Air supply optimization method for long-distance slag particle conveying pipeline

Abstract

The invention provides an air supply optimization method for a long-distance slag particle conveying pipeline, and relates to the technical field of pneumatic conveying, based on an actual topological structure of the conveying pipeline, the conveying pipeline is divided into space grid units, a risk scoring function is constructed, a conveying parameter-blockage level-blockage grid position database is constructed, and intervention priority candidate units are marked. And extracting a corresponding air supply parameter set, and generating a personalized air supply scheme. The problem that in the prior art, due to the fact that air supply operation depends on a preset strategy or manual intervention, the air supply amount cannot be adjusted in real time, the conveying state change in a pipeline cannot be accurately handled, and the blocking risk is increased is solved. By constructing the grid chart containing the conveying pipe section topological structure and the blockage risk level and combining the conveying parameter-blockage level-blockage grid position database, the accuracy of blockage risk identification of different grid units is improved, the timeliness of an air supply intervention scheme is enhanced, and the blockage risk is remarkably reduced.

Description

Technical Field

[0001] The present application relates to the technical field of pneumatic conveying, and particularly to a method for optimizing air supplement in a long-distance slag particle conveying pipeline. Background Art

[0002] With the continuous development of industrial solid waste resource utilization and dry conveying technology, the long-distance and high-efficiency transmission of solid particles such as slag particles through a pneumatic conveying system has become a common process path. Such gas-solid two-phase conveying systems have the advantages of flexible layout, low pollution, and high automation, and are widely used in the slag particle treatment and conveying links of industries such as electric power, metallurgy, and building materials.

[0003] However, during the long-distance and high-concentration slag particle conveying process, due to factors such as imbalance of gas-solid mixing ratio, system pressure fluctuation, uneven flow velocity, or complex local pipeline structure, it is extremely easy for the conveying pipeline to have phenomena such as slag particle accumulation, blocked flow, and even blockage. Once blockage occurs, it will not only interrupt the entire conveying process, but may also cause system safety risks, increase energy consumption and maintenance costs, seriously affecting the continuity and stability of industrial production.

[0004] In the prior art, air supplement interfaces are generally set along the conveying pipeline, and compressed air is quantitatively supplemented into the pipeline in a manual or preset timing control manner to increase the local gas-solid ratio and disperse the accumulated matter. However, this traditional air supplement method has most air supplement operations relying on preset strategies or manual intervention, failing to achieve real-time dynamic response to the conveying state, easily causing over-air supplement or response lag, and being difficult to accurately match the air supplement timing and intensity according to the actual operating state. This results in low air supplement efficiency, increased system energy consumption, and even in some high-risk areas, the slag particle accumulation trend is aggravated due to air supplement delay, increasing the probability of blockage and the risk of safety accidents. Summary of the Invention

[0005] The present application provides a method for optimizing air supplement in a long-distance slag particle conveying pipeline, which solves the problem that the prior art cannot respond to the change of the conveying state in the pipeline in real time and dynamically due to the air supplement operation relying on preset strategies or manual intervention, and achieves the effect of intelligently identifying abnormal trends and dynamically optimizing the air supplement strategy based on the operation state parameters obtained in real time, thereby improving the accuracy and timeliness of air supplement response and significantly reducing the blockage risk.

[0006] In view of the above problems, the present application provides an air supplement optimization method for a long-distance slag particle conveying pipeline, and the method includes: arranging pressure sensors, air flow velocity sensors, and particulate matter concentration monitors at key nodes of the conveying pipeline to collect the operating state parameters of the gas-solid mixture in the pipeline in real time, where the key nodes include pipeline bends, pipe diameter changes, branch points, the source end and the end position of the conveying pipeline; based on the actual topological structure of the conveying pipeline, dividing the conveying pipeline into spatial grid units according to its physical structure and key control points, where the spatial grid units have a one-to-one correspondence with the geometric layout of the conveying pipeline, and each grid unit is provided with a unique identifier corresponding to its spatial position in the conveying pipeline; based on the historical blockage data of the conveying pipeline, by statistically analyzing the blockage occurrence frequency, blockage duration, and the fluctuation of conveying parameters before blockage in each grid unit, constructing a risk scoring function; combining the historical blockage data with the real-time obtained operating state parameters, inputting the risk scoring function to evaluate the blockage risk of each grid unit, and dividing the grid units into five levels of blockage risk levels, constructing a grid map including the topological structure of the conveying pipe section and the corresponding blockage risk levels; based on a preset time window, continuously collecting the operating data obtained by the sensors arranged at the key nodes of the conveying pipeline and updating the operating data to the grid map including the topological structure of the conveying pipe section and the corresponding blockage risk levels in real time; based on the grid map including the topological structure of the conveying pipe section and the corresponding blockage risk levels and combining historical blockage events, constructing a conveying parameter-blockage level-blockage grid position database; based on the currently collected operating state parameters, comparing with the blockage characteristics in the conveying parameter-blockage level-blockage grid position database, identifying potential blockage risk areas and determining whether they are intervention priority candidate units, and marking the intervention priority candidate units; for the marked intervention priority candidate units, retrieving from the conveying parameter-blockage level-blockage grid position database blockage events that are similar to the current operating state parameters and have successfully removed blockages in history, and extracting the corresponding air supplement parameter set, where the air supplement parameters include air supplement position, air supplement pressure or flow rate, and air supplement duration; based on the operating state of the current conveying system, combining the extracted successful air supplement parameters, generating a personalized air supplement plan, where the air supplement plan includes air supplement position suggestions, air supplement pressure or flow rate, air supplement duration, and the priority of the air supplement strategy.

[0007] One or more technical solutions provided in the present application have at least the following technical effects or advantages: Based on the constructed database of conveying parameters - blockage levels - blockage grid positions, combined with the operation status parameters collected in real time, the dynamic perception and level classification of blockage risks are realized, effectively improving the early warning ability for potential blockage areas; by extracting the current parameter change trends of high-risk grid cells and comparing with the historical blockage evolution paths, the intervention priority candidate areas are accurately identified, thus avoiding the resource waste and local disturbances caused by the "extensive net casting" air supplementation in traditional methods; using the successful blockage removal cases in history as air supplementation experience samples, combined with the current system operation status for adaptability analysis, a personalized air supplementation plan that adapts to local conditions and adjusts according to needs is generated, and the air supplementation parameters are more in line with the actual conveying environment; effectively reducing the frequency of shutdowns, pressure relief and backwashing operations caused by blockages, prolonging the continuous and stable operation time of the system, reducing the operation and maintenance costs, and enhancing the overall anti-blockage ability of the system.

