Multi-parameter coordinated control method and system for super-high power graphite electrode baking

Abstract

The present application belongs to the technical field of cooperative control, and belongs to a multi-parameter cooperative control method and system for super-high-power graphite electrode baking, which comprises collecting full-dimensional operation parameters of a baking system, dividing the baking furnace into partitions, and collecting coupling state data of each partition in real time. Based on the coupling state data, different baking abnormal scenarios are identified, and process cooperative risk data under different baking abnormal scenarios is constructed in combination with the current baking process stage and the furnace body aging state. According to the process cooperative risk data, the parameter set to be adjusted in the cooperative control strategy is marked, and the optimized cooperative control strategy is obtained by adjustment. According to the balance index, each control node in the optimized cooperative control strategy is comprehensively evaluated, the control nodes that fail to pass the evaluation are defined as risk nodes, and a risk adjustment strategy pointing to the risk nodes is generated. The present application can realize multi-objective cooperative optimization, reduce production cost, and improve the stability and controllability of the baking process.

Description

Technical Field

[0001] This invention belongs to the field of collaborative control technology, specifically a multi-parameter collaborative control method and system for ultra-high power graphite electrode calcination. Background Technology

[0002] Ultra-high power graphite electrodes are core consumables in electric arc furnace steelmaking, and their production quality directly determines steelmaking efficiency and energy consumption levels. The calcination process, a crucial step in graphite electrode preparation, requires precise control of process parameters such as the furnace temperature field, atmosphere composition, and pressure gradient to ensure uniform carbonization of the green billet under high-temperature conditions, thereby achieving stable bulk density and low resistivity characteristics.

[0003] Traditional roasting control methods mostly employ a uniform parameter setting scheme for the entire furnace, neglecting the imbalance in parameter distribution caused by differences in fire channel radiation, uneven heat dissipation from the furnace wall, and fluctuations in the permeability of the filler material in different areas of the furnace. This leads to inconsistent heating and coking processes in the green body, resulting in poor product performance consistency. Regarding anomaly identification, existing technologies largely rely on manual inspections and offline detection, making it difficult to capture latent anomalies such as fire channel blockage, furnace sealing failure, and filler material agglomeration in real time. Furthermore, anomaly risk assessment remains at the qualitative level, failing to incorporate quantitative analysis based on the sensitivity of the roasting process stage and the aging state of the furnace body. This can easily lead to insufficiently targeted risk control measures, resulting in quality defects such as electrode cracking and oxidation. In addition, traditional control strategies are mostly static preset schemes, unable to dynamically adjust parameters based on real-time anomaly risks during the roasting process. When parameters deviate within the furnace, strategy adjustments often lag behind, and it is difficult to balance the control requirements of the three core objectives of volume density, resistivity, and energy consumption, easily leading to a "one-sided" problem that affects product qualification rate and causes energy waste.

[0004] In summary, developing a multi-parameter collaborative control method and system for ultra-high power graphite electrode calcination has become a key technical challenge that urgently needs to be solved in the industry. Summary of the Invention

[0005] To overcome the shortcomings of existing technologies, this invention proposes a multi-parameter collaborative control method and system for ultra-high power graphite electrode calcination. This invention primarily addresses the problems of insufficient multi-parameter coupling control in the graphite electrode calcination process, inadequate anomaly identification and risk quantification, and poor adaptive capability of the control strategy.

[0006] The technical solution adopted by this invention to solve its technical problem is: the multi-parameter coordinated control method for ultra-high power graphite electrode calcination provided by this invention, comprising:

[0007] Collect all dimensions of the calcination system's operating parameters, divide the calcination furnace into zones, and collect data in real time on the furnace temperature field distribution, atmosphere component ratio, furnace pressure gradient, green body thermal conductivity, and filler permeability of each zone as coupled state data.

[0008] Based on the coupling state data, different roasting abnormality scenarios are identified. Combined with the current stage of the roasting process and the aging state of the furnace body, process collaborative risk data under different roasting abnormality scenarios are constructed.

[0009] Based on the preset control requirements, a corresponding collaborative control strategy is formulated. According to the process collaborative risk data, the set of parameters to be adjusted is marked in the collaborative control strategy, and the optimized collaborative control strategy is obtained by making adjustments.

[0010] The balance index of the coupling state data of each partition after real-time acquisition of collaborative control is used to comprehensively evaluate each control node in the optimized collaborative control strategy. Control nodes that fail the evaluation are defined as risk nodes, and risk adjustment strategies are generated for the risk nodes.

[0011] The multi-parameter coordinated control method for ultra-high power graphite electrode calcination provided by this invention includes the following steps for dividing the calcination furnace into zones:

[0012] The furnace body structural dimensions, fire channel distribution location, burner layout parameters, and green billet loading density are collected as all-dimensional operating parameters.

[0013] Based on the electrode green specifications and the target roasting cycle, the distribution of the fire channels is designed to meet the requirements for uniform heat supply, and the roasting furnace chamber is uniformly divided into zones based on the distribution of the fire channels.

[0014] Based on the fixed distance between the placement of the green blanks and the center of the fire channel, radial zones are formed with the fire channel as the center to determine the zone boundaries.

[0015] Temperature sensors, pressure sensors, and gas component analyzers are deployed in each zone based on the number of zones and zone boundaries, and the sensors are calibrated for each zone.

[0016] The multi-parameter coordinated control method for calcination of ultra-high power graphite electrodes provided by this invention includes the following steps for acquiring coupling state data:

[0017] Based on multi-source sensors deployed in zones, the temperature data of the upper, middle and lower points of the green billet, the fire channel outlet point and the edge point of the furnace cavity are collected to form a temperature field dataset. The maximum temperature difference and temperature gradient are calculated, and the uniformity characteristics of the temperature field are recorded to form the temperature field distribution.

[0018] The volume fractions of CO, CO2, and O2 in each zone are collected, and the concentration data of the components formed by flue gas temperature and humidity are recorded. The atmospheric component ratio is obtained by correcting for humidity.

[0019] The static pressure value inside the furnace and the pressure difference between the fire channel and the cranial cavity are collected at a preset frequency as pressure data. The pressure gradient within the zone is calculated, and the pressure fluctuation amplitude and frequency, as well as the pressure change period, are used as the pressure gradient inside the furnace.

