Power plant fuel supply equipment management method and system based on three-dimensional modeling

Abstract

The application provides a power plant fuel supply equipment management method and system based on three-dimensional modeling, obtains a three-dimensional model and equipment operation data of a power plant fuel supply equipment, and correlates and maps to obtain an equipment three-dimensional operation correlation model; then a pre-trained equipment state intelligent analysis model is called to perform state evaluation and analysis on the equipment three-dimensional operation correlation model, to obtain an equipment operation state evaluation result; based on the equipment operation state evaluation result, an equipment management instruction for the power plant fuel supply equipment is generated and sent to a power plant fuel supply equipment management terminal to trigger equipment management operation; the application realizes deep fusion of equipment physical structure and operation data, can comprehensively and accurately evaluate equipment state, timely triggers management operation, improves equipment operation stability and reliability, reduces maintenance cost, and improves management intelligent level.

Description

Technical Field

[0001] This invention relates to the field of smart power plant technology, and more specifically, to a method and system for managing power plant fuel supply equipment based on three-dimensional modeling. Background Technology

[0002] In the field of power plant operation and management, the stable operation of fuel supply equipment is crucial for ensuring the continuity and efficiency of power production. Traditional management methods for power plant fuel supply equipment mainly rely on regular manual inspections and monitoring based on simple sensor data. Manual inspections suffer from problems such as long inspection cycles and susceptibility to subjective factors, making it difficult to grasp the equipment's operating status in real time and comprehensively. Monitoring based on simple sensor data often only obtains single operating parameters of the equipment, failing to intuitively present the relationships between various structural components and the overall operating status of the equipment. With the continuous development of 3D modeling technology, although some industries have begun to try applying 3D models to equipment management, in the management of power plant fuel supply equipment, there is still no mature solution that deeply correlates 3D models with equipment operating data and uses intelligent analysis models for comprehensive status assessment, thereby achieving precise equipment management. Therefore, existing technologies are insufficient to meet the needs of efficient and precise management of power plant fuel supply equipment. Summary of the Invention

[0003] In view of the aforementioned problems, and in conjunction with the first aspect of the present invention, embodiments of the present invention provide a method for managing power plant fuel supply equipment based on three-dimensional modeling, the method comprising: Obtain 3D models and equipment operation data of power plant fuel supply equipment; A three-dimensional operational association model of the power plant's fuel supply equipment is obtained by performing an association mapping process between the three-dimensional model of the equipment and the equipment's operating data. The pre-trained intelligent analysis model for equipment status is invoked to perform status assessment analysis on the three-dimensional operation association model of the equipment, and the equipment operation status assessment result is obtained. Based on the equipment operation status assessment results, generate equipment management instructions for the power plant's fuel supply equipment; The equipment management command is sent to the power plant fuel supply equipment management terminal to trigger the equipment management operation.

[0004] In another aspect, embodiments of the present invention also provide a power plant fuel supply equipment management system based on three-dimensional modeling, including a processor and a machine-readable storage medium connected to the processor. The machine-readable storage medium is used to store programs, instructions, or code, and the processor is used to execute the programs, instructions, or code in the machine-readable storage medium to implement the above-described method.

[0005] Based on the above, this embodiment of the invention acquires a three-dimensional model of the power plant's fuel supply equipment and its operating data, and performs correlation mapping processing to generate a three-dimensional operating correlation model of the equipment. This achieves deep integration of the equipment's physical structure and operating data. A pre-trained intelligent equipment status analysis model is then invoked to perform status assessment analysis on the three-dimensional operating correlation model. This comprehensively considers the spatial relationships between various structural components of the equipment, the correlation of operating monitoring data, and the changing trends over time, thereby obtaining accurate and comprehensive equipment operating status assessment results. Based on these equipment operating status assessment results, equipment management instructions are generated and sent to the management terminal. This allows for timely triggering of equipment management operations, effectively preventing equipment failures, improving the stability and reliability of equipment operation, reducing equipment maintenance costs, and enhancing the intelligence level and overall efficiency of power plant fuel supply equipment management. Attached Figure Description

[0006] Figure 1 This is a schematic diagram of the execution flow of the power plant fuel supply equipment management method based on three-dimensional modeling provided in an embodiment of the present invention.

[0007] Figure 2 This is a schematic diagram of exemplary hardware and software components of a power plant fuel supply equipment management system based on 3D modeling provided in an embodiment of the present invention. Detailed Implementation

[0008] The present invention will now be described in detail with reference to the accompanying drawings. Figure 1 This is a flowchart illustrating a power plant fuel supply equipment management method based on 3D modeling, according to an embodiment of the present invention. The following is a detailed description of this power plant fuel supply equipment management method based on 3D modeling.

[0009] Step S110: Obtain the 3D model of the power plant's fuel supply equipment and the equipment operation data.

[0010] In this embodiment, the power plant's fuel supply equipment includes various components, such as coal conveyor belts, coal bunkers, and coal feeders. Taking the coal conveyor belt as an example, its three-dimensional model is obtained. This three-dimensional model can be accurately created using professional 3D modeling software based on the actual size, shape, and other parameters of the coal conveyor belt. The equipment operation data includes the operating speed of the coal conveyor belt, motor current, and belt tension. This data can be collected in real time by sensors installed on the coal conveyor belt. For example, a speed sensor can measure the operating speed of the coal conveyor belt, a current sensor can monitor the motor current, and a tension sensor can detect the belt tension.

[0011] Step S120: Perform correlation mapping processing on the three-dimensional model of the power plant fuel supply equipment and the equipment operation data to obtain the equipment three-dimensional operation correlation model.

[0012] Next, the three-dimensional model of the coal conveyor belt needs to be correlated and mapped with the collected operational data.

[0013] Step S121: Load the 3D model of the power plant fuel supply equipment, perform structural component analysis on the 3D model of the power plant fuel supply equipment, and identify the structural components of each equipment contained in the 3D model of the power plant fuel supply equipment.

[0014] Taking a 3D model of a coal conveyor belt as an example, the 3D model is loaded using a 3D model parsing tool to read its structural description information. Based on this information, the structural regions corresponding to each independent functional unit in the 3D model are identified, such as the belt section, drive motor section, and idler roller section of the coal conveyor belt. Each structural region corresponds to a potential equipment structural component. Then, the geometric parameters and functional identification information of each potential equipment structural component are extracted. The geometric parameters include the component's length, width, thickness, and other information describing its shape and size characteristics. The functional identification information describes the component's function, such as the belt conveyor for transporting fuel and the drive motor for providing power. Based on the functional identification information, each potential equipment structural component is classified into fuel transport components (such as coal conveyor belts), fuel storage components (such as coal bunkers), and auxiliary control components (such as the control device for the coal feeder). Finally, each classified potential equipment structural component is uniquely identified and assigned a unique component number, such as A1 for the belt section of the coal conveyor belt and A2 for the drive motor section. This process ultimately determines the equipment structural components and their corresponding component numbers contained in the 3D model of the power plant's fuel supply equipment.

