Electrode working length control method and device

Abstract

The present application provides a method and device for controlling the working length of an electrode. When adjusting the working length of an electrode, the method inputs measurement parameters into a neural network model to obtain the electrode consumption rate of each electrode; and based on the electrode consumption rate and the actual working time of each electrode, the electrode consumption length of each electrode is determined. Then, based on the original length corresponding to each electrode, the exposed length measured in real time, and the determined electrode consumption length, the position of the electrode tip of each electrode deep into the furnace charge is determined. For each electrode, based on the position of the electrode tip of the electrode, the gripper to which the electrode belongs is controlled to raise or lower the depth of the electrode in the furnace charge, so that the depth of each electrode deep into the furnace charge is the same. It can be seen that the technical solution provided by this embodiment can improve the accuracy of electrode length measurement while also meeting the requirements for refined management of electrode working length adjustment and reducing safety hazards.

Description

Technical Field

[0001] The present application relates to the technical field of calcium carbide furnaces, and in particular to a method and device for controlling the working length of an electrode. Background Art

[0002] At present, the measurement of the electrode length of the calcium carbide furnace is generally based on the brazing method. This brazing method requires manual assistance in the process of brazing the electrode length of the calcium carbide furnace to achieve the measurement of the electrode length. This also makes the brazing of the electrode length involve many factors of human participation. For example, different manual operations have different understandings of the working conditions of the calcium carbide furnace, which will lead to operational differences. The output is mainly based on experience judgment, resulting in fluctuating production. The furnace conditions controlled by the manual workers of each shift are different. In addition, the electrode operation is unstable, the three-phase work is unbalanced, the length of the electrode entering the furnace is different, the working conditions are unstable, etc., which will cause large errors in the measurement of the electrode length. In addition, the brazing method cannot achieve real-time monitoring and timely adjustment, which makes it difficult to control the electrode length index and it is difficult to meet the requirements of refined management of the adjustment of the electrode working length. At the same time, the brazing method has the risk of material collapse during the electrode measurement process, which may cause flame-spraying and injury accidents, thus posing a major safety hazard. Summary of the Invention

[0003] In view of this, the present application provides an electrode working length control method and device, which can improve the electrode length measurement accuracy while also meeting the requirements of refined management of electrode working length adjustment and reducing safety hazards.

[0004] Specifically, this application is implemented through the following technical solutions:

[0005] In a first aspect, an embodiment of the present application provides a method for controlling the working length of an electrode. The method is applied to a controller of a pressure-release measuring device, wherein the pressure-release measuring device further includes a synchronous belt provided with a magnetic block, wherein the magnetic block is used to be adsorbed on the outside of a holder for clamping an electrode in a calcium carbide furnace device, and the controller is electrically connected to a position sensor of the calcium carbide furnace device for measuring the exposed length of the electrode exposed to the charge surface. The method includes:

[0006] Obtaining measurement parameters corresponding to each electrode in the calcium carbide furnace device and used to characterize electrode loss;

[0007] Inputting the measurement parameters into a preset neural network model to obtain an electrode loss rate corresponding to each electrode; wherein, when the neural network model is used for the first time, the neural network model is an initially trained neural network model; and when the neural network model is not used for the first time, the trained neural network model is a neural network model obtained through adaptive training using the obtained measurement parameters during the actual use of the neural network model;

[0008] Determine the electrode consumption length corresponding to each electrode according to the electrode consumption rate corresponding to each electrode and the recorded actual working time of each electrode;

[0009] The exposed length of each electrode on the charge surface, as measured by the position sensor, is obtained. Based on the original length, exposed length, and consumed length of each electrode, the position of each electrode's tip within the charge is determined. For each electrode, the gripper associated with that electrode is controlled to raise or lower the electrode within the charge based on the tip's position, ensuring that each electrode penetrates the charge to the same depth.

[0010] In a second aspect, an embodiment of the present application provides an electrode working length control device, which is applied to a controller of a pressure-release measuring device. The pressure-release measuring device also includes a synchronous belt provided with a magnetic block, wherein the magnetic block is used to be adsorbed on the outside of a holder for clamping the electrode in the calcium carbide furnace equipment. The controller is electrically connected to a position sensor of the calcium carbide furnace equipment for measuring the exposed length of the electrode exposed to the charge surface. The device includes:

[0011] A measurement parameter acquisition module is used to obtain the measurement parameters corresponding to each electrode in the calcium carbide furnace equipment and used to characterize the electrode loss;

[0012] An electrode consumption rate module is used to input the measurement parameters into a preset neural network model to obtain the electrode consumption rate corresponding to each electrode; wherein, when the neural network model is used for the first time, the neural network model is an initially trained neural network model; when the neural network model is not used for the first time, the trained neural network model is a neural network model obtained through adaptive training using the obtained measurement parameters during the actual use of the neural network model;

[0013] An electrode consumption length determination module is used to determine the electrode consumption length corresponding to each electrode according to the electrode consumption rate corresponding to each electrode and the recorded actual working time of each electrode;

[0014] The electrode working length control module is used to obtain the exposed length of each electrode exposed to the charge surface measured by the position sensor, and determine the position of the electrode tip of each electrode penetrating into the charge based on the original length, exposed length and electrode consumption length corresponding to each electrode. For each electrode, according to the electrode tip position of the electrode, the holder belonging to the electrode is controlled to raise or lower the depth of the electrode in the charge, so that the depth of each electrode penetrating into the charge is the same.

[0015] It can be seen that the embodiment of the present application provides an electrode working length control method and device. When adjusting the electrode working length, the method inputs the measurement parameters obtained in real time into an adaptively trained and high-precision neural network model to obtain the electrode consumption rate corresponding to each electrode; and determines the electrode consumption length corresponding to each electrode according to the electrode consumption rate corresponding to each electrode and the recorded actual working time of each electrode, and then determines the electrode tip position of each electrode in the charge according to the original length corresponding to each electrode, the exposed length measured in real time and the determined electrode consumption length, so as to control the gripper to which the electrode belongs to raise and lower the depth of the electrode in the charge according to the electrode tip position of the electrode, so that the depth of each electrode in the charge is the same. It can be seen that the application of the technical solution provided in this embodiment basically requires no human intervention, but instead determines the actual length data of the electrode through a high-precision and adaptively trained neural network model. This not only reduces the labor intensity and skill requirements of workers, but also reduces the technical problem of large errors in electrode length measurement caused by human factors. At the same time, it can also make timely adjustments when the electrode length tends to be too long or too short, and control the electrode length within a reasonable range, meeting the requirements of refined management of electrode working length adjustment. In addition, it can also reduce the frequency of electrode measurement and reduce the safety risks brought by electrode measurement. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 This is a flow chart of a method for controlling the working length of an electrode shown in an exemplary embodiment of the present application;

[0017] Figure 2 is a flowchart of an adaptive training of a neural network model shown in an exemplary embodiment of the present application;

[0018] Figure 3 is a flow chart of an electrode management method shown in an exemplary embodiment of the present application;

[0019] Figure 4 1 is a schematic structural diagram of an electrode working length control device according to an exemplary embodiment of the present application;

[0020] Figure 5 This is a structural diagram of an electronic device provided by the present application. DETAILED DESCRIPTION

[0021] Exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. In the following description, when referring to the drawings, identical numerals in different figures represent identical or similar elements, unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.

[0022] The terms used in this application are for the purpose of describing specific embodiments only and are not intended to limit this application. The singular forms "a," "an," and "the" used in this application and the appended claims are also intended to include plural forms unless the context clearly indicates otherwise. It should also be understood that the term "and / or" as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0023] It should be understood that although the terms first, second, third, etc. may be used in this application to describe various information, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from each other. For example, without departing from the scope of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0024] At present, the measurement of calcium carbide furnace electrode length is generally based on the brazing method. In the process of brazing the electrode length of the calcium carbide furnace, this brazing method requires manual assistance to achieve the measurement of the electrode length. This also makes the brazing of the electrode length require many factors of manual participation. These manual participations will cause many problems, which are mainly reflected in the following aspects:

[0025] First, the operating cognition is different. Specifically, manual operation has different understandings of the working conditions of the calcium carbide furnace, which will lead to operational differences. The output fluctuates based on experience, and the furnace conditions controlled by each shift are different.

[0026] Second, electrode management is unstable, specifically: unstable electrode operation, unbalanced three-phase work, different lengths of electrodes entering the furnace, and unstable operating conditions.

