Electrode melting rate intelligent control system based on start-stop control

Abstract

The invention discloses an intelligent electrode melting rate control system based on start-stop control, and relates to the technical field of electrode melting rate control. According to the intelligent electrode melting rate control system, alternative melting rate intervals of electrodes are obtained through analysis according to quality constraints, and then the alternative melting rate intervals are screened according to environmental protection constraints; and finally, the deviation correction rate of the electrode is obtained through analysis based on the optimal melting rate interval of the electrode, the deviation correction duration is compared with the time point interval duration during deviation correction, and then deviation correction or operation stopping is judged. According to the method, limitation caused by single quality constraint or single environment-friendly constraint is avoided, the problem of target weakening caused by traditional weight setting is also avoided, meanwhile, molten steel quality fluctuation caused by the fact that correction is not thorough and still deviates from the interval during deviation correction is avoided, and the quality stability of products is guaranteed.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of electrode melting rate control, and particularly relates to an electrode melting rate intelligent control system based on start-stop control. BACKGROUND

[0002] In the smelting process of metal materials, the electrode generates an electric arc or resistance heat through power supply, converts electric energy into heat energy, makes the metal material reach the melting temperature, and forms uniform molten steel. The melting rate of the electrode directly affects the melting degree of the metal raw material, the composition and temperature of the molten steel, etc. Controlling the melting rate of the electrode not only ensures the quality of the metal product, but also reduces the safety risk of the equipment. Therefore, it is crucial to control the melting rate of the electrode.

[0003] The prior art has some deficiencies in controlling the electrode melting rate, which are embodied in the following aspects: the prior art mostly associates the electrode melting rate with the product quality or the equipment safety situation, and then controls the electrode melting rate, without considering that the total amount of harmful substances generated is also greatly different when the electrode melting rate is different. Therefore, the current technology for controlling the electrode melting rate is not optimal. Meanwhile, the current technology does not consider the influence of the deviation adjustment rate and the deviation adjustment time length on the product quality in the aspect of deviation adjustment of the electrode melting rate, and it is difficult to adapt to the smelting scene with high requirements for the product. SUMMARY

[0004] In view of the above technical deficiencies, the purpose of the present application is to provide an electrode melting rate intelligent control system based on start-stop control.

[0005] To solve the above technical problems, the present application adopts the following technical scheme: the present application provides an electrode melting rate intelligent control system based on start-stop control, which comprises: an information acquisition module: used for acquiring device information, process conditions, environmental information and production information in a target factory from a management center.

[0006] A melting rate analysis module: used for performing melting tests on each raw material steel of the target factory, training an electrode melting rate decision model according to the test results, analyzing to obtain an electrode candidate melting rate interval corresponding to the target raw material steel, performing an environmental protection test on the target raw material steel according to the electrode candidate melting rate interval, obtaining an electrode optimal melting rate interval corresponding to the target raw material steel, and finally testing the optimal deviation correction rate of the target raw material steel according to the optimal melting rate interval.

[0007] A detection module: used for monitoring the electrode melting rate in real time through a sensing device during the electrode melting process.

[0008] The control module is used for acquiring electrode melting rate data at a plurality of continuous time points in the past, predicting the electrode melting rate at a next time point, and sending a control instruction to the execution terminal according to the prediction result.

[0009] The execution module is used for receiving the instruction of the control module and executing a corresponding control operation.

[0010] The present application has the following advantages: 1. The present application firstly trains a target factory-specific electrode melting rate decision model according to various types of information of the target factory, then analyzes an electrode melting rate interval suitable for production requirements, and further screens the electrode melting rate interval suitable for quality requirements based on environmental protection requirements to obtain an optimal electrode melting rate interval, thereby avoiding the limitations caused by single quality constraint or single environmental protection requirement constraint, avoiding the problem of losing one thing to gain another caused by traditional weight setting, ensuring the unique priority of quality constraint, and finally obtaining an optimal deviation correction rate based on the optimal melting rate interval, which is specifically adapted to the optimal melting rate interval, thereby improving the correction accuracy by nearly 90%, and avoiding the production risks such as electrode loss caused by general correction rate.