[0008] In summary, the present application realizes the accurate identification of potential blockage areas and the generation of personalized air supplementation intervention strategies by constructing a grid map including the topological structure of the conveying pipe section and the blockage risk level, as well as the database of conveying parameters - blockage levels - blockage grid positions, combined with the operation status parameters collected in real time and the historical blockage evolution characteristics. It not only improves the accuracy and effectiveness of air supplementation intervention, but also reduces the system disturbances and energy consumption waste caused by ineffective air supplementation, effectively reducing the frequency of pipeline shutdowns, backwashing and maintenance caused by blockages. At the same time, through the adaptability analysis and strategy screening of the current operation status and historical successful air supplementation samples, the air supplementation parameter combination can be dynamically adjusted to accurately match the current blockage trend development stage, preventing small blockages from evolving into serious pipeline blockage events, thus significantly improving the operation stability and continuity of the long-distance slag particle conveying system.

[0009] The above description is only an overview of the technical solution of the present application. In order to be able to understand the technical means of the present application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features and advantages of the present application more obvious and understandable, the specific embodiments of the present application are given below. Brief Description of the Drawings

[0010] Figure 1 It is a flow schematic diagram of an air supplementation optimization method for a long-distance slag particle conveying pipeline provided by an embodiment of the present application. Detailed Embodiment

[0011] By providing a method and system for optimizing air supplement in a long-distance slag particle conveying pipeline, the embodiments of the present application solve the problems in the prior art that there is a lack of dynamic recognition and precise intervention capabilities for the evolution trend of local blockage in the conveying pipeline, resulting in a lagging air supplement strategy, unreasonable selection of air supplement areas, frequent occurrence of conveying interruption or system backwashing, and achieve the intelligent air supplement intervention goal based on risk level recognition, parameter feature comparison, and air supplement experience learning. Thus, the operation continuity of the slag particle conveying system and the effectiveness of the air supplement operation are improved, and the energy consumption loss, maintenance cost, and operation risk caused by blockage are significantly reduced.

[0012] Embodiment 1, as Figure 1 shown, a method for optimizing air supplement in a long-distance slag particle conveying pipeline, the method comprising: S100: Arrange pressure sensors, air flow velocity sensors, and particulate matter concentration monitors at key nodes of the conveying pipeline to collect the operation state parameters of the gas-solid mixture in the pipeline in real time. The key nodes include pipeline bends, pipe diameter changes, branch points, and the source and end positions of the conveying pipeline.

[0013] Specifically, arrange a sensor group in key areas within the conveying pipeline to obtain the operation state parameters obtained in real time during the slag particle conveying process. The key areas include, but are not limited to: the elbow area of the pipeline, the vertical or slope change area, the area near the air supplement device, the pipeline end, and the pipeline joint area. The sensor group includes a pressure sensor, a flow velocity sensor, and a density sensor, which are used to collect the pressure change, flow velocity change, and material density change during the slag particle conveying process respectively. The operation state parameters include: pressure parameters, flow velocity parameters, density parameters, gas-solid ratio parameters, and abnormal fluctuation parameters, which are used to characterize the conveying state and serve as the input basis for blockage trend recognition and air supplement regulation.

[0014] S200: Based on the actual topological structure of the conveying pipeline, divide the conveying pipeline into spatial grid units according to its physical structure and key control points. The spatial grid units have a one-to-one correspondence with the geometric layout of the conveying pipeline, and each grid unit is provided with a unique identifier, and the identifier corresponds to its spatial position in the conveying pipeline.

[0015] Specifically, first, based on the actual topological structure of the conveying pipeline, a spatial model of the conveying system is established. Specifically, the entire conveying pipeline is divided into several spatial grid units according to its physical structure characteristics, geometric shape, and the positions of key control points. Each spatial grid unit has a one-to-one correspondence with the geometric layout of the actual conveying pipeline, ensuring the accuracy and traceability of the constructed grid map in spatial mapping. To achieve fine management of the conveying state and risk identification in each area, each grid unit is provided with a unique identifier, which reflects its spatial position in the overall structure of the conveying pipeline, such as the corresponding pipe section number, longitudinal mileage, and the control point interval it belongs to. This unique identifier is not only used for data association, risk grading, and strategy formulation but also serves as a key reference for the subsequent positioning and implementation of the air supplement plan.

[0016] S300: Based on the historical blockage data of the conveying pipeline, by statistically analyzing the blockage occurrence frequency, blockage duration, and the fluctuation of conveying parameters before the blockage in each grid unit, a risk scoring function is constructed.

[0017] Specifically, based on the historical blockage data of the conveying pipeline, the characteristics of blockage events are statistically analyzed for each of the divided spatial grid units. Through multi-dimensional statistics on the occurrence frequency, blockage duration of historical blockage events in each grid unit, and the fluctuation characteristics of operating state parameters (such as pressure, flow rate, particle concentration, etc.) during a period before the blockage, typical evolution patterns are extracted. A risk scoring function for measuring the blockage tendency of each grid unit is constructed. This function can comprehensively evaluate: the frequency of historical blockages occurring in this unit; the severity of the impact of blockages on the system; the correlation between abnormal fluctuations of operating state parameters and blockages. The risk scoring function outputs risk values based on grid units, which can reflect the potential probability of blockages occurring in each area during long-term operation and their impact degree, providing a quantitative basis for subsequent risk grading, judgment of air supplement priorities, and formulation of personalized intervention strategies.

[0018] Furthermore, step S300 of the embodiment of the present application further includes: S301: Extract the data of blockage events that have occurred from the historical operation records of the conveying system, and collect the relevant conveying parameter data before, during, and after the blockage; S302: Divide the entire conveying pipeline into several spatial grid units according to the preset physical topological structure, and map each blockage event to the corresponding grid number; S303: For each grid area, count the blockage indicators, and the blockage indicators include blockage frequency, average blockage duration, and parameter fluctuation characteristics; S304: Construct a risk scoring function = α× F + β× D + γ× V ; wherein, is the risk score of the th grid, F is the blockage frequency of the th grid, D is the average blockage duration, V is the parameter fluctuation characteristic index, α is the weight coefficient of the blockage frequency of the th grid, β is the weight coefficient of the average blockage duration, and γ is the weight coefficient of the parameter fluctuation characteristic index; S305: Mark the calculation results on the grid map of the conveying pipeline to form a risk heat map.