[0020] The rate of temperature change around the gap between the green blanks in each zone is detected, and the thermal conductivity of the green blank is calculated according to Fourier's law of heat conduction.

[0021] The gas flow rate through the filler layer in each zone is measured. The air permeability of the upper, middle and lower layers of the filler is calculated according to Darcy's law. The air permeability difference of different layers is recorded to obtain the air permeability data of the filler.

[0022] Based on the system timestamp, the temperature field distribution, atmosphere component ratio, furnace pressure gradient, green body thermal conductivity and filler permeability data of the same zone are synchronized in time, and the correlation characteristics between different parameters are marked to obtain coupled state data.

[0023] The multi-parameter coordinated control method for ultra-high power graphite electrode calcination provided by this invention includes the following steps for identifying different calcination anomaly scenarios:

[0024] The coupling state data of each partition is standardized and aligned in spatiotemporal dimension according to partition number and timestamp to obtain the coupled state processing data.

[0025] From the coupled state processing data, parameter features and coupling features related to roasting anomalies are extracted as roasting anomaly features.

[0026] Based on the requirements of the ultra-high power graphite electrode calcination process, three threshold levels were set for the extracted calcination anomaly characteristics.

[0027] A matching rule base for abnormal scenarios is established based on the three-level threshold and roasting anomaly characteristics. The coupling state processing data of each partition is traversed, and the corresponding roasting anomaly scenario is determined by combining the matching rule base.

[0028] The multi-parameter coordinated control method for ultra-high power graphite electrode calcination provided by this invention includes the following steps for obtaining process coordination risk data:

[0029] The absolute deviation values ​​of the roasting process stage data corresponding to different roasting anomaly scenarios are converted into relative deviation rates. Based on the sensitivity of different processes to roasting anomaly scenarios, the basic weights of the process stages are set.

[0030] The furnace body aging coefficient is calculated by normalizing the refractory thermal conductivity decay rate, furnace body sealing performance degradation rate, sensor detection accuracy deviation rate, burner efficiency decay rate, and furnace body cumulative operating time.

[0031] For abnormal roasting scenarios, risk factors for abnormal scenarios are classified according to the degree of harm, scope of impact, and duration of the abnormality.

[0032] The process sensitivity factor is calculated by combining the basic weight and relative deviation rate of the current process stage, and the aging amplification factor is calculated based on the furnace body aging coefficient.

[0033] By using a weighted summation method, the risk index is calculated by coupling the risk factors of abnormal scenarios, the sensitivity factors of processes, and the aging amplification factor.

[0034] Based on a preset numerical range, the collaborative risk index is divided into multiple risk levels, and the risk characteristics and control requirements corresponding to each risk level are determined to obtain process collaborative risk data.

[0035] The multi-parameter coordinated control method for calcination of ultra-high power graphite electrodes provided by this invention includes the following steps in formulating a coordinated control strategy:

[0036] Electrode volume density target, resistivity constraint and energy consumption threshold are taken as control requirements, decomposed into process parameter target values, and target weight coefficients are set according to production needs.

[0037] Based on historical process data, thermal parameters, atmosphere pressure parameters, and material parameters are selected as key process parameters, and a target correlation model is established between these parameters and their target values.

[0038] Based on the roasting process and the target values ​​of the process parameters, the parameter threshold ranges for each process are set, and a preliminary control strategy is formulated according to the linkage rules between different parameters.

[0039] For the initial control strategy, the volume density, resistivity and energy consumption are verified, and the coordinated control strategy is obtained by optimizing according to the target weight coefficient.

[0040] The multi-parameter coordinated control method for calcination of ultra-high power graphite electrodes provided by this invention includes the following steps for adjusting and obtaining an optimized coordinated control strategy:

[0041] By analyzing the impact parameters corresponding to the process synergy risk data of different roasting anomaly scenarios, and determining the risk mitigation logic of impact parameter adjustment, a risk parameter association rule library is obtained.

[0042] For each calcination anomaly scenario, the sensitivity coefficient of the influencing parameters is calculated.

[0043] Based on the risk parameter association rule base, the parameter categories, ranges and priorities that need to be adjusted are marked in the collaborative control strategy to obtain the parameter set to be adjusted.

[0044] The adjustment direction is determined based on the mitigation logic, the adjustment range is calculated by combining different risk levels and sensitivity coefficients, and the parameter adjustment sequence is designed for multi-parameter linkage adjustment scenarios to obtain the parameter adjustment scheme.

[0045] Substitute the parameter adjustment scheme into the collaborative control strategy, determine whether the control requirements are met, and if so, generate an optimized collaborative control strategy; otherwise, modify the adjustment range and direction.

[0046] The multi-parameter coordinated control method for calcination of ultra-high power graphite electrodes provided by this invention includes the following steps for obtaining the uniformity index:

[0047] After collecting and coordinating control data, the coupled state data of each partition is collected, and the different collection frequency is set according to the state change characteristics. The data is then normalized to obtain the coordinating data.

[0048] The mean, standard deviation, and coefficient of variation of the same parameter in each zone of the entire furnace are calculated. For a single zone, the fluctuation amplitude and fluctuation frequency within a continuous acquisition period are calculated to obtain the single equilibrium characteristic.

[0049] Based on the single equilibrium characteristics, different weights are assigned to spatial consistency and temporal stability to calculate the single-parameter equilibrium index.

[0050] By combining the influence weights of different parameters on the calcination process, the corresponding single-parameter equilibrium indexes are weighted and summed to obtain the equilibrium index.

[0051] The multi-parameter coordinated control method for calcination of ultra-high power graphite electrodes provided by this invention includes the following steps in generating a risk adjustment strategy:

[0052] The optimized collaborative control strategy is categorized and sorted by process stage, control zone, and parameter type. The parameter values, control range, and control object of each control node are determined to obtain the node characteristics.

[0053] By using historical control data, the weight of the deviation impact of each control node on the equilibrium index is calculated.

[0054] For each control node, based on its node characteristics and deviation impact weight, the node evaluation results are obtained by evaluating it according to the preset balance index threshold and the preset node control deviation threshold.

[0055] Node risk values ​​are calculated based on node assessment results, node risk levels are divided according to preset ranges, and nodes that meet preset requirements are selected as risk nodes.

[0056] For each risk node, analyze the root cause of the control failure, and generate risk adjustment strategies based on the problem type of the root cause and the risk level of the node.