[0011] 2. The present application analyzes the correction duration of the melting rate deviation according to the deviation correction rate, compares the correction duration with the time point interval duration, judges whether to correct or stop, and avoids the risk of invalid correction. When the correction duration is insufficient, forcibly adjusting the electrode rate may cause system shock and electrode impact, and aggravate equipment wear or failure. At this time, the machine is directly stopped, effectively avoiding such mechanical loss and prolonging the service life of the equipment. BRIEF DESCRIPTION OF DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description only constitute some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor.

[0013] Figure 1 The present application is a system structure connection diagram. DETAILED DESCRIPTION

[0014] The technical solutions in the embodiments of the present application will be described clearly and completely in the following with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments only constitute some embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0015] Referring to Figure 1 The first aspect of the present application provides an electrode melting rate intelligent control system based on start-stop control, comprising: an information acquisition module: used for acquiring device information, process conditions, environmental information and production information in a target factory from a management center.

[0016] In a specific example, the device information includes smelting device information and auxiliary device information; the process conditions include melting process type and slag characteristics; the environmental information includes physical environment parameters and environmental interference parameters; and the production information includes raw steel information and production plan information.

[0017] It should be noted that the smelting device information includes the size, capacity and working parameters of the electric arc furnace and the electroslag furnace in the target factory, the type, material and size of the electrode used in the target factory, and the working parameters of the power supply device; the auxiliary device information includes the model and parameters of the cooling device, ventilation device and monitoring device; the physical environment parameters include the temperature range, humidity range, air pressure range and dust concentration range in the workshop; the environmental interference parameters include the fluctuation interference range of voltage and the vibration interference range generated by adjacent devices; the raw steel information includes the model of raw steel and the size and weight of the ingot; and the production plan information includes historical production plan information and expected production plan information.

[0018] It should be noted that the production plan information includes the size, shape, weight and allowable deviation, technical requirements, test methods, inspection rules, packaging, labeling and quality certificate requirements of the target die steel produced.

[0019] A melting rate analysis module: used for melting test on each raw steel of the target factory, and training an electrode melting rate decision model according to the test results, and then analyzing to obtain the electrode candidate melting rate interval corresponding to the target raw steel, and then performing environmental test on the target raw steel according to the electrode candidate melting rate interval, to obtain the electrode optimal melting rate interval corresponding to the target raw steel, and finally testing the optimal deviation correction rate of the target raw steel according to the optimal melting rate interval.

[0020] In one specific example, the raw steels of the target factory are subjected to melting tests, and the specific test process is as follows: a plurality of raw steels of any type are obtained, denoted as test raw steels, and a corresponding consumable electrode is obtained according to the type of the raw steel, denoted as a test electrode; the device information, process conditions and environmental information of the raw steel of the type during historical production are obtained according to historical production information, and the test conditions of the test raw steels are set according to the information, and the test conditions of the test raw steels are kept unchanged; at the same time, the melting rates are set according to a preset gradient, and the test raw steels are subjected to melting tests at the melting rates; after a preset time period of testing, the quality data of the corresponding liquid steel samples at the melting rates are detected, and the type of the raw steel, the test conditions, the melting rates and the quality data of the corresponding liquid steel samples at the melting rates are collectively denoted as test data.

[0021] It should be noted that the test corresponding to each melting rate is repeated three times, and the test data is the average of the three repeated test data.

[0022] It should be noted that the quality data includes the chemical composition content in the mold steel cast from the liquid steel sample, the qualified level of non-metallic inclusions, the grain size, the qualified level of microstructure, the ultrasonic flaw detection result and the number of surface defects.

[0023] It should be noted that the above test method can be used to test the raw steels of various types in the target factory.