[0019] It should be understood that the data of the occurred blockage events are extracted from the historical operation records of the conveying system, and the key conveying parameter data before the blockage, during the blockage, and after the blockage removal operation are collected, such as flow rate, pressure, particle concentration, energy consumption change, etc., to reflect the complete process of blockage evolution. According to the physical topology structure of the conveying pipeline, the entire pipeline is divided into several spatial grid units, and the grid units correspond one by one to the geometric structure of the conveying pipeline and the key control nodes. Each grid unit is set with a unique number identifier to reflect its spatial position in the system. Subsequently, each blockage event extracted in step S301 is mapped to the corresponding grid number according to its geographical location and system topology information, so as to realize the position calibration of the blockage event in the grid structure. For each grid area, key indicators related to blockage are statistically calculated, including: Blockage frequency: the number of blockages occurred in the grid unit within the set time window; Average blockage duration: the average value of the time from the occurrence to the removal of each blockage event; Parameter fluctuation characteristics: statistical characteristics such as the variation range and mutation rate of the relevant parameters (such as pressure, velocity, concentration) before the blockage. The summary analysis is carried out for all grid units, and the calculation results are marked in the grid map structure of the conveying pipeline in a graphical manner, so as to generate a risk heat map reflecting the blockage risk levels at different spatial positions. This heat map can be used to visually identify the high-risk areas, and assist in the subsequent formulation of the air supplement strategy and intervention decision-making.

[0020] S400: Combine the historical blockage data with the operation state parameters obtained in real time, input the risk scoring function to evaluate the blockage risk of each grid unit, and divide the grid units into five levels of blockage risk grades, and construct a grid map including the topological structure of the conveying pipe section and the corresponding blockage risk grades.

[0021] Specifically, by combining the historical blockage data collected from the conveying system with the currently real-time obtained operating state parameters, comprehensively analyze the operating states of each spatial grid unit in the conveying pipeline, and input the data into a preset risk scoring function for evaluation. The risk scoring function is used to quantify the blockage risk level of each grid unit, and the considered factors include the historical blockage frequency of the grid unit, the statistical distribution of the blockage duration, the fluctuation pattern of the conveying parameters before the blockage occurs, the characteristic similarity between the current operating state parameters and the historical blockage events, and the relative position of the grid unit in the topological structure of the conveying system (such as being located in a high-drop section, a horizontal section, an elbow, etc.). According to the risk level results, combined with the actual topological structure of the conveying pipe section, construct a grid risk level map, that is, on the grid structure with consistent topology, mark the corresponding risk level information of each unit to form a multi-dimensional fusion map containing spatial position, operating characteristics, and blockage risk information. This grid map can be used as the core reference basis for subsequent blockage trend monitoring, active air supply strategy formulation, and intervention area identification.

[0022] Furthermore, step S400 of the embodiment of the present application further includes: S401: Extract the blockage events that have occurred in each grid area, including the blockage frequency, duration, and the fluctuation of the conveying parameters before the blockage; S402: Obtain the real-time pressure, air flow velocity, particle concentration, temperature, and humidity parameters in each current grid area through the arranged sensors; S403: Using the statistical features extracted from the historical blockage data, combined with the real-time parameter changes, calculate the risk score of each grid area: = α× F + β× D + γ× ΔP + δ× C ; where is the risk score of the i-th grid at time t, F is the historical blockage rate, D is the average blockage duration, ΔP is the real-time pressure fluctuation index, C is the real-time particle concentration change index, and α, β, γ, δ are weighting coefficients; S404: Normalize the risk scores of all grid units, and divide all grids into five levels according to the risk score range. The risk levels include first-level risk, second-level risk, third-level risk, fourth-level risk, and zero-level risk; S405: Mark the evaluated risk levels to each grid unit, and at the same time retain the topological correspondence between the grid unit and the conveying pipe section, and construct a grid map of the topological structure of the conveying pipe section and the corresponding blockage risk levels; S406: Based on a preset time window, continuously collect sensor data, update the risk scores and risk levels of the grid units in real time, and dynamically adjust the grid map.

[0023] It should be understood that the clogging events that have occurred in each grid area are extracted from the historical operation records of the conveying system, and the following clogging characteristic indicators are statistically summarized: the frequency of clogging occurrence (F), which represents the number of clogging occurrences in a certain grid area per unit time; the average clogging duration (D), which reflects the severity of the clogging phenomenon in this area; the fluctuation characteristics of the conveying parameters before the clogging occurs, including the pressure change rate, the change trend of the particle concentration, etc. Through the sensor devices arranged at the key nodes and grid areas of the conveying pipeline, the real-time operation state parameters at the current moment are obtained, including but not limited to: the pressure value and its change rate (ΔP) inside the pipeline; the air flow velocity; the particle concentration change index (C); environmental parameters such as temperature and humidity. Based on the historical statistical characteristics and real-time parameters, a risk scoring function is used to perform risk quantification calculations on each grid cell.

[0024] The risk scoring results of all grid cells are normalized, and according to the set risk scoring threshold interval, the grid cells are divided into five risk levels, specifically including: level one risk (extremely high risk); level two risk (high risk); level three risk (medium risk); level four risk (low risk); level zero risk (safe area). The risk level assessment results are marked on the corresponding spatial grid cells, and at the same time, the grid numbers are kept in one-to-one correspondence with the actual physical topology of the conveying pipeline, and a grid map integrating the conveying topology information and risk level information is constructed for subsequent analysis and air supplement strategy formulation. Based on the preset time sliding window mechanism, the real-time operation data obtained by the sensors is continuously collected, and in a periodic or event-driven manner, the risk score and corresponding risk level of each grid cell are updated in real time to realize the dynamic adjustment and precise perception of the clogging risk heat map.

[0025] Furthermore, step S404 of the embodiment of the present application further includes: S404-1: The method of using the min-max normalization method for risk score normalization: = ; where The original risk score, is the minimum score among all grid cells, The maximum score among all grid cells, is the normalized score value, ; S404-2: Divide the risk level based on the normalization result; S404-3: When the risk level is level zero risk, the risk level scoring interval is , described as having no risk of blockage; S404-4: When the risk level is a four - level risk, the risk level scoring range is , described as having an extremely low risk; S404-5: When the risk level is a three - level risk, the risk level scoring range is , described as having a medium - level risk of blockage; S404-6: When the risk level is a two - level risk, the risk level scoring range is , described as having a relatively high risk; 404-7: When the risk level is a one - level risk, the risk level scoring range is , described as a high risk, and priority should be given to air supplement.

