not and meeting certain conditions, when larger deviation occurs, tracing and analyzing the monitoring data in the mining period, finding out main causes, executing weight increasing operation on control influence factors corresponding to the causes, enhancing the monitoring and management of a control system on a control process, increasing the weight of related control influence factors, realizing the purpose of correcting the deviation in a targeted manner, and improving the control accuracy.

In summary, the electric furnace temperature monitoring control method based on the 5G technology provided by the embodiment of the application has the following technical effects:

the method comprises the steps of interacting instant information of a target electric furnace, determining pre-control information, and providing an information basis for optimizing control by acquiring the instant information such as temperature, working state and the like of the electric furnace and determining the pre-control information; determining a control domain based on the instant information and the pre-control information, performing step dissociation and coordinate system conversion, determining a step track, and providing a basis for sensing monitoring and control; configuring a sensing monitoring device, determining a target step length node to perform control monitoring on the target electric furnace by taking the step length track as a standard, acquiring target monitoring data, monitoring the target electric furnace by the sensing monitoring device, acquiring target monitoring data such as electric furnace temperature and the like, and providing data support for the input of a tuning model; calculating control difference based on the target monitoring data, judging whether the control difference meets a difference threshold, and providing a data basis for the input of the self-adaptive tuning model; if the current value is not met, inputting the target monitoring data and the control difference into an adaptive tuning model, outputting tuning control information, wherein the adaptive tuning model has capacity expansion and compatibility, and providing optimization information for the optimization control of the temperature of the electric furnace; based on the tuning control information, matching a control domain of a lower step node in a step track, performing feedback compensation, transmitting to an electric furnace temperature controller to perform optimization control of a lower step interval, and establishing loop correlation between the step track, the self-adaptive tuning model and the electric furnace temperature controller to realize refined control of target electric furnace temperature; traversing the step track, gradually growing the nodes to perform the stepwise control and adjustment of the target electric furnace, thereby achieving the technical effects of precisely controlling the temperature of the electric furnace in real time and improving the temperature control precision of the electric furnace.

Example two

Based on the same inventive concept as the electric furnace temperature monitoring control method based on the 5G technology in the foregoing embodiments, as shown in fig. 4, an embodiment of the present application provides an electric furnace temperature monitoring control system based on the 5G technology, the system including:

the pre-control information determining module 11 is used for interacting the instant information of the target electric furnace and determining the pre-control information;

a step track determining module 12, configured to determine a control domain based on the instant information and the pre-control information, and perform step dissociation and coordinate system conversion to determine a step track;

the target detection data module 13 is used for configuring a sensing monitoring device, determining a target step length node to perform control monitoring of the target electric furnace by taking the step length track as a standard, and obtaining target monitoring data;

a control difference determination module 14 that calculates a control difference based on the target monitoring data and determines whether the control difference satisfies a difference threshold;

the tuning control information module 15 is configured to input the target monitoring data and the control difference into an adaptive tuning model, and output tuning control information if the target monitoring data and the control difference are not satisfied, where the adaptive tuning model has capacity expansion compatibility;

the step length interval optimizing module 16 is used for matching the control domain of a lower step length node in the step length track based on the tuning control information, performing feedback compensation, transmitting the control domain to the electric furnace temperature controller, and executing optimizing control of the lower step length interval, wherein the step length track, the self-adaptive tuning model and the electric furnace temperature controller are in loop correlation;

And the electric furnace instant control and instant adjustment module 17 is used for traversing the step track and gradually growing the nodes to perform the stepwise instant control and instant adjustment of the target electric furnace.

Further, the step track determining module 12 includes the following steps:

determining a control domain based on the instant information and the pre-control information, wherein the control domain comprises a multi-dimensional control index value: output power, temperature control circuit state, conduction time, heating speed and step interval;

configuring a preset segmentation step length, dividing the step length interval, and obtaining N step lengths, wherein the N step length time sequences are connected;

based on the N item step sizes, dissociating the control domain to obtain a target dissociation result, wherein the target dissociation result corresponds to N groups of sub-level control domains, and the N groups of sub-level control domains are in one-to-one correspondence with the N item step sizes;

and generating the step track based on the N item step sizes and the N groups of sub-level control fields.

Further, the step track determining module 12 further includes the following steps:

the step interval comprises a temperature control step interval and a time step interval, and an initialization coordinate system is constructed by taking the temperature control step and the time step as coordinate axes;

determining N item coordinates based on the N item step sizes;

In the initialization coordinate system, positioning and distributing the N-item coordinates to be used as a step size coordinate system;

and based on the N groups of sub-level control domains, carrying out matching identification on the N items of coordinates in the step size coordinate system, and generating the step size track.

Further, the embodiment of the application also comprises a tuning model construction module, which comprises the following execution steps:

invoking a sample data set, wherein the sample data set comprises sample monitoring data and sample control difference, sample lower step length pre-control information and sample tuning control information;

dividing the sample data set to determine N groups of sample data;

training and generating N tuning sub-models based on the N groups of sample data, wherein each tuning sub-model is a three-layer fully-connected neural network model;

and integrating the N tuning sub-models to generate the self-adaptive tuning model.