[0024] In one specific example, the electrode melting rate decision model is trained according to the test results, and the specific training process is as follows: first, the test data is classified and coded according to the type of the raw steel, and a three-section architecture of a feature extraction layer, a target prediction layer and a rate decision layer is used as the basic architecture of the electrode melting rate decision model; 2 layers of fully connected networks are set in the feature extraction layer to capture the nonlinear correlation between the test data; an output branch is set in the target prediction layer to output the quality data; the rate decision layer is used to select the rate interval of the quality data that meets the set quality data interval as the output electrode candidate melting rate interval; the basic architecture of the electrode melting rate decision model is trained and verified after the test data is preprocessed, and the electrode melting rate decision model of the target factory is obtained.

[0025] It should be noted that the quality data interval is a critical value for evaluating whether the quality of the steel meets the standard, and the higher the requirement for the quality data interval, the higher the requirement for the quality of the steel. The specific value of the quality data interval is obtained from the production requirements of the steel.

[0026] It should be noted that the preprocessing includes outlier rejection, feature selection, data normalization and data set division, etc. Outlier rejection, feature selection, data normalization and data set division are all prior art and will not be described here.

[0027] In one specific example, the analysis obtains an electrode candidate melting rate interval corresponding to the target raw material steel, and the specific process is as follows: obtaining the current production plan according to the production information, and obtaining the model and production requirements of the target die steel corresponding to the target raw material steel according to the current production plan, inputting the model and production requirements into the electrode melting rate decision model, and outputting the electrode candidate melting rate interval of the target raw material steel through the electrode melting rate decision model.

[0028] In one specific example, the target raw material steel is tested according to the electrode candidate melting rate interval to obtain an electrode optimal melting rate interval corresponding to the target raw material steel, and the specific process is as follows: selecting a plurality of completely identical raw material steels based on the model of the target raw material steel, denoted as each test raw material steel, setting each test rate according to the preset gradient based on the candidate melting rate interval corresponding to the target raw material steel, melting each test raw material steel according to each test rate until each test raw material steel is melted into a steel liquid, detecting the total amount of harmful substances generated corresponding to each test rate, and combining each test rate with the lowest total amount of harmful substances to obtain the electrode optimal melting rate interval corresponding to the target raw material steel.

[0029] It should be noted that the specific gradient value of the preset gradient is set by the relevant staff, and is not limited here, wherein the smaller the preset gradient, the more accurate the optimal melting rate interval obtained by the test.

[0030] It should be noted that when the total amount of harmful substances is the lowest and there is only one test rate, the gradient is set with the test rate as the midpoint, and then each test rate is reacquired and each test raw material steel is tested again until the electrode optimal melting rate interval is obtained.

[0031] In one specific example, the optimal deviation correction rate of the target raw material steel is obtained according to the optimal melting rate interval, and the specific analysis process is as follows: selecting a plurality of deviation test raw material steels completely identical to the target raw material steel, dividing each deviation test raw material steel into each control group, and each control group has the same number of several deviation test raw material steels, setting each deviation correction rate corresponding to each melting rate deviation value according to the optimal melting rate interval corresponding to the target raw material steel and the preset gradient, wherein the melting rate deviation values of each deviation test raw material steel in the same control group are the same, correcting each deviation test raw material steel in each control group according to each deviation correction rate, detecting the index information of the steel liquid sample corresponding to each deviation correction rate after the correction is completed, and obtaining the mean value of each deviation correction rate corresponding to the steel liquid sample most consistent with the standard index information in each control group, denoted as the optimal deviation correction rate of the target raw material steel.

[0032] It should be noted that the index information includes melting uniformity, component consistency and grain refinement degree, and the standard index information is the quality data requirement specified in the target raw steel production requirement.

[0033] The detection module is used to monitor the electrode melting rate in real time through the sensing device during the electrode melting process.

[0034] It should be noted that the initial weight of the electrode is measured by the pressure sensor, and the remaining weight of the electrode is collected in real time during the operation of the electrode, and the melting time is recorded, and the melting rate of the electrode at the current time point is calculated by the initial weight, the remaining weight, the working time and the melting rate at each historical time point.