[0026] It should be understood that the original risk score values of all grid cells are normalized using the min - max normalization method, so that each score value falls within the interval. Based on the normalized risk score values, the classification interval thresholds are set, and all grid cells are divided into five risk levels, namely: zero - level risk, four - level risk, three - level risk, two - level risk, and one - level risk.

[0027] S500: Based on a preset time window, continuously collect the operation data obtained by sensors arranged at key nodes of the conveying pipeline, and update the operation data in real - time to the grid map containing the topological structure of the conveying pipe section and the corresponding blockage risk level.

[0028] Specifically, the system continuously collects the operation data obtained by various types of sensors arranged at each key node of the conveying pipeline based on a preset time window (such as every 5 seconds, 10 seconds, or 30 seconds). The operation data includes, but is not limited to: node pressure value, air flow velocity, particulate matter concentration, humidity, temperature, and pipeline vibration signal, etc. The system automatically associates and maps the collected real - time data to the corresponding spatial grid cells, and updates the current operation status parameters of each grid cell. Subsequently, based on the above - mentioned real - time operation status parameters and historical statistical characteristics, the system dynamically calls the risk scoring function, calculates the latest risk score value of each grid cell, and adjusts the risk level in real - time. The updated risk level information is synchronized to the corresponding grid map in real - time, so that the grid map always maintains consistency with the actual operation status of the conveying system. The constructed topological structure - blockage risk level grid map of the conveying pipe section has the ability of dynamic update, and can support the real - time response and intelligent decision - making of downstream personalized air supplement strategies.

[0029] S600: Based on the grid map containing the topological structure of the conveying pipe section and the corresponding blockage risk level, combined with historical blockage events, construct a database of conveying parameters - blockage level - blockage grid location.

[0030] Specifically, after completing the construction of the grid map of the topological structure of the conveying pipe section and the blockage risk level, further based on the existing historical blockage event records, extract the occurrence time, the spatial grid number where each blockage event occurred, the operating state parameters at that time (including pressure, flow rate, particle concentration, temperature and humidity, etc.), as well as information such as the blockage duration, the removal method, and the removal result. For each blockage event, the system marks it corresponding to the grid cell where it is located, records the conveying parameter characteristics corresponding to this event (such as the pressure fluctuation amplitude within 10 minutes before the blockage, the change trend of particle concentration, etc.), and combines the blockage level (for example, the risk level obtained by the scoring function at that time) and the blockage location (i.e., the grid number) to form structured data items. On this basis, the system constructs a data table or database entry containing the following content: the conveying parameter feature vector (multi-dimensional); the blockage level (such as level 1 to level 0 risk); the blockage occurrence location (the corresponding grid number); the air supplement intervention result (if applicable); the success / failure mark. The data is organized in a unified format to form a three-dimensional associated database of "conveying parameters - blockage level - blockage grid location", providing basic data support for subsequent risk prediction, similar event matching, and air supplement scheme recommendation.

[0031] Furthermore, step S600 of the embodiment of the present application further includes: S601: Collect historical blockage event information, including the blockage time, blockage location, blockage duration, and the conveying parameter data before and after the blockage; S602: Classify the blockage events according to preset rules to obtain the corresponding blockage levels, and the blockage levels include level 0 risk, level 1 risk, level 2 risk, and level 3 risk; S603: Based on the conveying parameters, blockage levels, and corresponding grid locations in the historical blockage events, construct a database of conveying parameters - blockage level - blockage grid location.

[0032] It should be understood that historical blockage event information is collected, including the occurrence time (blockage time) of each blockage event, the occurrence location (blockage location, corresponding to the specific spatial grid number), the blockage duration, and the conveying parameter data recorded by the system before and after the event. The conveying parameter data includes, but is not limited to, indicators such as pressure, air flow velocity, particle concentration, temperature and humidity. Preprocess each piece of historical blockage event information collected, clean abnormal data and unify the data format for subsequent feature extraction and analysis. According to the preset blockage event classification rules of the system, comprehensively consider the frequency of blockage, the duration, and the impact on the conveying efficiency, and assign a corresponding risk level to each blockage event. The blockage levels include: level 0 risk (no risk), level 3 risk (low risk), level 2 risk (medium risk), and level 1 risk (high risk), and this level definition system is consistent with the risk heat map constructed in the system. After completing the blockage event level division, combine the conveying parameter characteristics corresponding to each event (such as the pressure fluctuation characteristics before blockage, particle concentration changes, etc.), the determined blockage level, and the corresponding grid position where it occurs, and uniformly encode these data items to construct a "conveying parameter - blockage level - blockage grid position" database. This database organizes information in a ternary structure to form a historical knowledge support system for subsequent matching of similar events and recommendation of air supplement strategies.

[0033] S700: Based on the currently collected operating state parameters, compare with the blockage characteristics in the "conveying parameter - blockage level - blockage grid position" database, identify potential blockage risk areas, determine whether they are priority candidate units for intervention, and mark the priority candidate units for intervention.

[0034] Specifically, based on the currently collected operating state parameters, combined with the previously constructed "conveying parameter - blockage level - blockage grid position" database. First, collect the operating state parameters of the current conveying system in real time. The operating state parameters include, but are not limited to, indicators such as the pressure value, air flow velocity, particle concentration, temperature and humidity of each grid area. Then, by calculating the similarity between the current operating state parameters and the historical blockage event characteristics recorded in the "conveying parameter - blockage level - blockage grid position" database, identify the matching degree between the current conveying state and the known blockage patterns. Under the condition that the similarity reaches the preset threshold, the system compares the current operating state with the information such as the marked blockage level and grid position in the "conveying parameter - blockage level - blockage grid position" database to identify the areas with potential blockage risks. Further, considering factors such as the blockage risk score, evolution trend, and historical intervention effect of the current grid area, determine whether this area belongs to the priority candidate unit for intervention. For the identified priority candidate units for intervention, the system marks them on the grid map for subsequent use in air supplement strategy recommendation and intelligent intervention operations. The marking result will also be used as the input for closed-loop optimization and participate in the air supplement plan screening and feedback update process.

