CN116182564A - Intelligent control system for ignition furnace of sintering machine - Google Patents
Intelligent control system for ignition furnace of sintering machine Download PDFInfo
- Publication number
- CN116182564A CN116182564A CN202310460085.0A CN202310460085A CN116182564A CN 116182564 A CN116182564 A CN 116182564A CN 202310460085 A CN202310460085 A CN 202310460085A CN 116182564 A CN116182564 A CN 116182564A
- Authority
- CN
- China
- Prior art keywords
- data
- time
- combustion
- temperature
- gas flow
- 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.)
- Granted
Links
- 238000005245 sintering Methods 0.000 title claims abstract description 36
- 230000002787 reinforcement Effects 0.000 claims abstract description 13
- 238000002485 combustion reaction Methods 0.000 claims description 105
- 238000000034 method Methods 0.000 claims description 41
- 238000012549 training Methods 0.000 claims description 28
- 238000006243 chemical reaction Methods 0.000 claims description 26
- 230000008569 process Effects 0.000 claims description 22
- 230000002159 abnormal effect Effects 0.000 claims description 20
- 238000012216 screening Methods 0.000 claims description 20
- 238000012937 correction Methods 0.000 claims description 14
- 238000004364 calculation method Methods 0.000 claims description 11
- 238000002790 cross-validation Methods 0.000 claims description 6
- 238000001514 detection method Methods 0.000 claims description 6
- 238000010586 diagram Methods 0.000 claims description 6
- 238000010801 machine learning Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 239000003034 coal gas Substances 0.000 claims description 2
- 239000000463 material Substances 0.000 abstract description 25
- 230000000694 effects Effects 0.000 abstract description 5
- 238000004519 manufacturing process Methods 0.000 abstract description 5
- 230000008859 change Effects 0.000 abstract description 3
- 238000005265 energy consumption Methods 0.000 abstract description 3
- 238000004383 yellowing Methods 0.000 abstract description 3
- 239000007789 gas Substances 0.000 description 94
- 239000000203 mixture Substances 0.000 description 6
- 238000012360 testing method Methods 0.000 description 6
- 238000011156 evaluation Methods 0.000 description 5
- 238000013528 artificial neural network Methods 0.000 description 4
- 230000009191 jumping Effects 0.000 description 4
- 230000006854 communication Effects 0.000 description 3
- 239000000446 fuel Substances 0.000 description 3
- 238000010438 heat treatment Methods 0.000 description 3
- 230000035699 permeability Effects 0.000 description 3
- 229910000831 Steel Inorganic materials 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000013210 evaluation model Methods 0.000 description 2
- 239000002737 fuel gas Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 239000010959 steel Substances 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 238000007792 addition Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000002844 melting Methods 0.000 description 1
- 230000008018 melting Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F27—FURNACES; KILNS; OVENS; RETORTS
- F27B—FURNACES, KILNS, OVENS, OR RETORTS IN GENERAL; OPEN SINTERING OR LIKE APPARATUS
- F27B21/00—Open or uncovered sintering apparatus; Other heat-treatment apparatus of like construction
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F27—FURNACES; KILNS; OVENS; RETORTS
- F27D—DETAILS OR ACCESSORIES OF FURNACES, KILNS, OVENS, OR RETORTS, IN SO FAR AS THEY ARE OF KINDS OCCURRING IN MORE THAN ONE KIND OF FURNACE
- F27D19/00—Arrangements of controlling devices
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F27—FURNACES; KILNS; OVENS; RETORTS
- F27D—DETAILS OR ACCESSORIES OF FURNACES, KILNS, OVENS, OR RETORTS, IN SO FAR AS THEY ARE OF KINDS OCCURRING IN MORE THAN ONE KIND OF FURNACE
- F27D19/00—Arrangements of controlling devices
- F27D2019/0028—Regulation
- F27D2019/0034—Regulation through control of a heating quantity such as fuel, oxidant or intensity of current
- F27D2019/004—Fuel quantity
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Regulation And Control Of Combustion (AREA)
- Manufacture And Refinement Of Metals (AREA)
Abstract
The invention discloses an intelligent control system of an ignition furnace of a sintering machine, which belongs to the technical field of intelligent control of ignition furnaces and comprises an reinforcement learning module, a server, a storage module, a global state parameter judging module, an emergency module and a picture display module, wherein the purpose of stably controlling the ignition temperature is achieved by automatically adjusting gas and air flow; when the speed of the sintering machine changes, in order to maintain the original ignition intensity, the gas quantity is automatically adjusted in the ignition temperature control range, the change of the ignition intensity is reversely compensated, and the ignition effect is ensured; the accurate control of the energy consumption of the burning furnace is achieved through the prediction of the feedback prediction model, the conditions of ignition yellowing or overmelting of the material surface of the sintering material are stopped on the basis of guaranteeing the ignition temperature control range, the influence of the gas pressure or heat value fluctuation on the sintering production process is reduced, and the ignition gas consumption is reduced.
Description
Technical Field
The invention belongs to the technical field of intelligent control of ignition furnaces; in particular to an intelligent control system of an ignition furnace of a sintering machine.
Background
In the sintering field, an ignition furnace is used as core equipment on a sintering process production line, the ignition effect of the ignition furnace has a great influence on the quality of the sintering ore, and the ignition furnace is in a very critical position on the whole sintering process. After the mixture is fed onto the sintering pallet, the mixture is first ignited by an ignition furnace. The temperature of the ignition furnace is generally about 1250 ℃ according to operation experience. Too high a temperature can melt the surface of the material layer, worsen the air permeability, too low a temperature, and the surface of the material layer is not well ignited, so that the combustion of the sinter is affected. In both cases, the yield and quality of the sintered ore are reduced. Therefore, in order to ensure that the mixture is well sintered, the optimal ignition temperature of the material layer is required, and in order to enable the fuel gas to be fully combusted, a reasonable air-fuel ratio value is also required, so that it is important to realize intelligent control of the ignition furnace.
Disclosure of Invention
The invention aims to provide an intelligent control system for an ignition furnace of a sintering machine, which solves the problem of intelligent combustion control of the ignition furnace.