[0015] Step S1211: Load the 3D model of the power plant fuel supply equipment using the 3D model parsing tool and read the structural description information of the 3D model.

[0016] Taking a large generator set in a power plant as an example, a 3D model of the generator set is loaded using professional 3D model analysis software. This 3D model is constructed based on detailed design drawings, actual manufacturing processes, and on-site installation data, accurately reflecting the actual structure and component layout of the generator set. During the loading process, the software reads the structural description information of the 3D model, including details such as the shape, size, positional relationships, and connection methods of each component.

[0017] Step S1212: Based on the structural description information, identify the structural regions corresponding to each independent functional unit in the 3D model. Each structural region corresponds to a potential device structural component.

[0018] Based on the structural description information obtained, the structural regions corresponding to each independent functional unit in the 3D model are carefully analyzed and identified. For example, the generator body in a generator set, which is the core component that converts mechanical energy into electrical energy, occupies a specific spatial region in the 3D model; this region is a potential equipment structural component. Similarly, the turbine section, as the power source driving the generator's rotation, also corresponds to a potential equipment structural component in its structural region. In addition, the structural regions corresponding to each independent functional unit, such as the cooling system and lubrication system, are also considered potential equipment structural components.

[0019] Step S1213: Extract the geometric parameter information and functional identification information of each potential equipment structural component. The geometric parameter information is used to describe the shape and size characteristics of the component, and the functional identification information is used to describe the function of the component.

[0020] For each potential equipment structural component, its geometric parameters and functional identification information are extracted. Taking the generator body as an example, its geometric parameters include the inner diameter, outer diameter, and length of the stator; the diameter and length of the rotor; and the number of turns and wire diameter of the windings. These parameters accurately describe the shape and size characteristics of the generator body. Its functional identification information is "converting mechanical energy into electrical energy," clearly defining the core role of the generator body in the generator set. For the steam turbine, the geometric parameters include the length, width, and angle of the blades; and the diameter and length of the cylinder. Its functional identification information is "converting the thermal energy of steam into mechanical energy to drive the generator to rotate."

[0021] Step S1214: Classify each potential equipment structural component according to the functional identification information, and distinguish between fuel delivery components, fuel storage components and auxiliary control components.

[0022] Based on the functional identification information of each potential equipment structural component, they are classified. For example, fuel conveying components include coal conveyor belts, coal feeders, and oil pumps, whose main function is to transport fuel (such as coal and fuel oil) to the corresponding parts of the generator set; fuel storage components, such as coal bunkers and oil tanks, are used to store fuel; auxiliary control components include various sensors, controllers, and valves, whose function is to monitor and control the operating status of the generator set to ensure its safe, stable, and efficient operation. This classification provides a clearer understanding of the position and role of each equipment structural component in the power plant's fuel supply system, facilitating targeted management and maintenance.

[0023] Step S1215: Uniquely identify each potential equipment structure component after classification, assign an independent component number to each component, and finally determine the equipment structure components and their corresponding component numbers contained in the three-dimensional model of the power plant fuel supply equipment.

[0024] Each potential equipment structural component after classification is uniquely identified and assigned a unique component number. For example, the generator body is numbered C1, the steam turbine C2, the coal conveyor belt C3, the coal bunker C4, the temperature sensor C5, and so on. In this way, each equipment structural component in the 3D model of the power plant's fuel supply equipment is given a unique identifier, enabling accurate identification and location of each component during subsequent management and maintenance, thus improving management efficiency and accuracy.

[0025] Step S122: Extract the equipment operation monitoring items contained in the equipment operation data. The equipment operation monitoring items are the monitoring contents used to reflect the equipment operation status.

[0026] For the operating data of the coal conveyor belt, data parsing and processing are performed to separate different types of monitoring data, each corresponding to a specific equipment operation monitoring item. For example, operating speed data is separated from the collected data, and its corresponding equipment operation monitoring item is "coal conveyor belt operating speed"; motor current data is separated, and its corresponding equipment operation monitoring item is "coal conveyor belt motor current," and so on. A monitoring type identifier is added to each equipment operation monitoring item, including real-time monitoring items and periodic monitoring items. For example, "coal conveyor belt operating speed" can be set as a real-time monitoring item, while maintenance cycle-related data for some equipment can be set as periodic monitoring items.

[0027] Step S1221: Perform data parsing and processing on the equipment operation data to separate different types of monitoring data, with each type of monitoring data corresponding to a specific equipment operation monitoring item.

[0028] The operational data of power plant fuel supply equipment is processed using specialized data analysis software. This software can analyze and filter the large amounts of collected data, separating different types of monitoring data. For example, temperature data can be separated from the data, with the corresponding equipment operation monitoring item being "equipment temperature"; pressure data can be separated, with the corresponding equipment operation monitoring item being "equipment pressure"; flow data can be separated, with the corresponding equipment operation monitoring item being "fuel flow," and so on. Through this data analysis processing, complex equipment operation data is broken down into specific and meaningful equipment operation monitoring items.

[0029] Step S1222: Add a monitoring type identifier to each device operation monitoring item. The monitoring type identifier includes real-time monitoring items and periodic monitoring items.

[0030] After separating the monitoring items for each piece of equipment, a monitoring type identifier is added to each item. For example, the "equipment temperature" monitoring item typically requires real-time monitoring to ensure that the equipment does not malfunction due to overheating during operation; therefore, it is identified as a real-time monitoring item. On the other hand, data related to equipment maintenance cycles, such as regular maintenance times and parts replacement cycles, are considered periodic monitoring items and do not require real-time monitoring; they only need to be checked and recorded at specific time intervals. By adding monitoring type identifiers, equipment operation monitoring data can be better managed and utilized, improving equipment operating efficiency and reliability.

[0031] Step S1223: Based on the functional identification information of each equipment structural component, determine the types of parameters that need to be monitored during the operation of each equipment structural component.

[0032] Based on the previously extracted functional identification information of each equipment structural component, the types of parameters that need to be monitored for each component during operation are determined. For example, for the generator itself, since it generates a large amount of heat during operation, parameters such as stator temperature and rotor temperature need to be monitored to ensure the normal operation of the generator; at the same time, to ensure the quality of the power output from the generator, parameters such as voltage, current, and frequency also need to be monitored. For the steam turbine, parameters such as steam pressure, steam temperature, speed, and vibration need to be monitored to reflect the operating status and performance of the steam turbine. By determining the types of parameters that need to be monitored for each equipment structural component, equipment operating data can be collected and analyzed in a targeted manner, problems in the equipment can be identified in a timely manner, and corresponding measures can be taken to deal with them.

[0033] Step S1224: Match the monitoring content of the equipment operation monitoring items with the parameter types that need to be monitored for the equipment structural components, so that each equipment structural component is associated with at least one corresponding equipment operation monitoring item.