[0027] Third, it leads to abnormal working conditions, specifically: the operator needs to be highly concentrated, the labor intensity is high, it is easy to make mistakes due to fatigue, there are many equipment failures, and tendon breaking often occurs.

[0028] Fourth, energy consumption and product quality are unstable. Specifically, different operating levels and operating habits of workers lead to inconsistent operations, resulting in unstable energy consumption and product quality.

[0029] All of these will cause large errors in the measurement of electrode length. In addition, this brazing method cannot achieve real-time monitoring and timely adjustment, which makes it difficult to control the electrode length index and it is difficult to meet the requirements of refined management of the adjustment of the electrode working length. At the same time, this brazing method has the risk of material collapse during the electrode measurement process, which may cause flame-spraying and injury accidents, thus posing a major safety hazard.

[0030] In order to solve the above technical problems, an embodiment of the present application provides an electrode working length control method, which is applied to the controller of a pressure-release measuring device, and the pressure-release measuring device also includes a synchronous belt provided with a magnetic block, wherein the magnetic block is used to adsorb on the outside of a holder for clamping the electrode in the calcium carbide furnace equipment, and the controller and the calcium carbide furnace equipment are electrically connected to a position sensor for measuring the exposed length of the electrode exposed to the charge surface. The method includes: obtaining measurement parameters corresponding to each electrode in the calcium carbide furnace equipment for characterizing the electrode loss; inputting the measurement parameters into a preset neural network model to obtain the electrode loss rate corresponding to each electrode; wherein, when the neural network model is used for the first time, the neural network model is an initially trained neural network model, and when the neural network When the model is not used for the first time, the trained neural network model is a neural network model obtained after adaptive training using the obtained measurement parameters during the actual use of the neural network model; the electrode consumption length corresponding to each electrode is determined according to the electrode consumption rate corresponding to each electrode and the recorded actual working time of each electrode; the exposed length of each electrode exposed to the charge surface obtained by the position sensor is obtained, and the position of the electrode tip of each electrode penetrating into the charge is determined according to the original length, exposed length and electrode consumption length corresponding to each electrode, so as to control the gripper to which the electrode belongs to raise or lower the depth of the electrode in the charge according to the electrode tip position of the electrode, so that the depth of each electrode penetrating into the charge is the same.

[0031] It can be seen that the technical solution provided in this embodiment inputs the measurement parameters obtained in real time into the adaptively trained and highly accurate neural network model when regulating the working length of the electrode, and obtains the electrode consumption rate corresponding to each electrode; and determines the electrode consumption length corresponding to each electrode according to the electrode consumption rate corresponding to each electrode and the recorded actual working time of each electrode, and then determines the position of the electrode tip of each electrode deep into the charge according to the original length corresponding to each electrode, the exposed length measured in real time and the determined electrode consumption length, so as to control the gripper to which the electrode belongs to raise or lower the depth of the electrode in the charge according to the electrode tip position of each electrode, so that the depth of each electrode penetrating into the charge is the same. It can be seen that the application of the technical solution provided in this embodiment basically requires no human intervention, but instead determines the actual length data of the electrode through a high-precision and adaptively trained neural network model. This not only reduces the labor intensity and skill requirements of workers, but also reduces the technical problem of large errors in electrode length measurement caused by human factors. At the same time, it can also make timely adjustments when the electrode length tends to be too long or too short, and control the electrode length within a reasonable range, meeting the requirements of refined management of electrode working length adjustment. In addition, it can also reduce the frequency of electrode measurement and reduce the safety risks brought by electrode measurement.

[0032] The following is a detailed description in the form of embodiments:

[0033] See also Figure 1 , Figure 1 This is a flow chart of an electrode working length control method shown in an embodiment of the present application. The method is applied to the controller of a pressure-release measuring device. The pressure-release measuring device also includes a synchronous belt provided with a magnetic block, wherein the magnetic block is used to adsorb on the outside of a holder for clamping the electrode in the calcium carbide furnace equipment. The controller and the calcium carbide furnace equipment are electrically connected to a position sensor for measuring the exposed length of the electrode exposed to the furnace charge surface. In some embodiments, the pressure-release measuring device also includes an encoder for measuring the pressure release amount of the electrode. The encoder is connected to the above-mentioned synchronous belt. When the synchronous belt rotates, it will synchronously drive the encoder to rotate. The encoder can measure the pressure release amount of the electrode during the rotation process.

[0034] The method comprises the following steps:

[0035] Step 101: Obtain measurement parameters corresponding to each electrode in the calcium carbide furnace equipment, which are used to characterize electrode loss.

[0036] In this embodiment, some of the three-phase electrodes of the calcium carbide furnace equipment are inserted into the charge of the calcium carbide furnace equipment. Some of the electrodes inserted into the charge of the calcium carbide furnace equipment will be consumed during the chemical reaction, and the electrode loss can be measured through some physical quantities produced after the chemical reaction, such as exhaust gas, temperature, and current. The automatically set reference parameters include current (primary, secondary, low-compensation), voltage (primary, secondary, low-compensation), power factor, active power, gear, current-pressure ratio, operating resistance and branch resistance. In some embodiments, the measurement parameter can be the current on the electrode.

[0037] The measurement parameters of this embodiment can be manually input into the controller, or sent to the controller through an electronic device used to measure the corresponding measurement parameters. This embodiment is not limited to this. In some embodiments, the measurement parameters can be pre-processed data, such as noise-removed data.

[0038] Step 102: Input the measurement parameters into a preset neural network model to obtain the electrode loss rate corresponding to each electrode.

[0039] Among them, when the neural network model is used for the first time, the neural network model is the initially trained neural network model. When the neural network model is not used for the first time, the trained neural network model is the neural network model obtained after adaptive training using the obtained measurement parameters during the actual use of the neural network model.

[0040] In this embodiment, when the neural network model is first applied to the controller, it has been trained in advance. The neural network model first applied to the controller is the initially trained neural network model. During the actual application of the controller, as the types of measured parameters increase during the actual application, the trained neural network model is no longer suitable for the actual application conditions, and the accuracy of the output electrode consumption rate becomes increasingly lower. When the accuracy of the neural network model has been tested to a set accuracy threshold, in order not to affect the operation of the calcium carbide furnace equipment, the neural network model is subjected to online adaptive reinforcement training. The specific adaptive training process will be described in detail later in this embodiment and will not be repeated here. As an embodiment, after this step 102, the following may also be included: determining the accuracy of the neural network model. If the accuracy of the neural network model reaches the accuracy threshold, step 103 is executed. If the accuracy of the neural network model is lower than the accuracy threshold, a training prompt is issued to indicate that the neural network model needs to be adaptively trained. In other embodiments, the neural network model can be adaptively trained at set time intervals to obtain a neural network training model with higher accuracy.

[0041] It should be noted that the accuracy of the neural network model used in this controller is higher than that of the neural network models used before.

[0042] There are three-phase electrodes in the calcium carbide furnace equipment. Based on this, the neural network model also outputs the electrode consumption rate of each electrode.

[0043] Step 103 : determining the electrode consumption length corresponding to each electrode according to the electrode consumption rate corresponding to each electrode and the recorded actual working time of each electrode.

[0044] The actual working time of each electrode in this embodiment can be from the initial working time of the electrode to the current time when the electrode consumption time needs to be calculated. The actual working time of each electrode can be recorded by a counter specifically used to record the working time of each electrode. The counter is connected to the controller so that the working time corresponding to each electrode can be obtained from the counter according to actual needs. It can also be the working time corresponding to each electrode recorded by the controller when it determines that each electrode has started working. Of course, it can also be other electronic devices that record the working time of each electrode. These electronic devices are connected to the controller and can be obtained from other electronic devices when the working time corresponding to each electrode is needed. This embodiment does not limit this.

[0045] Step 104, obtain the exposed length of each electrode exposed on the charge surface measured by the position sensor, and determine the position of the electrode tip of each electrode deep into the charge based on the original length, exposed length and electrode consumption length corresponding to each electrode. For each electrode, according to the electrode tip position of the electrode, control the gripper to which the electrode belongs to raise or lower the depth of the electrode in the charge, so that the depth of each electrode in the charge is the same.

