Intelligent production process data control method and system for yellow phosphorus production

Abstract

The invention relates to the technical field of yellow phosphorus production process data control, in particular to an intelligent production process data control method and system for yellow phosphorus production, and effectively overcomes the technical defects of a traditional process through the intelligent control method: accurate moisture control (0.8%-1.2%) is realized in a raw material pretreatment link, the feeding positioning precision reaches 1cm, and the production efficiency is improved; a foundation is laid for stable operation of the electric furnace, and arc breaking accidents are reduced by more than 95% in combination with a molten pool state prediction model; an innovative three-dimensional molten pool monitoring technology is adopted, so that the identification precision of a slag-iron interface reaches 2cm, and the three-phase power balance deviation is controlled within 1.5%; the intelligent energy efficiency optimization system enables the power consumption per ton of phosphorus to be reduced to 10500 kWh or below, and saves energy by 12% or above compared with a traditional process; the automatic material distribution system realizes the layer thickness control precision of + / -1cm, and the material surface flatness reaches 0.5 cm; an established multi-parameter linkage safety mechanism shortens the emergency response time to be within 50 ms, and the production safety is greatly improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of yellow phosphorus production process data control, in particular to an intelligent production process data control method and system for yellow phosphorus production. BACKGROUND

[0002] In the yellow phosphorus production method, the electric furnace method is the main method for industrial production of yellow phosphorus. The method uses phosphate rock, coke and silica as raw materials, and generates yellow phosphorus through a reduction reaction in a high-temperature electric furnace. The traditional yellow phosphorus production process faces many technical bottlenecks: the raw material pretreatment link relies on manual experience, the coke moisture control is not accurate (the fluctuation range is 1.5% to 3%), which leads to low electric furnace reaction efficiency; the electrode adjustment adopts mechanical control, the response speed is slow (> 2 seconds), and the furnace charge collapse cannot be responded in time, and arc breaking accidents occur frequently; the molten pool monitoring means is backward, relies on manual observation and experience judgment, the three-phase power imbalance is serious (deviation > 8%), the slag-iron interface recognition error is large (> 5 cm); the energy consumption management is extensive, the production cannot be optimized according to the real-time electricity price, the ton phosphorus power consumption is high (> 12000 kWh); the material uniformity is poor, the material layer thickness deviation is large (> 3 cm), which affects the reaction efficiency; the safety protection system response is slow (> 200 ms), and there is a major safety hazard. The prior art lacks a complete solution that organically integrates intelligent sensing, real-time control and energy efficiency optimization, therefore, there is an urgent need to develop a scheme to solve the problems of low efficiency caused by the raw material pretreatment link relying on manual experience, slow response, backward molten pool monitoring means, serious three-phase power imbalance, and large energy consumption and material layer error. SUMMARY

[0003] The purpose of the present application is to provide an intelligent production process data control method and system for yellow phosphorus production to improve the problems of poor moisture control (1.5% to 3%), slow electrode response (> 2s), inaccurate molten pool monitoring (error > 5cm), high energy consumption (> 12000kWh), uneven material distribution (deviation > 3cm) and slow safety response (> 200ms) in the above-mentioned yellow phosphorus production process, and lack of intelligent integration scheme.

[0004] In order to achieve the above-mentioned purpose, the present application provides the following technical scheme: On the one hand, the present application provides an intelligent production process data control method for yellow phosphorus production, which comprises: The particle size distribution data of the phosphate rock, silica and coke are collected in real time by a laser particle size analyzer in the raw material pretreatment stage, and the coke moisture data are collected by an external moisture monitor and transmitted to a central control system; The central control system generates a raw material proportioning scheme based on the received particle size distribution data, and outputs a microwave drying control instruction based on the moisture data to stabilize the moisture content of the coke at 0.8% to 1.2%; the digital twin model generates an optimal feeding path according to the raw material characteristic data, and controls the AGV trolley to perform precise feeding; In the electric furnace reduction stage, the molten pool resistance data are collected in real time by a magnetic fluid sensor, the AI controller processes the resistance data every 0.1 second and outputs an electrode adjustment instruction, the hydraulic servo system is controlled to realize the adjustment of the electrode insertion depth with a precision of ±2 cm; a 32-channel infrared thermal imager collects the molten pool temperature data to construct a three-dimensional thermal field model, a microwave radar collects the slag-iron interface data, and the central control system comprehensively processes the above data to output a three-phase power balance instruction; the digital twin model analyzes the energy consumption data every 5 minutes in combination with real-time electricity price information to output a load adjustment instruction to control the electric furnace to maintain 90% load during the peak period and increase to 105% load during the valley period. In the production control stage, the material surface morphology data are collected by a 3D scanner, the central control system processes the data to output a layered feeding instruction to control the mechanical arm to complete the feeding of the coke bottom layer, the sand mixed layer and the coke capping layer with a precision of ±2 cm; the oxygen content sensor monitors the environmental data in real time, and the central control system outputs an emergency stop instruction when the oxygen content is detected to be greater than 0.6%; a sonar slag probe collects the slag channel state data, and the central control system processes the data to output a slag discharge instruction to control the electromagnetic pulse device and the slag removing robot to complete the dredging and cleaning of the slag channel.