[0034] The monitoring content of equipment operation monitoring items is matched one by one with the parameter types that need to be monitored for the equipment structural components, establishing a correlation mapping relationship between them. For example, the "equipment temperature" monitoring item is associated with equipment structural components such as the generator body and steam turbine, because these components require temperature monitoring during operation; the "fuel flow" monitoring item is associated with fuel conveying components such as coal conveyor belts and coal feeders, because the operating status of these components directly affects the fuel delivery rate. Through this matching method, each equipment structural component is associated with at least one corresponding equipment operation monitoring item, achieving a close integration between equipment operation data and equipment structural components.

[0035] Step S1225: Record the correspondence between each equipment structural component and the associated equipment operation monitoring item, and generate an association mapping table. The association mapping table contains the component number, component name, monitoring item name and monitoring type identifier.

[0036] After establishing the mapping relationship between equipment structural components and equipment operation monitoring items, this correspondence is recorded to generate a mapping table. The mapping table contains information such as component number, component name, monitoring item name, and monitoring type identifier. For example, in the mapping table, the generator body (component number C1) is associated with monitoring items such as "equipment temperature" (real-time monitoring item), "voltage" (real-time monitoring item), "current" (real-time monitoring item), and "frequency" (real-time monitoring item); the steam turbine (component number C2) is associated with monitoring items such as "equipment temperature" (real-time monitoring item), "steam pressure" (real-time monitoring item), "steam temperature" (real-time monitoring item), "speed" (real-time monitoring item), and "vibration" (real-time monitoring item). By generating the mapping table, the correspondence between equipment structural components and equipment operation monitoring items can be clearly displayed, facilitating querying and analysis by management personnel.

[0037] Step S123: Establish the association mapping relationship between each equipment structural component and each equipment operation monitoring item, so that each equipment structural component corresponds to at least one equipment operation monitoring item.

[0038] Based on the functional identification information of each equipment structural component, determine the types of parameters that need to be monitored during the operation of each component. For example, for the belt section of a coal conveyor belt, the parameters that need to be monitored during its operation include speed and tension. Match the monitoring content of the equipment operation monitoring items with the parameter types that need to be monitored for each equipment structural component, so that each equipment structural component is associated with at least one corresponding equipment operation monitoring item. For example, the "coal conveyor belt operating speed" monitoring item is associated with the belt section of the coal conveyor belt, and the "coal conveyor belt tension" monitoring item is also associated with the belt section of the coal conveyor belt. Record the correspondence between each equipment structural component and the associated equipment operation monitoring items, and generate an association mapping table. The association mapping table contains the component number, component name, monitoring item name, and monitoring type identifier. For example, in the association mapping table, the belt section of the coal conveyor belt with component number A1 has the corresponding monitoring item name "coal conveyor belt operating speed" and the monitoring type identifier "real-time monitoring item"; the corresponding monitoring item name is "coal conveyor belt tension," and the monitoring type identifier is also "real-time monitoring item."

[0039] Step S124: Based on the association mapping relationship, embed the data of each equipment operation monitoring item into the position of the corresponding equipment structural component in the three-dimensional model of the power plant fuel supply equipment to generate the initial equipment three-dimensional operation association model.

[0040] Based on the correspondence in the association mapping table, data on equipment operation monitoring items such as the operating speed and tension of the coal conveyor belt are embedded into the corresponding belt section locations in the 3D model of the coal conveyor belt. For example, the real-time collected coal conveyor belt operating speed data is displayed at a specific location on the belt section of the 3D model, and the belt tension data is also displayed at the corresponding location, thereby generating an initial 3D equipment operation association model.

[0041] Step S125: Perform mapping integrity verification on the initial equipment 3D operation association model to confirm that all equipment structural components have been associated with the corresponding equipment operation monitoring data, and obtain the final equipment 3D operation association model.

[0042] The generated initial 3D operational model of the equipment is checked to see if all equipment structural components are associated with the corresponding equipment operation monitoring data. For example, check if the belt, drive motor, and idler rollers in the 3D model of the coal conveyor belt have corresponding monitoring data embedded. If any equipment structural component lacks associated data, the establishment of the association mapping relationship needs to be rechecked, or if there are any problems with the data acquisition and embedding process, until it is confirmed that all equipment structural components are associated with the corresponding equipment operation monitoring data, thus obtaining the final 3D operational model of the equipment.

[0043] Step S130: Call the pre-trained intelligent analysis model of equipment status to perform status evaluation analysis on the three-dimensional operation association model of the equipment, and obtain the equipment operation status evaluation result.

[0044] In this embodiment, the intelligent analysis model for device status is obtained through training with a large amount of data.

[0045] Step S131: Input the equipment 3D operation association model into the feature processing layer of the equipment status intelligent analysis model, and perform feature extraction processing on the equipment operation monitoring item data and corresponding equipment structural component information embedded in the equipment 3D operation association model to obtain the equipment association feature vector.

[0046] Taking a 3D operational model of a coal conveyor belt as an example, this model is input into the feature processing layer. The feature processing layer analyzes and processes data embedded in the model, including equipment operation monitoring items such as the coal conveyor belt's operating speed and tension, as well as information on structural components such as the belt itself and the drive motor. Through a series of algorithms and calculations, key features reflecting the equipment's operating status are extracted, and these features are combined to form an equipment-related feature vector. For example, features such as the rate of change of speed and the range of tension fluctuations might be extracted as part of the equipment-related feature vector.

[0047] Step S132: Input the equipment association feature vector into the spatial association layer of the equipment status intelligent analysis model, analyze the spatial positional relationship between different equipment structural components and the correlation of corresponding equipment operation monitoring data, and generate spatial association features.

[0048] After receiving the equipment association feature vector, the spatial association layer extracts the spatial coordinate information of each equipment structural component and the corresponding equipment operation monitoring data contained in the feature vector. For example, for the belt section, drive motor section, and idler section of a coal conveyor belt, it obtains their coordinate positions in three-dimensional space and their corresponding operating speed, current, and other data. Then, it calculates the spatial distance and relative orientation between any two equipment structural components to determine the degree of spatial correlation between each component. For example, it calculates the distance and relative orientation between the belt section and the drive motor section. Next, it analyzes the consistency of changes in the equipment operation monitoring data corresponding to equipment structural components with similar spatial positions to determine whether there is a collaborative relationship in the data changes. For example, it checks whether the operating speed data of the belt section and the idler section have similar changing trends. Based on the degree of spatial correlation and the collaborative relationship of data changes, a spatial association matrix is ​​constructed. The spatial association matrix is ​​used to represent the correlation strength of each equipment structural component at the spatial and data levels. Finally, feature extraction processing is performed on the spatial association matrix to extract key association information from the matrix and generate spatial association features that can be used for time series analysis.

[0049] Step S1321: Receive the device association feature vector and extract the spatial coordinate information of each device structural component and the corresponding device operation monitoring data contained in the device association feature vector.