[0057] The ultra-high power graphite electrode calcination multi-parameter collaborative control system provided by this invention includes:

[0058] The coupled data acquisition module is used to collect all-dimensional operating parameters of the roasting system, divide the roasting furnace into zones, and collect data on the furnace temperature field distribution, atmosphere component ratio, furnace pressure gradient, green body thermal conductivity and filler permeability of each zone in real time as coupled state data.

[0059] The process collaboration risk identification module is used to identify different roasting anomaly scenarios based on coupled state data. It combines the current stage of the roasting process and the aging state of the furnace body to construct process collaboration risk data under different roasting anomaly scenarios.

[0060] The collaborative control strategy optimization module is used to formulate corresponding collaborative control strategies based on preset control requirements. It marks the set of parameters to be adjusted in the collaborative control strategy according to the process collaborative risk data, and then adjusts them to obtain the optimized collaborative control strategy.

[0061] The node control feedback module is used to collect the balance index of the coupling state data of each partition after collaborative control in real time, to comprehensively evaluate each control node in the optimized collaborative control strategy, to define the control node that fails the evaluation as a risk node, and to generate a risk adjustment strategy pointing to the risk node.

[0062] The beneficial effects of this invention are as follows:

[0063] 1. This invention effectively suppresses furnace temperature field distortion, atmosphere segregation, and pressure fluctuations through zoned fine-tuning and multi-parameter coordinated control, improving the consistency of the product's microstructure. The accuracy of abnormal scenario identification is improved, and the response time is shortened, enabling early detection of potential risks and initiation of intervention measures, reducing major process accidents such as furnace failure, stack collapse, and electrode cracking. Comprehensive risk assessment and control optimization considering the furnace's aging state avoid structural damage caused by overheating or pressure shocks, delaying equipment degradation. Precise control of key indicators such as volumetric density and resistivity is achieved, meeting the requirements of ultra-high power graphite electrodes for high conductivity and high strength, enhancing product market competitiveness. Attached Figure Description

[0064] The invention will now be further described with reference to the accompanying drawings.

[0065] Figure 1 This is a schematic diagram of the multi-parameter coordinated control method for ultra-high power graphite electrode calcination provided in this embodiment of the invention.

[0066] Figure 2 This is a schematic diagram of the process for obtaining clinical mechanical characterization data in the multi-parameter collaborative control method for calcination of ultra-high power graphite electrodes provided in this embodiment of the invention.

[0067] Figure 3 This is a flowchart illustrating the multi-parameter collaborative control system for ultra-high power graphite electrode calcination provided in an embodiment of the present invention. Detailed Implementation

[0068] To make the technical means, creative features, objectives and effects of this invention easier to understand, the invention will be further described below in conjunction with specific embodiments.

[0069] like Figures 1 to 3 As shown, the multi-parameter coordinated control method for ultra-high power graphite electrode calcination provided in this embodiment of the invention includes:

[0070] Collect all dimensions of the calcination system's operating parameters, divide the calcination furnace into zones, and collect data in real time on the furnace temperature field distribution, atmosphere component ratio, furnace pressure gradient, green body thermal conductivity, and filler permeability of each zone as coupled state data.

[0071] The steps for dividing the roasting furnace into zones include:

[0072] The furnace body structural dimensions, fire channel distribution location, burner layout parameters, and green billet loading density are collected as all-dimensional operating parameters.

[0073] Based on the electrode green specifications and the target roasting cycle, the distribution of the fire channels is designed to meet the requirements for uniform heat supply, and the roasting furnace chamber is uniformly divided into zones based on the distribution of the fire channels.

[0074] Based on the fixed distance between the placement of the green blanks and the center of the fire channel, radial zones are formed with the fire channel as the center to determine the zone boundaries.

[0075] Using the geometric center of each fire channel as the radiation origin, the shortest / longest distance from the center of the fire channel to the surrounding green billets is measured, and the average distance is taken as the baseline value of the radiation radius. Using the center of the fire channel as the center and the radiation radius as the baseline, for the overlapping radiation zones of adjacent fire channels, the boundaries are demarcated according to the principle of "equivalent heat flux intensity." If the heat flux intensity in the overlapping zone is higher, the boundary is shifted towards the side with weaker heat flux. Heat loss exists in the furnace wall area; therefore, the range of the edge zones needs to be appropriately reduced, or auxiliary heating points need to be added to the edge zones to compensate for the temperature deviation caused by heat dissipation from the furnace wall.

[0076] Temperature sensors, pressure sensors, and gas component analyzers are deployed in each zone based on the number of zones and zone boundaries, and the sensors are calibrated for each zone.

[0077] Temperature sensors: One tungsten-rhenium thermocouple is deployed at the top, middle and bottom of each zone, and an additional infrared thermometer is added to the edge zones to monitor the effect of furnace wall heat dissipation on temperature.

[0078] Pressure sensor: Installed at the fire channel outlet and the middle of the furnace cavity within the zone to monitor changes in pressure gradient within the zone.

[0079] Gas component analyzer: Deployed at the exhaust port of the zone to detect the CO / CO2 ratio and O2 content in real time.

[0080] Zonal calibration: Using standard heat sources and standard pressure sources, each zone sensor is calibrated one by one, and the response values ​​and errors of the sensors under different operating conditions are recorded.

[0081] Establish a partitioned data correction model: compensate and correct the collected data for factors such as sensor measurement errors and furnace wall heat dissipation interference to ensure parameter accuracy.

[0082] The steps for collecting coupling state data include:

[0083] Based on multi-source sensors deployed in zones, the temperature data of the upper, middle and lower points of the green billet, the fire channel outlet point and the edge point of the furnace cavity are collected to form a temperature field dataset. The maximum temperature difference and temperature gradient are calculated, and the uniformity characteristics of the temperature field are recorded to form the temperature field distribution.

[0084] The volume fractions of CO, CO2, and O2 in each zone are collected, and the concentration data of the components formed by flue gas temperature and humidity are recorded. The atmospheric component ratio is obtained by correcting for humidity.

[0085] The static pressure value inside the furnace and the pressure difference between the fire channel and the cranial cavity are collected at a preset frequency as pressure data. The pressure gradient within the zone is calculated, and the pressure fluctuation amplitude and frequency, as well as the pressure change period, are used as the pressure gradient inside the furnace.