Further, the tuning control information module 15 includes the following steps:

inputting the target monitoring data and the control difference into a self-adaptive tuning model, and matching the target tuning sub-model;

judging whether the calculation power of the target tuning sub-model meets the data processing requirement, and if not, generating a capacity expansion and merger instruction;

Based on the capacity expansion and merger instruction, carrying out similarity analysis on the target modem model and the other N-1 modem models, determining N-1 similarity and carrying out positive serialization sequencing;

determining a to-be-merged sub-model based on the data processing requirements and the similarity;

and performing temporary fusion on the target tuning sub-model and the sub-model to be merged.

Further, the tuning control information module 15 further includes the following steps:

determining control influence factors, wherein the control influence factors comprise natural environment and electric furnace service states;

based on the control influence factors, acquiring factor index values and analyzing factor index influence coefficients;

configuring distribution weights, carrying out weighted summation on the factor index influence coefficients, and generating control influence coefficients;

and correcting the tuning control information based on the control influence coefficient.

Further, the tuning control information module 15 further includes the following steps:

configuring an excavating period, calling the control difference of step length nodes in the period, performing deviation analysis, and determining periodic deviation information;

if the periodic deviation information meets the deviation condition, a deviation tracing instruction is generated;

And calling the target monitoring data of the step-length nodes in the period, tracing the source of the deviation incentive and executing the weight increasing process.

Any of the steps of the methods described above may be stored as computer instructions or programs in a non-limiting computer memory and may be called by a non-limiting computer processor to identify any method for implementing an embodiment of the present application, without unnecessary limitations.

It will be apparent to those skilled in the art that various modifications and variations can be made to the present application without departing from the scope of the application. Thus, the present application is intended to include such modifications and alterations insofar as they come within the scope of the application or the equivalents thereof.

Claims (4)

1. An electric furnace temperature monitoring control method based on a 5G technology is characterized in that the method is applied to an electric furnace temperature control system, the system is in communication connection with an electric furnace temperature controller, and the method comprises the following steps:

the instant information of the target electric furnace is interacted, and pre-control information is determined;

determining a control domain based on the instant information and the pre-control information, performing step dissociation and coordinate system conversion, and determining a step track;

the method for determining the step track comprises the steps of determining a control domain based on the instant information and the pre-control information, performing step dissociation and coordinate system conversion, and determining the step track, wherein the method comprises the following steps:

Determining a control domain based on the instant information and the pre-control information, wherein the control domain comprises a multi-dimensional control index value: output power, temperature control circuit state, conduction time, heating speed and step interval;

configuring a preset segmentation step length, dividing the step length interval, and obtaining N step lengths, wherein the N step length time sequences are connected;

based on the N item step sizes, dissociating the control domain to obtain a target dissociation result, wherein the target dissociation result corresponds to N groups of sub-level control domains, and the N groups of sub-level control domains are in one-to-one correspondence with the N item step sizes;

generating the step track based on the N item step sizes and the N groups of sub-level control domains;

wherein the step track is generated based on the N item step sizes and the N groups of sub-level control domains, and the method comprises the following steps:

the step interval comprises a temperature control step interval and a time step interval, and an initialization coordinate system is constructed by taking the temperature control step and the time step as coordinate axes;

determining N item coordinates based on the N item step sizes;

in the initialization coordinate system, positioning and distributing the N-item coordinates to be used as a step size coordinate system;

based on the N groups of sub-level control domains, carrying out matching identification on the N items of coordinates in the step size coordinate system to generate the step size track;

Configuring a sensing monitoring device, and determining a target step length node to perform control monitoring of the target electric furnace by taking the step length track as a standard to acquire target monitoring data;

calculating a control difference based on the target monitoring data, and judging whether the control difference meets a difference threshold;

if the target monitoring data and the control difference are not satisfied, inputting the target monitoring data and the control difference into an adaptive tuning model, and outputting tuning control information, wherein the adaptive tuning model has capacity expansion and compatibility;

before the target monitoring data and the control difference are input into the adaptive tuning model, the method comprises the following steps:

invoking a sample data set, wherein the sample data set comprises sample monitoring data and sample control difference, sample lower step length pre-control information and sample tuning control information;

dividing the sample data set to determine N groups of sample data;

training and generating N tuning sub-models based on the N groups of sample data, wherein each tuning sub-model is a three-layer fully-connected neural network model;

integrating the N tuning sub-models to generate the self-adaptive tuning model;

the method for inputting the target monitoring data and the control difference into the adaptive tuning model comprises the following steps:

Inputting the target monitoring data and the control difference into a self-adaptive tuning model, and matching the target tuning sub-model;

judging whether the calculation power of the target tuning sub-model meets the data processing requirement, and if not, generating a capacity expansion and merger instruction;

based on the capacity expansion and merger instruction, carrying out similarity analysis on the target modem model and the other N-1 modem models, determining N-1 similarity and carrying out positive serialization sequencing;

determining a to-be-merged sub-model based on the data processing requirements and the similarity;

performing temporary fusion on the target tuning sub-model and the sub-model to be merged;

based on the tuning control information, matching the control domain of a lower step node in the step track, performing feedback compensation, transmitting to the electric furnace temperature controller to perform optimization control of a lower step interval, and establishing loop correlation between the step track, the self-adaptive tuning model and the electric furnace temperature controller;

traversing the step track, and gradually growing the nodes to perform the stepwise control and adjustment of the target electric furnace.

