Submerged arc furnace control method, system, storage medium and electronic equipment

Abstract

The present invention proposes a method, system, storage medium and electronic device for controlling an electric arc furnace, which belongs to the field of automatic control technology. The method includes S1: obtaining the diameter of the electrode, the center distance multiple of the electrode, the specific resistance of the charge and the heat energy distribution coefficient of the charge layer in the electric arc furnace; S2: constructing an electric arc furnace control model; S3: substituting the i-phase operating resistance of the electrode into the electric arc furnace control model to determine the i-phase insertion depth of the electrode, and then optimizing the i-phase insertion depth of the electrode through the BP neural network model to obtain the optimal i-phase insertion depth, and controlling and adjusting the electric arc furnace through the optimal i-phase insertion depth. The present invention uses the operating resistance as the controlled variable, and the operating resistance is inversely proportional to the insertion depth of the electrode. When the operating resistance of one phase on the electrode changes and is automatically adjusted, the other two phases of the electrode will not participate in the automatic adjustment, thereby ensuring the reasonable heat distribution between the charge area and the molten pool area and the stability of the adjustment.

Description

Technical Field

[0001] The present invention belongs to the field of automatic control technology, and relates to automatic control technology of an electric arc furnace, and specifically to an electric arc furnace control method, system, storage medium and electronic equipment. Background Art

[0002] Submerged arc furnace is an electric furnace that melts materials by converting the buried hot arc of the electrode and the material resistance into heat energy. The electrode is an important part of the submerged arc furnace. During the smelting process, it is necessary to adjust the insertion depth of the electrode in the charge according to the changes in the furnace conditions to adjust the size of the furnace power and its power distribution in the charge area and the molten pool area. When smelting calcium carbide, a submerged arc furnace formed by a three-phase transformer in a right triangle arrangement is generally used. From an electrical point of view, the submerged arc furnace requires the three-phase load current to operate at a balanced rated value to fully utilize the potential of the submerged arc furnace and ensure the safe operation of the submerged arc furnace. Therefore, it is necessary to raise and lower the electrode during the smelting process to adjust the size of the three-phase load current. From the perspective of smelting technology, in addition to ensuring a certain power input, the submerged arc furnace also requires a certain insertion depth of the electrode in the charge, so that the electric heat power distribution in the charge area and the molten pool area is appropriate, so that the three phases of the electrode are connected to the molten pool, so as to achieve better production results.

[0003] The current submerged arc furnace control system uses current as the controlled variable, and adjusts the active power of the submerged arc furnace by adjusting the current. Since the insertion depth of the electrode is not linearly proportional to the current, using current as the controlled variable cannot guarantee that the electrode has a certain insertion depth in the charge, and thus cannot guarantee a reasonable heat distribution between the charge area and the molten pool area. In addition, when the current of one phase of the electrode deviates and is automatically adjusted, it will inevitably affect the automatic adjustment of the current of the other two phases of the electrode, resulting in unstable adjustment. Summary of the invention

[0004] In view of the above background technology description, the current control system of the electric arc furnace uses electric current as the regulated variable, and there are technical problems such as failure to ensure reasonable heat distribution between the charge area and the molten pool area and unstable regulation. To solve this technical problem, the present invention proposes an electric arc furnace control method, system, storage medium and electronic equipment.

[0005] The present invention uses the operating resistance as the adjusted variable. Since the operating resistance is inversely proportional to the insertion depth of the electrode, that is, the operating resistance and the insertion depth of the electrode are linearly related, when the operating resistance of one phase of the electrode changes and is automatically adjusted, the other two phases of the electrode will not participate in the automatic adjustment, thereby ensuring reasonable heat distribution between the charge area and the molten pool area and the stability of the adjustment.