[0035] The control module is used to obtain the electrode melting rate data at a plurality of continuous historical time points, and then predict the electrode melting rate at the next time point, and send a control instruction to the execution terminal according to the prediction result.

[0036] In one specific example, the electrode melting rate data at a plurality of continuous historical time points is obtained, and then the electrode melting rate at the next time point is predicted, and the specific process is as follows: the electrode melting rate monitored at a plurality of continuous historical time points is obtained from the data center, the change characteristics of the electrode melting rate are captured through a time series prediction algorithm, and then the melting rate of the electrode at the next time is predicted.

[0037] It should be noted that the plurality of continuous historical time points are a plurality of continuous time points before the current time point, including the current time point.

[0038] It should be noted that the time series prediction algorithm includes LSTM, ARIMA and XGBoost, wherein LSTM, ARIMA and XGBoost are all existing algorithm technologies, and therefore will not be described again.

[0039] Exemplarily, after the electrode melting rate data at a plurality of continuous historical time points is preprocessed, the LSTM model is input, and the RMSE and MAE are used as indexes to adjust the model parameters, and the model is trained and optimized accordingly, wherein the model parameters include the number of hidden layer nodes of LSTM, etc., and the model calculates and directly outputs the electrode melting rate prediction value at the next time point at the current time point. Each new actual monitoring value is incrementally trained, thereby ensuring the timeliness of the prediction.

[0040] In one specific example, the control instruction is sent to the execution terminal according to the prediction result, and the specific process is as follows: the melting rate of the electrode at the next time point is compared with the optimal melting rate interval and the alternative melting rate interval of the electrode, when the electrode melting rate at the next time point belongs to the optimal melting rate interval, the control instruction 00 is sent to the execution terminal; when the electrode melting rate at the next time point does not belong to the alternative melting rate interval, the control instruction 11 is sent to the execution terminal, when the electrode melting rate at the next time point does not belong to the optimal melting rate interval but belongs to the alternative melting rate interval, the deviation correction duration is calculated according to the optimal deviation correction rate and the deviation amount at the next time point, the deviation correction duration is compared with the time point interval duration, if the deviation correction duration is less than or equal to the time point interval duration, the control instruction 010 is sent to the execution terminal, otherwise the control instruction 011 is sent to the execution terminal.

[0041] Execution terminal: used for receiving the instruction of the control module and executing the corresponding control operation.

[0042] In one specific example, the control instruction of the control module is received and the corresponding control operation is executed, and the specific process is as follows: when the execution terminal receives the control instruction 00, no operation is performed.

[0043] When the execution terminal receives the control instruction 11, the stop operation is performed.

[0044] When the execution terminal receives the control instruction 010, the deviation correction is performed according to the optimal deviation correction rate; when the execution terminal receives the control instruction 011, the stop operation is performed.

[0045] It should be noted that when the electrode melting rate at the next time point is predicted to deviate, the deviation correction is immediately performed at the current time point until the electrode melting rate at the next time point is predicted to be not deviated.

[0046] It should be noted that the correction duration for the melting rate deviation is obtained by analyzing the deviation correction rate, when the correction duration is greater than the time point interval duration, it means that the deviation correction cannot be completed before the next monitoring, at this time the stop operation is performed, which can avoid the quality fluctuation of the molten steel caused by incomplete correction and deviating from the interval, and reduce the invalid resource consumption such as electric energy and electrode loss in the correction process.

[0047] It should be noted that after the stop operation is performed, the related staff checks the abnormal reasons, including the prediction model accuracy, the electrode state, the raw material characteristics and the equipment failure, and then a targeted treatment scheme is developed.