[0046] The position sensor of this embodiment is installed in the holder of the calcium carbide furnace equipment, which can measure the exposed length of each electrode exposed to the material surface. After knowing the original length, exposed length and electrode consumption length of each electrode, the position of the electrode tip of each electrode deep into the furnace charge can be determined, so as to better regulate the depth of each electrode inserted into the furnace charge in the calcium carbide furnace equipment, so that the depth of each electrode inserted into the furnace charge in the calcium carbide furnace equipment is consistent, that is, the working length of each electrode is consistent, so that the various working conditions and required indicators in the calcium carbide furnace equipment will be better. It should be noted that the electrode tip positions of each electrode are best in the same plane, which is the most ideal furnace condition.

[0047] So far, completed Figure 1 Description of the display.

[0048] It can be seen that in the technical solution of the embodiment of the present application, when adjusting the working length of the electrode, the measurement parameters obtained in real time are input into the adaptively trained and high-precision neural network model to obtain the electrode consumption rate corresponding to each electrode; and according to the electrode consumption rate corresponding to each electrode and the recorded actual working time of each electrode, the electrode consumption length corresponding to each electrode is determined, and then according to the original length corresponding to each electrode, the exposed length measured in real time and the determined electrode consumption length, the position of the electrode tip of each electrode deep into the charge is determined, so that for each electrode, according to the electrode tip position of the electrode, the holder to which the electrode belongs is controlled to raise or lower the depth of the electrode in the charge, so that the depth of each electrode deep into the charge is the same. It can be seen that the application of the technical solution provided in this embodiment basically requires no human intervention, but instead determines the actual length data of the electrode through a high-precision and adaptively trained neural network model. This not only reduces the labor intensity and skill requirements of workers, but also reduces the technical problem of large errors in electrode length measurement caused by human factors. At the same time, it can also make timely adjustments when the electrode length tends to be too long or too short, and control the electrode length within a reasonable range, meeting the requirements of refined management of electrode working length adjustment. In addition, it can also reduce the frequency of electrode measurement and reduce the safety risks brought by electrode measurement.

[0049] As an embodiment, this embodiment will only perform adaptive training on the neural network training model applied in this controller when it is necessary to perform adaptive training on the neural network training model. In order to influence the operation of the calcium carbide furnace and improve the accuracy of the neural network training model, this embodiment adopts online adaptive reinforcement training. In some embodiments, the situation where the neural network training model needs to be adaptively trained can be the consumption length error between the electrode consumption length corresponding to each electrode determined in step 103 and the actual electrode consumption length corresponding to each electrode. If the consumption length error is lower than the error threshold, it is considered that the neural network model does not need to be reinforced again. If the consumption length error is higher than the error threshold, it is considered that the neural network model needs to be reinforced again. Among them, one way to realize the actual electrode consumption length corresponding to each electrode is to stop the operation of the calcium carbide furnace equipment and take out the electrode from the charge for measurement. Another implementation method may be: a high-temperature resistant sensor is set within the interval length of the electrode. When the end of the electrode is located at the high-temperature resistant sensor, the high-temperature resistant sensor sends position information representing the position of the electrode end to the controller. After obtaining the position information, the controller controls the high-temperature resistant sensor to detach from the electrode and pull the electrode out of the charge. The position information sent by the high-temperature resistant sensor obtained by the controller is the actual electrode length of the electrode.

[0050] In some embodiments, as Figure 2 As shown in Figure 2, the training process of the network model adaptation is as follows:

[0051] Step 201: During the operation of the calcium carbide furnace equipment, a measurement parameter corresponding to each electrode in the calcium carbide furnace equipment and used to characterize electrode loss is obtained.

[0052] The measurement parameters obtained in this embodiment are actual measurement parameters obtained while the calcium carbide furnace equipment is still in operation. The actual measurement parameters can be preprocessed measurement parameters for input into the neural network model.

[0053] Step 202: Input the measurement parameters into a preset neural network model to obtain the electrode loss rate corresponding to each electrode.

[0054] As an embodiment, the neural network model used in this embodiment is a convolutional neural network built using TensorFlow. TensorFlow is an end-to-end open source machine learning platform. It has a comprehensive and flexible ecosystem that includes various tools, libraries, and community resources to help researchers advance the development of advanced machine learning technologies and enable developers to easily build and deploy applications powered by machine learning. The features of the framework are as follows: Easily build models. Easily build and train machine learning models using intuitive high-level APIs such as Keras in an immediate execution environment that enables us to quickly iterate models and easily debug models. Reliable machine learning production anytime, anywhere. No matter which language you use, you can easily train and deploy models in the cloud, locally, in the browser, or on a device. Powerful research experiments. A simple and flexible architecture allows you to more quickly transform new ideas from concept to code, then create advanced models and ultimately release them to the outside world.

[0055] As an embodiment, the neural network model of this embodiment adopts the relu function as the input function and the sofemax function of TensorFlow as the output function.

[0056] Step 203, determining the consumed length of each electrode according to the electrode consumption rate of each electrode and the actual working time of each electrode, and determining the predicted remaining length of each electrode according to the original length of each electrode and the consumed length of each electrode.

[0057] In this embodiment, for each electrode, the predicted remaining length of the electrode is the original length of the electrode minus the consumed length of the electrode.

[0058] Step 204: Obtain the actual remaining length of each electrode actually measured.

[0059] One way to implement the actual remaining length of this embodiment is to stop the operation of the calcium carbide furnace equipment, take out the electrode from the furnace charge of the calcium carbide furnace equipment, and measure the length obtained. The actual remaining length is the remaining length obtained by subtracting the consumed length of the electrode from the original length of the electrode.

[0060] Step 205, calculate the consumption length error based on the determined predicted remaining length and the actual remaining length, and record the consumption length error this time. If the recorded consumption length error this time is smaller than the consumption length error recorded last time, record the consumption length error this time, and execute step 104; when the consumption length error recorded within the set number of times is in convergence, determine the neural network model as the neural network model set in the controller for updating. If the recorded consumption length error this time is larger than the consumption length error recorded last time, delete the consumption length error this time, adjust the model parameters of the neural network model, determine the adjusted neural network model as the new neural network model, and continue to execute step 201.

[0061] In this embodiment, the recorded error in the consumed length this time is smaller than the error in the consumed length last time, which indicates that the accuracy of the neural network model trained this time is higher than the accuracy of the previously trained neural network model. When the recorded errors in the consumed length within a set number of times are all on a decreasing trend, it indicates that the neural network model is converging, and the neural network model obtained after the last training is determined to be used to update the neural network model set in the controller. During the training process, if the recorded error in the consumed length this time is larger than the error in the consumed length last time, it indicates that the neural network model has not been trained to the optimal level, and it is necessary to delete the error in the consumed length this time and adjust the model parameters of the neural network model. The adjusted neural network model is determined as the new neural network model, and the process returns to step A to continue training the neural network model until a converged neural network model is obtained.

[0062] In this embodiment, when it is determined that the error of the consumption length determined by the electrode consumption rate output by the currently used neural network model is small and better than the error of the consumption length determined by the neural network model used last time, this indicates that the accuracy of the currently used neural network model is better. Based on this, the electrode consumption length predicted by the electrode consumption rate output by the currently used neural network model is used.

[0063] It can be seen that in the actual application process, this embodiment adopts adaptive training of the existing neural network model, which can further improve the accuracy of the neural network model without delaying the actual operation of the calcium carbide furnace equipment, so as to more accurately predict the electrode consumption rate.

[0064] In the process of controlling the holder of the electrode to raise or lower the depth of the electrode in the charge, the method further includes:

[0065] During the operation of the calcium carbide furnace equipment, the current on each electrode is detected in real time. Based on the current detected on each electrode, the electrode coupling rules and the three-phase current balance are used to determine whether the length of the electrode in the furnace charge should be increased or decreased.

[0066] In order to increase the stability of the electrodes in the furnace, in some embodiments, during the operation of the calcium carbide furnace equipment, the current on each electrode is detected in real time. For the current on each electrode detected, the electrode coupling rule and the three-phase current balance are used to determine whether the length of the electrode in the furnace charge is to be raised or lowered. In this embodiment, the calcium carbide furnace equipment is provided with an ammeter for measuring the current on the electrode. The ammeter is used to detect the current of the electrode in real time and send the detected current to the controller. After obtaining the current of the electrode, the controller will determine whether the length of the electrode in the furnace charge is to be raised or lowered for the current on each electrode with the help of the electrode coupling rule and the three-phase current balance. In this embodiment, the electrode coupling rule is an inherent characteristic of the three-phase electrode. When the current on electrode A1 is abnormal, the electrode B1 connected to electrode A1 is adjusted. When the current on electrode B1 is abnormal, the electrode C1 connected to electrode B1 is adjusted. When the current on electrode C1 is abnormal, the electrode A1 connected to electrode C1 is adjusted.

