Method for optimizing material pushing mode and controlling burnout phenomenon in industrial silicon smelting

Abstract

The invention relates to the technical field of industrial silicon smelting, in particular to a method for optimizing a material pushing mode and controlling a burnout phenomenon in industrial silicon smelting. Comprising the following steps that a layered material distribution mode combining axial material pushing and radial material pushing is adopted, material distribution control is achieved through a multi-stage material pushing mechanism, burnout suppression operation is dynamically triggered on the basis of real-time temperature monitoring data, inert gas injection and covering material layer supplementing are synchronously executed, material pushing parameters are optimized in combination with an intelligent algorithm, and the material pushing efficiency is improved. The material pushing movement track and speed are automatically adjusted according to raw material characteristics and working condition changes. According to the method for optimizing the material pushing mode and controlling the burnout phenomenon in industrial silicon smelting, an integrated control system of dynamic self-adaptive material distribution, high-precision burnout suppression and multi-parameter intelligent optimization is constructed, and the problems existing in the prior art are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial silicon smelting technology, and in particular to a method for optimizing a material pushing mode and controlling a sparking phenomenon in industrial silicon smelting. Background Art

[0002] In the industrial silicon smelting process, pushing operations and ignition control are the core links that affect production efficiency, energy consumption and equipment life. However, the current technical solutions generally have the following key problems: traditional pushing devices mostly adopt a fixed pushing mode in a single direction (such as only axial or only radial), which leads to uneven distribution of materials in the furnace and easily forms local accumulation or areas with excessive porosity. Conventional ignition control relies on manual experience judgment or single-point temperature monitoring, and the response time is usually more than 30 seconds. Existing inert gas injection technologies mostly use a fixed angle and constant pressure injection strategy, and the gas coverage range does not match the shape of the ignition area well. Summary of the Invention

[0003] The present invention proposes a method for optimizing the material pushing method and controlling the sparking phenomenon in industrial silicon smelting, and solves the problems existing in the prior art by constructing an integrated control system of "dynamic adaptive material distribution-high-precision sparking suppression-multi-parameter intelligent optimization".

[0004] The technical solution adopted by the present invention is: a method for optimizing the material pushing method and controlling the spark phenomenon in industrial silicon smelting, comprising the following steps:

[0005] Step 1: Adopt a layered material distribution method that combines axial pushing and radial pushing, and realize material distribution control through a multi-level pushing mechanism;

[0006] Step 2: Dynamically trigger the fire suppression operation based on real-time temperature monitoring data, and simultaneously perform inert gas injection and replenishment of the cover layer;

[0007] Step 3: Combine intelligent algorithms to optimize pushing parameters and automatically adjust the pushing motion trajectory and speed according to raw material characteristics and working conditions.

[0008] As a further improvement of the present invention, the multi-stage pushing mechanism includes an adjustable angle pushing plate with a high-temperature resistant coating on the surface, and the inclination angle of the pushing plate can be accurately adjusted within the range of 30 degrees to 75 degrees.

[0009] As a further improvement of the present invention, the adjustable angle push plate is provided with a pressure sensing module and an angle feedback mechanism. When the pushing resistance value exceeds a preset threshold, the angle compensation adjustment is automatically triggered, and the compensation amplitude is 5%-15% of the detected resistance change.

[0010] As a further improvement of the present invention, the real-time temperature monitoring adopts a programmable multi-point infrared temperature measurement array, and the temperature measurement unit spacing and sampling frequency are dynamically configured according to the size of the furnace body.

[0011] As a further improvement of the present invention, the multi-point infrared temperature measurement array establishes a linkage control with the pushing mechanism. When the axial temperature gradient is detected to exceed 50°C / m, the pushing plate inclination angle is automatically adjusted by 3°-8° and the pushing speed is reduced by 10%-20%.

[0012] As a further improvement of the present invention, the inert gas injection adopts mixed gas injection with adjustable pressure, and the gas component ratio and injection duration are associated with the detected degree of temperature anomaly.