2. The method of claim 1, wherein after the outputting of the tuning control information, the method comprises:

Determining control influence factors, wherein the control influence factors comprise natural environment and electric furnace service states;

based on the control influence factors, acquiring factor index values and analyzing factor index influence coefficients;

configuring distribution weights, carrying out weighted summation on the factor index influence coefficients, and generating control influence coefficients;

and correcting the tuning control information based on the control influence coefficient.

3. The method of claim 2, wherein the configuring distributes weights, the method comprising:

configuring an excavating period, calling the control difference of step length nodes in the period, performing deviation analysis, and determining periodic deviation information;

if the periodic deviation information meets the deviation condition, a deviation tracing instruction is generated;

and calling the target monitoring data of the step-length nodes in the period, tracing the source of the deviation incentive and executing the weight increasing process.

4. A 5G technology based electric furnace temperature monitoring control system for implementing the 5G technology based electric furnace temperature monitoring control method of any one of claims 1-3, the system being communicatively connected to an electric furnace temperature controller, the system comprising:

the pre-control information determining module is used for interacting instant information of the target electric furnace and determining pre-control information;

The step track determining module is used for determining a control domain based on the instant information and the pre-control information, performing step dissociation and coordinate system conversion, and determining a step track;

the step track determining module comprises the following executing steps:

determining a control domain based on the instant information and the pre-control information, wherein the control domain comprises a multi-dimensional control index value: output power, temperature control circuit state, conduction time, heating speed and step interval;

configuring a preset segmentation step length, dividing the step length interval, and obtaining N step lengths, wherein the N step length time sequences are connected;

based on the N item step sizes, dissociating the control domain to obtain a target dissociation result, wherein the target dissociation result corresponds to N groups of sub-level control domains, and the N groups of sub-level control domains are in one-to-one correspondence with the N item step sizes;

generating the step track based on the N item step sizes and the N groups of sub-level control domains;

the step track determining module further comprises the following executing steps:

the step interval comprises a temperature control step interval and a time step interval, and an initialization coordinate system is constructed by taking the temperature control step and the time step as coordinate axes;

Determining N item coordinates based on the N item step sizes;

in the initialization coordinate system, positioning and distributing the N-item coordinates to be used as a step size coordinate system;

based on the N groups of sub-level control domains, carrying out matching identification on the N items of coordinates in the step size coordinate system to generate the step size track;

the target detection data module is used for configuring a sensing monitoring device, determining a target step length node to perform control monitoring of the target electric furnace by taking the step length track as a standard, and acquiring target monitoring data;

a control difference determination module that calculates a control difference based on the target monitoring data and determines whether the control difference satisfies a difference threshold;

the tuning control information module is used for inputting the target monitoring data and the control difference into an adaptive tuning model and outputting tuning control information if the target monitoring data and the control difference are not met, and the adaptive tuning model has capacity expansion and compatibility;

wherein, the tuning model construction module further comprises the following execution steps:

invoking a sample data set, wherein the sample data set comprises sample monitoring data and sample control difference, sample lower step length pre-control information and sample tuning control information;

Dividing the sample data set to determine N groups of sample data;

training and generating N tuning sub-models based on the N groups of sample data, wherein each tuning sub-model is a three-layer fully-connected neural network model;

integrating the N tuning sub-models to generate the self-adaptive tuning model;

wherein, the tuning control information module further comprises the following execution steps:

inputting the target monitoring data and the control difference into a self-adaptive tuning model, and matching the target tuning sub-model;

judging whether the calculation power of the target tuning sub-model meets the data processing requirement, and if not, generating a capacity expansion and merger instruction;

based on the capacity expansion and merger instruction, carrying out similarity analysis on the target modem model and the other N-1 modem models, determining N-1 similarity and carrying out positive serialization sequencing;

determining a to-be-merged sub-model based on the data processing requirements and the similarity;

performing temporary fusion on the target tuning sub-model and the sub-model to be merged;

the step length interval optimizing module is used for matching the control domain of a lower step length node in the step length track based on the tuning control information, performing feedback compensation, transmitting the control domain to the electric furnace temperature controller, executing optimizing control of the lower step length interval, and establishing loop association between the step length track, the self-adaptive tuning model and the electric furnace temperature controller;

The electric furnace instant control and instant adjustment module is used for traversing the step track, and gradually growing the nodes to perform the stepwise instant control and instant adjustment of the target electric furnace.