[0048] The application provides an electrode melting rate intelligent control system based on start-stop control, first obtains an optional melting rate interval of the electrode according to quality constraint analysis, then screens the optional melting rate interval according to environmental protection constraint, obtains an optimal melting rate interval of the electrode, finally analyzes a deviation correction rate of the electrode based on the optimal melting rate interval of the electrode, compares a deviation correction duration and a time point interval duration when deviation correction is performed, and then judges whether to perform deviation correction or stop operation. The application not only avoids limitations caused by single quality constraint or single environmental protection constraint, but also avoids target weakening problems caused by traditional weight setting, and avoids liquid steel quality fluctuation caused by incomplete correction and deviation from the interval when deviation correction is performed, and guarantees product quality stability.

[0049] The examples described in the application are not limited to the specific ways listed in the above embodiments, and the examples are only exemplary descriptions provided for the convenience of understanding the application and do not constitute limitations on the protection scope of the application. Any modifications, equivalent replacements and the like made within the spirit and principle of the application shall be included in the protection scope.

[0050] The above content is only an example and description of the concept of the application, and those skilled in the art can make various modifications or supplements or use similar ways to replace the described specific embodiments, as long as the modifications, supplements or replacements do not deviate from the concept of the application or exceed the range defined in the specification, and all of them shall belong to the protection scope of the application.

Claims

1. A start-stop control based intelligent control system for electrode melting rate, characterized in that, Comprise the following modules: Information acquisition module: for obtaining equipment information, process conditions, environmental information and production information in the target factory from the management center; Melting rate analysis module: for performing melting tests on each raw steel of the target factory, and training an electrode melting rate decision model according to the test results, and then analyzing to obtain the electrode candidate melting rate interval corresponding to the target raw steel, and then performing environmental test on the target raw steel according to the electrode candidate melting rate interval, to obtain the electrode optimal melting rate interval corresponding to the target raw steel, and finally testing the optimal deviation correction rate of the target raw steel according to the optimal melting rate interval; Detection module: for monitoring the electrode melting rate in real time through a sensing device during the electrode melting process; Control module: for obtaining electrode melting rate data at a plurality of consecutive time points in history, and then predicting the electrode melting rate at the next time point, and sending control instructions to the execution terminal according to the prediction results; Execution terminal: for receiving instructions from the control module and performing corresponding control operations.

2. The intelligent control system for electrode melting rate based on start-stop control according to claim 1, characterized in that, The equipment information includes smelting equipment information and auxiliary equipment information; the process conditions include melting process type and slag characteristics; the environmental information includes physical environmental parameters and environmental interference parameters; the production information includes raw steel information and production plan information.

3. The intelligent electrode melting rate control system based on start-stop control according to claim 2, characterized in that, The melting test on each raw steel of the target factory is as follows: Obtain a plurality of raw steels of any type, denoted as each test raw steel, and obtain the corresponding consumable electrode according to the type of the raw steel, denoted as the test electrode, obtain the equipment information, process conditions and environmental information of the raw steel of this type during the historical production according to the historical production information, set the test conditions of each test raw steel according to the above information, and keep the test conditions of each test raw steel unchanged, and set the melting rate according to the preset gradient, melt each test raw steel according to each melting rate, test for a preset period of time, detect the quality data of the corresponding liquid steel sample under each melting rate, and comprehensively record the raw steel type, test conditions, each melting rate and the quality data of the corresponding liquid steel sample under each melting rate as test data.

4. The intelligent electrode melting rate control system based on start-stop control according to claim 3, characterized in that, The training of the electrode melting rate decision model according to the test results is as follows: First, classify and encode each test data according to the type of the raw steel, and use a three-section architecture of a feature extraction layer, a target prediction layer and a rate decision layer as the basic architecture of the electrode melting rate decision model, set a 2-layer fully connected network in the feature extraction layer to capture the nonlinear correlation between the test data, set an output branch in the target prediction layer to output the quality data, and set the rate decision layer to filter the rate interval of the quality data that meets the set quality data interval as the output electrode candidate melting rate interval, and then train and verify the basic architecture of the electrode melting rate decision model after preprocessing each test data, to obtain the electrode melting rate decision model of the target factory.