[0006] In order to solve the above technical problems, the present invention adopts the following technical solutions:

[0007] The method for controlling a submerged arc furnace of the present invention comprises the following steps:

[0008] S1: Obtain the electrode diameter, electrode center distance multiple, charge specific resistance and charge layer heat energy distribution coefficient in the ore-fired furnace;

[0009] S2: Constructing the submerged arc furnace control model:

[0010]

[0011] In the formula, For electrode Phase operating resistance, unit: Ω; is the heat energy distribution coefficient of the charge layer, dimensionless; is the specific resistance of the charge, unit: Ω·cm; For electrode Phase insertion depth, unit: cm; is the center distance of the electrodes, unit: cm; is the multiple of the center distance of the electrodes, dimensionless; is the diameter of the electrode, unit: cm; is the phase identifier of the electrode, dimensionless;

[0012] S3: Place the electrode The phase operating resistance is substituted into the submerged arc furnace control model to determine the electrode Phase insertion depth, and then the BP neural network model is used to analyze the electrode Phase insertion depth is optimized to obtain the best Phase insertion depth, through the optimal The phase insertion depth is used to control the furnace.

[0013] Further defined, in step S3, the electrode The calculation formula of phase operating resistance is:

[0014]

[0015]

[0016]

[0017]

[0018]

[0019] In the formula, is the voltage difference between phase C and phase A of the electrode, unit: V; is the A-phase current of the electrode, unit: A; is the A-phase operating resistance of the electrode, unit: Ω; is the C-phase current of the electrode, unit: A; is the phase angle between the C phase and the A phase of the electrode, unit: °; is the C-phase operating resistance of the electrode, unit: Ω; is the C-phase short-circuit reactance of the electrode, unit: Ω; is the A-phase short-circuit reactance of the electrode, unit: Ω; is the B-phase current of the electrode, unit: A; is the phase angle between the A phase and the B phase of the electrode, unit: °; is the B-phase operating resistance of the electrode, unit: Ω; is the B-phase short-circuit reactance of the electrode, unit: Ω.

[0020] It is further defined that step S3 specifically includes: substituting the operating resistance into the submerged arc furnace control model to determine the insertion depth of the electrode, then optimizing the insertion depth of the electrode through the BP neural network model to obtain the optimal insertion depth, and controlling the submerged arc furnace through the optimal insertion depth.

[0021] It is further defined that the optimization of the insertion depth of the electrode through the BP neural network model specifically includes: inputting the maximum power of the electrode into the BP neural network model, performing optimization calculations using the BP neural network model, and obtaining the optimal insertion depth of the electrode; wherein the BP neural network model is trained using the historical maximum power data of the electrode and the historical optimal insertion depth data of the electrode.

[0022] It is further defined that the number of neurons in the input layer of the BP neural network model is There are three, which are the maximum power of phase A of the electrode , the maximum power of the electrode phase B The maximum power of phase C of the electrode ;

[0023] The number of neurons in the output layer of the BP neural network model There are three, which are the optimal insertion depth h of the electrode phase A. A , the optimal insertion depth h of the electrode B phase B The optimal insertion depth h of the C phase of the electrode C .

[0024] Further defined, the calculation formula of the heat energy distribution coefficient of the charge layer is:

[0025]

[0026] In the formula, is the heat of the charge layer, unit: J; is the heat of the molten pool layer, unit: J; is the heat energy distribution coefficient of the charge layer, dimensionless.

[0027] It is further defined that the method for controlling an electric arc furnace is applied to the smelting production of calcium carbide.

[0028] The submerged arc furnace control system of the present invention is applied to the submerged arc furnace control method described above, and comprises:

[0029] Parameter acquisition module: used to obtain the electrode diameter, electrode center distance multiple, charge specific resistance and charge layer heat energy distribution coefficient in the ore-fired furnace;

[0030] Model building module: used to build the submerged arc furnace control model:

[0031]

[0032] In the formula, For electrode Phase operating resistance, unit: Ω; is the heat energy distribution coefficient of the charge layer, dimensionless; is the specific resistance of the charge, unit: Ω·cm; For electrode Phase insertion depth, unit: cm; is the center distance of the electrodes, unit: cm; is the multiple of the center distance of the electrodes, dimensionless; is the diameter of the electrode, unit: cm; is the phase identifier of the electrode, dimensionless;

[0033] And furnace control module: used to adjust the electrode The phase operating resistance is substituted into the submerged arc furnace control model to determine the electrode Phase insertion depth, and then the BP neural network model is used to analyze the electrode Phase insertion depth is optimized to obtain the best Phase insertion depth, through the optimal The phase insertion depth is used to control the furnace.