[0050] When the equipment association feature vector is input into the spatial association layer of the intelligent equipment status analysis model, the model first receives the vector. Then, it extracts the spatial coordinate information of each equipment structural component and the corresponding equipment operation monitoring data from the vector. Taking a large boiler in a power plant as an example, the three-dimensional model of the boiler contains numerous equipment structural components, such as the combustion chamber, superheater, and economizer. By extracting the equipment association feature vector, the spatial coordinates (X1, Y1, Z1) of the combustion chamber and its corresponding temperature, pressure, and other equipment operation monitoring data can be obtained; the spatial coordinates (X2, Y2, Z2) of the superheater and its corresponding temperature, steam flow, and other equipment operation monitoring data can be obtained; the spatial coordinates (X3, Y3, Z3) of the economizer and its corresponding water temperature, flue gas flow, and other equipment operation monitoring data can be obtained. The above spatial coordinate information and equipment operation monitoring data are the basis for subsequent analysis of the spatial positional relationships and data correlations between different equipment structural components.

[0051] Step S1322: Calculate the spatial distance and relative orientation between any two equipment structural components to determine the degree of spatial correlation between each component.

[0052] After obtaining the spatial coordinate information of each equipment structural component, the spatial distance and relative orientation between any two equipment structural components are calculated. For example, the spatial distance between the combustion chamber and the superheater can be calculated using the formula for spatial coordinates: D1 = √[(X2-X1)^2 + (Y2-Y1)^2 + (Z2-Z1)^2]. Simultaneously, the relative orientation of the superheater relative to the combustion chamber is determined; for example, the superheater is located α degrees above and to the left of the combustion chamber. By calculating the spatial distance and relative orientation between all equipment structural components, the spatial relationship between each component can be fully understood, thus determining the degree of spatial correlation between them. The degree of spatial correlation can be represented by a numerical value. For example, when the spatial distance between two equipment structural components is close and their relative orientation is relatively fixed, their spatial correlation is high; conversely, when the spatial distance is far or the relative orientation changes significantly, the degree of spatial correlation is low.

[0053] Step S1323: Analyze the consistency of changes in equipment operation monitoring data corresponding to equipment structural components with similar spatial locations, and determine whether there is a collaborative relationship between the data changes.

[0054] After determining the spatial correlation between the various equipment structural components, the focus is on analyzing the consistency of changes in the equipment operation monitoring data corresponding to spatially close equipment structural components. Taking the combustion chamber and superheater as examples, they are spatially close and both are closely related to steam generation and transmission. Therefore, the consistency of changes in equipment operation monitoring data such as temperature and pressure in the combustion chamber is analyzed with that in the superheater, such as temperature and steam flow rate. If the temperature of the combustion chamber increases, the temperature of the superheater also increases, and the steam flow rate increases accordingly, then it can be determined that there is a synergistic relationship between the changes in the equipment operation monitoring data corresponding to these two equipment structural components; conversely, if there is no obvious correlation or pattern in the changes of the data, then there is no synergistic relationship. By analyzing the synergistic relationship of data changes between spatially close equipment structural components, the mutual influence and coupling effects between equipment can be further understood.

[0055] Step S1324: Construct a spatial correlation matrix based on the degree of spatial location correlation and the collaborative relationship of data changes. The spatial correlation matrix is ​​used to represent the correlation strength of each device structural component at the spatial and data levels.

[0056] Based on the calculated spatial correlation and the determined data change synergy, a spatial correlation matrix is ​​constructed. The spatial correlation matrix is ​​a two-dimensional matrix, where rows and columns represent different equipment structural components. The element values ​​in the matrix represent the correlation strength between two corresponding equipment structural components at the spatial and data levels. For example, for the combustion chamber and the superheater, their corresponding element values ​​in the spatial correlation matrix can be determined based on their spatial correlation and data change synergy. If the spatial correlation between the two is high and the data change synergy is significant, then the element value can be set to a larger value, such as 0.8; if the spatial correlation is low or the data change synergy is not significant, the element value can be set to a smaller value, such as 0.3. By constructing the spatial correlation matrix, the correlation strength between each equipment structural component at the spatial and data levels can be visually displayed.

[0057] Step S1325: Perform feature extraction processing on the spatial correlation matrix to extract key correlation information from the matrix and generate spatial correlation features that can be used for time series analysis.

[0058] After constructing the spatial correlation matrix, feature extraction is performed. Feature extraction is the process of extracting key correlation information reflecting the relationships between equipment structural components from the spatial correlation matrix. By applying specific mathematical algorithms and techniques, such as principal component analysis and singular value decomposition, key eigenvalues ​​and eigenvectors can be extracted from the spatial correlation matrix. These eigenvalues ​​and eigenvectors can effectively represent the spatial and data relationships between equipment structural components, removing redundant information and highlighting key information. For example, through feature extraction, some main eigenvectors can be obtained. The larger the eigenvalues ​​of these eigenvectors, the more significant the impact of the relationships between the equipment structural components they represent on the overall state of the equipment. After extracting the key correlation information, spatial correlation features suitable for time-series analysis are generated.

[0059] Step S133: Input the spatial correlation features into the time series analysis layer of the intelligent analysis model of equipment status, analyze the changing trend of equipment operation monitoring data over time, and extract time series change features.

[0060] Spatial correlation features are combined with historical data of corresponding equipment operation monitoring items to construct a time-series analysis dataset. Taking a coal conveyor belt as an example, the spatial correlation features of the coal conveyor belt are combined with historical data such as the operating speed and tension of the coal conveyor belt collected over a period of time to form a time-series analysis dataset containing spatial correlation features and corresponding monitoring data at different time points. Then, the time-series analysis dataset is divided into time series segments according to preset time intervals. For example, a day's data is divided into 24 time series segments with each hour as a time interval. Next, the magnitude and direction of change of equipment operation monitoring items within each time series segment are analyzed to determine the local change trend of the data within the segment. For example, whether the change in the operating speed of the coal conveyor belt increases or decreases within each hour is analyzed. By comparing the local change trends between adjacent time series segments, the continuity or abruptness of the trend is identified, and the time points of trend change are recorded. For example, whether the change trends of the operating speed of the coal conveyor belt are consistent between two adjacent hours is determined; if they are inconsistent, this time point is recorded. Finally, based on the local change trends, trend continuity, and abrupt change time points, features that reflect the long-term change patterns of the data are extracted to generate time-series change features.

[0061] Step S1331: Combine the spatial correlation features with the historical data of the corresponding equipment operation monitoring items to construct a time series analysis dataset. The time series analysis dataset contains the spatial correlation features and corresponding monitoring data at different time points.