5. The intelligent electrode melting rate control system based on start-stop control according to claim 4, characterized in that, The analysis of the electrode candidate melting rate interval corresponding to the target raw steel is as follows: According to the production information, the current production plan is obtained, and the model number and production requirements of the target raw material steel corresponding to the target mold steel are obtained according to the current production plan, and the model number and production requirements are input into the electrode melting rate decision model, and the electrode candidate melting rate interval of the target raw material steel is output through the electrode melting rate decision model.

6. The intelligent electrode melting rate control system based on start-stop control according to claim 5, wherein, The target raw material steel is tested according to the electrode candidate melting rate interval, and the electrode optimal melting rate interval corresponding to the target raw material steel is obtained, and the specific process is as follows: Based on the model number of the target raw material steel, a plurality of completely same raw material steels are selected, which are denoted as each test raw material steel, and each test rate is set according to the candidate melting rate interval corresponding to the target raw material steel according to a preset gradient, and each test raw material steel is melted according to each test rate, until each test raw material steel is melted into a steel liquid, the total amount of harmful substances generated corresponding to each test rate is detected, and each test rate with the lowest total amount of harmful substances is combined to obtain the electrode optimal melting rate interval corresponding to the target raw material steel.

7. The intelligent electrode melting rate control system based on start-stop control according to claim 6, characterized in that, The optimal deviation correction rate of the target raw material steel is obtained according to the optimal melting rate interval test, and the specific analysis process is as follows: Selecting each deviation test raw material steel completely same as the target raw material steel, the deviation test raw material steel is divided into each control group, and each control group contains the same number of several deviation test raw material steels, and each deviation correction rate corresponding to each melting rate deviation value is set according to the preset gradient according to the optimal melting rate interval corresponding to the target raw material steel, wherein the melting rate deviation values of the deviation test raw material steels in the same control group are the same, and the deviation test raw material steels in each control group are corrected according to the deviation correction rate, and after the correction, the index information of the steel liquid sample corresponding to each deviation correction rate is detected, and the mean value of each deviation correction rate corresponding to the steel liquid sample most meeting the standard index information in each control group is obtained, which is denoted as the optimal deviation correction rate of the target raw material steel.

8. The intelligent electrode melting rate control system based on start-stop control according to claim 7, characterized in that, The electrode melting rate data at a plurality of continuous time points in the history is obtained, and then the electrode melting rate at the next time point is predicted, and the specific process is as follows: The electrode melting rate monitored at a plurality of continuous time points in the history is obtained from the data center, the change characteristics of the electrode melting rate are captured through the time sequence prediction algorithm, and then the melting rate of the electrode at the next time is predicted.

9. The intelligent electrode melting rate control system based on start-stop control according to claim 8, wherein, The control instruction is sent to the execution terminal according to the prediction result, and the specific process is as follows: The melting rate of the electrode at the next time point is compared with the optimal melting rate interval and the alternative melting rate interval of the electrode, when the electrode melting rate at the next time point belongs to the optimal melting rate interval, the control instruction 00 is sent to the execution terminal; when the electrode melting rate at the next time point does not belong to the alternative melting rate interval, the control instruction 11 is sent to the execution terminal, when the electrode melting rate at the next time point does not belong to the optimal melting rate interval but belongs to the alternative melting rate interval, the deviation correction time is calculated according to the optimal deviation correction rate and the deviation amount at the next time point, the deviation correction time is compared with the time point interval time, if the deviation correction time is less than or equal to the time point interval time, the control instruction 010 is sent to the execution terminal, otherwise the instruction 011 is sent to the execution terminal.

10. The intelligent electrode melting rate control system based on start-stop control according to claim 9, wherein, The control instruction of the receiving control module is received, and the corresponding control operation is performed, and the specific process is as follows: When the execution terminal receives the control instruction 00, no operation is performed; When the execution terminal receives the control instruction 11, the stop operation is performed; When the execution terminal receives the control instruction 010, the deviation is corrected according to the optimal deviation correction rate; when the execution terminal receives the control instruction 011, the stop operation is performed.

Images