The aim of the invention can be achieved by the following technical scheme:
an intelligent control system of a sintering machine ignition furnace comprises an reinforcement learning module, a server, a storage module, a global state parameter judging module, an emergency module and a picture display module;
the reinforcement learning module is used for predicting the gas outlet flow, and the specific method comprises the following steps:
step S1: generating a training data set by using historical manual furnace burning data;
step S11: screening historical data by using coal gas with the flow rate greater than M, wherein the difference value of adjacent index in the screened data is smaller than L, and is considered to be in the same combustion period, otherwise, the data is considered to be in another combustion period, so that complete combustion period data is obtained, and the data quantity according to the combustion period is greater than P;
step S12: calculating average vault temperature, vault temperature standard deviation, vault temperature maximum value, vault temperature minimum value and average value of heat value point multiplied by gas flow in each combustion cycle to generate new screening conditions;
step S13: according to the new screening conditions in the step S12, two data sets are obtained respectively, then combustion period data with combustion periods both appearing in the two data sets are taken, then data after D minutes of each combustion period are taken, label of the data is dome temperature at time t+1, variables are combustion time, dome temperature (right) of F minutes before time t and flue temperature of F minutes before time t, and finally the data are stored as a csv file;
step S14: taking data after D minutes of each combustion period of the data screened in the step S11, wherein Label of the data is gas flow at time t+1, variables are combustion time, heat value from F to Z minutes before time t, vault temperature from F minutes before time t, and gas flow from F minutes before time t, and finally storing the data as a csv file;
step S2: training a predicted dome temperature model and a predicted gas flow model using the two data sets;
step S21: training a prediction dome temperature model, wherein Label of training data is dome temperature at time t+1, and variables are dome temperature (right) of F minutes before the time t and a model of flue temperature of F minutes before the time t;
step S22: a ten-fold cross-validation comparison common machine learning method is adopted; according to the absolute error mean value, the mean square error and the determinable coefficient as selection model standards, an extreme random tree model is selected after the selection model standards are integrated; the extreme random tree model is saved;
step S23: training a predicted gas flow model, wherein the training Label is the gas flow at the time t+1, and the variables are the combustion time, the heat value from F to Z minutes before the time t of the combustion, the vault temperature of F minutes before the time t of the combustion, and the gas flow model of F minutes before the time t of the combustion;
step S24: a ten-fold cross-validation comparison common machine learning method is adopted; selecting an extreme random tree model according to the absolute error mean, the mean square error and the determinable coefficient as selection model standards and comprehensively selecting the model standards; the extreme random tree model is saved;
step S25: each furnace is provided with two models, model prediction is carried out, the dome temperature, the combustion time, the heat value of F minutes before the combustion time t, the flue temperature of F minutes before the combustion time t, the dome temperature (right) of F minutes before the combustion time t and the gas flow of F minutes before the combustion time t which are predicted by the dome temperature models are input into a predicted gas flow model, and the gas flow at the time t+1 is obtained;
step S3: and processing the parameters transmitted to the PID module to obtain the output gas flow.
Further, generating new screening conditions in step S12 includes:
step S121: describing the relationship between the maximum value of the dome temperature of each combustion cycle and the mean value of the heat value point multiplied by the gas flow of each combustion cycle;
step S122: describing the relationship between the average value of the heat value point multiplied by the gas flow rate of each combustion period and the highest air supply temperature in the air supply period after the combustion period is finished;
step S123: and obtaining two screening conditions according to the two scatter diagrams and the average vault temperature, the vault temperature standard deviation, the vault temperature maximum value, the vault temperature minimum value, the average value of the heat value multiplied by the gas flow and the air supply temperature of each combustion cycle.
Further, the emergency module is used for detecting the heartbeat of the system link state and carrying out emergency treatment on the detection result, and the specific method comprises the following steps: the abnormal state of the system link is obtained in real time, the abnormal state of the system link comprises a server shutdown, a network interruption and a switch failure, when the abnormal state of the link exists, a heartbeat signal interruption is caused, and when the heartbeat signal interruption is detected, the original control system is switched back to continuously control the hot blast stove.
Further, the picture display module is used for displaying technological process and working condition parameters, and is provided with an alarm unit, a printing unit and a history trend unit, wherein the alarm unit receives alarm signals sent by a server and sends alarm information to an administrator.
Further, a corresponding display node is arranged at the working position of the first-line worker, and corresponding data display is carried out through the display node.
Further, the working method of the display node comprises the following steps:
determining each target item data, collecting each target conversion mode corresponding to the target item data, screening the obtained target conversion modes, obtaining an implementation conversion mode corresponding to the target item data, carrying out real-time conversion on corresponding professional display data displayed in a picture display module based on each implementation conversion mode, and carrying out real-time display on each converted target item data in a display interface.
Further, the method for screening the obtained target transformation mode comprises the following steps:
obtaining application scores corresponding to all target conversion modes, evaluating the implementation of all target conversion modes to obtain corresponding correction coefficients, and calculating corresponding priority values QY according to a priority formula QY=c×YZ, wherein c is a correction coefficient; YZ is the application score; and selecting the target conversion mode with the highest priority value as the implementation conversion mode of the target item data.
Further, the global state parameter judging module is used for judging a calculation process in the reinforcement learning module, marking a normal state as 1 when the calculation process is normal, marking an abnormal state as 0 when the calculation process is abnormal, sending a judging result to the server, and when a parameter received by the server is 0, not executing a gas flow regulation task, automatically switching to manual control, generating an alarm signal and sending the alarm signal to the alarm unit; setting an input data limiting range and an output data limiting range of the reinforcement learning module, analyzing the input data and the output data, generating a state parameter of 0 when the input data is not in the input data limiting range or the output data is not in the output data limiting range, generating a state parameter of 1 when the input data is in the input data limiting range or the output data is in the output data limiting range, transmitting the state parameter to a server, and when the parameter received by the server is 0, not executing a gas flow regulation task, automatically switching to manual control, generating an alarm signal and transmitting the alarm signal to an alarm unit.