[0005] Optionally, the central control system fuses and analyzes the received particle size distribution data and moisture data to establish a raw material characteristic database, and the digital twin model dynamically optimizes the microwave drying parameters and the feeding path planning algorithm based on the database, so that the moisture control accuracy is improved to ±0.1%, and the feeding positioning error is less than 1 cm.

[0006] Optionally, the central control system stores and analyzes historical resistance data to establish a molten pool state prediction model, and outputs an electrode adjustment instruction 50-100 ms in advance when an abnormal resistance change trend is detected, so that the collapse warning response time of the furnace charge is shortened to within 0.3 seconds.

[0007] Optionally, the infrared thermal imager data are processed by a temperature compensation algorithm in combination with the penetration scanning data of the microwave radar to construct a three-dimensional dynamic model of the molten pool, so that the thickness identification error of the slag-iron interface is less than 2 cm, and the three-phase power balance deviation is controlled within ±1.5%.

[0008] Optionally, the central control system accesses real-time load prediction data of the power grid, the digital twin model dynamically adjusts the load distribution strategy in combination with the electricity price fluctuation curve and the operating state of the electric furnace, so that the comprehensive electricity consumption per ton of phosphorus is further reduced to below 10,500 kWh during the valley period.

[0009] Optionally, the 3D scanner monitors the cloth effect in real time, and the central control system continuously optimizes the cloth parameters through a machine learning algorithm, so that the thickness uniformity error of each material layer is controlled within ±1 cm, and the flatness deviation of the material surface is less than 0.5 cm.

[0010] Optionally, a multi-parameter linkage early warning mechanism is established, when the oxygen content is abnormal, the temperature changes suddenly or the pressure fluctuates, the central control system completes the risk level evaluation within 50 ms and executes the graded emergency response, and when the highest level response is executed, the power supply can be cut off within 30 ms and multiple protection measures are started.

[0011] In a second aspect, the embodiment provides an intelligent production process data control system for yellow phosphorus production, the system comprising: A first analysis module, in the raw material pretreatment stage, the particle size distribution data of phosphate rock, silica and coke are collected in real time by a laser particle size analyzer, and the moisture data of coke are collected by an external moisture monitor and transmitted to the central control system; A first output module, the central control system generates a raw material ratio scheme based on the received particle size distribution data, and outputs a microwave drying control instruction based on the moisture data to stabilize the moisture of coke at 0.8% to 1.2%; the digital twin model generates an optimal feeding path according to the raw material characteristic data, and controls the AGV car to execute precise feeding; A second output module, in the electric furnace reduction stage, the molten pool resistance data are collected in real time by a magnetic fluid sensor, the AI controller processes the resistance data every 0.1 second and outputs an electrode adjustment instruction to control the hydraulic servo system to realize ±2 cm precision adjustment of the electrode insertion depth; a 32-channel infrared thermal imager collects molten pool temperature data to construct a three-dimensional thermal field model, a microwave radar collects slag-iron interface data, and the central control system comprehensively processes the above data to output a three-phase power balance instruction; the digital twin model analyzes energy consumption data every 5 minutes combined with real-time electricity price information to output a load adjustment instruction to control the electric furnace to maintain 90% load during peak period and increase to 105% load during trough period; A third output module, in the production control stage, the material surface morphology data are collected by a 3D scanner, and the central control system processes the data to output a layered cloth instruction to control the mechanical arm to complete the cloth of the coke bottom layer, the sand mixed layer and the coke top layer with ±2 cm precision; the oxygen content sensor monitors the environmental data in real time, and when the oxygen content is detected to be greater than 0.6%, the central control system outputs an emergency stop instruction; a sonar slag probe collects slag channel state data, and the central control system processes the data to output a slag discharge instruction to control the electromagnetic pulse device and the slag removing robot to complete the dredging and cleaning of the slag channel. Multi-level safety response module, integrated oxygen content sensor, distributed temperature probe and pressure sensor, real-time collection of environmental data; Central control system built-in risk rating algorithm, when oxygen content > 0.6%, determine as a first-level risk, 30ms output command to cut off the main power and activate the inert gas covering system of the whole plant; When detecting local temperature gradient mutation (> 100℃ / m) and accompanied by pressure fluctuation > 15kPa, determine as a second-level risk, 50ms start regional isolation barrier and directional spray cooling device, synchronous adjustment of electrode lifting speed to safety threshold; Molten pool state cooperative control module, including magnetic fluid sensor array, 32-channel infrared thermal imager and microwave radar, magnetic fluid sensor real-time collection of molten pool resistance data and transmission to AI controller, AI controller with 0.1 second cycle output electrode adjustment instruction to hydraulic servo system; After the infrared thermal imager data is eliminated by the temperature compensation unit, it is input into the three-dimensional reconstruction unit synchronously with the slag-iron interface scanning data of the microwave radar, generating a dynamic model of the molten pool thermodynamics; Central control system based on the model real-time calculation of three-phase power deviation value, when the deviation > 1%, output current phase correction instruction to the electric furnace transformer; Dynamic energy efficiency optimization module, access to real-time electricity price data and load prediction database, digital twin model combined with electric furnace operating state (including electrode wear coefficient, furnace lining thickness data) to generate load scheduling strategy: during trough period, increase load to 105% and start electrode automatic compensation program to offset the insertion depth deviation caused by overload; During peak period, switch to 90% load, simultaneously shut down non-core power units, and increase the steam output of the waste heat boiler by 20% to drive auxiliary equipment; Material self-correcting module, real-time acquisition of material surface morphology point cloud data by 3D scanner, thickness distribution of coke bottom layer, mixed layer of sand and sealing layer identified by central control system through convolutional neural network, when detecting layer thickness uniformity deviation > 1cm or flatness error > 0.5cm, recalculate mechanical arm material distribution track parameters, and real-time adjust the opening degree of the material valve and the moving speed of the mechanical arm through the PID controller, realize the closed-loop control of layered material precision.