[0062] After inputting spatial correlation features into the time-series analysis layer of the intelligent equipment status analysis model, they are first combined with the historical data of the corresponding equipment operation monitoring items. Taking a power plant's generator set as an example, spatial correlation features reflect the spatial and data correlation relationships between various equipment structural components in the generator set, while the historical data of equipment operation monitoring items records the operating status data of these equipment structural components at different points in time, such as temperature, pressure, current, and voltage. The spatial correlation features and the historical data of equipment operation monitoring items are matched and integrated in chronological order to construct a time-series analysis dataset. For example, for a certain time t1, the spatial correlation features at that time are combined with the monitoring data of temperature, pressure, current, and voltage of various equipment structural components collected at that time to form a data record; similarly, a similar combination is performed for different time nodes such as t2 and t3, ultimately constructing a time-series analysis dataset containing spatial correlation features and corresponding monitoring data of multiple time nodes.

[0063] Step S1332: Divide the time series analysis dataset into time series segments according to a preset time interval.

[0064] After constructing the time-series analysis dataset, it is divided into time series segments. Based on actual needs and the purpose of data analysis, a suitable time interval is preset, such as one hour, one day, or one week. Then, the data in the time-series analysis dataset is divided into multiple consecutive time-series segments according to this time interval. For example, one day's time-series analysis data can be divided into 24 consecutive time-series segments, with each hour as a time interval. Each time-series segment contains the spatial correlation characteristics and corresponding equipment operation monitoring data for that hour. By dividing the data into time series segments, continuous time-series data can be decomposed into relatively independent time-series segments, facilitating the analysis and comparison of changes in equipment operating status at different time scales. This also reduces the amount of data and improves the efficiency and accuracy of data analysis.

[0065] Step S1333: Analyze the magnitude and direction of change of the equipment operation monitoring data within each time segment to determine the local change trend of the data within the segment.

[0066] For each defined time segment, the magnitude and direction of change of the equipment operation monitoring data are analyzed. Taking temperature monitoring data as an example, within a time segment, the maximum temperature Tmax and minimum temperature Tmin are recorded, and the magnitude of temperature change ΔT = Tmax - Tmin is calculated. Simultaneously, the direction of temperature change is observed, i.e., whether the temperature is increasing or decreasing. If Tmax > Tmin, the temperature is increasing; otherwise, it is decreasing. Similarly, similar analyses are performed on other equipment operation monitoring data, such as pressure, current, and voltage, to determine their magnitude and direction of change within each time segment. By analyzing the magnitude and direction of change of the equipment operation monitoring data within each time segment, the changes in the equipment's operating status during that time period can be understood, and the local trend of data change within the segment can be determined. For example, in a certain time segment, the temperature shows a gradual increasing trend, while the pressure remains relatively stable, and the current and voltage fluctuate somewhat but remain within the normal range.

[0067] Step S1334: Compare the local change trends between adjacent time segments, identify the continuity or abrupt change of the trend, and record the time nodes of the trend change.

[0068] After analyzing the local trends of equipment operation monitoring data within each time segment, the local trends of adjacent time segments are compared. If the trends of equipment operation monitoring data in two adjacent time segments are the same (e.g., temperature rises in one segment and continues to rise in the next segment with similar magnitudes), then the trend of the equipment operation monitoring data can be considered continuous. Conversely, if the trends of adjacent time segments are different (e.g., temperature rises in one segment and suddenly decreases in the next), then abrupt changes in the trend can be identified. For each identified trend change, the corresponding time point is recorded. For example, when the temperature suddenly changes from an increasing trend to a decreasing trend, the time point of this change is recorded. By comparing the local trends of adjacent time segments, identifying the continuity or abruptness of the trend, and recording the time points of trend changes, a more comprehensive understanding of the dynamic changes in equipment operating status can be obtained, allowing for timely detection of abnormalities or potential problems during equipment operation.

[0069] Step S1335: Based on local change trends, trend continuity, and abrupt change time points, extract features that can reflect the long-term change patterns of the data and generate time-series change features.

[0070] After analyzing the local trends, trend continuity, and abrupt change points of equipment operation monitoring data within each time segment, features reflecting the long-term variation patterns of the data are extracted based on this information to generate time-series variation features. For example, by observing temperature changes across multiple time segments, it is found that temperature exhibits periodic fluctuations, with sudden increases or decreases in temperature at certain specific time points. These features can serve as time-series variation features reflecting the long-term variation patterns of temperature. Similarly, for other equipment operation monitoring data such as pressure, current, and voltage, corresponding time-series variation features can be extracted using similar methods. Time-series variation features are an abstract representation of the long-term variation patterns of equipment operation monitoring data, reflecting the trends and characteristics of equipment operating status changes at different time scales. By extracting time-series variation features, large amounts of equipment operation monitoring data can be transformed into valuable information, helping managers better understand the equipment's operating status, generate reasonable maintenance plans and management strategies, and improve equipment reliability and operating efficiency.

[0071] Step S134: Input the time-series change characteristics into the state classification layer of the intelligent analysis model of equipment state to classify and judge the operating state of the power plant fuel supply equipment and determine the current state category of the equipment.

[0072] The generated time-series variation features are input into the state classification layer. The state classification layer then classifies and judges the operating status of the power plant's fuel supply equipment based on preset classification rules and algorithms. Taking a coal conveyor belt as an example, based on the speed change trend and tension change reflected in the time-series variation features, it determines whether the coal conveyor belt is currently in a normal operating state, an abnormal operating state (such as abnormal speed or tension), or a fault state. This determines the current state category of the equipment.

[0073] Step S135: Based on the status category, generate an equipment operation status assessment result that includes descriptions of the operating status of each structural component of the equipment and conclusions on the overall status determination.

[0074] Based on the determined status category, an equipment operation status assessment result is generated. For coal conveyor belts, the assessment result will include a description of the operation status of each structural component of the conveyor belt, such as the belt section, drive motor section, and idler roller section. For example, it will specify whether the belt section's operating speed is normal and whether the tension is within a reasonable range. It will also include a conclusion regarding the overall status of the coal conveyor belt, such as "operating normally" or "abnormal speed exists, requiring attention."

[0075] Step S140: Generate equipment management instructions for the power plant's fuel supply equipment based on the equipment operation status assessment results.

[0076] Step S141: Analyze the equipment operation status assessment results and extract the operating status of each structural component of the equipment and the overall status judgment conclusions described therein.

[0077] Taking the equipment operation status assessment results of a coal conveyor belt as an example, we analyze them. We extract the operating status information of each structural component of the coal conveyor belt, such as whether the belt speed is normal and whether the tension is abnormal, as described in the assessment results, as well as the judgment conclusions on the overall status of the coal conveyor belt, such as whether it is operating normally and whether there are potential faults.

[0078] Step S142: Identify the equipment structural components corresponding to the abnormal operating states marked in the evaluation results, and determine the component number and abnormal behavior of the abnormal components.

[0079] If the assessment results show that the coal conveyor belt has an abnormal operating state, such as excessive belt tension, then the corresponding equipment structural component is identified as the belt section of the coal conveyor belt, its component number is determined to be A1, and the abnormal manifestation is clearly defined as "excessive belt tension".