The invention has the beneficial effects that: the purpose of stably controlling the ignition temperature is achieved by automatically adjusting the gas and air flow; when the speed of the sintering machine changes, in order to maintain the original ignition intensity, the gas quantity is automatically adjusted in the ignition temperature control range, the change of the ignition intensity is reversely compensated, and the ignition effect is ensured; the accurate control of the energy consumption of the burning furnace is achieved through the prediction of the feedback prediction model, the conditions of ignition yellowing or overmelting of the material surface of the sintering material are stopped on the basis of ensuring the ignition temperature control range, the influence of the gas pressure or heat value fluctuation on the sintering production process is reduced, and the ignition gas consumption is reduced; by setting the evaluation correction unit, the prediction result of the feedback prediction model can be evaluated, the feedback prediction model can be relearned, the feedback prediction model can be timely adjusted, the accuracy of the feedback prediction model is ensured, and resource waste caused by untimely adjustment or non-adjustment is avoided.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic block diagram of the present invention;
FIG. 2 is a flowchart of the algorithm of the present invention;
FIG. 3 is a flow chart of the gas prediction of the present invention.
Detailed Description
The technical solutions of the present invention will be clearly and completely described in connection with the embodiments, and it is obvious that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In the sintering field, an ignition furnace is used as core equipment on a sintering process production line, the ignition effect of the ignition furnace has a great influence on the quality of the sintering ore, the ignition furnace is in a very critical position on the whole sintering process, and after the mixture is fed onto a sintering machine trolley, the ignition furnace is used for igniting the mixture; according to operation experience, the temperature of the ignition furnace is generally about 1250 ℃, and the excessive temperature can lead to melting of the surface of the material layer, poor air permeability, low temperature, poor ignition of the surface of the material layer and influence on the combustion of the sinter; in both cases, the yield and quality of the sintered ore are reduced; therefore, in order to ensure that the mixture is well sintered, the optimal ignition temperature of the material layer is required, and in order to enable the fuel gas to be fully combusted, a reasonable air-fuel ratio value is also required, so that it is important to realize intelligent control of the ignition furnace.
1-3, the intelligent control system of the sintering machine ignition furnace comprises an reinforcement learning module, a server, a storage module, an emergency module, a global state parameter judging module, an anti-interference module, a picture display module and a picture monitoring module.
The reinforcement learning module comprises a feedback prediction model and an evaluation correction unit, wherein the feedback prediction model is used for predicting the opening degree of the gas electric valve and the opening degree of the air electric valve, and the specific prediction method comprises the following steps:
acquiring ignition temperature, gas flow and air flow of the ignition furnace in real time, integrating the ignition temperature, the gas flow and the air flow and marking the ignition temperature, the gas flow and the air flow as input data; acquiring a feedback prediction model; inputting input data into a feedback prediction model to obtain an output result and marking the output result as a prediction label, wherein the prediction label is a state label corresponding to the input data; the state label is sent to a server, and the server adjusts the opening degree of the electric valve and the opening degree of the air electric valve according to the state label; the purpose of stably controlling the ignition temperature is achieved by automatically adjusting the gas and air flow; when the speed of the sintering machine changes, in order to maintain the original ignition intensity, the gas quantity is automatically adjusted in the ignition temperature control range, the change of the ignition intensity is reversely compensated, and the ignition effect is ensured.
The method for acquiring the feedback prediction model specifically comprises the following steps: acquiring historical ignition furnace working condition data through a storage module; the ignition furnace working condition historical data comprise ignition temperature, gas flow and air flow which are N minutes before the gas electric valve opening degree and the air electric valve opening degree are adjusted; wherein N is a preset value, and N is more than or equal to 10; setting a state label for the historical data of the ignition furnace working condition; the state label comprises the opening degree of the gas electric valve, the opening degree of the air electric valve and state parameters; the state parameter is used for judging whether the state of the computing process is normal or not by the global state parameter judging module; constructing an artificial intelligent model, wherein the artificial intelligent model comprises an error back propagation neural network, an RBF neural network and a deep convolution neural network; dividing the communication history data and the corresponding state label into a training set, a testing set and a checking set according to a set proportion; the set proportion includes 3:2: 2. 3:2:1 and 3:1:1, a step of; training, testing and checking the artificial intelligent model through the training set, the testing set and the checking set; and marking the trained artificial intelligent model as a feedback prediction model.
Through the setting of feedback prediction model for the ignition furnace has realized intelligent control, avoids because the temperature is too high, can make the bed of material surface melt, and the gas permeability variation, the temperature is too low, the not good problem of bed of material surface ignition, still can predict reasonable air-fuel ratio.
The evaluation correction unit is used for evaluating the prediction result of the feedback prediction model and relearning the feedback prediction model, and the specific method comprises the following steps: acquiring recorded data for adjusting the opening degree of the electric valve and the opening degree of the air electric valve according to the prediction result and corresponding burning conditions of the sintering material surface, and accurately controlling the energy consumption of the sintering furnace by the prediction of a feedback prediction model, so that the condition of ignition yellowing or overmelting of the sintering material surface is stopped on the basis of ensuring the ignition temperature control range, the influence of gas pressure or heat value fluctuation on the sintering production process is reduced, and the ignition gas consumption is reduced; setting a scoring table according to the obtained recorded data and the corresponding burning condition of the sintered material level, wherein the scoring table can be adjusted according to the actual condition of a customer, the scoring table comprises a comparison image of the burning condition of the sintered material level, the obtained corresponding burning image of the sintered material level is matched with the comparison image of the burning condition of the sintered material level in the scoring table, a corresponding prediction result score is obtained, when the prediction result score is qualified, no operation is performed, when the prediction result score is unqualified, the corresponding recorded data is obtained, the opening degree of the electric valve and the opening degree of the air electric valve in the recorded data are modified, the opening degree of the electric valve, the opening degree of the air electric valve and the corresponding input data which are completed by modification are marked as self-learning data, and the self-learning data are input into a feedback prediction model for re-learning.