[0086] The rate of temperature change around the gap between the green blanks in each zone is detected. Based on Fourier's law of heat conduction, the thermal conductivity of the green blank is calculated using the following formula:

[0087]

[0088] In the formula, It is the thermal conductivity of the green body. It's the power of the hot wire. It refers to the temperature difference at different times.

[0089] The gas flow rate through the filler layer in each zone is measured. The air permeability of the upper, middle and lower layers of the filler is calculated according to Darcy's law. The air permeability difference of different layers is recorded to obtain the air permeability data of the filler.

[0090] The formula for calculating the air permeability of fillers according to Darcy's law is expressed as follows:

[0091]

[0092] In the formula, It is the gas flow rate. It is the viscosity of the gas. It refers to the thickness of the filler. It is the detection area. It detects the pressure difference in the chamber. It refers to air permeability.

[0093] Based on the system timestamp, the temperature field distribution, atmosphere component ratio, furnace pressure gradient, green body thermal conductivity and filler permeability data of the same zone are synchronized in time, and the correlation characteristics between different parameters are marked to obtain coupled state data.

[0094] Related characteristics: for example, "temperature rises → pressure rises → CO / CO2 ratio changes" and "filler permeability decreases → zoned pressure gradient increases".

[0095] Based on the coupling state data, different roasting abnormality scenarios are identified. Combined with the current stage of the roasting process and the aging state of the furnace body, process collaborative risk data under different roasting abnormality scenarios are constructed.

[0096] The steps to identify different roasting anomalies include:

[0097] The coupling state data of each partition is standardized and aligned in spatiotemporal dimension according to partition number and timestamp to obtain the coupled state processing data.

[0098] Standardization processing: Absolute parameters such as temperature field distribution and pressure gradient are converted into deviation rates relative to the target value (deviation rate = (measured value - target value) / target value × 100%). Relative parameters such as atmosphere component ratio, green body thermal conductivity, and filler permeability are normalized to the 0-1 range to eliminate dimensional differences. It is ensured that the five types of coupled parameters at the same time and in the same zone correspond one-to-one, forming a three-dimensional dataset of "zone-time-parameter," avoiding data confusion across zones and time periods.

[0099] From the coupled state processing data, parameter features and coupling features related to roasting anomalies are extracted as roasting anomaly features.

[0100] Parameter feature table:

[0101]

[0102] Coupling characteristics may include: Feature 1: Uneven temperature field + excessive pressure gradient → indicating blockage of the fire channel or abnormal burner injection angle, resulting in an imbalance between heat flow and airflow distribution.

[0103] Feature 2: Excessive O2 content + decreased CO / CO2 ratio → indicates furnace seal failure, air infiltration causing localized oxidation.

[0104] Feature 3: Decreased air permeability of filler + increased pressure gradient + lower temperature → indicates filler agglomeration, poor volatile matter discharge, and inhibition of green body temperature rise.

[0105] Feature 4: Decreased thermal conductivity of green body + uneven temperature field → indicates the presence of pores or cracks inside the green body, affecting heat conduction.

[0106] Based on the requirements of the ultra-high power graphite electrode calcination process, three threshold levels were set for the extracted calcination anomaly characteristics.

[0107] Three-level threshold table:

[0108]

[0109] A matching rule base for abnormal scenarios is established based on the three-level threshold and roasting anomaly characteristics. The coupling state processing data of each partition is traversed, and the corresponding roasting anomaly scenario is determined by combining the matching rule base.

[0110] Matching rule base:

[0111]

[0112] For identified abnormal scenarios, record the occurrence zone, occurrence time, and deviation of characteristic parameters to form an abnormal scenario ledger.

[0113] The steps to obtain process collaboration risk data include:

[0114] The absolute deviation values ​​of the roasting process stage data corresponding to different roasting anomaly scenarios are converted into relative deviation rates. Based on the sensitivity of different processes to roasting anomaly scenarios, the basic weights of the process stages are set.

[0115] The furnace body aging coefficient is calculated by normalizing the refractory thermal conductivity decay rate, furnace body sealing performance degradation rate, sensor detection accuracy deviation rate, burner efficiency decay rate, and furnace body cumulative operating time.

[0116] For abnormal roasting scenarios, risk factors for abnormal scenarios are classified according to the degree of harm, scope of impact, and duration of the abnormality.

[0117] The process sensitivity factor is calculated by combining the basic weight and relative deviation rate of the current process stage, and the aging amplification factor is calculated based on the furnace body aging coefficient.

[0118] By using a weighted summation method, the risk index is calculated by coupling the risk factors of abnormal scenarios, the sensitivity factors of processes, and the aging amplification factor.

[0119] Based on a preset numerical range, the collaborative risk index is divided into multiple risk levels, and the risk characteristics and control requirements corresponding to each risk level are determined to obtain process collaborative risk data.

[0120] The risk level can be divided into five levels, and the corresponding process collaboration risk data may include:

[0121] Level I, 0-1.0, localized minor anomalies, low sensitivity to process stage, minimal impact from furnace aging, no significant impact on product, no parameter adjustment required, continuous monitoring is sufficient.

[0122] Level II, 1.0-2.5, single zone abnormality, parameter deviation rate <100%, furnace body aging has little impact, may slightly affect performance consistency. Fine-tune local parameters, such as zone heating rate, and strengthen monitoring.

[0123] Level III, 2.5-4.0, multiple zones are abnormal, key parameter deviation rate >100%, process sensitive stage, furnace body aging amplification risk, start zone coordinated adjustment, adjust pressure / atmosphere parameters, limit abnormal diffusion.

[0124] Level IV, 4.0-6.0, systemic anomaly, parameters severely deviate, sensitive process stage, risk of accelerated furnace aging, easily leading to product defects. Initiate coordinated correction of all furnace parameters, reduce heating rate, adjust negative pressure, and suspend roasting if necessary.

[0125] Level V, >6.0 Major systemic anomalies, such as failure of the entire furnace seal or large-scale blockage of the fire channel, which may easily lead to safety accidents or batch scrapping. Immediately stop roasting, investigate equipment failures, and replace damaged parts, such as fillers and seals.

[0126] Based on the preset control requirements, a corresponding collaborative control strategy is formulated. According to the process collaborative risk data, the set of parameters to be adjusted is marked in the collaborative control strategy, and the optimized collaborative control strategy is obtained by making adjustments.