[0013] As a further improvement of the present invention, the mixed gas injection adopts a multi-angle dynamic blowing strategy, and the angle between the blowing axis and the material surface normal is dynamically adjusted to 15°-60° according to the temperature distribution characteristics, and the blowing angle in the high-temperature core area is 10°-25° larger than that in the edge area.

[0014] As a further improvement of the present invention, the intelligent algorithm includes a time series prediction model based on deep learning, which generates push parameter optimization instructions by fusing historical operation data with real-time sensor information.

[0015] As a further improvement of the present invention, the time series prediction model has a built-in adaptive learning mechanism, which automatically updates the model parameters after each production cycle. The updated weight coefficient is dynamically calculated based on the operating data of the last three cycles, and the update frequency is controlled to iterate once every 8-12 hours.

[0016] Beneficial effects of the present invention: The present invention realizes the intelligent linkage of axial and radial coordinated material distribution, real-time analysis of multi-dimensional temperature fields and dynamic blowing of inert gas by constructing a closed-loop control system of "dynamic pushing-intelligent perception-precise suppression", breaking through the technical bottlenecks of uneven material distribution, delayed fire response and rigid parameter control in traditional technologies, thereby improving the uniformity of material distribution by 40%, shortening the fire suppression response time to within 3 seconds, and reducing the power consumption per ton of silicon by 200-300kWh, while achieving the technical synergy effect of millisecond-level working condition recognition, multi-parameter dynamic matching and full-cycle self-optimization. DETAILED DESCRIPTION

[0017] In order to make the technical problems, technical solutions and beneficial effects to be solved by this application more clearly understood, this application is further described in detail below in conjunction with the embodiments. It should be understood that the embodiments described herein are only used to explain this application and are not intended to limit this application.

[0018] The present invention provides a method for optimizing the material pushing mode and controlling the spark phenomenon in industrial silicon smelting, comprising the following steps:

[0019] Step 1: Adopt a layered material distribution method that combines axial pushing and radial pushing, and realize material distribution control through a multi-level pushing mechanism;

[0020] Step 2: Dynamically trigger the fire suppression operation based on real-time temperature monitoring data, and simultaneously perform inert gas injection and replenishment of the cover layer;

[0021] Step 3: Combine intelligent algorithms to optimize pushing parameters and automatically adjust the pushing motion trajectory and speed according to raw material characteristics and working conditions.

[0022] In the present invention, the multi-stage pushing mechanism includes an adjustable angle pushing plate with a high temperature resistant coating on the surface, and the inclination angle of the pushing plate can be accurately adjusted within the range of 30 degrees to 75 degrees.

[0023] In the present invention, the adjustable angle push plate is provided with a pressure sensing module and an angle feedback mechanism. When the push resistance value exceeds a preset threshold, the angle compensation adjustment is automatically triggered, and the compensation amplitude is 5%-15% of the detected resistance change.

[0024] In the present invention, real-time temperature monitoring adopts a programmable and controlled multi-point infrared temperature measurement array, and the temperature measurement unit spacing and sampling frequency are dynamically configured according to the size of the furnace body.

[0025] In the present invention, a multi-point infrared temperature measurement array establishes a linkage control with the pushing mechanism. When the axial temperature gradient is detected to exceed 50°C / m, the pusher plate tilt angle is automatically adjusted by 3°-8° and the pushing speed is reduced by 10%-20%.

[0026] In the present invention, the inert gas blowing adopts the mixed gas injection with adjustable pressure, and the gas component ratio and blowing duration are related to the detected temperature anomaly degree.

[0027] In the present invention, the mixed gas injection adopts a multi-angle dynamic injection strategy, and the angle between the injection axis and the material surface normal is dynamically adjusted to 15°-60° according to the temperature distribution characteristics, and the injection angle in the high-temperature core area is 10°-25° larger than that in the edge area.

[0028] In the present invention, the intelligent algorithm includes a time series prediction model based on deep learning, which generates push parameter optimization instructions by fusing historical operation data with real-time sensor information.