[0034] The present invention provides a storage medium storing a program file, wherein the program file is executed to implement program instructions formed by the above-mentioned method for controlling an electric arc furnace.

[0035] The present invention provides an electronic device, comprising a processor and a memory coupled to each other, wherein:

[0036] The memory is used to store program instructions formed by the above-mentioned method for controlling the electric arc furnace;

[0037] The processor is used to execute program instructions stored in the memory.

[0038] Compared with the prior art, the present invention has the following beneficial effects:

[0039] 1. The method for controlling an electric arc furnace of the present invention uses the operating resistance as the controlled variable. Since the operating resistance is inversely proportional to the insertion depth of the electrode, that is, the operating resistance is linearly related to the insertion depth of the electrode, when the operating resistance of one phase of the electrode changes and is automatically adjusted, the other two phases of the electrode will not participate in the automatic adjustment, thereby ensuring reasonable heat distribution between the charge area and the molten pool area and the stability of the adjustment.

[0040] 2. In the actual adjustment process of the submerged arc furnace, the insertion depth of each phase of the electrode needs to be adjusted separately according to the actual furnace conditions. Phase operating resistance calculation of electrode Phase insertion depth, according to the electrode Phase operated resistance control electrode The insertion depth is more in line with the furnace control adjustment of the ore-fired furnace during actual operation, further ensuring the reasonable heat distribution between the charge area and the molten pool area and the stability of the adjustment, avoiding over-burning or under-burning during the melting process.

[0041] 3. In the present invention, the insertion depth of the electrode is optimized through the BP neural network model to obtain the optimal insertion depth, and the furnace is controlled and adjusted by the optimal insertion depth. Mainly, the insertion depth of the electrode is optimized through the BP neural network model under the condition of taking the maximum power of the electrode as input, so that the submerged arc furnace can operate at the highest thermal efficiency, reduce heat consumption, and save energy. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 A schematic diagram of a method for controlling a mineral-arc furnace for calcium carbide according to the present invention;

[0043] Figure 2 It is a schematic diagram of the furnace control system of the electric carbide ore furnace of the present invention. DETAILED DESCRIPTION

[0044] The technical solution of the present invention is further explained below in conjunction with the accompanying drawings and embodiments, but the present invention is not limited to the implementation modes described below.

[0045] The operating resistance of an electric arc furnace essentially depends on the characteristics of the charge. The greater the charge resistance, the greater the operating resistance. Therefore, controlling the operating resistance to remain unchanged can control the charge resistance to remain unchanged. At the same time, the heat energy distribution coefficient of the charge layer changes with the change of the operating resistance. When the operating resistance is greater, the heat energy distribution coefficient of the charge layer is also greater, and more heat is used to heat the charge; when the operating resistance is smaller, the heat energy distribution coefficient of the charge layer is also smaller, and less heat is used to heat the charge. Therefore, the heat distribution of the charge layer can also be reasonably reflected by the operating resistance, that is, by adjusting the operating resistance, reasonable heat distribution between the charge area and the molten pool area can be achieved.

[0046] The operating resistance is inversely proportional to the insertion depth of the electrode. If the operating resistance is kept unchanged, the insertion depth of the electrode can be controlled, which is beneficial to ensure the stability of regulation in the charge area and the molten pool area.

[0047] The operating resistance is used as the controlled variable. The adjustment of the operating resistance is different from that of the current. When the operating resistance of one phase of the electrode increases or decreases, the operating resistance of the other two phases of the electrode will not participate in the adjustment. For example: when one phase of the electrode is short-circuited relative to the bottom of the ore-fired furnace, its current reaches the short-circuit current, and the effective voltage approaches zero. Therefore, the operating resistance of the electrode of this phase will be automatically adjusted because it is larger than the given value. The other two phases of the electrode will increase their current and voltage to the original value at the same time due to the displacement of the midpoint. times, so its ratio remains unchanged, that is, the operating resistance has no deviation from the given value and does not participate in the regulation. Therefore, it is most scientific and reasonable to take the operating resistance as the regulated quantity.