[0012] Optionally, the first analysis module comprises: The first analysis unit, the central control system fuses and analyzes the received particle size distribution data and moisture data, establishes a raw material characteristic database, and the digital twin model dynamically optimizes the microwave drying parameters and the material feeding path planning algorithm based on the database, so that the moisture control precision is improved to ±0.1%, and the material positioning error is less than 1cm.

[0013] Optionally, the second output module comprises: The first input unit, the central control system stores and analyzes historical resistance data to establish a molten pool state prediction model, and when an abnormal resistance change trend is detected, an electrode adjustment instruction is output in advance by 50-100 ms, so that the response time of the furnace charge collapse early warning is shortened to within 0.3 seconds.

[0014] The first calculation unit, the infrared thermal imager data is processed through a temperature compensation algorithm, combined with the penetration scanning data of the microwave radar, a three-dimensional dynamic model of the molten pool is constructed, the slag-iron interface thickness identification error is less than 2 cm, and the three-phase power balance deviation is controlled within ±1.5%.

[0015] The first running unit, the central control system accesses real-time load prediction data of the power grid, and the digital twin model dynamically adjusts the load distribution strategy in combination with the electricity price fluctuation curve and the electric furnace operation state, so that the comprehensive power consumption per ton of phosphorus is further reduced to below 10500 kWh during the trough period.

[0016] Optionally, the third output module comprises: The second input unit, the 3D scanner monitors the material distribution effect in real time, and the central control system continuously optimizes the material distribution parameters through a machine learning algorithm, so that the thickness uniformity error of each material layer is controlled within ±1 cm, and the material surface flatness deviation is less than 0.5 cm.

[0017] The first detection unit, a multi-parameter linkage early warning mechanism is established, when abnormal oxygen content, temperature sudden change or pressure fluctuation are detected, the central control system completes risk level evaluation and executes graded emergency response within 50 ms, and when the highest level response is executed, the power supply can be cut off within 30 ms and multiple protection measures are started.

[0018] The beneficial effects of the present application are: The present application effectively solves the technical defects of the traditional process by the intelligent control method: the raw material pretreatment link realizes accurate control of moisture (0.8% to 1.2%), the positioning accuracy of the material is 1 cm, which lays a foundation for stable operation of the electric furnace; the electrode adjustment response speed is improved to 0.1 seconds, combined with the molten pool state prediction model, the arc breaking accident is reduced by more than 95%; the innovative three-dimensional molten pool monitoring technology makes the slag-iron interface identification accuracy reach 2 cm, and the three-phase power balance deviation is controlled within 1.5%; the intelligent energy efficiency optimization system reduces the power consumption per ton of phosphorus to below 10500 kWh, which is more than 12% lower than the traditional process; the automatic material distribution system realizes a layer thickness control accuracy of ±1 cm, and the material surface flatness reaches 0.5 cm; the multi-parameter linkage safety mechanism shortens the emergency response time to within 50 ms, greatly improving the production safety. The data of each link is interacted in real time, forming a complete intelligent control closed loop, and realizing the accurate control of the whole process from raw materials to finished products in the yellow phosphorus production.

[0019] Other features and advantages of the present invention will be described in the following description, and in part will become apparent from the description, or understood by practicing the embodiments of the present invention. The purposes and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without paying any creative work.

[0021] Figure 1 This is a flow chart of an intelligent production process data control method for yellow phosphorus production described in an embodiment of the present invention; Figure 2 It is a structural diagram of the intelligent production process data control equipment for yellow phosphorus production described in an embodiment of the present invention. DETAILED DESCRIPTION

[0022] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. The components of the embodiments of the present invention generally described and shown in the drawings herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0023] It should be noted that similar reference numerals or letters represent similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings. At the same time, in the description of the present invention, the terms "first", "second", etc. are only used to distinguish the description and should not be understood as indicating or implying relative importance.

[0024] Example 1:

[0025] like Figure 1 As shown, this embodiment provides an intelligent production process data control method for yellow phosphorus production, which includes step S100, step S200, step S300 and step S400.