[0035] Further, step S700 of the embodiment of the present application further includes: S701: Based on the currently collected operation state parameters, compare with the clogging characteristics in the pre-constructed conveyance parameter - clogging level - clogging grid position database to identify potential clogging risk units; S702: Determine whether the risk units meet the determination conditions of the intervention priority candidate units, where the determination conditions include the similarity of the current operation state parameters with the characteristics of the clogging evolution process in historical clogging events, the geographical or topological position similarity, and whether this feature combination in the historical samples finally evolves into a clogging event; S703: Based on the feature matching degree between the currently collected operation state parameters and the historical clogging characteristics in the conveyance parameter - clogging level - clogging grid position database, identify potential clogging risk units, and the features include but are not limited to flow rate, pressure, particle concentration, fluctuation amplitude, and its change trend; S704: If the change trend of the current operation state parameters has a high similarity with the evolution process of historical clogging events, and the geographical location or pipeline topological position of the grid unit is close to the area where historical clogging events occurred, and this type of feature combination in the historical samples finally evolves into a clogging event, then mark this grid unit as an intervention priority candidate unit.

[0036] It should be understood that, based on the currently real-time collected operation state parameters, such as the air flow velocity, pressure value, particle concentration, parameter fluctuation characteristics and their change trends in each grid area of the pipeline, etc., the pre-constructed "transport parameter - blockage level - blocked grid position" database is called to conduct a comparison and analysis of parameter characteristics, and identify the grid areas that may have a blockage evolution trend, that is, potential blockage risk units. Determine whether the identified risk units meet the determination conditions of the intervention priority candidate units. The determination conditions include but are not limited to the following three aspects: the similarity in the feature dimension between the change trend of the current transport parameter and the blockage evolution process in historical blockage events; the proximity of the current grid unit's geographical location or topological structure position in the transport pipeline to the area where historical blockage events occurred; the relatively high statistical probability that the same or similar feature combinations in historical samples ultimately evolved into blockage events. By calculating the matching degree between the currently collected operation state parameters and historical blockage characteristics, the fine-grained identification of potential risk units is completed. The matching feature parameters may include but are not limited to: instantaneous or average flow velocity, pressure change amplitude per unit time, particle concentration distribution, slope (trend) of parameter change, etc., and the comparison is carried out by setting a feature vector distance threshold or using a machine learning model. When all of the following conditions are met, it is considered that this risk unit has a high possibility of evolving into a blockage event, so it is marked as an "intervention priority candidate unit": the change trend of the current transport parameter is highly similar to the evolution process of a certain type of historical blockage event (such as the cosine similarity is higher than the set threshold); the spatial position or topological structure of the current unit is adjacent to the high-incidence area of historical blockages; in historical data, the proportion of this type of feature combination evolving into actual blockage events at similar positions exceeds the preset risk probability threshold. After the above marking is completed, the system includes this type of unit in the scope of key monitoring and air supplement intervention strategy generation, providing an accurate target for subsequent personalized air supplement plans.

[0037] S800: For the marked intervention priority candidate units, retrieve from the "transport parameter - blockage level - blocked grid position" database the blockage events that are similar to the current operation state parameter characteristics and have been successfully unblocked historically, and extract the corresponding air supplement parameter set. The air supplement parameters include the air supplement position, air supplement pressure or flow rate, and air supplement duration.

[0038] Specifically, after the identification and marking of the intervention priority candidate units are completed, the system further retrieves case data from the pre-built "delivery parameter - blockage level - blockage grid position" database that is highly similar to the current operating state and has successfully relieved blockages through air replenishment in history, and extracts the corresponding air replenishment parameter set for generating a personalized air replenishment intervention strategy. The retrieval process includes the following steps: Feature matching: Extract the real-time operating state parameter features of the current candidate unit, including but not limited to air flow velocity, pipeline pressure, particle concentration, temperature and humidity, fluctuation trend, etc.; Using the above parameters as feature vectors, retrieve historical blockage events in the database with a similarity higher than the preset threshold, where the similarity can be evaluated using Euclidean distance, cosine similarity, or multi-dimensional distance weighted model; From the matched historical blockage events, screen those samples that have been successfully relieved of blockages through air replenishment means; Extract the corresponding air replenishment parameter set from these successful samples, and the air replenishment parameters include but not limited to: Air replenishment position: That is, the specific grid area or physical node where air replenishment intervention was implemented at that time; Air replenishment pressure or flow rate: Represents the set air replenishment pressure value or gas flow rate during the intervention process; Air replenishment duration: That is, the time period for maintaining the air replenishment operation. This air replenishment parameter set will serve as the basis for subsequent air replenishment optimization and decision support, generating the most likely successful personalized air replenishment plan for candidate units, and improving the accuracy and timeliness of blockage risk intervention.

[0039] Further, step S800 of the embodiment of the present application further includes: S801: Extract key feature data from the real-time operating state parameters collected by the sensor for matching with the blockage features in the historical database; S802: In the delivery parameter - blockage level - blockage grid position database, screen out the blockage event records with similar blockage features in history according to the current operating state parameter features as the retrieval condition; S803: Extract the corresponding air replenishment parameter set from the successfully relieved blockage events, and the air replenishment parameters include the air replenishment position, air replenishment pressure or flow rate, and air replenishment duration.

[0040] It should be understood that the conveying parameters in the current operating state, including data such as pressure, air flow velocity, particle concentration, temperature and humidity, are continuously collected from the sensors installed at key positions of the conveying pipeline. The system preprocesses and extracts features from the collected data to obtain key feature vectors that can be used for comparison. Taking the currently collected key feature vectors as retrieval conditions, they are input into the "Conveying Parameter - Blockage Level - Blockage Grid Position" database, and a feature matching algorithm (such as methods based on weighted Euclidean distance, cosine similarity after principal component analysis, etc.) is called to screen out historical blockage event records that are highly similar to the current operating state parameters. The goal of this step is to identify the problem areas where blockages have occurred under similar working conditions in history and their corresponding countermeasures. Among the screened historical blockage event records, further screen those event samples that have been successfully unblocked by the air supplement means during actual operation. The system extracts the corresponding air supplement parameter set from these samples, and the air supplement parameters include but are not limited to the following: Air supplement position: That is, the spatial position of the pipe section where the air supplement device acts, usually represented by the corresponding grid cell number or physical position coordinates; Air supplement pressure or flow rate: The pressure value or gas flow velocity set during the air supplement process; Air supplement duration: The length of time to maintain the air supplement effect, and the unit can be seconds or minutes depending on the actual situation. The above steps ensure that the air supplement optimization process has data support and empirical basis, provides a reliable parameter basis for the formulation of subsequent personalized air supplement strategies, and helps to improve the accuracy and success rate of air supplement intervention.