[0048] See also Figure 1 The present invention provides a method for controlling a submerged arc furnace, comprising the following steps:

[0049] S1: Obtain the electrode diameter, electrode center distance multiple, charge specific resistance and charge layer heat energy distribution coefficient in the ore-fired furnace;

[0050] S2: Constructing the submerged arc furnace control model:

[0051]

[0052] In the formula, For electrode Phase operating resistance, unit: Ω; is the heat energy distribution coefficient of the charge layer, dimensionless; is the specific resistance of the charge, unit: Ω·cm; For electrode Phase insertion depth, unit: cm; is the center distance of the electrodes, unit: cm; is the multiple of the center distance of the electrodes, dimensionless; is the diameter of the electrode, unit: cm; is the phase identifier of the electrode, dimensionless, is A, B or C;

[0053] S3: Substitute the operating resistance into the submerged arc furnace control model to determine the insertion depth of the electrode, thereby controlling and adjusting the submerged arc furnace.

[0054] In the present invention, step S3 specifically includes: substituting the operating resistance into the submerged arc furnace control model to determine the electrode insertion depth, then optimizing the electrode insertion depth through the BP neural network model to obtain the optimal insertion depth, and controlling the submerged arc furnace through the optimal insertion depth. Through the optimization process, the submerged arc furnace can work at the highest thermal efficiency, reduce heat consumption, and save energy.

[0055] Among them, the maximum power of the electrode is:

[0056]

[0057] In the formula, For electrode Maximum phase power, unit: W; For electrode Phase current, unit: V; For electrode Phase operating resistance, unit: Ω; is the phase identifier of the electrode, dimensionless, A, B or C.

[0058] Among them, the electrode The calculation formula of phase operating resistance is:

[0059]

[0060]

[0061]

[0062]

[0063]

[0064] In the formula, is the voltage difference between phase C and phase A of the electrode, unit: V; is the A-phase current of the electrode, unit: A; is the A-phase operating resistance of the electrode, unit: Ω; is the C-phase current of the electrode, unit: A; is the phase angle between the C phase and the A phase of the electrode, unit: °; is the C-phase operating resistance of the electrode, unit: Ω; is the C-phase short-circuit reactance of the electrode, unit: Ω; is the A-phase short-circuit reactance of the electrode, unit: Ω; is the B-phase current of the electrode, unit: A; is the phase angle between the A phase and the B phase of the electrode, unit: °; is the B-phase operating resistance of the electrode, unit: Ω; It is the short-circuit reactance of phase B of the electrode, unit: Ω.

[0065] The above equations can be combined to obtain the A-phase, B-phase and C-phase operating resistances of the electrode.

[0066] Specifically, optimizing the insertion depth of the electrode through the BP neural network model specifically includes: inputting the maximum power of the electrode into the BP neural network model, and performing optimization calculations using the BP neural network model to obtain the optimal insertion depth of the electrode; wherein the BP neural network model is trained using the historical maximum power data of the electrode and the historical optimal insertion depth data of the electrode, wherein the sample data formed by the historical maximum power data of the electrode and the sample data formed by the historical optimal insertion depth data of the electrode are both not less than 100.

[0067] In the present invention, the number of neurons in the input layer of the BP neural network model is There are three, which are the maximum power of phase A of the electrode , the maximum power of the electrode phase B The maximum power of phase C of the electrode ,Right now .

[0068] The number of neurons in the hidden layer of the BP neural network model is nine, namely .

[0069] The number of neurons in the output layer of the BP neural network model There are three, which are the optimal insertion depth h of the electrode phase A. A , the optimal insertion depth h of the electrode B phase B The optimal insertion depth h of the C phase of the electrode C ,Right now .

[0070] In the present invention, the calculation formula of the heat energy distribution coefficient of the charge layer is:

[0071]

[0072] In the formula, is the heat of the charge layer, unit: J; is the heat of the molten pool layer, unit: J; is the heat energy distribution coefficient of the charge layer, dimensionless.

[0073] Preferably, the method for controlling an electric arc furnace of the present invention is applied to the smelting production of calcium carbide. In addition, it can also be applied to the smelting production of other ores, metals, etc.