[0026] Step S100, raw material pretreatment stage by laser particle size analyzer real-time acquisition of phosphate rock, silica and coke particle size distribution data, through the external moisture monitoring instrument acquisition coke moisture data and transmission to the central control system; Step S200, the central control system generates raw material ratio scheme based on the received particle size distribution data, and outputs microwave drying control instruction based on the moisture data to stabilize the coke moisture at 0.8% to 1.2%; the digital twin model generates the optimal feeding path according to the raw material characteristic data, and controls the AGV car to execute precise feeding; Step S300, the electric furnace reduction stage, the molten pool resistance data are collected in real time by the magnetic fluid sensor, the AI controller processes the resistance data every 0.1 second and outputs the electrode adjustment instruction, and the hydraulic servo system is controlled to realize the electrode insertion depth ±2cm precision adjustment; the 32-channel infrared thermal imager collects the molten pool temperature data to construct a three-dimensional thermal field model, the microwave radar collects the slag-iron interface data, and the central control system comprehensively processes the above data to output the three-phase power balance instruction; the digital twin model analyzes the energy consumption data every 5 minutes combined with real-time electricity price information, and outputs the load adjustment instruction to control the electric furnace to maintain 90% load during peak period and increase to 105% load during valley period; Step S400, the production control stage, the material surface morphology data are collected by the 3D scanner, the central control system processes the data to output the layered distribution instruction to control the mechanical arm to complete the coke bottom layer, the sand mixed layer and the coke top layer distribution with ±2cm precision; the oxygen content sensor monitors the environmental data in real time, and the central control system outputs the emergency stop instruction when the oxygen content is greater than 0.6%; the sonar slag exploration instrument collects the slag channel state data, and the central control system processes the data to output the slag discharge instruction to control the electromagnetic pulse device and the slag robot to complete the slag channel dredging and cleaning.

[0027] Secondly, in step S100 of the embodiment, the raw material pretreatment stage includes: Step S110, the central control system fuses and analyzes the received particle size distribution data and moisture data, establishes a raw material characteristic database, and the digital twin model dynamically optimizes the microwave drying parameters and the feeding path planning algorithm based on the database, so that the moisture control accuracy is improved to ±0.1%, and the feeding positioning error is less than 1cm.

[0028] Secondly, in step S300 of the embodiment, the electric furnace reduction stage includes: Step S310, the central control system stores and analyzes the historical resistance data to establish a molten pool state prediction model, and outputs the electrode adjustment instruction 50-100ms in advance when detecting that the resistance change trend is abnormal, so that the furnace charge collapse early warning response time is shortened to within 0.3 seconds.

[0029] Secondly, in step S300 of the embodiment, the electric furnace reduction stage includes: Step S320, the infrared thermal imager data is processed by a temperature compensation algorithm, combined with the penetration scanning data of the microwave radar, a three-dimensional dynamic model of the molten pool is constructed, and the thickness identification error of the slag-iron interface is less than 2 cm, and the three-phase power balance deviation is controlled within ±1.5%.

[0030] Secondly, in step S300 of the embodiment, the energy efficiency optimization process includes: Step S330, the central control system accesses real-time load prediction data of the power grid, and the digital twin model combines the electricity price fluctuation curve and the electric furnace operation state to dynamically adjust the load distribution strategy, so that the comprehensive power consumption per ton of phosphorus is further reduced to below 10500 kWh during the trough period.

[0031] Secondly, in step S400 of the embodiment, the material control process includes: Step S410, the 3D scanner monitors the material effect in real time, and the central control system continuously optimizes the material parameters through machine learning algorithms, so that the thickness uniformity error of each material layer is controlled within ±1 cm, and the material surface flatness deviation is less than 0.5 cm.

[0032] Secondly, in step S400 of the embodiment, the safety control process includes: Step S420, a multi-parameter linkage early warning mechanism is established, when abnormal oxygen content, temperature sudden change or pressure fluctuation is detected, the central control system completes risk level assessment and executes graded emergency response within 50 ms, and when the highest level of response is reached, the power supply can be cut off within 30 ms and multiple protection measures are started.

[0033] In the embodiment, the technical defects of the traditional process are effectively solved by the intelligent control method: the raw material pretreatment link realizes accurate control of moisture (0.8%-1.2%), the positioning accuracy of feeding is 1 cm, which lays a foundation for stable operation of the electric furnace; the response speed of electrode adjustment is improved to 0.1 seconds, combined with the molten pool state prediction model, the arc breaking accident is reduced by more than 95%; the innovative three-dimensional molten pool monitoring technology makes the slag-iron interface identification accuracy reach 2 cm, and the three-phase power balance deviation is controlled within 1.5%; the intelligent energy efficiency optimization system reduces the power consumption per ton of phosphorus to below 10500 kWh, which is more than 12% lower than the traditional process; the automatic material distribution system realizes layer thickness control accuracy of ±1 cm, and the material surface flatness reaches 0.5 cm; the multi-parameter linkage safety mechanism shortens the emergency response time to within 50 ms, greatly improving the production safety. The data of each link is interacted in real time, forming a complete intelligent control closed loop, realizing the accurate control of the whole process from raw materials to finished products of yellow phosphorus production.

