A method for predicting and judging smelting collapse of a submerged arc furnace based on mutation detection, and an electronic device

Abstract

A kind of based on the prediction judgment method of smelting collapse of submerged arc furnace based on mutation detection, and electronic equipment for running the method.It relates to the technical field of submerged arc furnace electrode control, by real-time acquisition of the electrode current of three-phase electrode of submerged arc furnace;And calculate the current derivative of electrode current at current sampling time;Current derivative is compared with trigger threshold value, when detecting the current derivative of any phase electrode is less than trigger threshold value, start collapse prediction process;In collapse prediction process, current derivative is continuously lower than trigger threshold value in current detection period, and electrode current attenuation exceeds current warning value, trigger collapse fault early warning.Compared with traditional judgment mode, the method has better accuracy, and can shield disturbance well, and truly reflects the situation in the furnace, provides a good basis for user to judge smelting state and improve production level.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of electric arc furnace electrode control, in particular to a method for predicting and judging electric arc furnace smelting collapse based on mutation detection, and an electronic device. BACKGROUND

[0002] Collapse refers to the phenomenon that high-temperature gas in the furnace is rapidly ejected from the electric furnace along with red material and semi-finished product in the process of electric arc furnace smelting production. The collapse phenomenon reflects the permeability of the furnace charge. When the permeability of the furnace charge deteriorates, the furnace pressure increases, and the furnace gas is discharged along the periphery of the electrode, causing a fire, which increases the local temperature, while the temperature of the material layer decreases, resulting in heat loss. At this time, accidents such as collapse are prone to occur. Collapse can be roughly divided into large collapse and small collapse according to the intensity. Frequent small collapse is caused by high water content of raw materials and poor permeability. Frequent large collapse is caused by high magnesium oxide content in raw materials or excessive powder, which causes large-area material layer to be cemented, resulting in frequent and large collapse. Collapse can cause serious fire at the gap of the furnace cover, and even damage the explosion-proof port. Collapse can release high-temperature gas and vaporized metal steam in the crucible area, resulting in waste of heat and raw materials. Serious collapse accidents can cause severe vibration and shock waves, damage the heat insulation lining bricks, and cause the material to be ejected from the furnace outlet. Strong vibration can also damage other equipment around. Collapse can indirectly damage the material layer structure, causing the mixing of cold and hot materials, unreasonable temperature distribution of each layer of the furnace charge, heat waste, and impact on product quality.

[0003] Collapse is an important phenomenon of the reaction furnace condition. The frequency and intensity of collapse, combined with other auxiliary parameters, can be used to diagnose the causes of abnormal furnace conditions, including furnace water leakage, abnormal water content of raw materials, abnormal particle size of raw materials, and whether the electrode insertion depth is reasonable. Collapse is a common inducement of production accidents in electric arc furnaces. Through prediction and judgment of collapse, accidents can be avoided, causes can be found in time, production parameters can be adjusted, and collapse can be avoided or mitigated to ensure stable production. The existing methods for judging collapse are mostly realized by manual observation and analysis of the smelting material surface and the fire condition, and the judgment is made according to experience. This method has serious lag and the possibility of misjudgment, and it is impossible to observe and judge for a sealed furnace. SUMMARY

[0004] The present application aims to provide a method for predicting and judging electric arc furnace smelting collapse based on mutation detection, which can quickly and accurately predict and judge the occurrence of collapse, and has good shielding effect on disturbance.

[0005] Another object of the present application is to provide an electronic device which can be used to realize the above-mentioned method for predicting and judging electric arc furnace smelting collapse based on mutation detection.

[0006] Embodiments of the present application are implemented as follows:

[0007] A smelting collapse prediction and judgment method based on mutation detection of an electric arc furnace, comprising:

[0008] S1. Real-time collection of electrode current of three-phase electrodes of the electric arc furnace; and calculation of current derivative of the electrode current at a current sampling time;

[0009] S2. Comparison of the current derivative with a trigger threshold value; when the current derivative of any phase electrode is detected to be less than the trigger threshold value, a smelting collapse prediction process is started;

[0010] S3. In the smelting collapse prediction process, when the current derivative is continuously less than the trigger threshold value and the electrode current attenuation exceeds a current warning value within a current detection period, a smelting collapse fault warning is triggered.

[0011] Further, in other preferred embodiments of the present application, the trigger threshold value adopts a dynamic updating mechanism, comprising:

[0012] Under a normal furnace condition, every 10-15 minutes is taken as a sampling period, the current derivative within the current sampling period is continuously collected, and the minimum value of the current derivative is retained; at the end of the current sampling period, 1.1-1.3 times of the minimum value is taken as a new trigger threshold value.