[0080] Step S143: Load the power plant fuel supply equipment management strategy library, and retrieve the corresponding equipment management measures according to the type and abnormal behavior of the abnormal components.

[0081] The power plant's fuel supply equipment management strategy library is loaded via a strategy library call interface. This library stores mappings between different anomaly types and corresponding management measures. Taking excessive belt tension in a coal conveyor belt as an example, the type information of the anomalous component is extracted, identifying it as a fuel conveying component anomaly. Based on this type information, the corresponding strategy category directory is determined in the strategy library, and further searching is performed within that directory. In the strategy category directory for fuel conveying component anomalies, strategy entries with the same or similar anomaly descriptions are matched based on the anomaly symptom "excessive belt tension." The corresponding equipment management measures are extracted from the matched strategy entries, including operating methods (e.g., adjusting the belt tensioner); precautions (e.g., paying attention to belt operation during adjustment to avoid over-tensioning); and expected results (e.g., restoring belt tension to the normal range). The update time of the strategy entry is recorded to ensure the effectiveness of the measures.

[0082] Step S1431: Load the power plant fuel supply equipment management strategy library through the strategy library call interface. The strategy library stores the mapping relationship between different exception types and corresponding management measures.

[0083] When handling abnormal situations in power plant fuel supply equipment, the first step is to load the power plant fuel supply equipment management strategy library through a specially designed strategy library call interface. This management strategy library is a large and comprehensive knowledge base that stores the mapping relationship between various possible anomaly types and their corresponding detailed management measures. This mapping relationship is derived from long-term equipment operation experience, fault analysis, and expert knowledge summaries, and possesses high practicality and reliability. For example, for anomalies such as fuel pipeline blockage, the management strategy library stores corresponding management measures such as cleaning the pipeline and checking valves; for anomalies such as excessive equipment temperature, it stores management measures such as checking the cooling system and adjusting equipment operating parameters.

[0084] Step S1432: Extract the type information of the abnormal components. The type information includes abnormalities of fuel delivery components, abnormalities of fuel storage components, and abnormalities of auxiliary control components.

[0085] After detecting anomalies in the power plant's fuel supply equipment, the type of the abnormal component is extracted through analysis and diagnosis of the anomaly. For example, if an abnormal decrease in fuel flow is found in the fuel conveying pipeline, and further inspection determines that it is caused by a fault in the coal conveyor belt, then the type of abnormal component can be identified as a fuel conveying component anomaly. If an abnormal drop in the coal level in the coal bunker is found, and inspection determines that it is caused by a blockage at the coal bunker's outlet, then the type of abnormal component is a fuel storage component anomaly. If a fault is found in the equipment's control system, causing the equipment to malfunction, then the type of abnormal component is an auxiliary control component anomaly. By accurately extracting the type information of abnormal components, the scope of management measures can be narrowed, improving retrieval efficiency and accuracy.

[0086] Step S1433: Based on the type information of the abnormal component, determine the corresponding policy category directory in the policy library and enter that directory for further retrieval.

[0087] After extracting the type information of the abnormal component, the corresponding policy category directory is determined in the management policy library based on this information. For example, if the abnormal component type is a fuel delivery component abnormality, then the policy category directory for "Fuel Delivery Component Abnormality Handling" is found in the management policy library; if the abnormal component type is a fuel storage component abnormality, then the policy category directory for "Fuel Storage Component Abnormality Handling" is found; if the abnormal component type is an auxiliary control component abnormality, then the policy category directory for "Auxiliary Control Component Abnormality Handling" is found. Accessing the appropriate policy category directory allows for more targeted retrieval of management measures, improving the accuracy and effectiveness of the search.

[0088] Step S1434: In the corresponding policy category directory, match policy entries with the same or similar exception descriptions based on the abnormal behavior of the abnormal components.

[0089] After entering the corresponding strategy category directory, based on the specific abnormal behavior of the abnormal component, strategy entries with the same or similar abnormal descriptions are matched within that directory. For example, in the strategy category directory for "Abnormal Handling of Fuel Conveying Components," if the abnormal component is a coal conveyor belt and the abnormal behavior is belt slippage, then strategy entries related to belt slippage, such as adjusting belt tension or cleaning debris from the belt surface, are searched in the directory; if the abnormal behavior is belt misalignment, then strategy entries related to belt misalignment are searched, such as adjusting belt idlers or inspecting the belt drive unit. By matching strategy entries with the same or similar abnormal descriptions, the most suitable management measures for the current abnormal situation can be found, improving the efficiency and quality of problem solving.

[0090] Step S1435: Extract the corresponding equipment management measures from the matched policy entries, including operating methods, precautions and expected effects, and record the update time of the policy entries to ensure the effectiveness of the measures.

[0091] After matching a suitable strategy entry, the corresponding equipment management measures are extracted from the entry, including specific operating methods, precautions, and expected results. For example, for the abnormal situation of coal conveyor belt slippage, the operating method extracted from the matched strategy entry might be to use a special tool to adjust the belt tensioning device to achieve appropriate belt tension; precautions might include ensuring safety during the adjustment process to avoid injury from sudden belt loosening, and observing the belt's operation to ensure the adjustment's effectiveness; the expected result is to prevent the belt from slipping again and to ensure normal fuel transport. Simultaneously, the update time of the strategy entry is recorded to ensure that the management measures taken are up-to-date and most effective. Because some management measures may need continuous updating and improvement as equipment operation and the environment change, recording the update time allows for timely identification and adoption of the latest management measures, improving equipment management level and operational reliability.

[0092] Step S144: Combine the retrieved equipment management measures with the location information of the abnormal components and the current operating data to generate specific operation steps and form preliminary equipment management instructions.

[0093] The retrieved equipment management measures for adjusting belt tensioning devices are combined with the location information of the coal conveyor belt (such as its specific installation location in a power plant) and the current belt tension data. Specific operating procedures are generated, such as first stopping the operation of the coal conveyor belt, then determining the adjustment range of the tensioning device based on the current belt tension data, then operating the tensioning device to adjust it, and finally starting the coal conveyor belt and monitoring whether the belt tension has returned to normal, thus forming preliminary equipment management instructions.

[0094] Step S145: Perform a completeness check on the preliminary equipment management instructions to ensure that the instructions contain the operation objects, operation content, operation sequence and execution requirements, and finally generate equipment management instructions for the power plant fuel supply equipment.

[0095] The initial equipment management instructions are checked to see if they include the object of operation (i.e., the belt section of the coal conveyor), the operation content (adjusting the belt tensioner), the operation sequence (first stop operation, then adjust, and finally start and monitor), and the execution requirements (such as the specific range of adjustment). If there are any missing or incomplete parts in the instructions, they are supplemented and improved to finally generate equipment management instructions for the power plant's fuel supply equipment.