[0067] In other embodiments, the above-mentioned determination of whether to adjust or reduce the length of the electrode in the charge according to the electrode coupling rule and the three-phase current balance may include the following steps A to C:

[0068] In step A, when it is detected that the actual current of the electrode is higher than the current control range, step B is executed; when it is detected that the current of the electrode is lower than the current control range, step C is executed.

[0069] As an embodiment, the current control range may be determined according to the following setting basis, which includes at least one of operating resistance balance, power balance, electrode position balance, and normal power factor.

[0070] Taking electrode A1 as an example, the secondary current value is set to 108KA, with a control range of ±1.8KA. The upper and lower ranges of 108KA are 106.2~109.8KA. When the secondary current of electrode A1 is less than 106.2KA, the control output is used to indicate that the electrode A1 is decreasing. The controller receives the decreasing signal and executes step H. When the secondary current C is greater than 109.8KA, the control output is used to indicate that the electrode A1 is increasing. Step G is executed.

[0071] In some embodiments, after adjusting the electrode, the power factor of the calcium carbide furnace is obtained. When the power factor of the calcium carbide furnace is within the set range, it means that the electrode will neither be lifted to the material surface nor inserted into the bottom of the furnace. If the set range is 0.73~0.83, it can be guaranteed that after the next adjustment, the electrode will neither be lifted to the material surface nor inserted into the bottom of the furnace.

[0072] Step B: controlling the holder to which the electrode belongs to increase the working length of the electrode in the charge according to a first set rate and a first set number of adjustments.

[0073] In this embodiment, the first set rate is named only for the convenience of distinguishing it from the set rates described later, and is not used to limit a certain set rate. Accordingly, the first set control times is named only for the convenience of distinguishing it from the set control times described later, and is not used to limit a certain set control times.

[0074] As an embodiment, the first set rate can be increased by 10 mm per millisecond. In order to maintain the stability of the electrode in the furnace, the working length of the electrode can be increased by at least one adjustment number. For example, if it is determined that it needs to be increased by 30 mm, it can be increased by 10 mm at the first set rate first, wait for 15 seconds, increase by 10 mm at the first set rate again, wait for 15 seconds, and finally increase by 10 mm at the first set rate. In this way, the electrode is increased by 30 mm while maintaining stable operation.

[0075] Step C: controlling the holder to which the electrode belongs to reduce the working length of the electrode in the charge according to a second set rate and a second set number of adjustments.

[0076] Here, the second set rate is only named for the convenience of description and is not used to limit a certain set rate. Accordingly, the second set control times is only named for the convenience of description and is not used to limit a certain set control times.

[0077] The first set rate may be the same as or different from the second set rate, which is not limited in this embodiment. Accordingly, the first set control times may be the same as or different from the second set control times, which is not limited in this embodiment.

[0078] In order to maintain the stability of the electrode in the furnace, the working length of the electrode can also be reduced by at least one adjustment. For example, if it is determined that it needs to be reduced by 20 mm, it can be increased by 10 mm at the second set rate, wait for 15 seconds, and then reduced by 10 mm at the second set rate to achieve the goal of reducing by 20 mm.

[0079] In some embodiments, the implementation of step B may include the following steps B1 to B3:

[0080] Step B1: Calculate the current difference between the current actual current and the first current threshold. If the current difference is within the first current control threshold, execute step B2. If the current difference is not within the first current threshold, execute step B3.

[0081] In this embodiment, the first current threshold is named only for the convenience of distinguishing it from the current thresholds described later, and is not used to limit a certain current threshold.

[0082] If the current difference is within the first current control threshold range, it means that the gripper only needs to raise the electrode to the working length of the calcium carbide furnace equipment once at the first set rate and the first set length, that is, execute step B2. If the current difference is not within the first current control threshold range, it means that the gripper needs to raise the electrode to the working length of the calcium carbide furnace equipment multiple times at the first set rate and the first set length to achieve the lifting target, that is, execute step B3.

[0083] Step B2: Control the holder to which the electrode belongs to elevate the electrode to a working length in the calcium carbide furnace equipment at a first set length and at a first set rate.

[0084] In this embodiment, the first set length is named only for the convenience of distinguishing it from the set control times described later, and is not used to limit a certain set length.

[0085] Step B3, control the holder to which the electrode belongs to raise the working length of the electrode in the charge at a first set length and at a first set rate, wait for a preset first observation time, and when the first observation time is reached, obtain the detected actual current, use the obtained actual current as the current actual current, and return to execute step B1.

[0086] As an embodiment, the first observation time is at least 15 seconds.

[0087] This embodiment increases the working length of an electrode and detects the actual current of the electrode to determine whether the working length of the electrode needs to be further increased, until the current difference between the detected actual current and the first current threshold is lower than the current threshold indicating that there is no need to regulate the current of the electrode, and stops controlling the gripper to regulate the working length of the electrode.

[0088] Based on the above embodiment, the implementation method of step C may include the following steps C1 to C3:

[0089] Step C1, calculate the current difference between the current actual current and the second current threshold. If the current difference is within the second current control threshold, execute step C2; if the current difference is not within the second current threshold, execute step C3.

[0090] In this embodiment, the second current threshold is named only for the convenience of distinguishing it from the current threshold described later, and is not used to limit a certain current threshold.

[0091] If the current difference is within the second current control threshold range, it means that the gripper only needs to reduce the working length of the electrode in the calcium carbide furnace equipment once at the second set rate and the second set length, that is, step C2 is executed. If the current difference is not within the second current control threshold range, it means that the gripper needs to reduce the working length of the electrode in the calcium carbide furnace equipment multiple times at the second set rate and the second set length to achieve the reduction target, that is, step C3 is executed.

[0092] Here, the second current threshold is simply named for ease of description and is not intended to limit a specific current threshold. Accordingly, the second set length is simply named for ease of description and is not intended to limit a specific set length. The first current threshold may be the same as or different from the second current threshold, and this embodiment does not limit this. The first set length may be the same as or different from the second set length, and this embodiment does not limit this.

[0093] Step C2: controlling the holder of the electrode to reduce the working length of the electrode in the charge by a second set length at a second set rate.

[0094] Step C3, controlling the holder to which the electrode belongs to reduce the working length of the electrode in the charge by a second set length at a second set rate, waiting for a preset second observation time, and when the second observation time is reached, obtaining the detected actual current, using the obtained actual current as the current actual current, and returning to the step of executing step C1.

[0095] This embodiment reduces the working length of a primary electrode and detects the actual current of the primary electrode to determine whether the working length of the electrode needs to be further reduced, until the current difference between the detected actual current and the second current threshold is lower than the current threshold used to indicate that there is no need to regulate the current of the electrode, and stops controlling the gripper to regulate the working length of the electrode.

[0096] As another embodiment, the implementation of step B may include the following steps B4 to B6:

[0097] Step B4, calculating the current difference between the current actual current and the first current threshold. If the current difference is within the first current control threshold, executing step B5; if the current difference is not within the first current threshold, executing step B6.

[0098] Step B5: controlling the holder of the electrode to raise the working length of the electrode in the charge at a first set speed and a first set length.

[0099] Step B6, determining the number of times the electrode is raised according to the current difference and the first current control threshold, and controlling the holder to which the electrode belongs to raise the working length of the electrode in the charge at a first set rate, a first set length and the determined number of times of control.

[0100] In this embodiment, the number of times the electrode needs to be raised is determined based on the current difference and a first current control threshold. The gripper is then controlled to raise the electrode to a working length within the charge at a first set rate, by a first set length, and for the determined number of times. In one embodiment, the first set length is determined based on the raising length threshold and the required electrode raising length. For example, if the raising length threshold is 10 mm and the required electrode raising length is 25 mm, the first set lengths are 10 mm and 5 mm.

[0101] Exemplarily, if the current difference is 30 mA and the first current control threshold is 10 mA, then the number of controls is 3 times. Another exemplary example is that if the current difference is 25 mA and the first current control threshold is 10 mA, then the number of controls is 3 times, and the third control is 5 mA.