[0013] Further, in other preferred embodiments of the present application, in the smelting collapse prediction process, the way of judging whether the current derivative is continuously less than the trigger threshold value is:

[0014] S31. Two counters Samps and Counter are set and reset to 0; within the current detection period, the Samps counter is added by 1 every time the current derivative is recorded; if the current derivative is less than the trigger threshold value, the Counter counter is added by 2, otherwise the Counter counter is subtracted by 1;

[0015] S32. Every time the counting is completed, a judgment is made; if the Counter counter is less than 0, the smelting collapse prediction process is directly ended; if the Counter counter is greater than 0, the next recording is continued until the current detection period is ended;

[0016] S33. After the current detection period is ended, the Counter counter and the Samps counter are compared; if the Counter counter is less than the Samps counter, the smelting collapse prediction process is directly ended; if the Counter counter is greater than the Samps counter, electrode current comparison is performed.

[0017] Further, in other preferred embodiments of the present application, the method of electrode current comparison comprises:

[0018] S34. Comparing the electrode current at the start point and the end point of the current detection period, taking 0.7-0.8 times of the electrode current at the start point as the current early warning value, if the electrode current at the end point is greater than the current early warning value, then directly ending the material collapse prediction process; if the electrode current at the end point is less than the current early warning value, then triggering the material collapse fault early warning.

[0019] Further, in other preferred embodiments of the present application, further comprising:

[0020] S4. After the material collapse fault early warning is triggered, starting the furnace pressure detection process, verifying whether the material collapse occurs according to the variation of the furnace pressure.

[0021] Further, in other preferred embodiments of the present application, the furnace pressure detection process comprises:

[0022] S41. Real-time collecting the furnace pressure of the electric arc furnace; and calculating the furnace pressure derivative of the furnace pressure at the current sampling time;

[0023] S42. Comparing the furnace pressure derivative with the furnace pressure threshold value, when the furnace pressure derivative is continuously less than the furnace pressure threshold value and the furnace pressure attenuation exceeds the furnace pressure warning value within the furnace pressure detection period, then determining that the material collapse actually occurs.

[0024] Further, in other preferred embodiments of the present application, further comprising:

[0025] S5. Continuously recording the current derivative and the furnace pressure derivative, when the current derivative is continuously greater than the trigger threshold value and the furnace pressure derivative is continuously greater than the furnace pressure threshold value, then determining that the material collapse has ended.

[0026] Further, in other preferred embodiments of the present application, the S5 step comprises:

[0027] S51. Setting the initial value of Samps to be 4-7 and the initial value of Counter to be 0, each time recording the current derivative, the Samps count is added by 1; if the current derivative is greater than the trigger threshold value, then the Counter count is added by 2, otherwise the Counter count is reduced by 1;

[0028] S52. Each time the counting is completed, determining, if the Counter count is greater than the Samps count, then determining that the current attenuation has ended;

[0029] S53. Referring to the S51-S52 steps, determining the furnace pressure derivative, if the Counter count is greater than the Samps count, then determining that the furnace pressure attenuation has ended;

[0030] S54. When the current attenuation and the furnace pressure attenuation have both ended, determining that the material collapse has ended.

[0031] Furthermore, in other preferred embodiments of the present invention, it further includes:

[0032] S6. Determine the specific location of the material collapse based on the degree of attenuation of the electrode current of the three-phase electrodes.

[0033] An electronic device includes a processor and a memory, the memory storing a computer program that, when executed by the processor, implements the above-described method for predicting and judging collapse in ferroalloy smelting based on mutation detection.

[0034] The beneficial effects of the embodiments of the present invention are:

[0035] This invention provides a method for predicting and judging material collapse in submerged arc furnace smelting based on mutation detection, as well as an electronic device for running the method. It collects the electrode currents of the three-phase electrodes of the submerged arc furnace in real time; calculates the current derivative of the electrode current at the current sampling moment; compares the current derivative with a trigger threshold; and initiates the material collapse prediction process when the current derivative of any phase electrode is detected to be less than the trigger threshold. During the material collapse prediction process, if the current derivative is continuously lower than the trigger threshold within the current detection cycle, and the electrode current decay exceeds the current warning value, a material collapse fault warning is triggered. Compared with traditional judgment methods, this method has better accuracy and can effectively shield disturbances, truly reflecting the furnace condition, providing a solid foundation for users to judge the smelting status and improve production levels. Attached Figure Description

[0036] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0037] Figure 1 A flowchart illustrating a method for predicting and judging collapse in submerged arc furnace smelting based on mutation detection, provided in an embodiment of the present invention.