[0096] Step S150: Send the equipment management command to the power plant fuel supply equipment management terminal to trigger the equipment management operation.

[0097] For example, step S151: Obtain the operation object information contained in the equipment management instruction, and determine the identification information of the power plant fuel supply equipment management terminal corresponding to the operation object.

[0098] Taking the equipment management command of a coal conveyor belt as an example, the operation object information contained in the command is obtained, namely the belt section of the coal conveyor belt. Based on the pre-established correspondence between equipment and management terminals, the identification information of the power plant fuel supply equipment management terminal corresponding to the operation object is determined, for example, the number of the management terminal is T1.

[0099] Step S152: Establish a communication connection with the management terminal based on the identification information of the management terminal, and verify the stability and security of the connection.

[0100] Based on the identification information T1 of the management terminal, a communication connection is established with the management terminal via a network communication protocol. During the connection establishment process, stability testing is performed, such as checking for data transmission interruptions or excessive latency. Simultaneously, connection security verification is conducted, such as encrypting transmitted data using encryption algorithms to prevent data theft or tampering.

[0101] Step S153: Convert the device management command into a format according to a preset communication protocol so that the command can be correctly parsed by the management terminal.

[0102] The generated device management commands are converted to a pre-defined communication protocol, such as into a binary format or a specific text format that the management terminal can recognize. This ensures that the commands can be correctly parsed and understood by the management terminal during transmission.

[0103] Step S154: Send the converted equipment management command to the corresponding power plant fuel supply equipment management terminal through the established communication connection.

[0104] Through an established and verified stable and secure communication connection, the converted equipment management instructions are sent to the corresponding power plant fuel supply equipment management terminal T1. After receiving the instructions, the management terminal will process them accordingly based on the operation content and sequence information in the instructions.

[0105] Step S155: Receive confirmation information from the management terminal. If the confirmation information is received, the device management instruction will be resent until confirmation information is received, thus completing the device management instruction delivery process.

[0106] After receiving a device management command, the management terminal sends a confirmation message back to the sending end. The sending end receives this confirmation, acknowledging that the command has been successfully delivered to the management terminal. If no confirmation message is received within a certain time, it indicates a potential problem with command transmission. The sending end will resend the device management command until it receives confirmation from the management terminal, completing the command delivery process. Afterward, the management terminal will trigger corresponding device management operations based on the received command, such as adjusting the tensioning device of the coal conveyor belt, thereby achieving effective management of the power plant's fuel supply equipment.

[0107] Figure 2 The illustration shows exemplary hardware and software components of a 3D modeling-based power plant fuel supply equipment management system 100 that can implement the ideas of this application, according to some embodiments of this application. For example, a processor 120 can be used on the 3D modeling-based power plant fuel supply equipment management system 100 and to perform the functions in this application.

[0108] The 3D modeling-based power plant fuel supply equipment management system 100 can be a general-purpose server or a special-purpose server; both can be used to implement the 3D modeling-based power plant fuel supply equipment management method of this application. Although only one server is shown in this application, for convenience, the functions described in this application can be implemented in a distributed manner on multiple similar platforms to balance the load.

[0109] For example, a 3D modeling-based power plant fuel supply equipment management system 100 may include a network port 110 connected to a network, one or more processors 120 for executing program instructions, a communication bus 130, and various forms of storage media 140, such as a disk, ROM, or RAM, or any combination thereof. Exemplarily, the 3D modeling-based power plant fuel supply equipment management system 100 may also include program instructions stored in ROM, RAM, or other types of non-transitory storage media, or any combination thereof. The methods of this application can be implemented according to these program instructions. The 3D modeling-based power plant fuel supply equipment management system 100 also includes an I / O interface 150 between the computer and other input / output devices.

[0110] For ease of explanation, only one processor is described in the 3D modeling-based power plant fuel supply equipment management system 100. However, it should be noted that the 3D modeling-based power plant fuel supply equipment management system 100 of this application may also include multiple processors. Therefore, the steps performed by one processor as described in this application may also be performed jointly or individually by multiple processors. For example, if the processor of the 3D modeling-based power plant fuel supply equipment management system 100 performs steps A and B, it should be understood that steps A and B may also be performed jointly by two different processors or individually by one processor. For example, the first processor performs step A, the second processor performs step B, or the first processor and the second processor jointly perform steps A and B.

[0111] Furthermore, this embodiment of the invention also provides a readable storage medium, wherein computer-executable instructions are preset in the readable storage medium, and when the processor executes the computer-executable instructions, the above-mentioned power plant fuel supply equipment management method based on three-dimensional modeling is implemented.

[0112] It should be noted that, in order to simplify the description of the present invention and thus help to understand one or more embodiments of the invention, multiple features may sometimes be grouped into one embodiment, drawing or description thereof in the foregoing description of the embodiments of the present invention.

Claims

1. A method for managing power plant fuel supply equipment based on 3D modeling, characterized in that, The method includes: Obtain 3D models and equipment operation data of power plant fuel supply equipment; A three-dimensional operational association model of the power plant's fuel supply equipment is obtained by performing an association mapping process between the three-dimensional model of the equipment and the equipment's operating data. The pre-trained intelligent analysis model for equipment status is invoked to perform status assessment analysis on the three-dimensional operation association model of the equipment, and the equipment operation status assessment result is obtained. Based on the equipment operation status assessment results, generate equipment management instructions for the power plant's fuel supply equipment; The equipment management command is sent to the power plant fuel supply equipment management terminal to trigger the equipment management operation; The process of acquiring a 3D model and equipment operation data of the power plant fuel supply equipment, and performing a correlation mapping process between the 3D model and the equipment operation data to obtain a 3D operation correlation model of the equipment includes: Load the three-dimensional model of the power plant fuel supply equipment, perform structural component analysis on the three-dimensional model of the power plant fuel supply equipment, and identify the various equipment structural components contained in the three-dimensional model of the power plant fuel supply equipment; Extract each equipment operation monitoring item contained in the equipment operation data, wherein the equipment operation monitoring item is the monitoring content used to reflect the equipment operation status; Establish an association mapping relationship between each equipment structural component and each equipment operation monitoring item, so that each equipment structural component corresponds to at least one equipment operation monitoring item; Based on the association mapping relationship, the data of each equipment operation monitoring item are embedded into the position of the corresponding equipment structural component in the three-dimensional model of the power plant fuel supply equipment to generate an initial equipment three-dimensional operation association model; The initial equipment 3D operation association model is subjected to mapping integrity verification to confirm that all equipment structural components have been associated with the corresponding equipment operation monitoring items, thus obtaining the final equipment 3D operation association model. The process involves calling a pre-trained intelligent analysis model of device status to perform a status assessment analysis on the three-dimensional operation association model of the device, thereby obtaining the device operation status assessment results, including: The equipment 3D operation association model is input into the feature processing layer of the equipment status intelligent analysis model. Feature extraction processing is performed on the equipment operation monitoring item data and corresponding equipment structural component information embedded in the equipment 3D operation association model to obtain the equipment association feature vector. The device-related feature vector is input into the spatial association layer of the device status intelligent analysis model to analyze the spatial positional relationship between different device structural components and the correlation of corresponding device operation monitoring data, and generate spatial association features. The spatial correlation features are input into the time series analysis layer of the intelligent analysis model of equipment status to analyze the changing trend of the equipment operation monitoring data over time and extract the time series change features; The time-series change features are input into the state classification layer of the intelligent equipment state analysis model to classify and judge the operating state of the power plant fuel supply equipment and determine the current state category of the equipment. Based on the state category, generate an equipment operation status assessment result that includes descriptions of the operating status of each structural component of the equipment and conclusions on the overall state.