By setting the evaluation correction unit, the prediction result of the feedback prediction model can be evaluated, the feedback prediction model can be relearned, the feedback prediction model can be timely adjusted, the accuracy of the feedback prediction model is ensured, and resource waste caused by untimely adjustment or non-adjustment is avoided.
The emergency module is used for detecting the heartbeat of the system link state and carrying out emergency treatment on the detection result, and the specific method comprises the following steps: acquiring abnormal states of a system link in real time, wherein the abnormal states of the system link comprise server shutdown, network interruption and switch failure, when the abnormal states of the link exist, heartbeat signals are interrupted, and when the interruption of the heartbeat signals is detected, the original control system is switched back to continuously control the hot blast stove, for example: the existing control system for the permanent steel detects the heartbeat of the intelligent control system in real time in the link state, if any abnormality exists in the link, such as server shutdown, network interruption, switch failure and other conditions, heartbeat signals are interrupted, and if the heartbeat signals are interrupted, the system automatically switches back to the free control system for the permanent steel to continuously control the hot blast stove.
The global state parameter judging module is used for judging a calculation process in the reinforcement learning module, marking a normal state as 1 when the calculation process is normal, marking an abnormal state as 0 when the calculation process is abnormal, sending a judging result to the server, and when a parameter received by the server is 0, not executing a gas flow regulation task, automatically switching to manual control, generating an alarm signal and sending the alarm signal to the alarm unit; setting an input data limiting range and an output data limiting range of the reinforcement learning module, wherein the input data limiting range and the output data limiting range are set by an expert group according to use specifications, use areas and customer requirements, analyzing the input data and the output data, generating a state parameter of 0 when the input data is not in the input data limiting range or the output data is not in the output data limiting range, wherein the input data is the data in the input neural network model, and the output data is the output result of the neural network model; when the input data is within the input data limit range or the output data is within the output data limit range, generating a state parameter of 1, sending the state parameter to the server, and when the parameter received by the server is 0, not executing the gas flow regulation task, automatically switching to manual control, generating an alarm signal and sending the alarm signal to the alarm unit.
The anti-interference module adopts a method of multilayer digital filtering, zero drift, delay jitter elimination, logic judgment and expert experience database to eliminate signal peak and noise interference.
The picture display module is used for displaying technological process and working condition parameters, and is provided with an alarm unit, a printing unit and a history trend unit, wherein the alarm unit receives alarm signals sent by the server and sends alarm information to an administrator to remind the administrator that the system is manually controlled.
In one embodiment, since the display of various working condition parameters, detection data and other data is directly performed, it is clear for the staff having related expertise to understand various display data, but it is difficult for the first-line worker, especially when an emergency occurs, the first-line worker is most suitable for processing the emergency problem, and it is important how to apply a suitable display mode to help the first-line worker understand various display data quickly, which is as follows:
setting corresponding display nodes at the positions of the first lines, namely, the display nodes are used for exclusively displaying data to first-line workers, and marking various data displayed in the picture display module as professional display data; marking data item data to be displayed to an inline worker in professional display data, namely, marking data item data to be displayed to the inline worker, which data is effective for the inline worker, as target item data; the method can be used for knowing how the target item data are displayed in a first-line worker questionnaire survey mode and the like to facilitate understanding of the target item data, if an emergency situation occurs, certain emergency adjustment data are displayed through corresponding special terms, in order to facilitate understanding, a valve at that position is rotated to that scale, a switch at that position is closed, buttons are clicked in sequence and the like, and the target item data are displayed in a popular and easily understood mode; corresponding summarization is carried out, a plurality of target conversion modes corresponding to the target item data are obtained, the application score of each target conversion mode is synchronously evaluated in the communication process, and the average is taken; evaluating corresponding correction coefficients of each target conversion mode from the angles of operation, implementation and the like, namely considering the actual application angle of the target conversion mode, specifically, establishing a corresponding correction evaluation model based on a CNN network or a DNN network, establishing a corresponding training set by a manual mode for training, and analyzing the corrected evaluation model after successful training to obtain the corresponding correction coefficients, wherein the neural network is the prior art in the field, so that the specific establishment and training process is not described in detail; marking the obtained application score and correction coefficient as YZ and c respectively, calculating a corresponding priority value according to a priority formula QY=c×YZ, selecting a target conversion mode with the highest priority value as an implementation conversion mode of the target item data, and constructing a display node display interface based on the implementation conversion mode corresponding to each target item data;
and identifying each target item data displayed in the picture display module in real time, and converting the obtained target item data into a corresponding display node in real time for display.