[0038] Figure 2 The flowchart illustrates the dynamic updating of the trigger threshold / furnace pressure threshold in a method for predicting and judging collapse in smelting in an electric arc furnace based on mutation detection, as provided in an embodiment of the present invention. Detailed Implementation

[0039] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention. Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to represent selected embodiments of the invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention. Example

[0040] This embodiment provides a method for predicting and judging material collapse in submerged arc furnace smelting based on mutation detection, referring to... Figure 1 As shown, it includes:

[0041] S1. Real-time acquisition of electrode currents of the three-phase electrodes of the electric arc furnace; and calculation of the current derivative of the electrode current at the current sampling moment.

[0042] The current derivative of each phase electrode is calculated independently, as follows:

[0043] ,

[0044] This involves subtracting the electrode current value from the previous sampling time from the current sampling time, and then dividing the difference by the interval between the two sampling times. Typically, the interval between two sampling times is 1 to 2 seconds.

[0045] S2. Compare the current derivative with the trigger threshold. When the current derivative of any phase electrode is detected to be less than the trigger threshold, start the collapse prediction process.

[0046] It should be noted that the trigger threshold uses a dynamic update mechanism, refer to... Figure 2 As shown, it includes:

[0047] Under normal furnace conditions, a sampling cycle is set at 10 minutes, and the current derivative within the current sampling cycle is continuously collected, while the minimum value of the current derivative is retained. At the end of the current sampling cycle, 1.2 times the minimum value is used as the new trigger threshold.

[0048] The dynamically updated trigger threshold can be adjusted in real time according to changes in furnace conditions, making it more adaptable and more accurate in predicting material collapse compared to a fixed preset value.

[0049] S3. In the material collapse prediction process, when the current derivative is continuously lower than the trigger threshold during the current detection cycle and the electrode current decays beyond the current warning value, a material collapse fault warning is triggered.

[0050] Furthermore, in the collapse prediction process, the method for determining whether the current derivative is continuously lower than the trigger threshold is as follows:

[0051] S31. Set two counters, Samples and Counter, and reset them to 0. During the current detection cycle (set to 2s here), the Samples counter is incremented by 1 each time the current derivative is recorded. If the current derivative is less than the trigger threshold, the Counter counter is incremented by 2, and vice versa.

[0052] S32. After each count is completed, a judgment is made. If the Counter count is less than 0, the collapse prediction process ends directly; if the Counter count is greater than 0, the next recording continues until the current detection cycle ends.

[0053] S33. After the current detection cycle ends, compare the Counter count and the Samples count. If the Counter count is less than the Samples count, then directly end the collapse prediction. Flow If the Counter count is greater than the Samples count, then an electrode current comparison is performed.

[0054] For collapse prediction processes that end prematurely, they are considered normal disturbances and will not trigger collapse fault warnings.

[0055] Furthermore, the methods for comparing electrode currents include:

[0056] S34. Compare the electrode currents at the start and end points of the current detection cycle, and use the electrode current at the start point (denoted as I) as the reference value. t0 The current warning value is 0.8 times that of the electrode current at the termination point (denoted as I). t If the current is greater than the current warning value, the collapse prediction process will end directly; if the electrode current at the termination point is less than the current warning value, a collapse fault warning will be triggered.

[0057] Furthermore, the method for predicting and judging collapse of smelting charge in an electric arc furnace based on mutation detection provided in this embodiment also includes:

[0058] S4. After the collapse fault warning is triggered, start the furnace pressure detection process and verify whether a collapse has occurred based on the changes in furnace pressure.

[0059] Furthermore, the furnace pressure testing process includes:

[0060] S41. Real-time acquisition of the furnace pressure inside the submerged arc furnace; and calculation of the furnace pressure derivative at the current sampling time;

[0061] S42. Compare the furnace pressure derivative with the furnace pressure threshold. During the furnace pressure detection cycle, if the furnace pressure derivative is continuously less than the furnace pressure threshold and the pressure decay in the furnace exceeds the furnace pressure warning value, then it is determined that the collapse has actually occurred.

[0062] Furthermore, the calculation method for the furnace pressure derivative is similar to that for the current derivative, and is calculated according to the following formula:

[0063] ,

[0064] The process involves subtracting the furnace pressure value from the previous sampling time from the current sampling time, and then dividing the difference by the interval between the two sampling times. Typically, the interval between two sampling times is 2 to 3 seconds.

[0065] Optionally, the furnace pressure threshold also adopts a real-time update mechanism, which can be referred to in the update method of the trigger threshold.