[0127] The steps to develop a coordinated control strategy include:

[0128] Electrode volume density target, resistivity constraint and energy consumption threshold are taken as control requirements, decomposed into process parameter target values, and target weight coefficients are set according to production needs.

[0129] Based on historical process data, thermal parameters, atmosphere pressure parameters, and material parameters are selected as key process parameters, and a target correlation model is established between these parameters and their target values.

[0130] Based on the roasting process and the target values ​​of the process parameters, the parameter threshold ranges for each process are set, and a preliminary control strategy is formulated according to the linkage rules between different parameters.

[0131] The drying period control parameters are: heating rate and furnace humidity. The parameter threshold range is: heating rate 1.5-2℃, humidity ≤10%, to avoid green body deformation and lay the foundation for subsequent density improvement.

[0132] The parameters for controlling the volatile matter removal period are: heating rate, negative pressure value, and air permeability of the filler. The parameter threshold range is: heating rate 0.8-1.2℃, negative pressure 0.02-0.03MPa, and air permeability ≥50cm3 / s, to ensure stable discharge of volatile matter and avoid excessive porosity.

[0133] The parameters for controlling the coking period are: heating rate, holding temperature, and holding pressure. The parameter threshold ranges are: heating rate 0.5-0.8℃, holding temperature 1200-1220℃, and holding pressure 0.04-0.05MPa, directly matching the target bulk density.

[0134] The parameters for controlling the high-temperature insulation period are: insulation duration and CO / CO2 ratio. The parameter threshold range is: insulation duration of 20-24 hours, satisfying the resistivity constraint.

[0135] The linkage rules may include: when the heat preservation pressure during the coking period is increased by 0.01 MPa, the heating rate is reduced by 0.1℃ simultaneously to ensure that the volume density is increased without increasing energy consumption.

[0136] When the CO / CO2 ratio is below 1.2 during the high-temperature insulation period, the exhaust volume should be increased appropriately, the negative pressure should be increased by 0.005MPa, and the insulation time should be extended by 2 hours to ensure that the resistivity meets the standard.

[0137] When energy consumption is close to the threshold, priority should be given to improving waste heat recovery efficiency rather than reducing the insulation temperature.

[0138] For the initial control strategy, the volume density, resistivity and energy consumption are verified, and the coordinated control strategy is obtained by optimizing according to the target weight coefficient.

[0139] Bulk density verification: Substitute the coking period parameters into the correlation model to predict whether the bulk density is within the range of 1.70±0.02g / cm3. If the predicted value is too low, increase the heat preservation pressure or reduce the heating rate.

[0140] Resistivity verification: Substitute the high-temperature insulation period parameters into the correlation model to predict whether the resistivity is ≤13.5μΩ·m. If the predicted value is too high, extend the insulation time or optimize the atmosphere composition.

[0141] Energy consumption verification: Calculate whether the total energy consumption of the entire process is ≤850kWh / ton of electrode. If it exceeds the standard, reduce costs by optimizing the heating rate curve and improving the waste heat recovery efficiency.

[0142] Density meets standards vs. energy consumption exceeds standards. Low heating rate during coking period increases density but causes energy consumption to exceed the threshold by 5%. Prioritize density and reduce energy consumption to within the threshold by improving waste heat recovery efficiency by 10%+ and optimizing fuel calorific value matching.

[0143] Resistivity meets standards vs. density decreases. Extending the high-temperature insulation time reduces resistivity but leads to a decrease in volume density of 0.03 g / cm3. Prioritizing density is achieved by increasing the insulation pressure by 0.01 MPa and fine-tuning the CO / CO2 ratio to 1.3, while also considering resistivity.

[0144] The steps to adjust and optimize the collaborative control strategy include:

[0145] By analyzing the impact parameters corresponding to the process synergy risk data of different roasting anomaly scenarios, and determining the risk mitigation logic of impact parameter adjustment, a risk parameter association rule library is obtained.

[0146] The influencing parameters are: zone heating rate, burner power, and induced draft volume. The mitigation logic is to reduce the heating rate of the clogged zone, reduce the corresponding burner power, and increase the induced draft volume to alleviate local high / low temperature deviations.

[0147] The influencing parameters are: furnace negative pressure and atmosphere composition (CO / CO2). The mitigation logic is: increase furnace negative pressure, supplement reducing gas, reduce O2 content, and inhibit electrode oxidation.

[0148] The influencing parameters are: filler particle size, insulation pressure, and heating rate. The mitigation logic is: replace the agglomerated filler, reduce the insulation pressure, slow down the heating rate, and promote the discharge of volatiles.

[0149] The influencing parameters are: the spacing between the green billets and the zone insulation temperature. The mitigation logic is to increase the spacing between the green billets with low thermal conductivity and fine-tune the zone insulation temperature to balance the heat transfer efficiency.

[0150] The influencing parameters are: waste heat recovery efficiency and fuel calorific value matching. The mitigation logic is: increase the load on the waste heat recovery system, switch to high-calorific-value fuels, and reduce energy consumption per unit product.

[0151] For each calcination anomaly scenario, the sensitivity coefficient of the influencing parameters is calculated.

[0152] Based on the risk parameter association rule base, the parameter categories, ranges and priorities that need to be adjusted are marked in the collaborative control strategy to obtain the parameter set to be adjusted.

[0153] Parameter set labeling principles may include: Risk level priority principle: parameters corresponding to higher risk levels are labeled first. Under the same risk, parameters with higher sensitivity coefficients are labeled first.

[0154] Target constraint compatibility principle: The marked parameters to be adjusted must take into account the three major targets of electrode volume density, resistivity and energy consumption, so as to avoid deviation of the target due to parameter adjustment.

[0155] Precise Zoning Principle: For local risks, only the parameters of the corresponding zone are marked, without adjusting the parameters of the entire furnace, thus reducing control redundancy.

[0156] The structured labeling of the parameter set to be adjusted involves screening each parameter in the original collaborative control strategy and labeling the parameter set to be adjusted in the format of "partition-parameter name-current set value-risk correlation-adjustment priority".

[0157] The adjustment direction is determined based on the mitigation logic, the adjustment range is calculated by combining different risk levels and sensitivity coefficients, and the parameter adjustment sequence is designed for multi-parameter linkage adjustment scenarios to obtain the parameter adjustment scheme.