[0074] The present invention uses the operating resistance as the adjusted variable, and the operating resistance is inversely proportional to the insertion depth of the electrode. When the operating resistance of one phase of the electrode changes and is automatically adjusted, the other two phases of the electrode will not participate in the automatic adjustment, thereby ensuring reasonable heat distribution between the charge area and the molten pool area and the stability of the adjustment.

[0075] See also Figure 2 The electric arc furnace control system of the present invention is applied to the electric arc furnace control method, comprising:

[0076] Parameter acquisition module: used to obtain the electrode diameter, electrode center distance multiple, charge specific resistance and charge layer heat energy distribution coefficient in the ore-fired furnace;

[0077] Model building module: used to build the submerged arc furnace control model:

[0078]

[0079] In the formula, For electrode Phase operating resistance, unit: Ω; is the heat energy distribution coefficient of the charge layer, dimensionless; is the specific resistance of the charge, unit: Ω·cm; For electrode Phase insertion depth, unit: cm; is the center distance of the electrodes, unit: cm; is the multiple of the center distance of the electrodes, dimensionless; is the diameter of the electrode, unit: cm; is the phase identifier of the electrode, dimensionless, is A, B or C;

[0080] And furnace control module: used to adjust the electrode The phase operating resistance is substituted into the submerged arc furnace control model to determine the electrode Phase insertion depth, and then the BP neural network model is used to analyze the electrode Phase insertion depth is optimized to obtain the best Phase insertion depth, through the optimal The phase insertion depth is used to control the furnace.

[0081] The submerged arc furnace control system of the present invention is completely corresponding to the above-mentioned submerged arc furnace control method. For the specific contents of the parameter acquisition module, model building module and furnace control module, please refer to the description of the above-mentioned submerged arc furnace control method.

[0082] The present invention provides a storage medium storing a program file, wherein the program file is executed to implement program instructions formed by the above-mentioned method for controlling an electric arc furnace.

[0083] The storage medium in the present invention may specifically include random access memory (RAM), internal memory, read-only memory (ROM), programmable ROM, erasable programmable ROM, register, hard disk, removable disk or CD-ROM. It should be noted that those skilled in the art may specifically select the form and type of storage medium according to actual use requirements, and the present invention does not make further specific limitations.

[0084] The present invention discloses an electronic device, comprising a processor and a memory coupled to each other, wherein the memory is used to store program instructions formed by the above-mentioned method for controlling an electric arc furnace; and the processor is used to execute the program instructions stored in the memory.

[0085] The electronic device in the present invention includes any electronic device that can execute program instructions, such as a computer, a mobile terminal or a wearable device.

[0086] The above content is only used to illustrate the technical solution of the present invention, rather than to limit the present invention. Although the present invention has been described in detail with reference to the foregoing, a person skilled in the art should understand that the technical solution described above can still be modified, or part or all of the technical features thereof can be replaced by equivalents. However, these modifications or replacements do not make the essence of the corresponding technical solution deviate from the scope of the technical solution of the present invention.

Claims

1. A method for controlling a submerged arc furnace, characterized in that: The following steps are involved: S1: Obtain the electrode diameter, electrode center distance multiple, charge specific resistance and charge layer heat energy distribution coefficient in the ore-fired furnace; S2: Constructing the submerged arc furnace control model: In the formula, For electrode Phase operating resistance, unit: Ω; is the heat energy distribution coefficient of the charge layer, dimensionless; is the specific resistance of the charge, unit: Ω·cm; For electrode Phase insertion depth, unit: cm; is the center distance of the electrodes, unit: cm; is the multiple of the center distance of the electrodes, dimensionless; is the diameter of the electrode, unit: cm; is the phase identifier of the electrode, dimensionless; S3: Place the electrode The phase operating resistance is substituted into the submerged arc furnace control model to determine the electrode Phase insertion depth, and then the BP neural network model is used to analyze the electrode Phase insertion depth is optimized to obtain the best Phase insertion depth, through the optimal The phase insertion depth is used to control the furnace. Among them, the electrode The calculation formula of phase operating resistance is: In the formula, is the voltage difference between phase C and phase A of the electrode, unit: V; is the A-phase current of the electrode, unit: A; is the A-phase operating resistance of the electrode, unit: Ω; is the C-phase current of the electrode, unit: A; is the phase angle between the C phase and the A phase of the electrode, unit: °; is the C-phase operating resistance of the electrode, unit: Ω; is the C-phase short-circuit reactance of the electrode, unit: Ω; is the A-phase short-circuit reactance of the electrode, unit: Ω; is the B-phase current of the electrode, unit: A; is the phase angle between the A phase and the B phase of the electrode, unit: °; is the B-phase operating resistance of the electrode, unit: Ω; It is the short-circuit reactance of phase B of the electrode, unit: Ω.