Another embodiment: the reinforcement learning module is used for predicting the gas outlet flow, and the specific method comprises the following steps:
step S1: generating a training data set by using historical manual furnace burning data;
step S11: screening historical data with a gas flow greater than M, wherein M is a preset value, preferably m=200;
the difference between adjacent index in the screened data is smaller than L, which is considered to be in the same combustion period, wherein L is a preset value, and preferably L=30; otherwise, the data is considered as the data of another combustion period, so that complete combustion period data is obtained, and the data is screened according to the fact that the data quantity of the combustion period is larger than P; to obtain complete combustion cycle data; wherein P is a preset value, preferably p=100;
step S12: calculating average vault temperature, vault temperature standard deviation, vault temperature maximum value, vault temperature minimum value and average value of heat value point multiplied by gas flow in each combustion cycle to generate new screening conditions;
step S13: according to the new screening conditions in the step S12, two data sets are obtained respectively, then the combustion period data with the combustion period both appearing in the two data sets is taken, and then the data after D minutes of each combustion period are taken, wherein D is a preset value, and preferably d=3; label of the data is vault temperature at time t+1, variables are combustion time, vault temperature (right) of F minutes before time t, flue temperature of F minutes before time t, and finally the variables are saved as csv file; wherein F is a preset value, preferably f=5;
step S14: taking data after D minutes of each combustion period of the data screened in the step S11, wherein Label of the data is gas flow at time t+1, variables are combustion time, heat value from F to Z minutes before time t, vault temperature from F minutes before time t, and gas flow from F minutes before time t, and finally storing the data as a csv file; wherein Z is a preset value, preferably z=9;
step S2: training a predicted dome temperature model and a predicted gas flow model using the two data sets;
step S21: training a prediction dome temperature model, wherein Label of training data is dome temperature at time t+1, and variables are dome temperature (right) of F minutes before the time t and a model of flue temperature of F minutes before the time t;
step S22: a ten-fold cross-validation comparison common machine learning method is adopted; according to the absolute error mean value, the mean square error, the determinable coefficient and the like as selection model standards, an extreme random tree model is selected after the selection model standards are comprehensively selected; the extreme random tree model is saved;
step S23: training a predicted gas flow model, wherein the training Label is the gas flow at the time t+1, and the variables are the combustion time, the heat value from F to Z minutes before the time t of the combustion, the vault temperature of F minutes before the time t of the combustion, and the gas flow model of F minutes before the time t of the combustion;
step S24: a ten-fold cross-validation comparison common machine learning method is adopted; selecting an extreme random tree model according to the absolute error mean, the mean square error, the determinable coefficient and the like as selection model standards, and comprehensively selecting the model standards; the extreme random tree model is saved;
step S25: each furnace is provided with two models, model prediction is carried out, the dome temperature, the combustion time, the heat value of F minutes before the combustion time t, the flue temperature of F minutes before the combustion time t, the dome temperature (right) of F minutes before the combustion time t and the gas flow of F minutes before the combustion time t which are predicted by the dome temperature models are input into a predicted gas flow model, and the gas flow at the time t+1 is obtained;
step S3: processing the parameters transmitted to the PID module to obtain output gas flow; the method for processing parameters by 3 furnaces is similar, and the processing flow of the furnace No. 1 is described as follows:
step S31: judging whether the furnace starts burning or not according to the burning time being more than 0, and predicting the vault temperature at the time t+1 according to the vault temperature at the time t, the top 5 minutes at the time t and the flue temperature at the top 5 minutes at the time t;
step S32: according to the fact that the combustion time t is smaller than 90 minutes, updating the predicted vault temperature at the time t+1, and taking the predicted vault temperature at the time t+1 and 1295 minimum value; otherwise, jumping to step S33;
step S33: according to the combustion time t being greater than 25 minutes and the combustion time t being less than 45 minutes, updating the dome temperature at the time t+1, and taking the maximum value of the dome temperature at the time t+1 and 1280 updated in the step S32; otherwise, jumping to step S34;
step S34: inputting data of the dome temperature at the time t-1, the dome temperature at the first 5 minutes at the time t-1 and the flue temperature at the first 5 minutes at the time t-1 into a dome temperature prediction model to obtain the dome temperature at the time t prediction;
step S35: according to the fact that the combustion time t-1 is smaller than 90 minutes, updating the predicted vault temperature at the time t, and taking the predicted vault temperature at the time t and the 1295 minimum value; otherwise, jumping to step S36;
step S36: according to the combustion time t-1 being more than 25 minutes and the combustion time t-1 being less than 45 minutes, the dome temperature at the moment t is updated, and the updated dome temperature at the moment t and the maximum value of 1280 in the step S35 are the maximum value; otherwise, jumping to step S37;
step S37: if the combustion time t is less than 5, outputting a fixed gas flow; if the combustion time t is more than or equal to 5, and the absolute error between the updated predicted vault temperature at the moment t and the current vault temperature at the moment t is less than 3, outputting the corrected gas flow; if the combustion time t is greater than or equal to 5 and the absolute error between the dome temperature at the predicted time t and the current dome temperature at the time t is greater than 3, inputting the combustion time t, the calorific value of F minutes before the time t of the combustion, the flue temperature of F minutes before the time t of the combustion, the dome temperature at the predicted time t+1 of the combustion and the gas flow of F minutes before the time t of the combustion into a predicted gas flow model to obtain the gas flow at the time t+1, updating the gas flow at the time t+1, and taking the minimum value of the recommended gas flow plus 1500 and the gas flow at the time t+1; and updating the gas flow at the time t+1 again, and taking the maximum value of the recommended gas flow minus 1500 and the gas flow at the time t+1 to obtain the final updated gas flow.
The gas flow correction formula for 3 furnaces:
furnace number 1 corrected gas flow = 2/3 recommended t moment gas flow +1/3*t moment gas flow-300+ (update predicted t moment dome temperature-t moment current dome temperature) 300;
furnace number 2 corrected gas flow = 2/3 recommended t moment gas flow +1/3*t moment gas flow-300+ (updated predicted t moment dome temperature-t moment current dome temperature) 300;
furnace number 3 corrected gas flow = 2/3 recommended t moment gas flow +1/3*t moment gas flow-200+ (update predicted t moment dome temperature-t moment current dome temperature) 600;
3 fixed gas flow formulas of the furnaces:
furnace No. 1 fixed gas flow = 30000 x 3300/t moment heating value;
furnace No. 2 fixed gas flow = 28000 x 3300/t moment heating value;
furnace No. 3 fixed gas flow = 27500 x 3300/t moment heating value;
step S38: finally outputting the gas flow;
generating new screening conditions in step S12 includes:
step S121: describing the relationship between the vault temperature maximum value of each combustion cycle and the average value of the heat value point of each combustion cycle multiplied by the gas flow, and can be seen through a scatter diagram of the vault temperature maximum value of each combustion cycle and the average value of the heat value point of each combustion cycle multiplied by the gas flow; the threshold value of the index is conveniently obtained;
step S122: describing the relationship between the average value of the heat value point of each combustion cycle multiplied by the gas flow and the highest air supply temperature in the air supply cycle after the combustion cycle is finished, wherein the relationship can be seen through a scatter diagram of the average value of the heat value point of each combustion cycle multiplied by the gas flow and the highest air supply temperature in the air supply cycle after the combustion cycle is finished; the threshold value of the air supply temperature index is conveniently obtained;
step S123: according to the two scatter diagrams and the average vault temperature, vault temperature standard deviation, vault temperature maximum value, vault temperature minimum value, heat value point multiplied by the average value of gas flow and air supply temperature of each combustion period, the air supply temperature is the highest air supply temperature of the same furnace in the air supply period after the end of each combustion period, two conditions of screening one combustion period and one air supply period are obtained: 1. the average value of the heat value points of the same furnace in the combustion period multiplied by the gas flow is smaller than 0.3 quantile after the average value of the heat value points of the same furnace in each combustion period multiplied by the gas flow in all combustion periods is ordered, so that the threshold value of the gas quantity is saved; 2. the highest supply air temperature of the supply air period after the combustion period of the same furnace is over 1193, and the threshold value of the supply air temperature; to illustrate how two screening conditions are obtained, the following table is used to illustrate:
note that: x1, x 2..is the mean of the heat value point of each combustion period multiplied by the gas flow; y1, y 2..is the highest supply air temperature for the supply air period of the furnace after each combustion period is completed; the 0.3 quantiles of the heat value point multiplied by the mean value of the gas flow are obtained by sorting x1, x2, x 3.