[0158] Based on the risk of excessive O2 levels, increasing negative pressure is the adjustment direction. Based on the risk of flue blockage, reducing the heating rate is the adjustment direction. The higher the risk level and the greater the sensitivity coefficient, the larger the adjustment range.

[0159] The parameter adjustment sequence for the risk of blockage is "first increase the induced draft volume → then reduce the burner power → finally reduce the heating rate". First, the induced draft volume is used to guide the flue gas, and then the heat input is reduced to gradually alleviate the problem of uneven temperature field.

[0160] Substitute the parameter adjustment scheme into the collaborative control strategy, determine whether the control requirements are met, and if so, generate an optimized collaborative control strategy; otherwise, modify the adjustment range and direction.

[0161] The balance index of the coupling state data of each partition after real-time acquisition of collaborative control is used to comprehensively evaluate each control node in the optimized collaborative control strategy. Control nodes that fail the evaluation are defined as risk nodes, and risk adjustment strategies are generated for the risk nodes.

[0162] The steps to obtain the balance index include:

[0163] After collecting and coordinating control data, the coupled state data of each partition is collected, and the different collection frequency is set according to the state change characteristics. The data is then normalized to obtain the coordinating data.

[0164] The mean, standard deviation, and coefficient of variation of the same parameter in each zone of the entire furnace are calculated. For a single zone, the fluctuation amplitude and fluctuation frequency within a continuous acquisition period are calculated to obtain the single equilibrium characteristic.

[0165] Based on the single equilibrium characteristic, and by assigning different weights to spatial consistency and temporal stability, a single-parameter equilibrium index is calculated, expressed by the formula:

[0166]

[0167] In the formula, It is the first The coefficient of variation of each parameter It is the spatial consistency score. It is the first The fluctuation range of each parameter This is the maximum allowable fluctuation range of the parameter. It is the time stability score. , These are weighting coefficients. It is a single-parameter balance index.

[0168] By combining the influence weights of different parameters on the calcination process, the corresponding single-parameter equilibrium indexes are weighted and summed to obtain the equilibrium index.

[0169] The influencing factors can be categorized as follows: Furnace temperature field distribution (0.35), directly affecting electrode coking quality and bulk density; Atmosphere component ratio (0.25), determining the furnace oxidation / reduction atmosphere and affecting electrode resistivity; Furnace pressure gradient (0.20), related to volatile matter discharge efficiency, preventing green sheet cracking; Green sheet thermal conductivity (0.10), affecting the uniformity of heat conduction within the green sheet; and Filler permeability (0.10), assisting in regulating atmosphere and pressure distribution.

[0170] The steps to generate a risk adjustment strategy include:

[0171] The optimized collaborative control strategy is categorized and sorted by process stage, control zone, and parameter type. The parameter values, control range, and control object of each control node are determined to obtain the node characteristics.

[0172] By using historical control data, the weight of the deviation impact of each control node on the equilibrium index is calculated.

[0173] For each control node, based on its node characteristics and deviation impact weight, the node evaluation results are obtained by evaluating it according to the preset balance index threshold and the preset node control deviation threshold.

[0174] Balance Index Compliance: The associated single-parameter balance index is ≥ the preset threshold. Node Control Accuracy: The deviation rate between the actual node control value and the target setting value is ≤ 5%. Node Effectiveness: After node adjustment, the improvement in the associated balance index is ≥ 20%.

[0175] The evaluation is scored on a 100-point scale, with the balance index (compliance with standards) accounting for 60%, the precision of regulation accounting for 20%, and the timeliness of the effect accounting for 20%.

[0176] Balance score: If the measured single-parameter balance index is greater than or equal to the threshold, 60 points are awarded. For every 0.1 points lower, 10 points are deducted.

[0177] Precision control score: 20 points if the deviation rate is ≤5%. 2 points are deducted for every 1% exceeding the deviation rate.

[0178] Timeliness score: 20 points if the improvement is ≥20%. 5 points are deducted for every 5% decrease.

[0179] Calculate the comprehensive score Sn for each node. If Sn ≥ 80, the node is considered qualified. If Sn ≤ 60 and Sn < 80, the node is considered a potential risk node. If Sn < 60, the node is considered a risk node.

[0180] Node risk values ​​are calculated based on node assessment results, node risk levels are divided according to preset ranges, and nodes that meet preset requirements are selected as risk nodes.

[0181] The formula for calculating the node risk value is expressed as:

[0182]

[0183] In the formula, It is the node risk value. It is the inverse proportion of the node evaluation score. The node affects the weight. It is the risk diffusion coefficient.

[0184] Significant risk: The control at node Rn≥0.8 has failed, resulting in a serious failure of the correlation equilibrium index, and the risk is likely to spread to the entire furnace.

[0185] The moderate risk (0.4≤Rn<0.8) node regulation effect is poor, the correlation equilibrium index does not meet the standard, and the risk is limited to the medium to high level in local partitions.

[0186] Mild risk (0.2≤Rn<0.4): Insufficient precision in node control; correlation equilibrium index close to the threshold; no significant risk diffusion.

[0187] The low-risk node with Rn < 0.2 passed the assessment, the correlation equilibrium index met the standard, and there was no risk of regulation.

[0188] Control nodes with risk levels of major risk and moderate risk were selected as risk nodes.

[0189] For each risk node, analyze the root cause of the control failure, and generate risk adjustment strategies based on the problem type of the root cause and the risk level of the node.

[0190] Issue with the zone heating rate adjustment node: The setpoint is too high, resulting in a temperature field uniformity index of 0.72 (threshold 0.85). Adjustment strategy: 1. Reduce the heating rate of this zone to 80% of the original setpoint. 2. Simultaneously reduce the corresponding burner power by 10%. 3. Collect temperature field data every 10 minutes to monitor changes in uniformity. Expected improvement target: Improve the temperature field uniformity index to ≥0.85.

[0191] Issue with the zoned negative pressure adjustment node: The setpoint is too low, resulting in a pressure gradient balance index of 0.78 (threshold 0.80). Adjustment strategies: 1. Increase the zoned negative pressure by 0.005 MPa. 2. Optimize the induced draft fan speed matching. 3. Monitor the atmospheric composition balance in conjunction with the setting to prevent excessively high negative pressure from causing atmospheric imbalance. Expected improvement target: Increase the pressure gradient balance index to ≥0.80.