[0034] Secondly, based on the above production process data control method, the embodiment also provides a corresponding dynamic control compensation method, which includes: In the electric furnace reduction stage, the molten pool resistance data is collected in real time by a magnetic fluid sensor and input to an AI controller; the AI controller processes the resistance data at a cycle of 0.1 seconds, generates electrode adjustment instructions and sends them to a hydraulic servo system to control the dynamic adjustment of the electrode insertion depth, with an accuracy of ±2 cm; at the same time, the central control system stores historical resistance data to build a molten pool state prediction model, which outputs electrode compensation adjustment instructions 50-100 ms in advance when the resistance change rate exceeds the threshold (>5Ω / s), synchronously corrects the output instructions of the AI controller, and compresses the response time of the charge collapse warning to within 0.3 seconds; In the molten pool monitoring link, the original temperature data collected by the 32-channel infrared thermal imager is processed by a temperature compensation algorithm to eliminate the interference of the furnace wall reflection, and the microwave radar performs penetration scanning on the slag-iron interface to obtain the original interface thickness data; the central control system aligns and fuses the temperature compensation data and the interface scanning data in time and space to build a three-dimensional dynamic model of the molten pool, and outputs the identification result of the slag-iron interface thickness error less than 2 cm in real time, and dynamically optimizes the three-phase power balance instructions based on the model, so that the three-phase power deviation is stabilized within ±1.5%; The specific implementation of the temperature compensation algorithm for eliminating the interference of the furnace wall reflection is as follows: , wherein is the compensated temperature data, is , by, A is , , A= , wherein , b is .

[0035] In the energy efficiency optimization link, the digital twin model analyzes the electric furnace energy consumption curve every 5 minutes, combines the real-time electricity price fluctuation data and load prediction information of the power grid, and dynamically generates a load distribution strategy: during the electricity price trough period, the electric furnace load is increased to 105%, and the waste heat recovery system is activated at the same time to reduce the flue gas temperature from 800℃ to below 350℃, and the recovered heat energy is used for raw material pre-drying; during the peak period, the load is reduced to 90%, and the energy storage power supply mode is switched; through the above dynamic compensation control, the comprehensive power consumption per ton of phosphorus is reduced to below 10500kWh during the trough period, and the waste heat utilization rate is increased by 40%; In the safety control link, a multi-parameter coupling analysis model of oxygen content, temperature gradient, and pressure fluctuation is established: when the oxygen content sensor detects a concentration > 0.6%, a first-level response is triggered, and the central control system cuts off the main power supply within 30 ms and starts the nitrogen covering system; when the infrared thermal imager detects a sudden change in local temperature (> 50℃ / s) and the pressure sensor detects a fluctuation > 10kPa, a second-level response is triggered, and the directional cooling nozzle and the furnace reinforcement device are started within 50 ms, while the electrode insertion depth is adjusted to compensate for thermal stress deformation.

[0036] It should be noted that the above dynamic compensation should be considered as a whole, the reasons are: the introduction of prediction model and AI controller double cascade compensation (intervention 50-100ms in advance) in electrode control solves the hysteresis problem of traditional single control response, secondly, the combined adjustment strategy of waste heat recovery and load (valley 105% load + waste heat utilization, peak 90% load + energy storage power supply) is proposed, which deeply binds energy optimization and equipment operation state, and through the design of multi-parameter coupling safety model, the oxygen content anomaly (first-level response) and local thermal mutation (second-level response) are distinguished, and precise hierarchical disposal is realized.