[0041] S900: Based on the operating state of the current conveying system and combined with the extracted successful air supplement parameters, generate a personalized air supplement plan, and the air supplement plan includes air supplement position suggestions, air supplement pressure or flow rate, air supplement duration, and air supplement strategy priority.

[0042] Specifically, after identifying the intervention priority candidate units and extracting historical successful air replenishment events with characteristics similar to the current operating state parameters, a personalized air replenishment plan is further generated based on the current operating state of the conveying system and in combination with the extracted successful air replenishment parameter samples. According to the position of the current intervention priority candidate unit and the topology of the conveying pipeline, and in combination with the spatial position with the best air replenishment effect in historical air replenishment events, the currently recommended air replenishment position is generated. The air replenishment position can be represented as spatial coordinates corresponding to the grid cell number to ensure that the air replenishment effect accurately covers potential blockage points or the upstream areas thereof. Based on the current system air source capacity, the current pipeline operating pressure, and the air replenishment pressure or flow rate data used in historical similar events, the personalized air replenishment intensity parameter is intelligently set. The parameter value with the best blockage removal effect in historical events is preferentially selected as the basic reference, and fine-tuning can be carried out in combination with the current system stability parameters when necessary. According to the blockage risk level, the change trend of the real-time obtained operating state parameters, and the execution duration of historical air replenishment events, the recommended air replenishment duration is calculated to ensure both effective intervention and avoidance of secondary fluctuations caused by air flow disturbance. Based on the risk score, feature matching degree, pipeline topology importance (such as whether it is a main trunk section), and historical event removal efficiency of the current grid cell, a strategy priority label, such as "execute immediately", "medium-priority candidate", or "delay for observation", etc., is assigned to each air replenishment plan. This priority can serve as an important basis for automatic execution or manual review decisions. Outputting a set of personalized air replenishment plans that highly match the current operating state not only enhances the target pertinence of the air replenishment operation but also improves the success rate and safety of the air replenishment behavior, providing decision-making support for the stable operation of the long-distance slag particle conveying system.

[0043] Furthermore, step S900 of the embodiment of the present application further includes: S901: For the grid cells currently marked as intervention - priority candidates, retrieve, from the pre - constructed database of gas - injection parameters - blockage level - blocked grid location, the gas - injection events that are similar to the current operating state characteristics and have successfully removed blockages historically, and extract the corresponding set of gas - injection parameters. The set of gas - injection parameters includes the gas - injection location, gas - injection pressure or flow rate, and gas - injection duration; S902: Based on the operating state of the current conveying system, conduct an adaptability analysis on the set of gas - injection parameters to screen out a subset of gas - injection parameters that match the current operating state. The adaptability analysis includes calculating the similarity between the current state and the historical successful gas - injection sample states and evaluating the system constraint conditions; S903: Combining the selected subset of gas - injection parameters, analyze the risk level, blockage evolution trend, and system response characteristics of the current grid area to generate a personalized gas - injection plan. The gas - injection plan includes suggestions for gas - injection locations, gas - injection pressure or flow rate, gas - injection duration, and the priority of the gas - injection strategy; S904: Comprehensively analyze the locations of the grid cells with a current risk level of level one or level two and their topological associations, and select the area most likely to experience blockages or pressure anomalies as the priority gas - injection location; S905: Execute the generated gas - injection plan and record it in the database.

[0044] It should be understood that, from the pre-constructed database of conveying parameters - blockage level - blockage grid position, retrieve the air supplement event records that are highly similar to the characteristics of the current conveying operation state and have successfully removed blockages in history. Structurally process the matched air supplement events, and extract the corresponding set of air supplement parameters, including but not limited to: air supplement position (corresponding grid number or spatial coordinates), air supplement pressure or flow rate (numerical range), air supplement duration (unit time period). For the set of air supplement parameters, in combination with the operating state of the current conveying system, conduct an adaptability analysis for each historical air supplement parameter sample. This analysis includes the following two aspects: State similarity calculation: Evaluate the multi-dimensional similarity between the current state and the historical successful air supplement samples based on key operating state parameters such as flow velocity, pressure, particle concentration, and fluctuation characteristics; System constraint condition assessment: Consider the operating constraints such as the pressure / flow rate limits that the current system can withstand, gas source capacity, and safety redundancy, and eliminate the air supplement parameters that do not meet the current conditions. Finally, screen out the subset of air supplement parameters that have a high degree of match with the current state and are feasible to execute. Based on the selected subset of air supplement parameters, in combination with the risk level of the current grid area, the blockage evolution trend, the historical blockage mode, and the system response characteristics of the current grid area, construct a personalized air supplement plan. This plan includes the following contents: Air supplement position suggestion: Determine the spatial coordinates or topological position of the air supplement point; Air supplement pressure or flow rate: The recommended gas injection intensity parameter; Air supplement duration: The recommended air supplement time length; Air supplement strategy priority: Divide the priority of the air supplement plan for the dispatching system to make execution decisions. Further comprehensively analyze the grid cells in the first-level or second-level risk levels and their topological association relationships in the conveying pipeline (such as the positions of main and branch pipes, turning sections, lifting sections, etc.), and select the areas that are most likely to evolve into blockages or have abnormal pressures as the priority air supplement positions in this round of air supplement strategy to improve the pertinence and efficiency of the air supplement behavior. According to the generated personalized air supplement plan, automatically or semi-automatically drive the air supplement control device to execute the air supplement operation. At the same time, record and store the actually used air supplement parameters, execution results (whether the blockage is removed or the risk is mitigated), and key parameters that change during the operation period in the database as historical samples for subsequent optimization and learning, continuously improving the intelligent level and dynamic adaptability of the air supplement strategy.