[0192] The issue encountered was clumping of the filler material, with an air permeability uniformity index of 0.70 (threshold 0.80). The proposed solutions were: 1. Replace the clumped filler with coke granules of more uniform particle size. 2. Reduce the insulation pressure in the corresponding zone by 0.003 MPa. 3. Conduct layer-by-layer air permeability testing to ensure uniformity across all layers. The expected improvement goal was to increase the air permeability uniformity index of the filler material to ≥0.80.

[0193] Based on the same general inventive concept, this invention also protects a multi-parameter coordinated control system for ultra-high power graphite electrode calcination, comprising:

[0194] The coupled data acquisition module is used to collect all-dimensional operating parameters of the roasting system, divide the roasting furnace into zones, and collect data on the furnace temperature field distribution, atmosphere component ratio, furnace pressure gradient, green body thermal conductivity and filler permeability of each zone in real time as coupled state data.

[0195] The process collaboration risk identification module is used to identify different roasting anomaly scenarios based on coupled state data. It combines the current stage of the roasting process and the aging state of the furnace body to construct process collaboration risk data under different roasting anomaly scenarios.

[0196] The collaborative control strategy optimization module is used to formulate corresponding collaborative control strategies based on preset control requirements. It marks the set of parameters to be adjusted in the collaborative control strategy according to the process collaborative risk data, and then adjusts them to obtain the optimized collaborative control strategy.

[0197] The node control feedback module is used to collect the balance index of the coupling state data of each partition after collaborative control in real time, to comprehensively evaluate each control node in the optimized collaborative control strategy, to define the control node that fails the evaluation as a risk node, and to generate a risk adjustment strategy pointing to the risk node.

[0198] In summary, the multi-parameter collaborative control method and system for ultra-high power graphite electrode calcination provided in this embodiment effectively solves problems such as uneven heating of green blanks and atmosphere imbalance through precise zoned control and early intervention for abnormal risks. This significantly improves the consistency of electrode volume density and resistivity, reducing product downgrade and scrap rates. Balancing core product performance with energy consumption control, and while meeting stringent requirements for volume density and resistivity, it reduces unit product energy consumption and significantly lowers production costs by optimizing parameters such as heating rate and waste heat recovery. Real-time identification of calcination anomalies and quantitative risk assessment enable "early detection and early control," preventing safety hazards caused by the escalation of anomalies. Targeted adjustment of risk nodes further enhances the controllability of the process. This improves the stability and controllability of the calcination process.

[0199] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0200] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A multi-parameter coordinated control method for calcination of ultra-high power graphite electrodes, comprising: Collect all dimensions of the operating parameters of the roasting system, divide the roasting furnace into zones, and collect data on the furnace temperature field distribution, atmosphere composition ratio, furnace pressure gradient, green body thermal conductivity and filler permeability of each zone in real time as coupled state data. Based on the coupling state data, different roasting abnormal scenarios are identified. Combined with the current stage of the roasting process and the aging state of the furnace body, process collaborative risk data under different roasting abnormal scenarios are constructed. Based on the preset control requirements, a corresponding collaborative control strategy is formulated. According to the process collaborative risk data, the set of parameters to be adjusted is marked in the collaborative control strategy, and the optimized collaborative control strategy is obtained by making adjustments. The balance index of the coupling state data of each partition after real-time acquisition of collaborative control is used to comprehensively evaluate each control node in the optimized collaborative control strategy. Control nodes that fail the evaluation are defined as risk nodes, and risk adjustment strategies are generated for the risk nodes. The steps to obtain the balance index include: Collect the coupled state data of each partition after collaborative control, and set a differentiated collection frequency according to the state change characteristics, and perform normalization processing to obtain collaborative processing data; The mean, standard deviation and coefficient of variation of the same parameter in each zone of the whole furnace are calculated. For a single zone, the fluctuation amplitude and fluctuation frequency in the continuous acquisition period are calculated to obtain the single equilibrium characteristics. Based on the single equilibrium characteristic, and by assigning different weights to spatial consistency and temporal stability, a single-parameter equilibrium index is calculated. The balance index is obtained by weighting the influence weights of different parameters on the roasting process and summing the corresponding single-parameter balance indices.

2. The multi-parameter coordinated control method for baking ultra-high power graphite electrodes according to claim 1, characterized in that: The steps for dividing the roasting furnace into zones include: The furnace body structural dimensions, fire channel distribution location, burner layout parameters, and green billet loading density are collected as the full-dimensional operating parameters. Based on the electrode green specifications and the target roasting cycle, the distribution of the fire channels is made to meet the requirements of uniform heat supply, and the roasting furnace chamber is uniformly cut to determine the number of partitions based on the distribution of the fire channels. Based on the fixed distance between the placement of the green blanks and the center of the fire channel, radial zones are formed with the fire channel as the center to determine the zone boundaries. Temperature sensors, pressure sensors, and gas component analyzers are deployed in each partition based on the number of partitions and the partition boundaries, and the sensors are calibrated for each partition.

3. The multi-parameter coordinated control method for calcination of ultra-high power graphite electrodes according to claim 1, characterized in that: The steps for collecting the coupling state data include: Based on multi-source sensors deployed in zones, the temperature of the upper, middle and lower points of the green billet, the fire channel outlet point and the edge point of the furnace cavity are collected to form a temperature field dataset. The maximum temperature difference and temperature gradient are calculated, and the uniformity characteristics of the temperature field are recorded to form the temperature field distribution. The volume fractions of CO, CO2, and O2 in each zone are collected, and the concentration data of the components formed by flue gas temperature and humidity are recorded. The proportion of the atmosphere components is obtained by correcting for humidity. The static pressure value inside the furnace and the pressure difference between the fire channel and the cranial cavity are collected at a preset frequency as pressure data. The pressure gradient within the zone is calculated, and the fluctuation amplitude and frequency of pressure and the time period of pressure change are used as the pressure gradient inside the furnace. The rate of temperature change around the gap between the green blanks in each zone is detected, and the thermal conductivity of the green blank is calculated according to Fourier's law of heat conduction. The gas flow rate through the filler is measured in each zone of the filler layer. The air permeability of the upper, middle and lower layers of the filler is calculated according to Darcy's law. The air permeability difference of different layers is recorded to obtain the air permeability data of the filler. Based on the system timestamp, the temperature field distribution, atmosphere component ratio, furnace pressure gradient, green body thermal conductivity and filler permeability data of the same partition are synchronized in time, and the correlation characteristics between different parameters are marked to obtain the coupling state data.