2. The power plant fuel supply equipment management method based on three-dimensional modeling according to claim 1, characterized in that, The process involves loading a 3D model of the power plant fuel supply equipment, performing structural component analysis on the 3D model, and identifying the various structural components contained within the 3D model of the power plant fuel supply equipment, including: The three-dimensional model of the power plant's fuel supply equipment is loaded using a three-dimensional model parsing tool, and the structural description information of the three-dimensional model is read. Based on the structural description information, the structural regions corresponding to each independent functional unit in the three-dimensional model are identified, and each structural region corresponds to a potential device structural component. Extract the geometric parameter information and functional identification information of each potential device structural component. The geometric parameter information is used to describe the shape and size characteristics of the component, and the functional identification information is used to describe the function of the component. Based on the functional identification information, each potential equipment structural component is classified into fuel delivery components, fuel storage components, and auxiliary control components. Each potential equipment structural component after classification is uniquely identified, and an independent component number is assigned to each potential equipment structural component. Finally, the equipment structural components and their corresponding component numbers contained in the three-dimensional model of the power plant fuel supply equipment are determined.

3. The power plant fuel supply equipment management method based on three-dimensional modeling according to claim 1, characterized in that, The step of extracting each equipment operation monitoring item from the equipment operation data and establishing the association mapping relationship between each equipment structural component and each equipment operation monitoring item includes: The equipment operation data is parsed and processed to separate different types of monitoring data, with each type of monitoring data corresponding to a specific equipment operation monitoring item. Add a monitoring type identifier to each device operation monitoring item. The monitoring type identifier includes real-time monitoring items and periodic monitoring items. Based on the functional identification information of each equipment structural component, determine the types of parameters that need to be monitored during the operation of each equipment structural component; The monitoring content of the equipment operation monitoring item is matched with the parameter types that need to be monitored for the equipment structural components, so that each equipment structural component is associated with at least one corresponding equipment operation monitoring item; Record the correspondence between each equipment structural component and the associated equipment operation monitoring items, and generate an association mapping table. The association mapping table contains component number, component name, monitoring item name and monitoring type identifier.

4. The power plant fuel supply equipment management method based on three-dimensional modeling according to claim 1, characterized in that, The step of inputting the device-related feature vector into the spatial association layer of the device status intelligent analysis model to analyze the spatial positional relationships between different device structural components and the correlation of corresponding device operation monitoring data, and generating spatial association features, includes: Receive the device-associated feature vector, and extract the spatial coordinate information of each device structural component and the corresponding device operation monitoring data contained in the device-associated feature vector; Calculate the spatial distance and relative orientation between any two equipment structural components to determine the degree of spatial correlation between each equipment structural component; Analyze the consistency of changes in equipment operation monitoring data corresponding to equipment structural components that are spatially close, and determine whether there is a collaborative relationship in the data changes; Based on the spatial location correlation degree and data change coordination relationship, a spatial correlation matrix is ​​constructed, which is used to represent the correlation strength of each device structural component at the spatial and data levels; Feature extraction processing is performed on the spatial correlation matrix to extract key correlation information and generate spatial correlation features that can be used for time series analysis.

5. The power plant fuel supply equipment management method based on three-dimensional modeling according to claim 1, characterized in that, The step of inputting the spatial correlation features into the time-series analysis layer of the intelligent analysis model of the equipment status to analyze the changing trend of the equipment operation monitoring data over time and extract time-series change features includes: The spatial correlation features are combined with the historical data of the corresponding equipment operation monitoring items to construct a time series analysis dataset, which includes spatial correlation features and corresponding monitoring data at different time points. The time series analysis dataset is divided into time series segments according to a preset time interval. Analyze the magnitude and direction of change of the equipment operation monitoring data within each time segment to determine the local change trend of the equipment operation monitoring data within the time segment. Compare the local change trends between adjacent time segments, identify the continuity or abrupt change of the local change trends, and record the time nodes of the changes in the local change trends; Based on the local change trend, trend continuity, and abrupt change time points, features that can reflect the long-term change patterns of the equipment operation monitoring data are extracted to generate time-series change features.

6. The power plant fuel supply equipment management method based on three-dimensional modeling according to claim 1, characterized in that, The generation of equipment management instructions for power plant fuel supply equipment based on the equipment operation status assessment results includes: Analyze the equipment operation status assessment results and extract the operation status of each structural component of the equipment and the overall status judgment conclusions described therein; Identify the equipment structural components corresponding to the abnormal operating states marked in the evaluation results, and determine the component number and abnormal behavior of the abnormal components; Load the power plant fuel supply equipment management strategy library and retrieve the corresponding equipment management measures based on the type and abnormal behavior of the abnormal components; By combining the retrieved equipment management measures with the location information of abnormal components and current operating data, specific operating steps are generated, and equipment management instructions for power plant fuel supply equipment are generated.

7. The power plant fuel supply equipment management method based on three-dimensional modeling according to claim 6, characterized in that, The loaded power plant fuel supply equipment management strategy library retrieves corresponding equipment management measures based on the type and abnormal behavior of the abnormal components, including: The power plant fuel supply equipment management strategy library is loaded through the strategy library call interface. The power plant fuel supply equipment management strategy library stores the mapping relationship between different anomaly types and corresponding management measures. Extract the type information of the abnormal components, including abnormalities in fuel delivery components, abnormalities in fuel storage components, and abnormalities in auxiliary control components; Based on the type information of the abnormal component, determine the corresponding strategy category directory in the power plant fuel supply equipment management strategy library, and then enter the strategy category directory for further retrieval. In the corresponding policy category directory, based on the abnormal behavior of the abnormal component, policy entries with the same or similar abnormal descriptions are matched; Extract the corresponding device management measures from the matched policy entries, including operating methods, precautions and expected effects, and record the update time of the policy entries.

8. A power plant fuel supply equipment management system based on 3D modeling, characterized in that, The power plant fuel supply equipment management system based on 3D modeling includes a processor and a memory, the memory and the processor being connected. The memory is used to store programs, instructions or code, and the processor is used to execute the programs, instructions or code in the memory to implement the power plant fuel supply equipment management method based on 3D modeling as described in any one of claims 1-7.

Images