[0045] In summary, the air supplement optimization method for a long-distance slag particle conveying pipeline provided by the embodiments of the present application has the following technical effects: By dividing the conveying pipeline into spatial grid cells and establishing a risk scoring function to quantitatively evaluate the blockage risk of each grid cell, the system can accurately identify high-risk areas, especially in easily blocked positions such as pipeline bends and pipe diameter change sections, realizing the visualization and hierarchical classification of blockage risks in the spatial dimension, and providing an objective basis for air supplement intervention. Based on the constructed database of conveying parameters - blockage level - blocked grid position, combined with the comparison and analysis of the characteristics of the currently real-time collected operating state parameters and historical successful air supplement events, a personalized air supplement plan for specific scenarios is generated. The air supplement position, pressure / flow rate, and time are all precisely matched according to the real-time state, effectively avoiding ineffective air supplement and over-air supplement phenomena. After identifying the blockage risk, it can preferentially mark the intervention candidate grid cells, automatically screen the subset of air supplement parameters that best matches the current operating state, and preferentially sort and execute the area in combination with the historical evolution trend and topological correlation, effectively improving the efficiency and success rate of air supplement decision-making, reducing the frequency of manual intervention, and enhancing the system's automatic operation ability. The execution result (whether the blockage is successfully removed) of each air supplement plan and the corresponding operating data are recorded back into the database to form a closed-loop data chain, providing a more accurate reference sample for the generation of strategies under similar working conditions in the future, and supporting the system to gradually evolve more efficient intelligent air supplement rules during long-term operation. The method of the present invention is particularly suitable for gas-solid two-phase slag particle conveying systems with complex structures, long distances, and variable operating state parameters, and has good scalability and adaptability. It can be widely applied to scenarios such as dry slag conveying and pneumatic conveying of powder materials in thermal power plants, metallurgy, cement and other industries, effectively reducing the system failure rate and operation and maintenance costs.

[0046] Overall, the embodiments of the present application achieve intelligent air supplement optimization control for long-distance slag particle conveying pipelines, not only improving the accuracy of air supplement regulation, but also enhancing the system's response ability to blockage risks, effectively reducing the risks of operation interruption and equipment loss caused by blockages; at the same time, by real-time parameter monitoring and historical blockage mode analysis, the evolution of potential abnormal trends is prevented, thus significantly improving the stability and safety of the conveying system, and providing a strong guarantee for the efficient operation of industrial continuous conveying processes.

[0047] Through the foregoing detailed description of a method for optimizing air supplement for a long-distance slag particle conveying pipeline in this specification, those skilled in the art can clearly know an air supplement optimization system for a long-distance slag particle conveying pipeline in this embodiment.

[0048] The foregoing description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An air supplement optimization method for a long-distance slag particle conveying pipeline, characterized in that, The method includes: S100. Arrange pressure sensors, air flow velocity sensors, and particulate matter concentration monitors at key nodes of the conveying pipeline to collect the operating state parameters of the gas-solid mixture in the pipeline in real time. The key nodes include pipeline bends, pipe diameter changes, branch points, and the source and end positions of the conveying pipeline; S200. Based on the actual topological structure of the conveying pipeline, divide the conveying pipeline into spatial grid units according to its physical structure and key control points. The spatial grid units have a one-to-one correspondence with the geometric layout of the conveying pipeline. Each grid unit is provided with a unique identifier, and the identifier corresponds to its spatial position in the conveying pipeline; S300. Based on the historical blockage data of the conveying pipeline, construct a risk scoring function by statistically analyzing the blockage occurrence frequency, blockage duration, and the fluctuation of conveying parameters before the blockage in each grid unit; S400. Combine the historical blockage data with the real-time obtained operating state parameters, input the risk scoring function to evaluate the blockage risk of each grid unit, and divide the grid units into five levels of blockage risk grades to construct a grid map including the topological structure of the conveying pipe section and the corresponding blockage risk grades; S500. Based on a preset time window, continuously collect the operating data obtained by the sensors arranged at the key nodes of the conveying pipeline and update the operating data to the grid map including the topological structure of the conveying pipe section and the corresponding blockage risk grades in real time; S600. Based on the grid map including the topological structure of the conveying pipe section and the corresponding blockage risk grades and combining historical blockage events, construct a conveying parameter-blockage grade-blockage grid position database; S700. Based on the currently collected operating state parameters, compare with the blockage characteristics in the conveying parameter-blockage grade-blockage grid position database, identify potential blockage risk areas and determine whether they are priority candidate units for intervention, and mark the priority candidate units for intervention; S800. For the marked priority candidate units for intervention, retrieve from the conveying parameter-blockage grade-blockage grid position database the blockage events that are similar to the current operating state parameters and have been successfully unblocked in history, and extract the corresponding air supplement parameter sets. The air supplement parameters include air supplement position, air supplement pressure or flow rate, and air supplement duration; S900. Based on the operating state of the current conveying system and combining the extracted successful air supplement parameters, generate a personalized air supplement plan. The air supplement plan includes air supplement position suggestions, air supplement pressure or flow rate, air supplement duration, and the priority of the air supplement strategy.

2. The air supplement optimization method for a long-distance slag particle conveying pipeline according to claim 1, wherein, Based on the historical blockage data of the conveying pipeline, construct a risk scoring function by statistically analyzing the blockage occurrence frequency, blockage duration, and the fluctuation of conveying parameters before the blockage in each grid unit, including: Extract the data of the occurred blockage events from the historical operation records of the conveying system, and collect the relevant conveying parameter data before, during, and after the blockage; Divide the entire conveying pipeline into several spatial grid units according to the preset physical topological structure, and map each blockage event to the corresponding grid number; For each grid area, count the blockage metrics, where the blockage metrics include blockage frequency, average blockage duration, and parameter fluctuation characteristics; Construct a risk scoring function = α× F + β× D + γ× V ; Among them, is the risk score of the -th grid, F is the clogging frequency of the -th grid, D is the average clogging duration, V is the parameter fluctuation characteristic index, α is the weight coefficient of the clogging frequency of the -th grid, β is the weight coefficient of the average clogging duration, and γ is the weight coefficient of the parameter fluctuation characteristic index; Mark the calculation results on the grid map of the conveying pipeline to form a risk heat map.