[0037] Embodiment 2: The embodiment provides an intelligent production process data control system for yellow phosphorus production, the system comprising: A first analysis module 71 is used to collect particle size distribution data of phosphate rock, silica and coke in the raw material pretreatment stage in real time through a laser particle size analyzer, and coke moisture data is collected through an external moisture monitor and transmitted to a central control system; A first output module 72 is used for the central control system to generate a raw material proportioning scheme based on the received particle size distribution data, and to output a microwave drying control instruction based on the moisture data to stabilize the coke moisture at 0.8% to 1.2%; a digital twin model generates an optimal feeding path according to the raw material characteristic data, and controls an AGV car to perform precise feeding; A second output module 73 is used to collect molten pool resistance data in real time through a magnetic fluid sensor in the electric furnace reduction stage, and an AI controller processes resistance data every 0.1 seconds and outputs electrode adjustment instructions to control a hydraulic servo system to realize electrode insertion depth ± 2cm precision adjustment; a 32-channel infrared thermal imager collects molten pool temperature data to construct a three-dimensional thermal field model, and a microwave radar collects slag-iron interface data, and a central control system comprehensively processes the above data to output three-phase power balance instructions; a digital twin model analyzes energy consumption data every 5 minutes combined with real-time electricity price information to output load adjustment instructions to control the electric furnace to maintain 90% load during peak period and increase to 105% load during valley period; The third output module 74 is used to collect the material surface morphology data by the 3D scanner in the production control stage, and the central control system processes the data and outputs the layered material distribution instruction to control the mechanical arm to complete the coke bottom layer, the mixed layer of sand and coke, and the coke top layer distribution with a precision of ±2 cm. The oxygen content sensor monitors the environmental data in real time, and when the oxygen content is detected to be greater than 0.6%, the central control system outputs an emergency stop instruction. The sonar slag exploration instrument collects the slag channel state data, and the central control system processes the data and outputs the slag discharge instruction to control the electromagnetic pulse device and the slag robot to complete the slag channel dredging and cleaning. The multi-stage safety response module 75 integrates the oxygen content sensor, the distributed temperature probe, and the pressure sensor to collect environmental data in real time. The central control system has a risk rating algorithm built-in. When the oxygen content is greater than 0.6%, it is determined to be a first-level risk, and within 30 ms, the main power supply is cut off and the inert gas covering system of the whole plant area is activated. When a local temperature gradient mutation (>100℃ / m) is detected and accompanied by a pressure fluctuation of >15kPa, it is determined to be a second-level risk, and within 50 ms, the regional isolation barrier and the directional spray cooling device are started, and the electrode lifting speed is adjusted to the safety threshold value synchronously. The molten pool state cooperative control module 76 includes a magnetic fluid sensor array, a 32-channel infrared thermal imager, and a microwave radar. The magnetic fluid sensor collects the molten pool resistance data in real time and transmits it to the AI controller. The AI controller outputs the electrode adjustment instruction to the hydraulic servo system with a period of 0.1 seconds. After the infrared thermal imager data is compensated by the temperature compensation unit to eliminate the interference of smoke and dust, it is input into the three-dimensional reconstruction unit synchronously with the slag-iron interface scanning data of the microwave radar to generate a dynamic model of the molten pool thermodynamics. The central control system calculates the three-phase power deviation value in real time based on the model, and outputs the current phase correction instruction to the electric furnace transformer when the deviation is greater than 1%. The dynamic energy efficiency optimization module 77 accesses the real-time electricity price data and the load prediction database of the power grid, and the digital twin model generates a load scheduling strategy in combination with the electric furnace operating state (including the electrode wear coefficient and the furnace lining thickness data): during the trough period, the load is increased to 105% and the electrode automatic compensation program is started to offset the insertion depth deviation caused by overload; during the peak period, the load is switched to 90%, the non-core power consumption units are closed synchronously, and the steam production of the waste heat boiler is increased by 20% to drive auxiliary equipment. The material self-correction module 78 obtains the material surface morphology point cloud data in real time by the 3D scanner, and the central control system identifies the thickness distribution of the coke bottom layer, the mixed layer of sand and coke, and the top layer by the convolutional neural network. When the layer thickness uniformity deviation is detected to be greater than 1 cm or the flatness error is greater than 0.5 cm, the mechanical arm material distribution trajectory parameters are recalculated, and the PID controller is used to adjust the material valve opening degree and the mechanical arm moving speed in real time to realize the closed-loop control of the layered material distribution precision.

[0038] Optionally, the first analysis module 71 comprises: The first analysis unit 711, the central control system fuses and analyzes the received particle size distribution data and moisture data, establishes a raw material characteristic database, and the digital twin model dynamically optimizes the microwave drying parameters and the feeding path planning algorithm based on the database, so that the moisture control accuracy is improved to ±0.1%, and the feeding positioning error is less than 1cm.

[0039] Optionally, the second output module 73 comprises: The first input unit 731, the central control system stores and analyzes historical resistance data to establish a molten pool state prediction model, and outputs electrode adjustment instructions 50-100ms in advance when detecting abnormal resistance change trend, so that the response time of the furnace charge collapse warning is shortened to within 0.3 seconds.

[0040] The first calculation unit 732, the infrared thermal imager data is processed by a temperature compensation algorithm, combined with the penetration scanning data of the microwave radar, a three-dimensional dynamic model of the molten pool is constructed, the slag-iron interface thickness identification error is less than 2cm, and the three-phase power balance deviation is controlled within ±1.5%.

[0041] The first running unit 733, the central control system accesses real-time load prediction data of the power grid, the digital twin model dynamically adjusts the load distribution strategy combined with the price fluctuation curve and the electric furnace operation state, so that the comprehensive power consumption per ton of phosphorus is further reduced to below 10500kWh at the trough period.

[0042] Optionally, the third output module 74 comprises: The second input unit 741, the 3D scanner monitors the cloth effect in real time, and the central control system continuously optimizes the cloth parameters through machine learning algorithm, so that the thickness uniformity error of each material layer is controlled within ±1cm, and the material surface flatness deviation is less than 0.5cm.

[0043] The first detection unit 742, a multi-parameter linkage early warning mechanism is established, when detecting abnormal oxygen content, temperature sudden change or pressure fluctuation, the central control system completes risk level evaluation and executes graded emergency response within 50ms, and when the highest level response, the power can be cut off within 30ms and multiple protection measures are started.