[0066] Furthermore, the method for determining whether the furnace pressure derivative is continuously less than the furnace pressure threshold is the same as that for the current derivative, and can be found in steps S31-S34. The furnace pressure at the start of the furnace pressure detection cycle (denoted as P) is used. t0 The furnace pressure warning value is 0.8 times that of the furnace pressure at the termination point (denoted as P). t If the pressure inside the furnace is greater than the furnace pressure warning value, it is determined that the collapse has not yet occurred; if the pressure inside the furnace at the termination point is less than the furnace pressure warning value, it is determined that the collapse has actually occurred.

[0067] Furthermore, the method for predicting and judging collapse of smelting charge in an electric arc furnace based on mutation detection provided in this embodiment also includes:

[0068] S5. Continuously record the current derivative and furnace pressure derivative. When the current derivative is continuously greater than the trigger threshold and the furnace pressure derivative is continuously greater than the furnace pressure threshold, it is determined that the collapse has ended.

[0069] Specifically, the S5 steps include:

[0070] S51. Set the initial value of Samples to 5 and the initial value of Counter to 0. Each time the current derivative is recorded, the Samples count is incremented by 1. If the current derivative is greater than the trigger threshold, the Counter count is incremented by 2, otherwise the Counter count is decremented by 1.

[0071] S52. After each count is completed, a judgment is made. If the Counter count is greater than the Samples count, the current decay is determined to be over.

[0072] S53. Referring to steps S51-S52, determine the furnace pressure derivative. If the Counter count is greater than the Samples count, then determine that the furnace pressure decay has ended.

[0073] S54. When both current decay and furnace pressure decay have ended, the collapse is considered to have ended.

[0074] Furthermore, the method for predicting and judging collapse of smelting charge in an electric arc furnace based on mutation detection provided in this embodiment also includes:

[0075] S6. Determine the specific location of the material collapse based on the degree of current decay of the three-phase electrodes. The collapse occurs near the electrode with the greatest current decay.

[0076] This embodiment also provides an electronic device, which includes a processor and a memory. The memory stores a computer program. When the computer program is executed by the processor, it implements the above-described method for predicting and judging material collapse in ferroalloy smelting based on mutation detection.

[0077] Application examples

[0078] This application example uses the collapse prediction and judgment method for submerged arc furnace smelting based on mutation detection provided in the example. Collapse prediction and judgment are performed in actual production with a one-year operating cycle, and the data is compared with the data before the method was not used (comparative example). The comparison results are as follows:

[0079] Table 1. Methods for Predicting and Judging Material Collapse

[0080] Number of early warning triggers Number of non-triggering Number of false triggers Number of non-timely triggering Miss rate Accuracy rate Timeliness rate Example 27 0 0 0 0 100% 100% Comparative example 25 6 3 5 21.4% 88.0% 80.0%

[0081] Among them, the number of warnings triggered refers to the total number of warnings triggered within a year; the number of warnings not triggered refers to the number of times a collapse actually occurred but a warning was not triggered; the number of warnings triggered falsely refers to the number of times a warning was triggered when a collapse did not actually occur; and the number of warnings not triggered in time refers to the number of times a warning was triggered when a collapse had already occurred.

[0082] False alarm rate = Number of untriggered events / (Number of untriggered events + Number of warnings triggered - Number of false alarms);

[0083] Accuracy = 1 – Number of false triggers / Number of warning triggers;

[0084] Timeliness rate = 1 – Number of untimely triggers / Number of warning triggers.

[0085] As shown in Table 1, the judgment method of this embodiment triggered 27 collapse warnings within a one-year period, with no instances of non-triggered, falsely triggered, or delayed triggering. In contrast, the traditional collapse prediction method triggered 25 collapse warnings within a year, including 6 missed warnings, 3 false triggers, and 5 delayed triggers. The missed warning rate was as high as 21.4%, and the accuracy and timeliness rates were only 88.0% and 80.0%, respectively. Therefore, the judgment method of this embodiment has better accuracy and timeliness compared to existing technologies, effectively helping operators assess furnace conditions and respond promptly.

[0086] In summary, this invention provides a method for predicting and judging material collapse in submerged arc furnace smelting based on mutation detection, as well as an electronic device for running this method. It collects the electrode currents of the three-phase electrodes of the submerged arc furnace in real time; calculates the current derivative of the electrode current at the current sampling moment; compares the current derivative with a trigger threshold; and initiates the material collapse prediction process when the current derivative of any phase electrode is detected to be less than the trigger threshold. During the material collapse prediction process, if the current derivative is continuously lower than the trigger threshold within the current detection cycle, and the electrode current decay exceeds the current warning value, a material collapse fault warning is triggered. Compared with traditional judgment methods, this method has better accuracy and can effectively shield disturbances, truly reflecting the furnace condition, providing a solid foundation for users to judge the smelting status and improve production levels.