[0029] In the present invention, the time series prediction model has a built-in adaptive learning mechanism, which automatically updates the model parameters after each production cycle. The updated weight coefficient is dynamically calculated based on the operating data of the last three cycles, and the update frequency is controlled to be iterated once every 8-12 hours.

[0030] Example:

[0031] An industrial silicon smelting enterprise adopts the method of the present invention for production implementation, and the specific operations are as follows

[0032] (1) Equipment configuration

[0033] Specifications of the submerged arc furnace: 33MVA three-phase electric furnace, furnace diameter 6.8m; Pushing system: Equipped with a three-stage pushing mechanism, the pushing plate adopts silicon carbide reinforced silicon nitride ceramic coating (thickness 2mm), equipped with a servo motor-driven angle adjustment mechanism (adjustment accuracy ±0.3°); Temperature monitoring: Installed 8 sets of infrared temperature measurement units (wavelength range 3-5μm), evenly distributed along the circumference of the furnace, with an axial spacing dynamic adjustment range of 300-800mm; Gas injection system: 36 nozzles arranged in a ring, equipped with a nitrogen / argon dual gas source mixing device (mixing ratio accuracy ±2vol%).

[0034] (2) Implementation process

[0035] Dynamic feeding stage: (1) Initial feeding parameter settings: first-stage pusher angle 45° (axial feeding); second-stage pusher angle 60° (radial feeding); feeding frequency: 8 times / minute. (2) Real-time adjustment mechanism: When the pressure sensor detects a sudden increase of 15% in the feeding resistance (corresponding to a 1.8% increase in the moisture content of the raw material), the angle compensation is triggered: the first-stage pusher angle is adjusted to 48° (compensation amplitude +3°), and the second-stage pusher angle is adjusted to 57° (compensation amplitude -3°). Based on the infrared temperature measurement data (axial temperature gradient reaches 43°C / m), the feeding speed is automatically reduced by 12%.

[0036] During the fire suppression phase: (1) the infrared temperature array detected a local temperature anomaly within 3.2 seconds (the temperature at coordinates X = 2.4 m, Y = 1.7 m jumped from 1450°C to 1680°C). (2) The control center synchronously executed the following: gas injection: injection angle of 52° (normal to the material surface) in the high-temperature core area; injection angle of 38° in the edge area; injection pressure of 0.65 MPa, duration of 8 seconds; gas ratio N2:Ar = 55:45. Covering material replenishment: the vibrating distributor operated at 85 Hz to replenish a layer of silica with a particle size of 5-8 mm and a thickness of 15 ± 1 mm.

[0037] Intelligent optimization stage: The deep learning model is updated every 10 hours based on the data from the last three cycles: (1) Input data: historical push angle sequence (sampling interval 5 seconds); temperature field temporal and spatial distribution data (resolution 100mm×100mm); raw material particle size distribution (D50=12mm, fluctuation ±1.5mm). (2) Output optimization instructions: push trajectory correction coefficient K=1.15 (increase radial distribution weight); push speed adjustment coefficient α=0.88 (reduce speed by 12%).

[0038] (3) Comparison of implementation effects

[0039] index Traditional methods Method of the present invention Improvement effect Material void ratio fluctuation ±22％ ±7％ 68% reduction Fire Response Time 32 seconds 2.8 seconds 91% shorter Power consumption per ton of silicon 12500kWh 12200kWh Reduce 300kWh Monthly electrode consumption 38 tons 34 tons 10.5% reduction Silicon recovery rate 89.2％ 91.7％ Increased by 2.5 percentage points

[0040] This example verifies the significant advantages of this method in terms of material distribution uniformity, spark suppression efficiency and energy consumption control, and achieves a breakthrough improvement in the industrial silicon smelting process through dynamic adjustment, intelligent linkage and closed-loop optimization.