[0102] Based on the above embodiment, the implementation method of step C may include steps C4 to C6:

[0103] Step C4, calculating the current difference between the current actual current and the second current threshold. If the current difference is within the second current control threshold, executing step C5; if the current difference is not within the second current threshold, executing step C6.

[0104] Step C5 , controlling the holder to which the electrode belongs to elevate the working length of the electrode in the charge at a second set speed and a second set length.

[0105] Step C6, determining the number of times to increase the electrode according to the current difference and the second current control threshold, and controlling the holder to which the electrode belongs to reduce the working length of the electrode in the charge according to the second set rate, the second set length and the determined number of controls.

[0106] In this embodiment, the number of times the electrode needs to be raised is determined based on the current difference and the second current control threshold. The gripper is then controlled to reduce the electrode's working length within the charge at a second set rate, by a second set length, and for the determined number of times. In one embodiment, the second set length is determined based on the length reduction threshold and the required electrode length reduction. For example, if the raising length threshold is 10 mm and the electrode length needs to be reduced by 25 mm, the second set lengths are 10 mm and 5 mm.

[0107] For example, if the current difference is 30 mA and the second current control threshold is 10 mA, then based on the relationship between current and reducing electrode length, the current difference is 30 mA and the second current control threshold is 10 mA, and the number of controls is determined to be 3 times.

[0108] In some embodiments, as Figure 3 As shown, during the operation of the calcium carbide furnace equipment, the method further includes the following steps:

[0109] Step 301: obtain characteristic parameters collected by various sensors provided on the calcium carbide furnace equipment and used to represent the operating status of the calcium carbide furnace, and determine the current calcium carbide furnace power of the calcium carbide furnace based on the characteristic parameters.

[0110] In this embodiment, some of the three-phase electrodes of the calcium carbide furnace equipment are inserted into the charge of the calcium carbide furnace equipment, and some of the electrodes inserted into the charge of the calcium carbide furnace equipment will be consumed during the chemical reaction. In actual operation, the operating status of the calcium carbide furnace can be measured by some characteristic parameters, such as primary / secondary current, primary / secondary voltage, single-phase power of each electrode, furnace power factor, real-time pressure in the furnace and real-time temperature of purified exhaust gas, current density on each electrode and electrode roasting time. In some embodiments, in AC equipment, the circuit power factor is the active power minus the apparent power.

[0111] Step 302, according to the relationship between the preset voltage and the calcium carbide furnace power, determine the voltage value corresponding to the current calcium carbide furnace power. When the voltage value is lower than the set voltage value, execute step 103.

[0112] As an embodiment, the method for determining the relationship between voltage and calcium carbide furnace power in step 102 includes steps A11 to A14:

[0113] Step A11, determining the power density of the crucible of the calcium carbide furnace according to the relationship between power and the volume of the crucible of the calcium carbide furnace.

[0114] In this step, P∝D3 is proportional, C=P / D3, D is the diameter of the calcium carbide furnace crucible, P is the power of the calcium carbide furnace, P is the total power of the calcium carbide furnace, and C is the power density of the calcium carbide furnace crucible. As an example, the C value can be 400-700KW / cubic meter.

[0115] Step A12, determining the current of the crucible of the calcium carbide furnace according to the power density of the crucible of the calcium carbide furnace and the first relationship between the current density of the crucible of the calcium carbide furnace and the cross-sectional area of the crucible of the calcium carbide furnace;

[0116] C4=4 I / πD2 or D=C4 I1 / 2.

[0117] Step A13, determining a second relationship between the current, the electrode power of the calcium carbide furnace, and the power density of the calcium carbide furnace crucible based on the relationship between the Andre formula and the current;

[0118] In this embodiment, by comparing the Andre formula: 1 / 4xπD2∝I, we can have: I=C3 P2 / 3.

[0119] Step A14, based on the power, current and voltage relationship and the second relationship, determine the relationship between voltage and calcium carbide furnace power.

[0120] In this embodiment, since P=IU=I2R, U=C2P1 / 3, R=C1P-1 / 3, and the relationship between voltage and calcium carbide furnace power P can be obtained.

[0121] This embodiment can determine the operating resistance corresponding to the electrode at the optimal usage power, that is, the upper limit of the usage power, by comparing with the Andre formula. After knowing the operating resistance, the voltage can be increased to the set voltage value through steps 103 to 104, so that the current power reaches the optimal usage power. It should be noted that if the optimal resistance is to be achieved, the operating resistance can be made to reach the optimal range according to the corresponding relationship between voltage and current, thereby making the usage power of the electrode reach the usage power set value.

[0122] Step 303 , determining whether the current electrode current has reached the set current upper limit, if not, executing step 304 , if reaching the current upper limit, executing step 305 .

[0123] In this embodiment, when the current of the electrode reaches the current upper limit, in order to protect the electrode, the current on the electrode needs to be reduced. At this time, if the voltage value is to reach the set voltage value, the voltage gear of the transformer to which the electrode belongs needs to be adjusted. When the current of the electrode does not reach the current upper limit, step 104 is executed.

[0124] Step 304: Adjust the current of the electrode so that the power used by the electrode reaches the set power value.

[0125] According to the relationship between current, voltage and power, if you want to increase the voltage to the set voltage value, you can first adjust the current of the electrode so that the power of the electrode reaches the upper limit of the working power. In this way, the voltage of the electrode will also increase.

[0126] Step 305 , reducing the current of the electrode and adjusting the voltage level of the transformer responsible for each electrode to adjust the voltage of the corresponding electrode so that the power used by the electrode reaches the set power value.

[0127] In this embodiment, when the voltage value is lower than the set voltage value, the electrode current is first adjusted. During the adjustment, if the current has not reached the current upper limit, the current is adjusted. If the current reaches the current upper limit, the voltage level of the transformer to which the electrode belongs is adjusted. The voltage level is a pre-set voltage range, and each level corresponds to a different voltage range. As an embodiment, a total of 48 levels can be set. Of course, the 48 levels in this embodiment are merely an example and can be set according to actual conditions. This embodiment does not limit this.

[0128] So far, completed Figure 3 Description of the display.

[0129] It can be seen that in the technical solution of the embodiment of the present application, when managing the electrode, the method determines the current calcium carbide furnace power of the calcium carbide furnace according to the characteristic parameters of the calcium carbide furnace equipment that have been obtained, and determines the voltage value corresponding to the current calcium carbide furnace power according to the relationship between the set voltage and the calcium carbide furnace power; when the voltage value is lower than the set voltage value, it is determined whether the current electrode current has reached the set current upper limit. If the current upper limit has not been reached, the current of the electrode is adjusted so that the electrode's power reaches the set power value; if the current upper limit is reached, the current of the electrode is reduced, and at the same time, the voltage gear of the transformer responsible for each electrode is adjusted to adjust the voltage of the corresponding electrode so that the electrode's power reaches the set power value. It can be seen that the technical solution provided by this embodiment basically does not require manual intervention, but by regulating the current and transformer gear, the electrode's power reaches the optimal power upper limit. This embodiment replaces the original manual operation method of the calcium carbide furnace, reducing the probability of unstable production and quality problems caused by different operating cognition and unstable electrode management.

[0130] As an embodiment, when each electrode is in a non-pressing and releasing period, after adjusting the current of the electrode in step 304, the method further includes: for each electrode, real-time detection of the number of press-release times of the holder clamping the electrode and the electrode lifting value of the electrode measured by the pressure-release measuring device; if it is detected that neither the number of press-release times nor the electrode lifting value has changed, it is determined that the electrode has not slipped; if it is detected that the number of press-release times has changed or the electrode lifting value has changed, it is determined that the electrode has slipped, and a slip alarm message indicating that the electrode has slipped is issued, or / and, the slip alarm message is sent to the remote control system.

[0131] In the present embodiment, when each electrode is in a non-pressing and releasing period, in order to stabilize the working condition in the calcium carbide furnace, it is necessary to maintain the electrode in an immobile state, that is, the electrode is neither pressed and released nor raised and lowered. Based on this, in order to detect whether the electrode has slipped, the present embodiment detects the pressing and releasing times of the holder in real time. If it is detected that the pressing and releasing times of the holder have changed, this means that the electrode has slipped and it is necessary to promptly alarm and process to maintain the electrode stability as soon as possible. In order to improve the accuracy of preventing slippage of the electrode, it is also necessary to measure the electrode lifting value of the electrode by a press-release measuring device. If it is detected that the electrode lifting value measured by the press-release measuring device has changed, this means that the electrode has slipped. In actual operation, no matter the holder or the press-release measuring device, the detected value will not change. Only when the electrode is pressed and released will the electrode slide. Accordingly, the pressing and releasing value of the detecting holder and the electrode lifting value measured by the press-release measuring device will change.