When the ignition device is used, the opening degree of the gas electric valve and the opening degree of the air electric valve are predicted through the feedback prediction model, the ignition temperature, the gas flow and the air flow of the ignition furnace are obtained in real time, and the ignition temperature, the gas flow and the air flow are integrated and marked as input data; acquiring a feedback prediction model; inputting input data into a feedback prediction model to obtain an output result and marking the output result as a prediction label, wherein the prediction label is a state label corresponding to the input data; the state label is sent to a server, and the server adjusts the opening degree of the electric valve and the opening degree of the air electric valve according to the state label; the method for acquiring the feedback prediction model specifically comprises the following steps: acquiring historical ignition furnace working condition data through a storage module; the ignition furnace working condition historical data comprise ignition temperature, gas flow and air flow which are N minutes before the gas electric valve opening degree and the air electric valve opening degree are adjusted; setting a state label for the historical data of the ignition furnace working condition; the state label comprises the opening degree of the gas electric valve, the opening degree of the air electric valve and state parameters; the state parameter is used for judging whether the state of the computing process is normal or not by the global state parameter judging module; constructing an artificial intelligent model, and dividing communication history data and corresponding state labels into a training set, a testing set and a checking set according to a set proportion; the set proportion includes 3:2: 2. 3:2:1 and 3:1:1, a step of; training, testing and checking the artificial intelligent model through the training set, the testing set and the checking set; and marking the trained artificial intelligent model as a feedback prediction model.
The method comprises the steps of evaluating a prediction result of a feedback prediction model through an evaluation correction unit, relearning the feedback prediction model, obtaining recording data for adjusting the opening degree of an electric valve and the opening degree of an air electric valve according to the prediction result and corresponding burning conditions of a sintered material surface, setting a scoring table according to the obtained recording data and the corresponding burning conditions of the sintered material surface, adjusting the scoring table according to the actual conditions of customers, wherein the scoring table comprises a sintered material surface burning condition comparison image, matching the obtained corresponding sintered material surface burning image with the sintered material surface burning condition comparison image in the scoring table, obtaining a corresponding prediction result score, when the prediction result score is qualified, not operating, obtaining corresponding recording data when the prediction result score is unqualified, modifying the opening degree of the electric valve and the opening degree of the air electric valve in the recording data, marking the modified electric valve opening degree, the air electric valve opening degree and the corresponding input data as self-learning data, and inputting the self-learning data into the feedback prediction model for relearning.
The system link state heartbeat detection is carried out through an emergency module, and the emergency treatment is carried out on the detection result, and the specific method comprises the following steps: acquiring abnormal states of a system link in real time, wherein the abnormal states of the system link comprise server shutdown, network interruption and switch failure, when the abnormal states of the link exist, heartbeat signals are interrupted, and when the interruption of the heartbeat signals is detected, the system is switched back to the original control system to continuously control the hot blast stove; the global state parameter judging module is used for judging state parameters contained in a state label in the feedback prediction model, marking the normal state as 1 when the calculation process is normal, marking the abnormal state as 0 when the calculation process is abnormal, sending a judging result to the server, and when the parameters received by the server are 0, not executing the adjustment tasks of the gas electric valve opening degree and the air electric valve opening degree, automatically switching to manual control, generating an alarm signal and sending the alarm signal to the alarm unit; setting an input data limiting range and an output data limiting range in a feedback prediction model, analyzing the input data and the output data in the feedback prediction model, generating a state parameter of 0 when the input data is not in the input data limiting range or the output data is not in the output data limiting range, generating a state parameter of 1 when the input data is in the input data limiting range or the output data is in the output data limiting range, transmitting the state parameter to a server, and when the parameters received by the server are 0, not executing the adjustment tasks of the gas electric valve opening degree and the air electric valve opening degree, automatically switching to manual control, generating an alarm signal and transmitting the alarm signal to an alarm unit; the picture display module is used for displaying technological process and working condition parameters, and is provided with an alarm unit, a printing unit and a history trend unit, wherein the alarm unit receives alarm signals sent by the server and sends alarm information to an administrator to remind the administrator that the system is manually controlled.
In the description of the present specification, the descriptions of the terms "one embodiment," "example," "specific example," and the like, mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature. In the description of the present invention, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.
The foregoing is merely illustrative and explanatory of the invention, as it is well within the scope of the invention as claimed, as it relates to various modifications, additions and substitutions for those skilled in the art, without departing from the inventive concept and without departing from the scope of the invention as defined in the accompanying claims.