[0087] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for predicting and judging material collapse in submerged arc furnace smelting based on mutation detection, characterized in that, include: S1. Real-time acquisition of electrode currents of the three-phase electrodes of the electric arc furnace; And calculate the current derivative of the electrode current at the current sampling time; S2. Compare the current derivative with the trigger threshold. When the current derivative of any phase electrode is detected to be less than the trigger threshold, start the collapse prediction process. S3. In the material collapse prediction process, when the current derivative is continuously lower than the trigger threshold during the current detection cycle, and the electrode current decays beyond the current warning value, a material collapse fault warning is triggered. S4. After the collapse fault warning is triggered, start the furnace pressure detection process and verify whether a collapse has occurred based on the changes in furnace pressure; In the collapse prediction process, the method for determining whether the current derivative is continuously lower than the trigger threshold is as follows: S31. Set two counters, Samples and Counter, and reset them to 0. During the current detection cycle, each time the current derivative is recorded, the Samples counter is incremented by 1; if the current derivative is less than the trigger threshold, the Counter counter is incremented by 2, otherwise the Counter counter is decremented by 1. S32. After each count is completed, a judgment is made. If the Counter count is less than 0, the collapse prediction process is terminated directly; if the Counter count is greater than 0, the next recording continues until the current detection cycle ends. S33. After the current detection cycle ends, compare the Counter count and the Samples count. If the Counter count is less than the Samples count, the collapse prediction process ends directly. If the Counter count is greater than the Samples count, the electrode current comparison is performed. The method for comparing electrode currents includes: S34. Compare the electrode currents at the start and end points of the current detection cycle, and use 0.7 to 0.8 times the electrode current at the start point as the current warning value. If the electrode current at the end point is greater than the current warning value, the collapse prediction process is terminated directly; if the electrode current at the end point is less than the current warning value, a collapse fault warning is triggered.

2. The method for predicting and judging material collapse in submerged arc furnace smelting according to claim 1, characterized in that, The trigger threshold adopts a dynamic update mechanism, including: Under normal furnace conditions, a sampling period of 10 to 15 minutes is used to continuously collect the current derivative within the current sampling period and retain the minimum value of the current derivative; at the end of the current sampling period, 1.1 to 1.3 times the minimum value is used as the new trigger threshold.

3. The method for predicting and judging material collapse in submerged arc furnace smelting according to claim 2, characterized in that, The furnace pressure detection process includes: S41. Real-time acquisition of the furnace pressure inside the submerged arc furnace; and calculation of the furnace pressure derivative at the current sampling time; S42. Compare the furnace pressure derivative with the furnace pressure threshold. During the furnace pressure detection cycle, if the furnace pressure derivative is continuously less than the furnace pressure threshold and the furnace pressure decay exceeds the furnace pressure warning value, then it is determined that the collapse has actually occurred.

4. The method for predicting and judging material collapse in submerged arc furnace smelting according to claim 3, characterized in that, Also includes: S5. Continuously record the current derivative and the furnace pressure derivative. When the current derivative is continuously greater than the trigger threshold and the furnace pressure derivative is continuously greater than the furnace pressure threshold, it is determined that the collapse has ended.

5. The method for predicting and judging material collapse in submerged arc furnace smelting according to claim 4, characterized in that, The S5 steps include: S51. Set the initial value of Samples to 4~7 and the initial value of Counter to 0. Each time the current derivative is recorded, the Samples count is incremented by 1. If the current derivative is greater than the trigger threshold, the Counter count is incremented by 2, otherwise the Counter count is decremented by 1. S52. After each count is completed, a judgment is made. If the Counter count is greater than the Samples count, the current decay is determined to be over. S53. Referring to steps S51-S52, determine the furnace pressure derivative. If the Counter count is greater than the Samples count, then determine that the furnace pressure decay has ended. S54. When both current decay and furnace pressure decay have ended, the collapse is considered to have ended.

6. The method for predicting and judging material collapse in submerged arc furnace smelting according to claim 5, characterized in that, Also includes: S6. Determine the specific location of the material collapse based on the degree of attenuation of the electrode currents of the three-phase electrodes.

7. An electronic device, characterized in that, It includes a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, it implements the method for predicting and judging the collapse of submerged arc furnace smelting material based on mutation detection as described in any one of claims 1 to 6.

Images