[0132] The downhill slide warning information of this embodiment may be displayed in the form of an alarm sound and / or a bright warning light to attract the attention of the operator.

[0133] The controller of this embodiment is electrically connected to a remote control system. In this embodiment, the controller determines that the electrode has slipped and issues a slip alarm message indicating that the electrode has slipped. In other embodiments, the controller determines that the electrode has slipped and issues a slip alarm message indicating that the electrode has slipped. In other embodiments, the controller determines that the electrode has slipped and issues a slip alarm message indicating that the electrode has slipped, and also sends the slip alarm message to the remote control system.

[0134] In some embodiments, after reducing the electrode current in step 304, the method further includes: obtaining the hydrogen content detected in the calcium carbide furnace in real time; and when it is determined that the hydrogen content is greater than a set hydrogen content, sending a downshift pulse signal to the transformer to indicate that the electrode should be downshifted. Excessively high hydrogen content indicates an increased risk index, and based on this, the transformer cannot continue to perform an upshift operation. Instead, the transformer must be controlled to perform a downshift operation, thereby protecting the electrodes. This embodiment can achieve automatic shifting and enhance electrode protection.

[0135] In other embodiments, after reducing the electrode current in step 304, the method further includes: for each electrode, when it is determined that the electrode is in the released state, prohibiting the transmission of an upshift pulse signal indicating that the voltage of the electrode should be increased. In this embodiment, when the electrode is in the released state, the transformer is prohibited from performing an upshift operation. In other words, when the electrode is in the released state, the transformer does not perform an upshift or downshift operation, thereby enhancing electrode protection.

[0136] In other embodiments, when it is determined that the calcium carbide furnace has a material collapse phenomenon, a stop pulse signal is sent to the transformer to indicate that the voltage of the electrode should stop being shifted up or down. In this embodiment, if it is detected that the calcium carbide furnace has a material collapse phenomenon, the transformer is prohibited from performing a shift up or down operation to achieve automatic shifting and enhance the protection of the electrode. As an embodiment, determining that the calcium carbide furnace has a material collapse phenomenon includes: when it is detected that the current of the electrode suddenly drops and automatically gradually rises to its original state within a set time period, it is determined that the calcium carbide furnace has a material collapse phenomenon. The set time period can be 3 to 6 minutes. When the data feature of the current suddenly dropping and automatically rising to its original state within a set time period is detected, it means that the calcium carbide furnace has a material collapse phenomenon.

[0137] In other embodiments, for each electrode, when it is determined that the electrode power corresponding to the electrode exceeds a set detection range, a downshift pulse signal is sent to the transformer associated with the electrode, indicating that the electrode should be downshifted. In this embodiment, when the electrode power exceeds the set detection range, the transformer is controlled to perform a downshift operation to achieve automatic gear shifting, enhance electrode protection, and stabilize the operating conditions within the calcium carbide furnace.

[0138] In some embodiments, for each electrode, when it is detected that the electrode is inserted into the calcium carbide furnace to a depth less than a set minimum length limit, a downshift pulse signal is sent to the transformer to which the electrode belongs, indicating that the electrode is to be downshifted. In this embodiment, the electrode depth is less than the set minimum length limit, which means that the electrode is too shallowly inserted into the furnace charge. In this case, it is necessary to control the transformer to perform a downshift operation to achieve automatic shifting, enhance electrode protection, and stabilize the operating conditions in the calcium carbide furnace.

[0139] In some embodiments, the pressure-release measurement device monitors the pressure-release amount of each electrode by the clamp to which each electrode belongs each time. If the deviation between the pressure-release amount and the average pressure-release amount in the previous set time period is greater than the set pressure-release amount, a pressure-release alarm message indicating that the pressure-release amount is too large is issued. This embodiment can achieve effective early warning for sudden excessive deviations in pressure-release amount, and promptly correct the unstable working conditions of the electrode caused by excessive pressure-release deviation. In other embodiments, the pressure-release alarm message is sent to the remote control system so that the operator can also remotely understand the working conditions in the calcium carbide furnace in a timely manner and make timely adjustments to it to avoid the impact caused by unstable working conditions of the electrode.

[0140] In some embodiments, during the operation of each electrode, the method further includes: obtaining a manual intervention signal for indicating that manual operation is allowed; according to the manual intervention signal, switching the automatic monitoring mode to the manual operation mode to allow manual intervention to intervene in the operation of the calcium carbide furnace. In this embodiment, random manual intervention is allowed to improve the flexibility of the calcium carbide furnace operation. In other embodiments, during the electrode lifting process, the electrode lifting time is recorded to automatically and accurately time the load electrode lifting and lowering process, avoid manual timing mistakes and reduce human errors. In other embodiments, for each electrode, the set power input for the electrode is obtained, and the actual power of the electrode operation is obtained; the actual power and the set power are compared to determine whether to send a pulse signal for an upshift operation or a downshift operation to the transformer to which the electrode belongs, so as to realize the voltage lifting or downshift operation of the electrode, so as to realize automatic current boost and current stabilization control. It can be seen that the application of the technical solution provided by this embodiment can improve system stability and reduce work accidents compared to the existing manual control.

[0141] As an embodiment, after obtaining the characteristic parameters sent by the sensors provided in the calcium carbide furnace equipment in step 301 and used to represent the operating status of the calcium carbide furnace, the method further includes: for each characteristic parameter obtained, drawing a curve for the characteristic parameter, and updating the historical curve of the characteristic parameter in real time. This enables the operator to view the historical trends of each characteristic parameter in real time, and thus to control the operating status of the calcium carbide furnace well. As other embodiments, electrode characteristic parameters for characterizing the operating status of the electrode are obtained from the obtained characteristic parameters, and electrode parameters are determined and displayed based on the electrode characteristic parameters. The technical solution provided in this embodiment can display the electrode characteristic parameters for the electrode, and thus enables the operator to know the electrode parameters in a timely manner.

[0142] On the other hand, Figure 4 As shown, this embodiment provides a schematic structural diagram of an electrode working length control device 300, which is applied to a controller of a pressure-release measuring device. The pressure-release measuring device also includes a synchronous belt provided with a magnetic block, wherein the magnetic block is used to be adsorbed on the outside of a holder for clamping the electrode in the calcium carbide furnace equipment. The controller is electrically connected to a position sensor of the calcium carbide furnace equipment for measuring the exposed length of the electrode exposed to the charge surface. The device includes:

[0143] The measurement parameter acquisition module 401 is used to obtain the measurement parameters corresponding to each electrode in the calcium carbide furnace equipment and used to characterize the electrode loss;

[0144] The electrode consumption rate module 402 is used to input the measurement parameters into a preset neural network model to obtain the electrode consumption rate corresponding to each electrode; wherein, when the neural network model is used for the first time, the neural network model is an initially trained neural network model; when the neural network model is not used for the first time, the trained neural network model is a neural network model obtained through adaptive training using the obtained measurement parameters during the actual use of the neural network model;

[0145] The electrode consumption length determination module 403 is used to determine the electrode consumption length corresponding to each electrode according to the electrode consumption rate corresponding to each electrode and the recorded actual working time of each electrode;

[0146] The electrode working length control module 404 is used to obtain the exposed length of each electrode exposed on the charge surface measured by the position sensor, and determine the position of the electrode tip of each electrode deep into the charge based on the original length, exposed length and electrode consumption length corresponding to each electrode. For each electrode, according to the electrode tip position of the electrode, the gripper belonging to the electrode is controlled to raise or lower the depth of the electrode in the charge, so that the depth of each electrode penetrating into the charge is the same.