2. The method for controlling a submerged arc furnace according to claim 1, characterized in that: The optimization of the electrode insertion depth by the BP neural network model specifically includes: inputting the maximum power of the electrode into the BP neural network model, performing optimization calculation using the BP neural network model, and obtaining the optimal insertion depth of the electrode; wherein the BP neural network model is trained using the historical maximum power data of the electrode and the historical optimal insertion depth data of the electrode.

3. The method for controlling a submerged arc furnace according to claim 2, characterized in that: The number of neurons in the input layer of the BP neural network model There are three, which are the maximum power of phase A of the electrode , the maximum power of the electrode phase B The maximum power of phase C of the electrode ; The number of neurons in the output layer of the BP neural network model There are three, which are the optimal insertion depth h of the electrode phase A. A , the optimal insertion depth h of the electrode B phase B The optimal insertion depth h of the C phase of the electrode C .

4. The method for controlling a submerged arc furnace according to any one of claims 1 to 3, characterized in that: The calculation formula of the heat energy distribution coefficient of the charge layer is: In the formula, is the heat of the charge layer, unit: J; is the heat of the molten pool layer, unit: J; is the heat energy distribution coefficient of the charge layer, dimensionless.

5. The method for controlling a submerged arc furnace according to any one of claims 1 to 3, characterized in that: The method for controlling a submerged arc furnace is applied to the smelting production of calcium carbide.

6. A submerged arc furnace control system, applied to the submerged arc furnace control method according to claim 1, characterized in that: include: Parameter acquisition module: used to obtain the electrode diameter, electrode center distance multiple, charge specific resistance and charge layer heat energy distribution coefficient in the ore-fired furnace; Model building module: used to build the submerged arc furnace control model: In the formula, For electrode Phase operating resistance, unit: Ω; is the heat energy distribution coefficient of the charge layer, dimensionless; is the specific resistance of the charge, unit: Ω·cm; For electrode Phase insertion depth, unit: cm; is the center distance of the electrodes, unit: cm; is the multiple of the center distance of the electrodes, dimensionless; is the diameter of the electrode, unit: cm; is the phase identifier of the electrode, dimensionless; And furnace control module: used to adjust the electrode The phase operating resistance is substituted into the submerged arc furnace control model to determine the electrode Phase insertion depth, and then the BP neural network model is used to analyze the electrode Phase insertion depth is optimized to obtain the best Phase insertion depth, through the optimal The phase insertion depth is used to control the furnace. Among them, the electrode The calculation formula of phase operating resistance is: In the formula, is the voltage difference between phase C and phase A of the electrode, unit: V; is the A-phase current of the electrode, unit: A; is the A-phase operating resistance of the electrode, unit: Ω; is the C-phase current of the electrode, unit: A; is the phase angle between the C phase and the A phase of the electrode, unit: °; is the C-phase operating resistance of the electrode, unit: Ω; is the C-phase short-circuit reactance of the electrode, unit: Ω; is the A-phase short-circuit reactance of the electrode, unit: Ω; is the B-phase current of the electrode, unit: A; is the phase angle between the A phase and the B phase of the electrode, unit: °; is the B-phase operating resistance of the electrode, unit: Ω; It is the short-circuit reactance of phase B of the electrode, unit: Ω.

7. A storage medium, characterized in that: A program file is stored, and the program file is executed to implement program instructions formed by the method for controlling an electric arc furnace according to any one of claims 1 to 3.

8. An electronic device, characterized in that: The invention comprises a processor and a memory coupled to each other, wherein: The memory is used to store program instructions formed by the method for controlling a submerged arc furnace according to any one of claims 1 to 3; The processor is used to execute program instructions stored in the memory.

Images