4. The multi-parameter coordinated control method for calcination of ultra-high power graphite electrodes according to claim 1, characterized in that: The steps to identify different roasting anomalies include: The coupling state data of each partition is standardized and aligned in spatiotemporal dimension according to partition number and timestamp to obtain the coupled state processing data; From the coupled state processing data, extract the parameter features and coupling features related to calcination anomalies as calcination anomaly features; Based on the requirements of the ultra-high power graphite electrode calcination process, a three-level threshold is set for the extracted calcination anomaly features; A matching rule base for abnormal scenarios is established based on the three-level threshold and the abnormal roasting characteristics. The coupling state processing data of each partition is traversed, and the corresponding abnormal roasting scenario is determined by combining the matching rule base.

5. The multi-parameter coordinated control method for calcination of ultra-high power graphite electrodes according to claim 1, characterized in that: The steps for obtaining the process collaboration risk data include: The absolute deviation values ​​of the roasting process stage data corresponding to different roasting anomaly scenarios are converted into relative deviation rates. Based on the sensitivity of different processes to roasting anomaly scenarios, the basic weights of the process stages are set. The furnace body aging coefficient is calculated by normalizing the refractory thermal conductivity decay rate, furnace body sealing performance decline rate, sensor detection accuracy deviation rate, burner efficiency decay rate, and furnace body cumulative running time. For the aforementioned abnormal roasting scenarios, risk factors for abnormal scenarios are classified according to the degree of harm, scope of impact, and duration of the abnormality type. The process sensitivity factor is calculated by combining the basic weight of the current process stage and the relative deviation rate, and the aging amplification factor is calculated based on the furnace body aging coefficient. The synergistic risk index is calculated by coupling the abnormal scenario risk factor, the process sensitivity factor, and the aging amplification factor using a weighted summation method. The collaborative risk index is divided into multiple risk levels according to a preset numerical range, and the risk characteristics and control requirements corresponding to each risk level are determined to obtain the collaborative risk data of the process.

6. The multi-parameter coordinated control method for calcination of ultra-high power graphite electrodes according to claim 1, characterized in that: The steps for formulating the aforementioned collaborative control strategy include: The electrode volume density target, resistivity constraint, and energy consumption threshold are taken as the control requirements, decomposed into process parameter target values, and target weight coefficients are set according to production requirements. Based on historical process data, thermal parameters, atmosphere pressure parameters, and material parameters are selected as key process parameters, and a target correlation model is established with the target values ​​of the process parameters. Based on the roasting process and the target values ​​of the process parameters, the parameter threshold ranges for each process are set, and a preliminary control strategy is formulated according to the linkage rules between different parameters. The preliminary control strategy is validated based on volume density, resistivity, and energy consumption, and then optimized according to the target weight coefficients to obtain the cooperative control strategy.

7. The multi-parameter coordinated control method for calcination of ultra-high power graphite electrodes according to claim 6, characterized in that: The steps for adjusting and obtaining the optimized collaborative control strategy include: By analyzing the impact parameters corresponding to the process coordination risk data of different roasting abnormal scenarios, and determining the risk mitigation logic of the adjustment of the impact parameters, a risk parameter association rule library is obtained. For each calcination anomaly scenario, the sensitivity coefficient of the influencing parameter is calculated. Based on the risk parameter association rule base, the parameter categories, ranges and priorities that need to be adjusted are marked in the collaborative control strategy to obtain the set of parameters to be adjusted; The adjustment direction is determined based on the mitigation logic, and the adjustment range is calculated by combining different risk levels and the sensitivity coefficient. The order of parameter adjustment is designed for multi-parameter linkage adjustment scenarios to obtain the parameter adjustment scheme. Substitute the parameter adjustment scheme into the collaborative control strategy to determine whether the control requirements are met. If so, generate the optimized collaborative control strategy; otherwise, correct the adjustment magnitude and the adjustment direction.

8. The multi-parameter coordinated control method for calcination of ultra-high power graphite electrodes according to claim 1, characterized in that: The steps for generating the risk adjustment strategy include: The optimized collaborative control strategy is categorized and sorted by process stage, control zone, and parameter type to identify all control nodes. The parameter values, control range, and control objects of each control node are determined to obtain node characteristics. The weight of the deviation impact of each control node on the equilibrium index is calculated using historical control data. For each control node, based on its node characteristics and deviation impact weight, the node evaluation results are obtained by evaluating it according to the preset balance index threshold and the preset node control deviation threshold. Calculate the node risk value based on the node evaluation results, divide the node risk level according to the preset range, and select the nodes that meet the preset requirements as the risk nodes. For each risk node, analyze the root cause of the control failure, and generate the risk adjustment strategy based on the problem type of the root cause and the risk level of the node.

9. A multi-parameter collaborative control system for ultra-high power graphite electrode calcination, applied to the multi-parameter collaborative control method for ultra-high power graphite electrode calcination as described in any one of claims 1 to 8, characterized in that, The control system includes: The coupled data acquisition module is used to collect all-dimensional operating parameters of the roasting system, divide the roasting furnace into zones, and collect data on the furnace temperature field distribution, atmosphere component ratio, furnace pressure gradient, green body thermal conductivity and filler permeability of each zone in real time as coupled state data. The process collaboration risk identification module is used to identify different roasting abnormal scenarios based on the coupling state data, and to construct process collaboration risk data under different roasting abnormal scenarios by combining the current stage of the roasting process and the aging state of the furnace body. The collaborative control strategy optimization module is used to formulate a corresponding collaborative control strategy based on preset control requirements, mark the set of parameters to be adjusted in the collaborative control strategy according to the process collaborative risk data, and make adjustments to obtain an optimized collaborative control strategy. The node control feedback module is used to collect the balance index of the coupling state data of each partition after collaborative control in real time, to comprehensively evaluate each control node in the optimized collaborative control strategy, to define the control node that fails the evaluation as a risk node, and to generate a risk adjustment strategy for the risk node.

Images