[0147] As an embodiment, the apparatus further includes: a model training module for adaptively training a trained neural network model, and is configured to:

[0148] During the operation of the calcium carbide furnace equipment, obtaining the measurement parameters corresponding to each electrode in the calcium carbide furnace equipment and used to characterize the electrode loss;

[0149] Determine the consumed length of each electrode according to the electrode consumption rate and the actual working time of each electrode, and determine the predicted remaining length of each electrode according to the original length and the consumed length of each electrode;

[0150] Obtaining the actual remaining length of each electrode actually measured;

[0151] The consumption length error is calculated based on the determined predicted remaining length and the actual remaining length, and the consumption length error is recorded. If the recorded consumption length error is smaller than the consumption length error recorded last time, the consumption length error is recorded, and the step of obtaining the exposed length of each electrode exposed to the charge surface measured by the position sensor is executed; when the consumption length error recorded within the set number of times is in convergence, the neural network model is determined as a new neural network model. If the recorded consumption length error is larger than the consumption length error recorded last time, the consumption length error is deleted, and the model parameters of the neural network model are adjusted. The adjusted neural network model is determined as the new neural network model, and the step of obtaining the measurement parameters corresponding to each electrode in the calcium carbide furnace equipment for characterizing the electrode loss is continued.

[0152] As an embodiment, the device further comprises:

[0153] The judgment module is used to detect the current on each electrode in real time during the operation of the calcium carbide furnace equipment. For the current on each electrode detected, it is used to determine whether the length of the electrode in the furnace charge should be increased or decreased according to the electrode coupling rules and the three-phase current balance.

[0154] As an embodiment, the judgment module includes a control unit for judging whether to adjust the length of the electrode in the charge according to the electrode coupling rule and the three-phase current balance. The control unit includes:

[0155] The detection subunit is used to trigger the first boost subunit when it detects that the actual current of the electrode is higher than the current control range, and trigger the second boost subunit when it detects that the current of the electrode is lower than the current control range.

[0156] a lifting subunit, configured to control a holder to which the electrode belongs to lift a working length of the electrode in the charge according to a first set rate and a first set number of adjustments;

[0157] The lowering subunit is used to control the holder to which the electrode belongs to reduce the working length of the electrode in the charge according to a second set rate and a second set number of adjustments.

[0158] As an embodiment, the lifting subunit is specifically used to:

[0159] Calculating the current difference between the current actual current and the first current threshold value, and if the current difference is within the first current control threshold value, controlling the gripper to which the electrode belongs to elevate the electrode to a working length in the calcium carbide furnace device at a first set rate and a first set length;

[0160] If the current difference is not within the first current threshold range, controlling the gripper to which the electrode belongs to elevate the working length of the electrode in the charge by a first set length at a first set rate, waiting for a preset first observation time, and when the first observation time is reached, obtaining the detected actual current, using the obtained actual current as the current actual current, and returning to the step of calculating the current difference between the current actual current and the first current threshold;

[0161] Lowering subunit, specifically for:

[0162] Calculating a current difference between a current actual current and a second current threshold value, and if the current difference is within the second current control threshold value, controlling a gripper to which the electrode belongs to reduce a working length of the electrode in the charge at a second set rate and by a second set length;

[0163] If the current difference is not within the second current threshold range, the holder to which the electrode belongs is controlled to reduce the working length of the electrode in the charge by a second set length at a second set rate, and wait for a preset second observation time. When the second observation time is reached, the detected actual current is obtained, and the obtained actual current is used as the current actual current. The process returns to the step of calculating the current difference between the current actual current and the current threshold.

[0164] As an embodiment, the lifting subunit is specifically used to:

[0165] Calculating a current difference between a current actual current and a first current threshold value, and if the current difference is within the first current control threshold value, controlling a gripper to which the electrode belongs to elevate a working length of the electrode in the charge at a first set rate and by a first set length;

[0166] If the current difference is not within the first current threshold, determining the number of times the electrode is raised according to the current difference and the first current control threshold, and controlling the gripper to which the electrode belongs to raise the working length of the electrode in the charge at a first set rate, a first set length, and the determined number of times;

[0167] Lowering subunit, specifically for:

[0168] Calculating a current difference between a current actual current and a second current threshold value, and if the current difference is within the second current control threshold value, controlling a gripper to which the electrode belongs to elevate a working length of the electrode in the charge at a second set rate and by a second set length;

[0169] If the current difference is not within the second current threshold, the number of times the electrode is controlled is determined to be increased based on the current difference and the second current control threshold, and the holder to which the electrode belongs is controlled to reduce the working length of the electrode in the charge at a second set rate, a second set length and the determined number of controls.

[0170] So far, completed Figure 4 Description of the display.

[0171] It can be seen that in the technical solution of the embodiment of the present application, when adjusting the working length of the electrode, the measurement parameters obtained in real time are input into the adaptively trained and high-precision neural network model to obtain the electrode consumption rate corresponding to each electrode; and according to the electrode consumption rate corresponding to each electrode and the recorded actual working time of each electrode, the electrode consumption length corresponding to each electrode is determined, and then according to the original length corresponding to each electrode, the exposed length measured in real time and the determined electrode consumption length, the position of the electrode tip of each electrode deep into the charge is determined, so that for each electrode, according to the electrode tip position of the electrode, the holder to which the electrode belongs is controlled to raise or lower the depth of the electrode in the charge, so that the depth of each electrode deep into the charge is the same. It can be seen that the application of the technical solution provided in this embodiment basically requires no human intervention, but instead determines the actual length data of the electrode through a high-precision and adaptively trained neural network model. This not only reduces the labor intensity and skill requirements of workers, but also reduces the technical problem of large errors in electrode length measurement caused by human factors. At the same time, it can also make timely adjustments when the electrode length tends to be too long or too short, and control the electrode length within a reasonable range, meeting the requirements of refined management of electrode working length adjustment. In addition, it can also reduce the frequency of electrode measurement and reduce the safety risks brought by electrode measurement.

[0172] The implementation process of the functions and effects of each unit in the above-mentioned device is specifically described in the implementation process of the corresponding steps in the above-mentioned method, and will not be repeated here.

[0173] The electronic device provided in the embodiment of the present application, from the hardware level, can be seen in the hardware architecture diagram. Figure 5 The invention comprises: a machine-readable storage medium and a processor, wherein: the machine-readable storage medium stores machine-executable instructions that can be executed by the processor; the processor is used to execute the machine-executable instructions to implement the electrode working length control operation disclosed in the above example.

[0174] The machine-readable storage medium provided in an embodiment of the present application stores machine-executable instructions. When the machine-executable instructions are called and executed by a processor, the machine-executable instructions prompt the processor to implement the RAID reconstruction operation disclosed in the above example.

[0175] Here, the machine-readable storage medium can be any electronic, magnetic, optical or other physical storage device that can contain or store information, such as executable instructions, data, etc. For example, the machine-readable storage medium can be: RAM (Random Access Memory), volatile memory, non-volatile memory, flash memory, storage drive (such as hard disk drive), solid state drive, any type of storage disk (such as CD, DVD, etc.), or similar storage media, or a combination thereof.

[0176] The systems, devices, modules, or units described in the above embodiments may be implemented by computer chips or entities, or by products having certain functions. A typical implementation device is a computer, which may be in the form of a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email transceiver, game console, tablet computer, wearable device, or any combination of these devices.

[0177] For the convenience of description, the above devices are described as being divided into various units according to their functions. Of course, when implementing this application, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0178] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the embodiments of the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0179] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0180] Furthermore, these computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0181] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable device to implement the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0182] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to the partial description of the method embodiments. The device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present application scheme. A person of ordinary skill in the art can understand and implement it without paying any creative work.

[0183] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

Claims

1. A method for controlling the working length of an electrode, characterized in that: The method is applied to a controller of a pressure-release measuring device, wherein the pressure-release measuring device further comprises a synchronous belt provided with a magnetic block, wherein the magnetic block is used to be adsorbed on the outside of a holder for clamping an electrode in a calcium carbide furnace device, and the controller is electrically connected to a position sensor of the calcium carbide furnace device for measuring the exposed length of the electrode exposed to the charge surface. The method comprises: Obtaining measurement parameters corresponding to each electrode in the calcium carbide furnace device and used to characterize electrode loss; Inputting the measurement parameters into a preset neural network model to obtain an electrode loss rate corresponding to each electrode; wherein, when the neural network model is used for the first time, the neural network model is an initially trained neural network model; and when the neural network model is not used for the first time, the trained neural network model is a neural network model obtained through adaptive training using the obtained measurement parameters during the actual use of the neural network model; Determine the electrode consumption length corresponding to each electrode according to the electrode consumption rate corresponding to each electrode and the recorded actual working time of each electrode; The exposed length of each electrode exposed to the charge surface measured by the position sensor is obtained, and the position of the electrode tip of each electrode penetrating into the charge is determined based on the original length, exposed length and electrode consumption length corresponding to each electrode. For each electrode, according to the electrode tip position of the electrode, the holder to which the electrode belongs is controlled to raise or lower the depth of the electrode in the charge, so that the depth of each electrode penetrating into the charge is the same. During the operation of the calcium carbide furnace equipment, the current on each electrode is detected in real time. For the current on each electrode detected, it is determined whether to regulate the length of the electrode in the charge to be raised or lowered based on the electrode coupling rule and the three-phase current balance.