Claims (8)
1. The intelligent control system of the sintering machine ignition furnace is characterized by comprising an enhanced learning module, a server, a storage module, a global state parameter judging module, an emergency module and a picture display module;
the reinforcement learning module is used for predicting the gas outlet flow, and the specific method comprises the following steps:
step S1: generating a training data set by using historical manual furnace burning data;
step S11: screening historical data by using coal gas with the flow rate greater than M, wherein the difference value of adjacent index in the screened data is smaller than L, and is considered to be in the same combustion period, otherwise, the data is considered to be in another combustion period, so that complete combustion period data is obtained, and the data quantity according to the combustion period is greater than P;
step S12: calculating average vault temperature, vault temperature standard deviation, vault temperature maximum value, vault temperature minimum value and average value of heat value point multiplied by gas flow in each combustion cycle to generate new screening conditions;
step S13: according to the new screening conditions in the step S12, two data sets are obtained respectively, then combustion period data with combustion periods both appearing in the two data sets are taken, then data after D minutes of each combustion period are taken, label of the data is dome temperature at time t+1, variables are combustion time, dome temperature (right) of F minutes before time t and flue temperature of F minutes before time t, and finally the data are stored as a csv file;
step S14: taking data after D minutes of each combustion period of the data screened in the step S11, wherein Label of the data is gas flow at time t+1, variables are combustion time, heat value from F to Z minutes before time t, vault temperature from F minutes before time t, and gas flow from F minutes before time t, and finally storing the data as a csv file;
step S2: training a predicted dome temperature model and a predicted gas flow model using the two data sets;
step S21: training a prediction dome temperature model, wherein Label of training data is dome temperature at time t+1, and variables are dome temperature (right) of F minutes before the time t and a model of flue temperature of F minutes before the time t;
step S22: a ten-fold cross-validation comparison common machine learning method is adopted; according to the absolute error mean value, the mean square error and the determinable coefficient as selection model standards, an extreme random tree model is selected after the selection model standards are integrated; the extreme random tree model is saved;
step S23: training a predicted gas flow model, wherein the training Label is the gas flow at the time t+1, and the variables are the combustion time, the heat value from F to Z minutes before the time t of the combustion, the vault temperature of F minutes before the time t of the combustion, and the gas flow model of F minutes before the time t of the combustion;
step S24: a ten-fold cross-validation comparison common machine learning method is adopted; selecting an extreme random tree model according to the absolute error mean, the mean square error and the determinable coefficient as selection model standards and comprehensively selecting the model standards; the extreme random tree model is saved;
step S25: each furnace is provided with two models, model prediction is carried out, the dome temperature, the combustion time, the heat value of F minutes before the combustion time t, the flue temperature of F minutes before the combustion time t, the dome temperature (right) of F minutes before the combustion time t and the gas flow of F minutes before the combustion time t which are predicted by the dome temperature models are input into a predicted gas flow model, and the gas flow at the time t+1 is obtained;
step S3: and processing the parameters transmitted to the PID module to obtain the output gas flow.
2. The intelligent control system for a sintering machine ignition furnace according to claim 1, wherein generating new screening conditions in step S12 comprises:
step S121: describing the relationship between the maximum value of the dome temperature of each combustion cycle and the mean value of the heat value point multiplied by the gas flow of each combustion cycle;
step S122: describing the relationship between the average value of the heat value point multiplied by the gas flow rate of each combustion period and the highest air supply temperature in the air supply period after the combustion period is finished;
step S123: and obtaining two screening conditions according to the two scatter diagrams and the average vault temperature, the vault temperature standard deviation, the vault temperature maximum value, the vault temperature minimum value, the average value of the heat value multiplied by the gas flow and the air supply temperature of each combustion cycle.
3. The intelligent control system of the sintering machine ignition furnace according to claim 1, wherein the emergency module is used for detecting a system link state heartbeat and performing emergency treatment on a detection result, and the specific method comprises the following steps: the abnormal state of the system link is obtained in real time, the abnormal state of the system link comprises a server shutdown, a network interruption and a switch failure, when the abnormal state of the link exists, a heartbeat signal interruption is caused, and when the heartbeat signal interruption is detected, the original control system is switched back to continuously control the hot blast stove.
4. The intelligent control system of the sintering machine ignition furnace according to claim 1, wherein the picture display module is used for displaying technological process and working condition parameters, and is provided with an alarm unit, a printing unit and a historical trend unit, and the alarm unit receives alarm signals sent by a server and sends alarm information to an administrator.
5. The intelligent control system of the ignition furnace of the sintering machine according to claim 1, wherein the global state parameter judging module is used for judging a calculation process in the reinforcement learning module, marking a normal state as 1 when the calculation process is normal, marking an abnormal state as 0 when the calculation process is abnormal, sending a judging result to the server, and when a parameter received by the server is 0, not executing a gas flow regulation task, automatically switching to manual control, generating an alarm signal and sending the alarm signal to the alarm unit; setting an input data limiting range and an output data limiting range of the reinforcement learning module, analyzing the input data and the output data, generating a state parameter of 0 when the input data is not in the input data limiting range or the output data is not in the output data limiting range, generating a state parameter of 1 when the input data is in the input data limiting range or the output data is in the output data limiting range, transmitting the state parameter to a server, and when the parameter received by the server is 0, not executing a gas flow regulation task, automatically switching to manual control, generating an alarm signal and transmitting the alarm signal to an alarm unit.
6. The intelligent control system of the ignition furnace of the sintering machine according to claim 4, wherein corresponding display nodes are arranged at working positions of workers in a line, and corresponding data display is performed through the display nodes.
7. The intelligent control system of a sintering machine ignition furnace of claim 6, wherein the working method of the display node comprises the following steps:
determining each target item data, collecting each target conversion mode corresponding to the target item data, screening the obtained target conversion modes, obtaining an implementation conversion mode corresponding to the target item data, carrying out real-time conversion on corresponding professional display data displayed in a picture display module based on each implementation conversion mode, and carrying out real-time display on each converted target item data in a display interface.