[0044] This embodiment effectively addresses the technical shortcomings of traditional processes through intelligent control methods. The raw material pretreatment stage achieves precise moisture control (0.8% to 1.2%), with a placement accuracy of 1 cm, paving the way for stable furnace operation. The electrode adjustment response speed is improved to 0.1 seconds, and combined with a molten pool state prediction model, arc failure accidents are reduced by over 95%. Innovative three-dimensional molten pool monitoring technology enables slag-iron interface identification with an accuracy of 2 cm, and three-phase power balance deviation is controlled within 1.5%. An intelligent energy efficiency optimization system reduces power consumption per ton of phosphorus to below 10,500 kWh, saving over 12% compared to traditional processes. The automatic material distribution system achieves layer thickness control accuracy of ±1 cm and a material surface flatness of 0.5 cm. A multi-parameter linkage safety mechanism reduces emergency response time to under 50 ms, significantly improving production safety. Real-time data interaction across all stages forms a complete intelligent control closed loop, enabling precise control of the entire yellow phosphorus production process, from raw materials to finished product.

[0045] like Figure 2 As shown, this embodiment provides It should be noted that, regarding the apparatus in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated on here.

[0046] Example 3:

[0047] Corresponding to the above method embodiment, the embodiment of the present disclosure also provides a device for identifying the type of partial discharge of high-voltage electrical equipment. The device for identifying the type of partial discharge of high-voltage electrical equipment described below and the intelligent production process data control method for yellow phosphorus production described above can be referenced to each other.

[0048] Figure 2 FIG. 1 is a block diagram of an intelligent production process data control device for yellow phosphorus production according to an exemplary embodiment. Figure 2 As shown, the electronic device 800 may include: a processor 801 , a memory 802 . The electronic device 800 may also include one or more of a multimedia component 803 , an I / O interface 804 , and a communication component 805 .

[0049] The processor 801 is configured to control overall operations of the electronic device 800 to complete all or part of the steps of the above-described intelligent production process data control method for yellow phosphorus production. The memory 802 is configured to store various types of data to support operations of the electronic device 800, which can include, for example, instructions for operating any application or method on the electronic device 800, and application-related data, such as contact data, sent and received messages, pictures, audio, video, and the like. The memory 802 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The multimedia component 803 can include a screen and an audio component. The screen can be, for example, a touch screen, and the audio component is configured to output and / or input audio signals. For example, the audio component can include a microphone configured to receive external audio signals. The received audio signals can be further stored in the memory 802 or transmitted through the communication component 805. The audio component also includes at least one speaker configured to output audio signals. The I / O interface 804 provides an interface between the processor 801 and other interface modules, which can be a keyboard, a mouse, a button, and the like. The buttons can be virtual buttons or physical buttons. The communication component 805 is configured to perform wired or wireless communication between the electronic device 800 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, near field communication (NFC), 2G, 3G or 4G, or a combination of one or more of them, so the corresponding communication component 805 can include a Wi-Fi module, a Bluetooth module, an NFC module.

[0050] In an example embodiment, the electronic device 800 can be implemented by one or more Application Specific Integrated Circuit (ASIC), Digital Signal Processor (DSP), Digital Signal Processing Device (DSPD), Programmable Logic Device (PLD), Field Programmable Gate Array (FPGA), controller, microcontroller, microprocessor or other electronic elements for executing the above-mentioned intelligent production process data control method for yellow phosphorus production.

[0051] In another example embodiment, a computer-readable storage medium including program instructions is also provided, which, when executed by a processor, implement the steps of the above-mentioned intelligent production process data control method for yellow phosphorus production. For example, the computer-readable storage medium can be the above-mentioned memory 802 including program instructions, and the above-mentioned program instructions can be executed by the processor 801 of the electronic device 800 to complete the above-mentioned intelligent production process data control method for yellow phosphorus production.

[0052] Embodiment 4:

[0053] Corresponding to the above method embodiments, the embodiments of the present disclosure also provide a readable storage medium. The readable storage medium described below can be referred to in conjunction with the above-mentioned intelligent production process data control method for yellow phosphorus production.

[0054] A readable storage medium, the readable storage medium storing a computer program, the computer program being executed by a processor to implement the steps of the above-mentioned intelligent production process data control method for yellow phosphorus production.

[0055] The readable storage medium can be specifically a U disk, a mobile hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and various readable storage media that can store program codes.

[0056] The above only describes the preferred embodiments of the present disclosure and is not used to limit the present disclosure. For those skilled in the art, the present disclosure can have various modifications and changes. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. An intelligent production process data control method for yellow phosphorus production, characterized in that: The method comprises: During the raw material pretreatment stage, a laser particle size analyzer is used to collect real-time particle size distribution data of phosphate rock, silica rock, and coke. An external moisture monitor is used to collect moisture data of coke and transmit it to the central control system. The central control system generates a raw material ratio plan based on the received particle size distribution data and outputs microwave drying control instructions based on the moisture data to stabilize the coke moisture content at 0.8% to 1.2%. The digital twin model generates the optimal feeding path based on the raw material characteristic data and controls the AGV vehicle to perform precise feeding. During the reduction phase of the electric furnace, a magnetic fluid sensor collects real-time data on the resistance of the molten pool. The AI ​​controller processes this data every 0.1 seconds and outputs electrode adjustment instructions, controlling the hydraulic servo system to achieve ±2cm precision adjustment of the electrode insertion depth. A 32-channel infrared thermal imager collects molten pool temperature data to construct a three-dimensional thermal field model, and a microwave radar collects slag-iron interface data. The central control system comprehensively processes this data and outputs three-phase power balance instructions. The digital twin model analyzes energy consumption data every 5 minutes, combined with real-time electricity price information, and outputs load adjustment instructions to control the electric furnace to maintain 90% load during peak hours and increase it to 105% load during trough hours. During the production control stage, a 3D scanner is used to collect material surface morphology data. After processing the data, the central control system outputs layered material distribution instructions to control the robotic arm to complete the distribution of the coke bottom layer, ore sand mixture layer and coke capping layer with an accuracy of ±2cm; the oxygen content sensor monitors environmental data in real time, and when the oxygen content is detected to be greater than 0.6%, the central control system outputs an emergency shutdown instruction; the sonar slag detector collects slag channel status data, and after processing the data, the central control system outputs slag discharge instructions to control the electromagnetic pulse device and the slag removal robot to complete the slag channel dredging and cleaning.