2. The method according to claim 1, characterized in that The adaptive training process of the neural network model is as follows: During the operation of the calcium carbide furnace equipment, obtaining a measurement parameter corresponding to each electrode in the calcium carbide furnace equipment and used to characterize electrode loss; Inputting the measurement parameters into a preset neural network model to obtain the electrode loss rate corresponding to each electrode; Determine the consumed length of each electrode according to the electrode consumption rate and the actual working time of each electrode, and determine the predicted remaining length of each electrode according to the original length and the consumed length of each electrode; Obtaining the actual remaining length of each electrode actually measured; Calculating a consumed length error based on the determined predicted remaining length and the actual remaining length, and recording the consumed length error; if the recorded consumed length error is smaller than the consumed length error recorded last time, recording the consumed length error; and performing the step of obtaining the exposed length of each electrode exposed to the charge surface measured by the position sensor; When the consumption length error recorded within the set number of times is in convergence, the neural network model is determined as the neural network model set in the controller for updating. If the consumption length error recorded this time is larger than the consumption length error recorded last time, the consumption length error this time is deleted, and the model parameters of the neural network model are adjusted. The adjusted neural network model is determined as the new neural network model, and the step of obtaining the measurement parameters corresponding to each electrode in the calcium carbide furnace equipment for characterizing the electrode loss is continued.

3. The method according to claim 1, characterized in that The determining whether to adjust the length of the electrode in the charge by raising or lowering the length of the electrode according to the electrode coupling rule and the three-phase current balance includes: When it is detected that the actual current of the electrode is higher than the current control range, the holder of the electrode is controlled to increase the working length of the electrode in the charge according to a first set rate and a first set number of controls; When it is detected that the current of the electrode is lower than the current control range, the holder to which the electrode belongs is controlled to reduce the working length of the electrode in the charge according to a second set rate and a second set control number.

4. The method according to claim 3, characterized in that The controlling of the holder of the electrode to increase the working length of the electrode in the calcium carbide furnace device according to a first set rate and a first set number of adjustments includes: Calculating the current difference between the current actual current and the first current threshold value, and if the current difference is within the first current control threshold value, controlling the gripper to which the electrode belongs to elevate the electrode to a working length of the calcium carbide furnace device at a first set rate and a first set length; If the current difference is not within the first current threshold range, controlling the gripper to which the electrode belongs to elevate the working length of the electrode in the charge by the first set length at a first set rate, waiting for a preset first observation time, and when the first observation time is reached, obtaining the detected actual current, using the obtained actual current as the current actual current, and returning to the step of calculating the current difference between the current actual current and the first current threshold; The controlling the holder of the electrode to reduce the working length of the electrode in the calcium carbide furnace device according to the second set rate and the second set regulation number includes: calculating a current difference between a current actual current and a second current threshold, and if the current difference is within the second current control threshold, controlling a gripper to which the electrode belongs to reduce a working length of the electrode within the charge at a second set rate and by a second set length; If the current difference is not within the second current threshold range, the holder to which the electrode belongs is controlled to reduce the working length of the electrode in the charge by a second set length at a second set rate, and wait for a preset second observation time. When the second observation time is reached, the detected actual current is obtained, and the obtained actual current is used as the current actual current. The process returns to the step of calculating the current difference between the current actual current and the current threshold.

5. The method according to claim 3, characterized in that The controlling the holder of the electrode to increase the working length of the electrode in the charge according to a first set rate and a first set number of adjustments includes: Calculating a current difference between a current actual current and a first current threshold value, and if the current difference is within the first current control threshold value, controlling a gripper to which the electrode belongs to elevate a working length of the electrode within the charge at a first set rate and a first set length; If the current difference is not within the first current threshold, determining the number of times to raise the electrode according to the current difference and the first current control threshold, and controlling the gripper to which the electrode belongs to raise the electrode to a working length within the charge at a first set rate, a first set length, and the determined number of times; The controlling the holder of the electrode to press and release the electrode to a working length in the charge according to a second set rate and a second set number of adjustments includes: Calculating a current difference between a current actual current and a second current threshold value, and if the current difference is within the second current control threshold value, controlling a gripper to which the electrode belongs to elevate a working length of the electrode within the charge at a second set rate and a second set length; If the current difference is not within the second current threshold, the number of times the electrode is increased is determined based on the current difference and the second current control threshold, and the holder to which the electrode belongs is controlled to reduce the working length of the electrode in the charge at a second set rate, a second set length and the determined number of controls.

6. An electrode working length control device, characterized in that: The device is applied to the controller of a pressure-release measuring device, wherein the pressure-release measuring device further comprises a synchronous belt provided with a magnetic block, wherein the magnetic block is used to be adsorbed on the outside of a holder for clamping an electrode in a calcium carbide furnace device, and the controller is electrically connected to a position sensor of the calcium carbide furnace device for measuring the exposed length of the electrode on the charge surface. The device comprises: A measurement parameter acquisition module, used to obtain the measurement parameters corresponding to each electrode in the calcium carbide furnace equipment and used to characterize the electrode loss; an electrode consumption rate module, configured to input the measurement parameters into a preset neural network model to obtain an electrode consumption rate corresponding to each electrode; wherein, when the neural network model is used for the first time, the neural network model is an initially trained neural network model; and when the neural network model is not used for the first time, the trained neural network model is a neural network model obtained through adaptive training using the acquired measurement parameters during the actual use of the neural network model; An electrode consumption length determination module is used to determine the electrode consumption length corresponding to each electrode according to the electrode consumption rate corresponding to each electrode and the recorded actual working time of each electrode; The electrode working length control module is used to obtain the exposed length of each electrode exposed to the surface of the furnace charge measured by the position sensor, and determine the electrode tip position of each electrode penetrating into the furnace charge based on the original length, exposed length and electrode consumption length corresponding to each electrode, so as to control the holder to which the electrode belongs to raise or lower the depth of the electrode in the furnace charge according to the electrode tip position of the electrode, so that the depth of each electrode penetrating into the furnace charge is the same, and during the operation of the calcium carbide furnace equipment, obtain real-time detection of the current on each electrode, and for the current on each electrode detected, determine whether to raise or lower the length of the electrode in the furnace charge based on the electrode coupling rule and the three-phase current balance.

7. The device according to claim 6, characterized in that The apparatus further includes a model training module for adaptively training a trained neural network model, wherein the model training module is configured to: During the operation of the calcium carbide furnace equipment, obtaining a measurement parameter corresponding to each electrode in the calcium carbide furnace equipment and used to characterize electrode loss; Determine the consumed length of each electrode according to the electrode consumption rate and the actual working time of each electrode, and determine the predicted remaining length of each electrode according to the original length and the consumed length of each electrode; Obtaining the actual remaining length of each electrode actually measured; The consumption length error is calculated based on the determined predicted remaining length and the actual remaining length, and the consumption length error is recorded. If the recorded consumption length error is smaller than the consumption length error recorded last time, the consumption length error is recorded, and the step of obtaining the exposed length of each electrode exposed to the charge surface measured by the position sensor is performed; when the consumption length error recorded within the set number of times is in convergence, the neural network model is determined as a new neural network model. If the recorded consumption length error is larger than the consumption length error recorded last time, the consumption length error is deleted, and the model parameters of the neural network model are adjusted. The adjusted neural network model is determined as the new neural network model, and the step of obtaining the measurement parameters corresponding to each electrode in the calcium carbide furnace equipment for characterizing the electrode loss is continued.

8. An electronic device, characterized in that: The electronic device includes a readable storage medium and a processor; Wherein, the readable storage medium is used to store machine-executable instructions; The processor is configured to read the machine-executable instructions on the readable storage medium and execute the instructions to implement the steps of any one of the methods of claims 1-5.

Images