3. The air supplement optimization method for a long-distance slag particle conveying pipeline according to claim 1, characterized in that Combining historical blockage data with the operation status parameters obtained in real time, input into the risk scoring function to evaluate the blockage risk for each grid cell, and divide the grid cells into five levels of blockage risk grades, constructing a grid map including the topological structure of the conveying pipe section and the corresponding blockage risk grades, including: Extract the blockage events that have occurred in each grid area, including blockage frequency, duration, and parameter fluctuations before blockage; Obtain the real-time parameters of pressure, air flow velocity, particle concentration, temperature, and humidity in each current grid area through the deployed sensors; Using the statistical features extracted from the historical blockage data, combined with the real-time parameter changes, calculate the risk score for each grid area: = α × F + β × D + γ × ΔP + δ × C ; wherein, is the risk score of the i-th grid at time t, F is the historical blockage rate, D is the average blockage duration, ΔP is the real-time pressure fluctuation index, C is the real-time particle concentration change index, and α, β, γ, δ are weighting coefficients; Normalize the risk scores of all grid cells, and divide all grids into five levels according to the risk score interval. The risk levels include level 1 risk, level 2 risk, level 3 risk, level 4 risk, and level 0 risk; Mark the evaluated risk levels to each grid cell, and at the same time retain the topological correspondence between the grid cell and the conveying pipe section, constructing a grid map of the topological structure of the conveying pipe section and the corresponding blockage risk grades; Based on a preset time window, continuously collect sensor data, update the risk scores and risk levels of grid cells in real time, and dynamically adjust the grid map.

4. The air supplement optimization method for a long-distance slag particle conveying pipeline according to claim 3, characterized in that, The risk score interval includes: Use the min-max normalization method for risk score normalization: = ； Among them, the original risk score, is the minimum score among all grid cells, the maximum score among all grid cells, is the normalized score value, ; Divide the risk levels based on the normalization results; When the risk level is zero risk, the risk level scoring range is , described as no blockage risk; When the risk level is a level-four risk, the risk-level scoring range is , described as having an extremely low risk; When the risk level is a level-three risk, the risk-level scoring range is , described as having a medium-level blockage risk; When the risk level is a secondary risk, the risk level scoring range is , described as relatively high risk; When the risk level is a first-level risk, the risk level scoring range is , described as a high risk, and replenishing qi is prioritized.

5. The air supplement optimization method for a long-distance slag particle conveying pipeline according to claim 1, characterized in that, Based on the grid map including the topological structure of the conveying pipe section and the corresponding blockage risk grades, combined with historical blockage events, construct a conveying parameter-blockage grade-blockage grid position database, including: Collect historical blockage event information, including blockage time, blockage location, blockage duration, and conveying parameter data before and after blockage; Classify the blockage events according to preset rules to obtain the corresponding blockage grades, where the blockage grades include level 0 risk, level 1 risk, level 2 risk, and level 3 risk; Based on the conveying parameters, blockage grades, and corresponding grid positions in the historical blockage events, construct a conveying parameter-blockage grade-blockage grid position database.

6. The air supplement optimization method for a long-distance slag particle conveying pipeline according to claim 1, characterized in that, Based on the currently collected operation status parameters, compare with the blockage characteristics in the conveying parameter-blockage grade-blockage grid position database, identify potential blockage risk areas and determine whether they are priority candidate units for intervention, and mark the priority candidate units for intervention, including: Based on the currently collected operation status parameters, compare with the blockage characteristics in the pre-constructed conveying parameter-blockage grade-blockage grid position database to identify potential blockage risk cells; Judge whether the risk cell meets the determination conditions of the priority candidate unit for intervention. The determination conditions include the similarity of the current operation status parameters with the characteristics of the blockage evolution process in the historical blockage events, geographical or topological location similarity, and whether this combination of characteristics in the historical samples ultimately evolves into a blockage event; Based on the feature matching degree between the currently collected operating state parameters and the historical clogging characteristics in the conveying parameter - clogging level - clogged grid position database, potential clogging risk units are identified, and the features include but are not limited to flow rate, pressure, particle concentration, fluctuation amplitude, and their change trends; If the change trend of the current operating state parameters has a high similarity with the evolution process of historical clogging events, and the geographical location or pipeline topological location of the grid unit is close to the area where historical clogging events occurred, and such a combination of features in the historical samples ultimately evolved into a clogging event, then this grid unit is marked as a candidate unit with priority for intervention.

7. The air supplement optimization method for a long-distance slag particle conveying pipeline according to claim 1, characterized in that, For the marked candidate units with priority for intervention, retrieve from the conveying parameter - clogging level - clogged grid position database clogging events that are similar to the current operating state parameters in terms of characteristics and have successfully removed clogs historically, and extract the corresponding air - supplement parameters set. The air - supplement parameters include air - supplement position, air - supplement pressure or flow rate, and air - supplement duration, including: Extract key feature data from the real - time operating state parameters collected by sensors for matching with the clogging characteristics in the historical database; In the conveying parameter - clogging level - clogged grid position database, use the current operating state parameter characteristics as the retrieval condition to screen out the clogging event records with similar clogging characteristics historically; Extract the corresponding air - supplement parameters set from the successfully unclogged events. The air - supplement parameters include air - supplement position, air - supplement pressure or flow rate, and air - supplement duration.

8. The air supplement optimization method for a long-distance slag particle conveying pipeline according to claim 1, wherein Based on the operating state of the current conveying system, combined with the extracted successful air - supplement parameters, generate a personalized air - supplement plan. The air - supplement plan includes air - supplement position suggestions, air - supplement pressure or flow rate, air - supplement duration, and the priority of the air - supplement strategy, including: For the currently marked grid units that are candidates with priority for intervention, retrieve from the pre - constructed conveying parameter - clogging level - clogged grid position database air - supplement events that are similar to the current operating state characteristics and have successfully removed clogs historically, and extract the corresponding air - supplement parameters set. The air - supplement parameters set includes air - supplement position, air - supplement pressure or flow rate, and air - supplement duration; Based on the operating state of the current conveying system, conduct an adaptability analysis on the air - supplement parameters set, and screen out the subset of air - supplement parameters that match the current operating state. The adaptability analysis includes calculating the similarity between the current state and the state of historical successful air - supplement samples and evaluating the system constraint conditions; Combined with the screened subset of air - supplement parameters, analyze the risk level, clogging evolution trend, and system response characteristics of the current grid area to generate a personalized air - supplement plan. The air - supplement plan includes air - supplement position suggestions, air - supplement pressure or flow rate, air - supplement duration, and the priority of the air - supplement strategy; Comprehensively analyze the positions and topological associations of grid units with a current risk level of level one or level two, and select the area most likely to have clogging or pressure anomalies as the priority air - supplement position; Execute the generated air - supplement plan and record it in the database.

Images