2. The intelligent production process data control method for yellow phosphorus production according to claim 1, characterized in that: It also includes the raw material pre-processing stage, where the central control system integrates and analyzes the received particle size distribution data and moisture data to establish a raw material characteristics database. The digital twin model dynamically optimizes the microwave drying parameters and the feeding path planning algorithm based on this database, improving the moisture control accuracy to ±0.1% and the feeding positioning error to less than 1 cm. The reduction phase of the electric furnace includes: the central control system stores and analyzes historical resistance data to establish a molten pool state prediction model. When an abnormal resistance change trend is detected, an electrode adjustment instruction is output 50-100ms in advance, shortening the charge collapse warning response time to less than 0.3 seconds; The molten pool monitoring process includes: infrared thermal imager data is processed through a temperature compensation algorithm, combined with microwave radar penetration scanning data to construct a three-dimensional dynamic model of the molten pool, achieving an error in identifying the thickness of the slag-iron interface of less than 2 cm and controlling the three-phase power balance deviation within ±1.5%.

3. The intelligent production process data control method for yellow phosphorus production according to claim 2, characterized in that: It also includes energy efficiency optimization processes, including: The central control system is connected to the real-time load forecast data of the power grid. The digital twin model combines the electricity price fluctuation curve and the operating status of the electric furnace to dynamically adjust the load distribution strategy, so that the comprehensive electricity consumption per ton of phosphorus is further reduced to below 10,500 kWh during the trough period.

4. The intelligent production process data control method for yellow phosphorus production according to claim 3, characterized in that: Also included are the cloth control processes, including: The 3D scanner monitors the fabric effect in real time, and the central control system continuously optimizes the fabric parameters through machine learning algorithms, so that the thickness uniformity error of each material layer is controlled within ±1cm and the flatness deviation of the material surface is less than 0.5cm.

5. The intelligent production process data control method for yellow phosphorus production according to claim 4, characterized in that: It also includes security control processes, including: A multi-parameter linkage early warning mechanism has been established. When abnormal oxygen content, sudden temperature changes or pressure fluctuations are detected, the central control system will complete the risk level assessment and implement a graded emergency response within 50ms. At the highest level of response, the power supply can be cut off within 30ms and multiple protection measures can be initiated.

6. An intelligent production process data control system for yellow phosphorus production, characterized in that: The system comprises: The first analysis module, during the raw material pretreatment stage, uses a laser particle size analyzer to collect real-time particle size distribution data of phosphate rock, silica rock, and coke, and uses an external moisture monitor to collect coke moisture data and transmit it to the central control system; In the first output module, the central control system generates a raw material ratio plan based on the received particle size distribution data and outputs microwave drying control instructions based on the moisture data to stabilize the coke moisture content at 0.8% to 1.2%. The digital twin model generates the optimal feeding path based on the raw material characteristic data and controls the AGV to perform precise feeding. In the second output module, during the reduction phase of the electric furnace, a magnetic fluid sensor collects real-time molten pool resistance data. The AI ​​controller processes this resistance data every 0.1 seconds and outputs electrode adjustment instructions, controlling the hydraulic servo system to achieve ±2cm precision adjustment of the electrode insertion depth. A 32-channel infrared thermal imager collects molten pool temperature data to construct a three-dimensional thermal field model, and a microwave radar collects slag-iron interface data. The central control system comprehensively processes this data and outputs three-phase power balance instructions. The digital twin model analyzes energy consumption data every 5 minutes and combines it with real-time electricity price information to output load adjustment instructions to control the electric furnace to maintain 90% load during peak hours and increase it to 105% load during trough hours. The third output module uses a 3D scanner to collect material surface morphology data during the production control stage. After processing the data, the central control system outputs layered material distribution instructions to control the robotic arm to complete the distribution of the coke bottom layer, ore sand mixed layer and coke capping layer with an accuracy of ±2cm; the oxygen content sensor monitors the environmental data in real time, and when the oxygen content is detected to be greater than 0.6%, the central control system outputs an emergency shutdown instruction; the sonar slag detector collects slag channel status data, and after processing the data, the central control system outputs a slag discharge instruction to control the electromagnetic pulse device and the slag removal robot to complete the slag channel dredging and cleaning.

Images