[0041] In summary, the present invention provides a method for optimizing the material pushing method and controlling the spark phenomenon in industrial silicon smelting. By adopting dynamic adaptive material distribution technology, combined with a high-precision spark suppression strategy and a multi-parameter intelligent optimization algorithm, it achieves a high degree of uniformity in the distribution of materials in the furnace and real-time control of the spark phenomenon. Compared with traditional methods, the implementation of the present invention not only significantly improves the uniformity of material distribution and reduces the fluctuation amplitude of the material void ratio, but also greatly shortens the spark response time, effectively suppresses energy consumption and electrode loss, and improves the silicon recovery rate. This series of improvements not only optimizes the production process, but also brings significant economic and environmental benefits to the enterprise, demonstrating the broad application prospects and technological innovation value of the present invention in the field of industrial silicon smelting.

[0042] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for optimizing the material pushing method and controlling the spark phenomenon in industrial silicon smelting, characterized in that: The following steps are involved: Step 1: Adopt a layered material distribution method that combines axial pushing and radial pushing, and realize material distribution control through a multi-level pushing mechanism; Step 2: Dynamically trigger the fire suppression operation based on real-time temperature monitoring data, and simultaneously perform inert gas injection and replenishment of the cover layer; Step 3: Combine intelligent algorithms to optimize pushing parameters and automatically adjust the pushing motion trajectory and speed according to raw material characteristics and working conditions.

2. The method for optimizing the material pushing mode and controlling the spark phenomenon in industrial silicon smelting according to claim 1, characterized in that: The multi-stage pushing mechanism includes an adjustable angle pushing plate with a high-temperature resistant coating on the surface, and the inclination angle of the pushing plate can be accurately adjusted within the range of 30 degrees to 75 degrees.

3. The method for optimizing the material pushing mode and controlling the spark phenomenon in industrial silicon smelting according to claim 2, characterized in that: The adjustable angle push plate is provided with a pressure sensing module and an angle feedback mechanism. When the push resistance value exceeds a preset threshold, the angle compensation adjustment is automatically triggered, and the compensation range is 5%-15% of the detected resistance change.

4. The method for optimizing the material pushing mode and controlling the spark phenomenon in industrial silicon smelting according to claim 1, characterized in that: The real-time temperature monitoring adopts a programmable and controlled multi-point infrared temperature measurement array, and the temperature measurement unit spacing and sampling frequency are dynamically configured according to the size of the furnace body.

5. The method for optimizing the material pushing mode and controlling the spark phenomenon in industrial silicon smelting according to claim 4, characterized in that: The multi-point infrared temperature measurement array establishes linkage control with the pushing mechanism. When it is detected that the axial temperature gradient exceeds 50°C / m, the pushing plate tilt angle is automatically adjusted by 3°-8° and the pushing speed is reduced by 10%-20%.

6. The method for optimizing the material pushing mode and controlling the spark phenomenon in industrial silicon smelting according to claim 1, characterized in that: The inert gas injection adopts mixed gas injection with adjustable pressure, and the gas component ratio and injection duration are related to the detected temperature anomaly degree.

7. The method for optimizing the material pushing mode and controlling the spark phenomenon in industrial silicon smelting according to claim 6, characterized in that: The mixed gas injection adopts a multi-angle dynamic injection strategy, and the angle between the injection axis and the material surface normal is dynamically adjusted to 15°-60° according to the temperature distribution characteristics, and the injection angle in the high-temperature core area is 10°-25° larger than that in the edge area.

8. The method for optimizing the material pushing mode and controlling the spark phenomenon in industrial silicon smelting according to claim 1, characterized in that: The intelligent algorithm includes a time series prediction model based on deep learning, which generates push parameter optimization instructions by fusing historical operation data with real-time sensor information.

9. The method for optimizing the material pushing mode and controlling the spark phenomenon in industrial silicon smelting according to claim 8, characterized in that: The time series forecasting model has a built-in adaptive learning mechanism, which automatically updates the model parameters after each production cycle. The updated weight coefficient is dynamically calculated based on the operating data of the last three cycles, and the update frequency is controlled to be iterated once every 8-12 hours.