8. The intelligent control system for a sintering machine ignition furnace according to claim 7, wherein the method for screening the obtained target conversion mode comprises the following steps:
obtaining application scores corresponding to all target conversion modes, evaluating the implementation of all target conversion modes to obtain corresponding correction coefficients, and calculating corresponding priority values QY according to a priority formula QY=c×YZ, wherein c is a correction coefficient; YZ is the application score; and selecting the target conversion mode with the highest priority value as the implementation conversion mode of the target item data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310460085.0A CN116182564B (en) | 2023-04-26 | 2023-04-26 | Intelligent control system for ignition furnace of sintering machine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310460085.0A CN116182564B (en) | 2023-04-26 | 2023-04-26 | Intelligent control system for ignition furnace of sintering machine |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116182564A true CN116182564A (en) | 2023-05-30 |
| CN116182564B CN116182564B (en) | 2024-01-23 |
Family
ID=86444656
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310460085.0A Active CN116182564B (en) | 2023-04-26 | 2023-04-26 | Intelligent control system for ignition furnace of sintering machine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116182564B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104613772A (en) * | 2014-12-27 | 2015-05-13 | 马钢(集团)控股有限公司 | Sintering ignition furnace device based on image recognition and combustion control method of sintering ignition furnace device |
| CN106657290A (en) * | 2016-12-05 | 2017-05-10 | 深圳市图焌科技有限公司 | Broadband data communication technology-based elevator Internet-of-Things system and control method |
| CN109179239A (en) * | 2018-10-24 | 2019-01-11 | 廊坊新赛浦特种装备有限公司 | A kind of hydraulic logging winch system |
| EP3741214A1 (en) * | 2019-05-20 | 2020-11-25 | BASF Agro Trademarks GmbH | Method for plantation treatment based on image recognition |
| CN112329269A (en) * | 2020-11-27 | 2021-02-05 | 中国地质大学（武汉） | Sintering ignition temperature modeling prediction method based on working condition identification |
| CN114622048A (en) * | 2022-03-15 | 2022-06-14 | 恒创数字科技(江苏)有限公司 | Combustion optimization system and method for hot blast stove |
| CN115268539A (en) * | 2022-09-27 | 2022-11-01 | 河北国正宏源科技有限公司 | Intelligent granulating control system and method for sintering mixture |
| CN115908051A (en) * | 2022-11-29 | 2023-04-04 | 国网冀北电力有限公司智能配电网中心 | Method for determining energy storage capacity of power system |
-
2023
- 2023-04-26 CN CN202310460085.0A patent/CN116182564B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104613772A (en) * | 2014-12-27 | 2015-05-13 | 马钢(集团)控股有限公司 | Sintering ignition furnace device based on image recognition and combustion control method of sintering ignition furnace device |
| CN106657290A (en) * | 2016-12-05 | 2017-05-10 | 深圳市图焌科技有限公司 | Broadband data communication technology-based elevator Internet-of-Things system and control method |
| CN109179239A (en) * | 2018-10-24 | 2019-01-11 | 廊坊新赛浦特种装备有限公司 | A kind of hydraulic logging winch system |
| EP3741214A1 (en) * | 2019-05-20 | 2020-11-25 | BASF Agro Trademarks GmbH | Method for plantation treatment based on image recognition |
| CN112329269A (en) * | 2020-11-27 | 2021-02-05 | 中国地质大学（武汉） | Sintering ignition temperature modeling prediction method based on working condition identification |
| CN114622048A (en) * | 2022-03-15 | 2022-06-14 | 恒创数字科技(江苏)有限公司 | Combustion optimization system and method for hot blast stove |
| CN115268539A (en) * | 2022-09-27 | 2022-11-01 | 河北国正宏源科技有限公司 | Intelligent granulating control system and method for sintering mixture |
| CN115908051A (en) * | 2022-11-29 | 2023-04-04 | 国网冀北电力有限公司智能配电网中心 | Method for determining energy storage capacity of power system |
Non-Patent Citations (1)
| Title |
|---|
| 金龙哲 等: "《安全学原理》", 冶金工业出版社, pages: 207 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116182564B (en) | 2024-01-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102364252B (en) | Automatic intelligent double cross limiting range combustion control method for heating furnace | |
| CN110486749B (en) | Thermal power generating unit boiler combustion optimization control method and system | |
| CN105157057B (en) | Combustion of Hot Air Furnace control method and system | |
| CN101995822A (en) | Grey active disturbance rejection control method of long time-delay system | |
| CN105925750A (en) | Steelmaking end point prediction method based on neural networks | |
| CN104778361B (en) | The method of modified EMD Elman neural network prediction molten iron silicon contents | |
| CN115141926B (en) | Method for generating billet target heating curve for guiding billet heating process control | |
| CN106773682A (en) | Based on the glass furnace bottom of pond temperature intelligent forecast Control Algorithm that time lag is dynamically determined | |
| CN114622048B (en) | Hot blast stove combustion optimization system and method | |
| CN107368125A (en) | A kind of blast furnace temperature control system and method based on CBR Yu the parallel mixed inferences of RBR | |
| CN109489261A (en) | A kind of hot-blast stove Intellectualized controller that can be monitored in real time | |
| CN111340269B (en) | Real-time optimization method for process industrial process | |
| CN102759939B (en) | Control system and control method of annealing furnace | |
| CN116182564B (en) | Intelligent control system for ignition furnace of sintering machine | |
| Geng et al. | Prediction of the cement grate cooler pressure in the cooling process based on a multi-model fusion neural network | |
| CN104763536A (en) | Method and system for combustion mode transfer for a gas turbine engine | |
| JP3231745B2 (en) | Adaptive control method and apparatus in thermal power plant | |
| CN115198047B (en) | Hot blast stove combustion monitoring system and method based on big data analysis | |
| CN109055700B (en) | Method and device for self-optimizing air-fuel ratio of annealing furnace | |
| CN115287446B (en) | Intelligent heating furnace remote big data centralized control system | |
| CN102876822A (en) | Blast furnace operation closed-loop control system | |
| CN116179840A (en) | Laser surface heat treatment temperature monitoring control system and control method | |
| Koyfman et al. | Using of Intelligence Analysis of Technological Parameters Database for Implementation of Control Subsystem of Hot Blast Stoves Block ACS. | |
| CN108594782A (en) | Periodic aluminium coiled material n 2 annealing stove intelligent self-diagnosing system | |
| TWI779724B (en) | Method and system of operating a furnace, computer readable medium having a program stored thereon for carrying out the method |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |