Analysis system for gas enterprise operation management

Abstract

The invention provides an analysis system for gas enterprise operation management, and relates to the technical field of intelligent control, and the analysis system comprises a data processing module which is used for generating a three-dimensional model of a gas transmission and distribution pipe network by using preprocessed data; according to the three-dimensional model, predicting the future operation state of the gas transmission and distribution pipe network to obtain a prediction result; generating a preliminary configuration scheme according to the prediction result; the optimization module is used for coding the parameters of the preliminary configuration scheme into genes through a genetic algorithm and creating a group of initial populations, namely a plurality of possible configuration schemes; performing iterative evolution on the population, and evaluating the fitness of each individual in each iteration; and selecting corresponding individuals for crossing to generate a new population, and carrying out multiple iterations to obtain a final configuration scheme. The safety and stability of the gas transmission and distribution pipe network can be improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent control technology, and in particular to an analysis system for operation and management of a gas enterprise. Background Art

[0002] The operation and management of gas companies are facing increasingly complex challenges, including ensuring the safe and stable operation of gas transmission and distribution networks, meeting the growing gas demand of users, and coping with changing weather conditions. Some traditional gas company operation and management methods are based on manual experience and simple data analysis, and therefore may have the following defects: 1. Relying on manual inspections and regular data collection, this approach is not only inefficient, but also difficult to ensure the real-time and accuracy of the data. In addition, the lack of an effective data preprocessing mechanism results in a large amount of noise and outliers in the original data, affecting the subsequent data analysis results.

[0003] 2. Some use two-dimensional plan views, which cannot truly reflect the complex spatial structure and operating status of the pipeline network. Therefore, it is difficult to accurately predict the future operating status of the pipeline network. Summary of the invention

[0004] The technical problem to be solved by the present invention is to provide an analysis system for operation and management of gas enterprises, which can improve the safety and stability of the gas transmission and distribution network.

[0005] In order to solve the above technical problems, the technical solution of the present invention is as follows: An analysis system for gas enterprise operation management, comprising: The data acquisition module is used to obtain the operating parameters of key nodes of the gas transmission and distribution network, the gas consumption data of the user terminal and the meteorological data of the environmental monitoring point in real time and pre-process them to obtain pre-processed data; The data processing module is used to generate a three-dimensional model of the gas transmission and distribution network using preprocessed data; based on the three-dimensional model, the future operation status of the gas transmission and distribution network is predicted using a machine learning prediction model to obtain prediction results, including the layout of the network, the location of key nodes, and the relationship with meteorological conditions; based on the prediction results, a preliminary configuration plan is generated; The optimization module is used to encode the parameters of the preliminary configuration scheme as "genes" through the genetic algorithm and create a set of initial "populations", that is, multiple possible configuration schemes; iteratively evolve the population, and in each iteration, evaluate the fitness of each individual; select the corresponding individuals for crossover to generate a new population, and after multiple iterations, obtain the final configuration scheme.

[0006] Furthermore, the preprocessed data is used to generate a three-dimensional model of the gas transmission and distribution network, including: Each pipe network node is regarded as a particle, and the position of the particle is initialized as a combination of two-dimensional coordinates and elevation data. A velocity vector is assigned to each particle, and the initial velocity is set to zero, indicating the moving direction and speed of the particle in three-dimensional space. Define the fitness function, which is used to evaluate the position of each particle, that is, the node in the three-dimensional space; In each iteration, the fitness value of each particle is evaluated according to the fitness function, and the speed and position of the particle are updated. After the iteration of the particle swarm optimization algorithm is completed, the final optimized particle position is mapped to the three-dimensional space to determine the position of each node in the three-dimensional coordinate system; Create a 3D pipe network element model, including pipes, valves and joints, based on the position of each node in the 3D coordinate system and known pipe information; According to the actual connection relationship between the pipe network elements, the various elements are assembled into a three-dimensional pipe network model.

[0007] Furthermore, based on the three-dimensional model, the machine learning prediction model is used to predict the future operation status of the gas transmission and distribution network to obtain prediction results. The prediction results include the layout of the network, the location of key nodes, and the relationship with meteorological conditions, including: Extract the pipe network layout information from the 3D model, including the length, diameter, material and connection method of the pipes; determine and extract the key node locations in the pipe network, which are branch points, control valves or pressure regulating stations; Acquire and process historical operating data of key nodes, including pressure, flow and temperature data; Obtain real-time meteorological data related to gas transmission and distribution from environmental monitoring points, including temperature, humidity, wind speed and direction, so that the real-time meteorological data can be matched with the timestamps of the pipeline network operation data; The network layout information and key node location data extracted from the 3D model are integrated with the historical operation data to form a preliminary data set; The meteorological data are fused with the preliminary data set so that the pipeline network operation data at each time point correspond to the corresponding meteorological conditions to obtain a fused data set; Preprocess the fused data set and divide the preprocessed data set into a training set, a validation set, and a test set; Use the training set to train the neural network model, and adjust the hyperparameters of the neural network model to optimize the performance of the neural network model; use the validation set to evaluate the performance of the neural network model during the training process to obtain the final prediction model; Input the current three-dimensional model data and real-time environmental meteorological data into the final prediction model to obtain the predicted operating status of each key node of the pipeline network in the future, including the predicted values ​​of pressure and flow.

[0008] Furthermore, the meteorological data are fused with the preliminary data set so that the network operation data at each time point corresponds to the corresponding meteorological conditions, thereby obtaining a fused data set, including: Determine the number of time points of pipeline operation data, set to M; determine the number of time points of meteorological data, set to N; create a two-dimensional matrix with M rows and N columns to store the similarities between time points; Initially, all elements in the matrix are set to a default value; For each time point of the pipe network operation data, set it to i; for each time point of the meteorological data, set it to j; set the initial distance to 0 at the upper left corner of the DTW matrix, i.e. the starting point; set the first row and the first column of the DTW matrix to infinity, indicating the unreachability between the starting point and the remaining points; starting from the first time point i of the pipe network operation data and the first time point j of the meteorological data, gradually traverse all pairs of time points; for each pair of time points (i, j), extract the corresponding pipe network operation data parameters and meteorological data parameters; calculate the Euclidean distance between the pipe network operation data parameters and the meteorological data parameters; According to the Euclidean distance between the pipe network operation data parameters and the meteorological data parameters and the values ​​of the adjacent cells filled in the DTW matrix, the value of the current cell is updated and moved to the next time point pair until all time point pairs are traversed; The final Euclidean distance value is found at the lower right corner of the DTW matrix, i.e. the end point, which represents the similarity between the entire pipeline network operation data sequence and the entire meteorological data sequence; Fill the similarity between i and j into the corresponding position of the two-dimensional matching matrix, i.e., row i, column j; create a dynamic programming table of the same size as the two-dimensional matching matrix; starting from the upper left corner, gradually fill each element in the dynamic programming table, and the value of each element represents the minimum cumulative similarity from the starting point to the current position; Update the value of the current position according to the minimum cumulative similarity of the previous position and the similarity of the current position, starting from the lower right corner of the dynamic planning table and gradually backtracking to the upper left corner. During the backtracking process, record the grid path passed, which is the final matching path between the pipe network operation data time point and the meteorological data time point; According to the final matching path, determine the meteorological data time point corresponding to each pipe network operation data time point; For each matched pipe network operation data time point, it is merged with the corresponding meteorological data time point into one record to obtain a fused data set.

[0009] Furthermore, based on the prediction results, a preliminary configuration plan is generated, including: Identify parameters important to the operation of the network from the prediction results; Set the goals of the configuration plan according to the operational needs of the gas company; Construct a preliminary configuration plan based on the parameters important to the operation of the pipeline network and the set configuration goals.

[0010] Furthermore, the parameters of the preliminary configuration scheme include pressure setpoints and flow distribution of the network nodes.

[0011] Furthermore, important parameters for pipeline network operation include pressure at key nodes, flow rate trends, and areas affected by meteorological conditions.

[0012] In a second aspect, an analysis method for gas enterprise operation management is provided, the method is used to execute the system, and the method comprises: Real-time acquisition of operating parameters of key nodes of the gas transmission and distribution network, gas consumption data of user terminals, and meteorological data of environmental monitoring points, and pre-processing to obtain pre-processed data; Using the preprocessed data, a three-dimensional model of the gas transmission and distribution network is generated; based on the three-dimensional model, a machine learning prediction model is used to predict the future operation status of the gas transmission and distribution network to obtain prediction results, including the layout of the network, the location of key nodes, and the relationship with meteorological conditions; based on the prediction results, a preliminary configuration plan is generated; The parameters of the preliminary configuration scheme are encoded as "genes" through the genetic algorithm, and an initial set of "populations", that is, multiple possible configuration schemes, are created; the population is iteratively evolved, and in each iteration, the fitness of each individual is evaluated; the corresponding individuals are selected for crossover to generate a new population, and after multiple iterations, the final configuration scheme is obtained.

[0013] According to a third aspect, a computing device includes: one or more processors; The storage device is used to store one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the method described.

[0014] In a fourth aspect, a computer-readable storage medium stores a program, and when the program is executed by a processor, the method described is implemented.

[0015] The above solution of the present invention includes at least the following beneficial effects: Through the data acquisition module, the system can obtain the operating parameters of key nodes of the gas transmission and distribution network, the gas consumption data of user terminals and the meteorological data of environmental monitoring points in real time, and perform preprocessing. This method significantly improves the efficiency and accuracy of data collection. The data processing module uses preprocessed data to generate a three-dimensional model of the gas transmission and distribution network, making the layout of the network and the location of key nodes more intuitive and visual. At the same time, combined with the machine learning prediction model, it can accurately predict the future operating status of the gas transmission and distribution network, including the relationship with meteorological conditions, thereby helping enterprises make more accurate decisions.

[0016] The optimization module encodes and optimizes the parameters of the preliminary configuration plan through genetic algorithms, and can generate a more scientific and reasonable final configuration plan. This optimization method not only improves the quality of the configuration plan, but also makes the gas transmission and distribution network more efficient and safe, thereby improving the overall operational efficiency of gas companies. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a schematic diagram of an analysis system for gas enterprise operation management provided by an embodiment of the present invention.

[0018] Figure 2 It is a flow chart of an analysis method for gas enterprise operation management provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0019] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0020] like Figure 1 As shown, an embodiment of the present invention provides an analysis system for gas enterprise operation management, including: The data acquisition module is used to obtain the operating parameters of key nodes of the gas transmission and distribution network, the gas consumption data of the user terminal and the meteorological data of the environmental monitoring point in real time and pre-process them to obtain pre-processed data; The data processing module is used to generate a three-dimensional model of the gas transmission and distribution network using preprocessed data; based on the three-dimensional model, the future operation status of the gas transmission and distribution network is predicted using a machine learning prediction model to obtain prediction results, including the layout of the network, the location of key nodes, and the relationship with meteorological conditions; based on the prediction results, a preliminary configuration plan is generated; The optimization module is used to encode the parameters of the preliminary configuration scheme as "genes" through the genetic algorithm and create a set of initial "populations", that is, multiple possible configuration schemes; iteratively evolve the population, and in each iteration, evaluate the fitness of each individual; select the corresponding individuals for crossover to generate a new population, and after multiple iterations, obtain the final configuration scheme.

[0021] In the embodiment of the present invention, by obtaining the operating parameters of the key nodes of the gas transmission and distribution network, the gas consumption data of the user terminal and the meteorological data of the environmental monitoring point in real time, the timeliness and accuracy of the data are ensured; the data is preprocessed to effectively remove noise, outliers and duplicate data, improve the data quality, and provide a more accurate and clean data set for subsequent data analysis and model prediction. The three-dimensional model of the gas transmission and distribution network is generated to realize the visual management of the network, which helps to understand the complex structure and layout of the network more intuitively and improve the efficiency and accuracy of operation management. The future operation state of the gas transmission and distribution network is predicted by using the machine learning prediction model, which helps enterprises to make operation planning and risk response in advance. This prediction ability can significantly reduce the operation risk and improve the stability and reliability of the system. The preliminary configuration plan is generated according to the prediction results, which provides a starting point based on data and prediction for the enterprise, and helps to quickly respond to market demand and system changes. The parameters of the preliminary configuration plan are encoded and optimized by genetic algorithm, and a better configuration plan can be searched. This method can handle complex optimization problems and find the global optimal solution or approximate optimal solution. By iteratively evolving the population and evaluating individual fitness, the configuration scheme is continuously optimized. This iterative process can ensure that the final configuration scheme is more in line with actual needs and improve the efficiency and safety of the gas transmission and distribution system. The final configuration scheme obtained after multiple iterative optimizations is the best result based on data and algorithm optimization, which helps enterprises achieve higher efficiency and lower costs in actual operations, while improving the stability and reliability of the system.

[0022] In another preferred embodiment of the present invention, the real-time acquisition of operating parameters of key nodes of the gas transmission and distribution network, gas consumption data of user terminals, and meteorological data of environmental monitoring points and preprocessing to obtain preprocessed data may include: Identify the key nodes in the gas transmission and distribution network, which are important parts of the network, such as pressure regulating stations, valves, sensors, etc. Their operating parameters are crucial to the stable operation of the entire network; secondly, identify the user terminals, that is, the gas consumption data collection points of gas users, which helps to understand the gas demand and pattern of users. Finally, identify environmental monitoring points to collect meteorological data, such as temperature, humidity, wind speed, etc., which have an important impact on predicting gas demand and the operation status of the network; install corresponding sensors and data acquisition equipment at each collection point, such as pressure sensors, flow meters, temperature sensors, etc., for real-time measurement and recording of operating parameters, gas consumption and meteorological data, and ensure smooth communication between data acquisition equipment and the central data processing system for real-time data transmission. Sensors and data acquisition devices will collect data at a set frequency (such as every second, every minute or every hour) and send the data to the central data processing system, which is responsible for receiving data from various collection points and performing preliminary data integration and storage; data preprocessing is an indispensable step in the data acquisition module, which involves operations such as cleaning, converting and standardizing the raw data; cleaning data mainly removes outliers, noise data and duplicate records to ensure the accuracy and consistency of the data, and converting data is to convert the raw data into a format suitable for subsequent analysis and processing, such as unifying data units and converting non-numeric data into numerical data. Standardized data is to eliminate the impact of different dimensions and value ranges on data analysis results and make the data comparable. The preprocessed data will be output to the next module (such as the data processing module) for further analysis and processing. The output format and quality of the preprocessed data will directly affect the accuracy and effectiveness of subsequent analysis.

[0023] In summary, the data acquisition module realizes the comprehensive, accurate and efficient collection of operating parameters of key nodes of the gas transmission and distribution network, gas consumption data of user terminals and meteorological data of environmental monitoring points by determining data collection points, building a data collection system, acquiring data in real time, preprocessing data and outputting preprocessed data.

[0024] In a preferred embodiment of the present invention, the three-dimensional model of the gas transmission and distribution network is generated by using preprocessed data, including: Each pipeline node is regarded as a particle, and the position of the particle is initialized as a combination of two-dimensional coordinates and elevation data. A velocity vector is assigned to each particle, and the initial velocity is set to zero, indicating the movement direction and speed of the particle in three-dimensional space. Specifically, the following steps are performed: determining the pipeline nodes and determining which points are nodes in the pipeline network. These nodes may be key locations such as pipeline connection points, valves, sensors, etc.; initializing the position of each node to a combination of two-dimensional coordinates (x, y) and elevation data z, which is based on actual measurements or geographic information system (GIS) data; assigning a three-dimensional velocity vector to each node, and its initial value is set to zero, which means that at the beginning of the optimization process, the particle (node) has not moved.

[0025] Define the fitness function, which is used to evaluate the position of each particle, that is, the node in the three-dimensional space. The calculation formula of the fitness function is: ; in, ,in,( , , ) represents the three-dimensional coordinates of the current node; ( , , ) represents the three-dimensional coordinates of the target node (based on actual measurement); n represents the total number of nodes; Indicates the actual connection length (the connection distance between the current node and other nodes); represents the expected connection length (the expected distance based on the actual pipe network layout); m represents the total number of connections; Indicates the angle between the current node and the adjacent node (such as the pipe bending angle); represents the average angle of adjacent nodes; p represents the number of adjacent node pairs; Indicates A connection is used to traverse the connection relationship between all nodes; Indicates For adjacent nodes, it is used to traverse all pairs of adjacent nodes; , and Represents the weight coefficient.

[0026] In each iteration, the fitness value of each particle is evaluated according to the fitness function, and the speed and position of the particle are updated. After the iteration of the particle swarm optimization algorithm is completed, the final optimized particle position is mapped to the three-dimensional space, and the position of each node in the three-dimensional coordinate system is determined. Specifically, in each iteration, the current position of each particle is evaluated using the defined fitness function, and the speed vector and position of each particle are adjusted based on the fitness evaluation result. The particle will update its speed and position according to its own historical best position and the historical best position of the group, and set the conditions for the termination of the iteration, such as reaching the maximum number of iterations. After the iterative optimization is completed, the final optimized particle position (that is, the position of the pipeline node) is mapped from the algorithm space to the actual three-dimensional coordinate system.

[0027] The speed of each particle It is updated in each generation (iteration), and the update formula is as follows: ; in, represents the speed of particle i at time t; w represents the inertia weight, which is used to control the jumping nature of the particle search space; and Represents the learning factor, which controls the particle to its optimal position and the attractiveness of the group's optimal location; and These two are random numbers between [0, 1]; represents the best historical position of particle i; represents the historical best position in the group; represents the current position of particle i at time t; ; in, represents particle i at time location; represents particle i at time speed.

[0028] According to the position of each node in the three-dimensional coordinate system and the known pipeline information, a three-dimensional pipe network element model is created, including pipes, valves and joints. Specifically, according to the position of each node in the three-dimensional coordinate system and the known pipeline information (such as length, diameter, material, etc.), various elements of the pipe network, including pipes, valves, joints, etc., are created using three-dimensional modeling software, and corresponding physical properties and parameters are assigned to each element to ensure that the model is consistent with the characteristics of the actual pipe network.

[0029] According to the actual connection relationship between the pipe network elements, the various elements are assembled into a three-dimensional pipe network model, specifically including: according to the actual connection relationship between the pipe network elements (such as which valve is connected to which section of the pipe), these elements are assembled into a complete pipe network model in three-dimensional space. After the assembly is completed, the model is verified to ensure its accuracy and completeness, which includes checking whether the connection points are correct and whether the pipes intersect.

[0030] In an embodiment of the present invention, by treating each pipe network node as a particle and initializing its position and speed, basic data is provided for subsequent reconstruction of the three-dimensional model. This particle representation method simplifies the complex pipe network structure and facilitates optimization. The fitness function is the key to evaluating the position of each particle (i.e., node) in three-dimensional space. By reasonably defining the fitness function, it is possible to ensure that the generated three-dimensional model is more in line with the layout and characteristics of the actual pipe network, thereby improving the accuracy and practicality of the model. By continuously updating the speed and position of the particles during the iterative optimization process, the optimal node layout can be found. This method can ensure that the position of the nodes in the three-dimensional model is more accurate, thereby improving the accuracy and reliability of the entire model. Mapping the optimized particle position to the three-dimensional space can intuitively display the spatial distribution of the pipe network nodes, which not only helps to understand and analyze the complex structure of the pipe network, but also provides accurate spatial positioning information for the subsequent construction of the three-dimensional model. According to the position of the node in the three-dimensional coordinate system and the known pipeline information, a three-dimensional model including elements such as pipes, valves, and joints is created, which enables the various components of the pipe network to be truly reproduced in three-dimensional space, thereby improving the visualization and fidelity of the model. According to the actual connection relationship between the pipeline network elements, the various elements are assembled into a complete three-dimensional pipeline network model, which helps to fully display the overall structure and layout of the pipeline network. Through the display of the three-dimensional model, the operating status and potential problems of the pipeline network can be more intuitively understood, and the efficiency and accuracy of operation management can be improved.

[0031] The fitness function takes into account the three key factors of distance, connection length and angle between nodes in a weighted manner, making the evaluation more comprehensive and accurate, which helps to find node positions that perform well in multiple dimensions. By adjusting the weight coefficients w1, w2 and w3, the importance of different factors in the evaluation can be flexibly adjusted. This flexibility enables the function to adapt to different application scenarios and needs. The D part of the function explicitly considers the distance between the node and the target node, which helps to guide the particle to the target position. By calculating the actual connection length Expected connection length This function can evaluate the degree of consistency between the current node layout and the expected network layout, thereby optimizing the overall layout effect. and By quantifying multiple considerations and weighted summing them, the function provides a clear numerical indicator to evaluate the pros and cons of node locations, which is convenient for comparison and selection.

[0032] In a preferred embodiment of the present invention, based on the three-dimensional model, a machine learning prediction model is used to predict the future operation state of the gas transmission and distribution network to obtain a prediction result, which includes the layout of the network, the location of key nodes, and the relationship with meteorological conditions, including: Extract the pipe network layout information from the 3D model, including the length, diameter, material and connection method of the pipes; determine and extract the key node locations in the pipe network, which are branch points, control valves or pressure regulating stations, including: According to the Canny edge detection algorithm, set the recognition parameters, including the length, diameter range, curvature threshold, etc. of the shape, to ensure that the algorithm can accurately identify the unique shape features of pipelines such as linear and tubular; preprocess the 3D model, such as removing noise and simplifying geometric details, to improve the accuracy of recognition; start traversing each element in the 3D model, which can be a polygonal mesh, and the traversal can be achieved recursively to ensure that each element is checked; initialize the Canny edge detection algorithm parameters, including the size and standard deviation of the Gaussian filter, which is used to smooth the image and reduce noise, and set two thresholds (high threshold and low threshold) for hysteresis threshold processing during edge detection; convert the currently traversed 3D model element into For a two-dimensional image, a Gaussian filter is applied to smooth the image to reduce the impact of noise on edge detection; the Sobel operator is used to calculate the gradient amplitude and direction of each pixel in the image, the gradient amplitude represents the strength of the edge, and the gradient direction represents the direction of the edge; each pixel of the image is traversed, and for each pixel, its gradient amplitude is compared with the gradient amplitude of the adjacent pixels along the gradient direction, the pixel with the largest local gradient amplitude is retained, and other non-maximum points are suppressed, thereby refining the edge; the gradient amplitude is thresholded using a high threshold and a low threshold, and the pixel points above the high threshold are considered to be confirmed edge points, and the pixel points below the low threshold are discarded. The pixel points between the two thresholds are considered to be edge points if they are connected to the confirmed edge points, otherwise they are discarded.

[0033] Extract shape features from the detected edge image, such as length (obtained by calculating the number of edge pixels or the total length of the edge curve), diameter (for tubular objects, it may be necessary to estimate the diameter by fitting a circle or ellipse), and curvature (obtained by calculating the rate of change of the tangent direction of the edge point); compare the extracted shape features with the preset pipe shape features. These preset features can be set based on actual needs. The comparison can be achieved by calculating the difference between the features, such as calculating the Euclidean distance between the shape features. According to the comparison result, if the shape feature of the current element matches the preset pipe shape feature (the difference is less than a certain threshold), the element is marked as a pipe. The marking can be achieved by changing the color, transparency, adding a label, or displaying it in a specific way in the model. Record the elements marked as pipes and their related information, such as position, shape feature value, etc.; continue to traverse the next element and repeat the above process until all elements have been processed. If all elements have been traversed and processed, the entire process ends.

[0034] For each identified pipeline element, use its unique identifier (such as ID, name, etc.) to query the corresponding attribute information in the metadata. The queried attributes include: length, diameter, material and other key information. The queried attribute information is stored in the attribute record of the pipeline element. If some attributes are missing in the metadata (that is, the query result is empty or does not exist), the missing situation is recorded; for the missing length information in the metadata, it is derived through the following steps: a. Get the 3D coordinate data of the pipeline element, which includes the coordinates of the two end points of the pipeline.

[0035] b. Use a distance formula in three-dimensional space (such as the Euclidean distance formula) to calculate the straight-line distance between the two endpoints.

[0036] c. Use the calculated straight-line distance as the length of the pipeline and add it to the pipeline's attribute record.

[0037] The derived length information is verified to ensure its rationality and accuracy. For example, it can be compared with other known attributes (such as diameter) to check whether there are obvious logical errors. If the verification passes, the derived length information is officially updated to the attribute record of the pipeline; if the verification fails, the problem is recorded and further investigation is carried out.

[0038] Throughout the process, the processing log of each pipeline element is recorded, including query results, missing attributes, derivation process, and any exceptions or error information.

[0039] If there are still unprocessed pipeline elements, continue to process according to the above steps. When all identified pipeline elements have been processed, the entire process ends.

[0040] Get all identified pipeline elements and their attribute information, determine which pipelines are adjacent by calculating the distance between the endpoints of pipeline elements, set a distance threshold, and if the distance between two pipeline endpoints is less than this threshold, they are considered adjacent; extract the three-dimensional coordinates of adjacent pipeline endpoints, calculate the direction of the pipeline, which can be obtained by the tangent or normal vector near the pipeline endpoint, compare the coordinates of adjacent pipeline endpoints to determine whether they are aligned, and if the coordinate difference is within the allowable error range, the endpoints are considered aligned.

[0041] For each pair of adjacent pipe elements, a search area in three-dimensional space is determined based on their endpoint positions and orientations. This area is the space between the two pipe endpoints and can be slightly expanded to accommodate possible connectors. Within the determined search area, an edge detection algorithm is used to find possible connector models to identify specific shapes, such as the circular contour of a flange or the specific structure of a joint. The results of shape recognition are filtered to remove recognitions with low confidence to reduce misidentification. Other information, such as the size and positional relationship of the connector, can be combined for further verification. Based on the alignment of adjacent pipe endpoints and Based on the identification results of the connectors, the connection mode is comprehensively judged. If the pipe endpoints are aligned and no connectors are identified, it is determined to be a direct connection. If a specific connector such as a flange is identified, it is determined to be a corresponding connection mode, such as a flange connection. The determined connection mode information is recorded in the attributes of the pipe element, which can be directly added to the metadata of the pipe, or this information is stored in a separate database table. The table should contain fields to record information such as the ID of the pipe element, the ID of the adjacent pipe element, the type of connection mode, etc. For each pair of adjacent pipe elements, the above steps are repeated until the connection modes of all adjacent pipes are determined and recorded.

[0042] Define a data structure containing key node type definitions, determine the attributes of key nodes, such as type, characteristics, identification rules, etc., define characteristics and identification rules for each key node type (such as branch points, control valves, pressure regulating stations, etc.), the characteristics may include shape, size, position relationship, etc., the identification rules may be based on shape matching algorithms, use actual 3D model data to test the accuracy and completeness of the knowledge base, adjust and optimize the identification rules and feature definitions based on the test results, combine the key node knowledge base with the analysis process of pipeline element connection methods, use the knowledge base to identify and classify key nodes during the analysis process, and update the knowledge base regularly as new types of key nodes emerge or identification technology improves.

[0043] Initialize the shape matching algorithm, traverse the elements in the 3D model, match each element with the shape template, identify the elements with high similarity to the shape template, and mark them as key nodes of the corresponding type. For example, locate the control valve and the pressure regulating station by identifying specific shapes (such as the handle of the valve, the appearance characteristics of the pressure regulating station, etc.). For the identified key nodes, use the spatial positioning function of the 3D model to obtain their precise spatial coordinates, and store the spatial coordinate information of the key nodes for integration with other pipe network data. Create a data structure (such as a database table or object model) to store the integrated information, fill the location and type information of the key nodes into the data structure, record the status information (such as the open / closed status) of the control valve, and record the relevant parameters (such as the pressure regulating range, set value, etc.) of the pressure regulating station.

[0044] Acquire and process historical operation data of key nodes, including pressure, flow and temperature data; acquire real-time meteorological data related to gas transmission and distribution from environmental monitoring points, including temperature, humidity, wind speed and direction, so that the real-time meteorological data can match the timestamp of the pipeline network operation data; fuse the pipeline network layout information extracted from the 3D model, key node location data and historical operation data to form a preliminary data set, including: Locate the database or data warehouse that stores historical operating data of key nodes, use SQL query or other data extraction tools to retrieve historical data of pressure, flow and temperature from the data source, clean the extracted data, remove duplicate, abnormal or invalid data points, and convert the cleaned data into a unified format; determine the location and access interface of the environmental monitoring point that provides real-time meteorological data, connect with the data interface of the environmental monitoring point through API calls, data stream subscriptions or file transfers, and obtain real-time data of temperature, humidity, wind speed and wind direction from the environmental monitoring point regularly (such as every minute or every hour), ensuring that the real-time meteorological data obtained contains accurate timestamps; import the three-dimensional model data containing the pipeline layout information and the key node locations into the data processing environment so that the key node locations in the three-dimensional model data correspond to the node identifiers in the historical operating data.

[0045] Read the preprocessed historical data from the specified data storage location (such as a database, file, etc.). The data is stored in a structured format (such as CSV, JSON) and contains fields such as timestamp, key node identifier (ID), pressure, flow, and temperature. Load the 3D model file and parse the key node information in the model, including the location and identifier of the node. The 3D model uses a specific file format (such as OBJ, FBX, etc.) and requires a corresponding parsing library or tool to read it. Iterate through each record in the historical data, extract the identifier of the key node, and then search for nodes with the same identifier in the 3D model data. Establish a mapping relationship between the successfully matched historical data records and the 3D model nodes. This can be achieved by creating a mapping table or dictionary, in which the key is the node identifier and the value is the corresponding historical data record. According to the preset visualization rules, determine to display the historical data time series in the 3D model. For example, you can choose to display a floating window containing a time series chart near the node. According to the determined overlay method, prepare corresponding visualization components, which may include chart libraries, color mapping functions, etc.; for each node with an established mapping relationship, obtain its corresponding historical data record, use the prepared visualization components, and generate a time series chart based on the historical data. The chart clearly shows the changes in the node's pressure, flow, and temperature over time; overlay the generated time series chart on the corresponding three-dimensional model node.

[0046] The meteorological data are fused with the preliminary data set so that the pipeline network operation data at each time point correspond to the corresponding meteorological conditions to obtain a fused data set; Preprocess the fusion data set and divide the preprocessed data set into training set, validation set and test set; use the training set to train the neural network model and adjust the hyperparameters of the neural network model to optimize the performance of the neural network model; use the validation set to evaluate the performance of the neural network model during the training process to obtain the final prediction model, including: Use the random partitioning algorithm to divide the preprocessed data set into training set, validation set and test set. The training set is used for model training, the validation set is used for model selection and hyperparameter adjustment, and the test set is used to evaluate the final performance of the model. The partition ratio is 70% training set, 15% validation set, and 15% test set. Define the input layer, hidden layer, and output layer of the convolutional neural network model, and set the initial hyperparameters, such as learning rate, batch size, optimizer (such as Adam, SGD, etc.), loss function, etc. Use the training set to train the neural network model, update the model weights through the back propagation algorithm and gradient descent optimizer, adjust the hyperparameters based on the performance evaluation results of the validation set, and use the grid search method to tune the hyperparameters until a satisfactory hyperparameter combination is found. Use the validation set to evaluate the performance of the model under different hyperparameter combinations, and select evaluation indicators, such as accuracy and precision. Based on the performance evaluation results on the validation set, select the best performing model as the final prediction model.

[0047] Input the current 3D model data and real-time environmental meteorological data into the final prediction model to obtain the predicted operating status of each key node of the pipeline network in the future, including the predicted values ​​of pressure and flow, including: Integrate the preprocessed 3D model data and real-time environmental meteorological data into appropriate input formats, such as tensors, data frames, etc. For time series prediction, construct a time window containing historical data as input; load the trained prediction model and configure the model's operating parameters, such as batch size, prediction step, etc., pass the prepared input data to the prediction model, perform forward propagation to obtain the model's predicted output, and perform multiple inferences to obtain more stable prediction results, such as through Monte Carlo simulation or integration methods. Extract the predicted operating status of each key node of the pipeline network from the output of the model, including the predicted values ​​of pressure and flow.

[0048] In an embodiment of the present invention, a comprehensive and detailed prediction model can be constructed by integrating the pipeline layout information, key node location data, historical operation data and real-time meteorological data in the three-dimensional model. This multi-dimensional data fusion can significantly improve the accuracy of the prediction and help managers to more accurately grasp the future operation status of the pipeline network. Accurate prediction results provide strong support for pipeline operation decisions. Managers can adjust the pipeline operation strategy in time according to the predicted key indicators such as pressure and flow, such as adjusting the valve opening, optimizing the pressure regulating station settings, etc., to ensure the safe and stable operation of the pipeline network. By predicting the future operation status, potential safety hazards and risk points can be discovered in time, which helps managers take preventive measures in advance to avoid or reduce the occurrence of safety accidents such as gas leaks and pipeline ruptures, thereby ensuring public safety and environmental protection. Based on accurate prediction data, pipeline network operations can be carried out more efficiently. For example, by predicting the flow changes of each key node, gas resources can be reasonably dispatched to reduce unnecessary energy waste and operating costs. The introduction of machine learning technology has enabled intelligent management of pipeline network operations. The automated data collection, processing, and prediction process has reduced the burden of manual operations and improved work efficiency. At the same time, the intelligent prediction system can continuously learn and optimize to adapt to various changes and challenges in pipeline network operations. Considering the impact of meteorological conditions on pipeline network operations makes the prediction model more robust and reliable. Under different climatic conditions, the operating status of the pipeline network may change significantly. By combining meteorological data with operating data, the prediction model can better capture these changes and provide corresponding prediction results.

[0049] In a preferred embodiment of the present invention, the meteorological data is fused with the preliminary data set so that the pipe network operation data at each time point corresponds to the corresponding meteorological conditions to obtain a fused data set, including: Determine the number of pipe network operation data time points, set to M; determine the number of meteorological data time points, set to N; create a two-dimensional matrix with M rows and N columns to store the similarities between time points, including: For the pipeline operation data, traverse the entire data set and count the number of unique time points contained, set to M. These time points can be recorded at fixed intervals (such as every minute, every hour) or can be non-uniform; similarly, for meteorological data, count the number of unique time points it contains, set to N; use an appropriate data structure (such as an array, a list of lists, etc.) to initialize a two-dimensional matrix with M rows and N columns. This matrix will be used to store the similarity values ​​between the pipeline operation data time points and the meteorological data time points. M is the number of pipeline operation data time points, and N is the number of meteorological data time points; initially, all elements in the matrix can be set to a default value, such as 0 or infinity (indicating that it is not calculated or unreachable); after completing the above steps, a prepared two-dimensional matrix is ​​obtained, which will be used in the subsequent DTW algorithm to calculate and store the similarity between the pipeline operation data time points and the meteorological data time points.

[0050] Initially, all elements in the matrix are set to a default value; for each time point of the network operation data, it is set to i; for each time point of the meteorological data, it is set to j; the initial distance is set to 0 at the upper left corner of the DTW matrix, i.e. the starting point; the first row and the first column of the DTW matrix are set to infinity, indicating the unreachability between the starting point and the remaining points; starting from the first time point i of the network operation data and the first time point j of the meteorological data, all time point pairs are traversed step by step; for each pair of time points (i, j), the corresponding network operation data parameters and meteorological data parameters are extracted; the Euclidean distance between the network operation data parameters and the meteorological data parameters is calculated, specifically including: The upper left corner element of the DTW matrix (i.e., the element in the first row and first column, corresponding to the starting time point of the pipe network operation data and meteorological data) is set to 0, indicating that the initial distance between the starting points is 0; all elements in the first row (except the starting point in the upper left corner) and the first column of the DTW matrix are set to infinity, which indicates the unreachability between the starting time point and the remaining time points, because in the matching process of the time series, the starting point can only correspond to the starting point, and no time point can be skipped; Starting from the first time point of the pipeline operation data (set as i=1) and the first time point of the meteorological data (set as j=1), all pairs of time points are traversed step by step. For each pair of time points (i, j), the data parameters corresponding to time point i (such as flow, pressure, etc.) are extracted from the pipeline operation data set, and the data parameters corresponding to time point j (such as temperature, humidity, etc.) are extracted from the meteorological data set. The Euclidean distance between the two data points is calculated. The Euclidean distance is a common similarity measure based on the straight-line distance of data points in multidimensional space. For each parameter, the square of its difference is calculated, and then the square differences of all parameters are added and the square root is taken to obtain the Euclidean distance. Use the calculated Euclidean distance and the rules in the DTW algorithm to update the value of position (i, j) in the current DTW matrix; the DTW algorithm takes into account the time distortion between time series, so the value of position (i, j) depends not only on the similarity of the current time point pair, but also on the similarity of its adjacent time point pairs. Specifically, the value of position (i, j) is calculated based on the values ​​of its three adjacent positions: the upper left corner (i-1, j-1), the left side (i, j-1), and the top side (i-1, j) and the Euclidean distance of the current time point pair; repeat the above process until all time point pairs (i, j) are traversed, where i ranges from 1 to M and j ranges from 1 to N.

[0051] According to the Euclidean distance between the pipe network operation data parameters and the meteorological data parameters and the values ​​of the adjacent cells filled in the DTW matrix, the value of the current cell is updated and moved to the next time point pair until all time point pairs are traversed; the final Euclidean distance value is found at the lower right corner of the DTW matrix, i.e. the end point, which represents the similarity between the entire pipe network operation data sequence and the entire meteorological data sequence, including: Starting from the upper left corner (starting point) of the DTW matrix, the value of this point has been set to 0. For each pair of time points (i, j), the Euclidean distance between the pipe network operation data parameters and the meteorological data parameters has been calculated; this Euclidean distance and the values ​​of the filled adjacent cells in the DTW matrix (i.e., the cells in the upper left corner, left, and top) are used to update the value of the current cell (i, j). The update rule takes the minimum value of the three adjacent cell values ​​in the upper left corner, left, and top, and then adds the Euclidean distance of the current time point pair. This is done to find a path with the minimum cumulative distance.

[0052] After updating the value of the current cell (i, j), move to the next time point pair, which usually means increasing i or j by 1, depending on the selected traversal strategy (such as traversal by row or column), and repeat the above process until all time point pairs are traversed, that is, the entire DTW matrix is ​​traversed; when all time point pairs are traversed and updated, the lower right corner of the DTW matrix, that is, the end point, will be reached. The value in this cell represents the similarity between the entire pipeline operation data sequence and the entire meteorological data sequence. Specifically, this value is the minimum cumulative distance from the starting point to the end point, taking into account the time distortion between time series. The smaller the similarity value, the more similar the two time series are; the larger the value, the greater the difference between them. This value can be used to evaluate the degree of association between pipeline operation data and meteorological data, or to compare the similarity of data in different time periods.

[0053] Fill the similarity between i and j into the corresponding position of the two-dimensional matching matrix, that is, the i-th row and the j-th column; create a dynamic programming table of the same size as the two-dimensional matching matrix; starting from the upper left corner, gradually fill each element in the dynamic programming table. The value of each element represents the minimum cumulative similarity from the starting point to the current position, including: According to the above two-dimensional matching matrix, its size is M rows and N columns, where M is the number of time points of the pipeline operation data and N is the number of time points of the meteorological data. For each pair of time points (i, j), the similarity (Euclidean distance) between the pipeline operation data and the meteorological data has been calculated; this similarity value is filled into the i-th row and j-th column of the two-dimensional matching matrix, so that each element in the two-dimensional matching matrix represents the similarity between the corresponding time point pairs; create a dynamic programming table of the same size as the two-dimensional matching matrix, that is, a table of M rows and N columns. This dynamic programming table will be used to store the minimum cumulative similarity from the starting point (upper left corner) to each position (i, j).

[0054] Set the upper left corner element of the dynamic programming table (corresponding to the starting point) to 0, indicating that the cumulative similarity from the starting point to the starting point is 0. Starting from the upper left corner of the dynamic programming table, gradually fill each element to the lower right. For each position (i, j), the calculation of its minimum cumulative similarity is based on the values ​​of the following three adjacent positions: the upper left corner (i-1, j-1), the left side (i, j-1) and above (i-1, j), select the value with the smallest cumulative similarity among these three adjacent positions, then add the similarity of the current position (i, j) (obtained from the two-dimensional matching matrix) to obtain the minimum cumulative similarity of the current position, fill this minimum cumulative similarity into the current position (i, j) of the dynamic programming table, and repeat the above process until all positions in the dynamic programming table are filled. In the filling process, a minimum cumulative similarity path from the starting point to each position is actually constructed; when the dynamic programming table is filled, the element in the lower right corner represents the minimum cumulative similarity between the entire pipeline operation data sequence and the entire meteorological data sequence. This value can be used as a measure of the similarity between the two time series for subsequent data analysis, comparison or classification tasks.

[0055] The value of the current position is updated according to the minimum cumulative similarity of the previous position and the similarity of the current position. Starting from the lower right corner of the dynamic planning table, it is gradually traced back to the upper left corner. During the traceback process, the grid path passed is recorded, which is the final matching path between the pipe network operation data time point and the meteorological data time point, including: The starting point of backtracking is the lower right corner of the dynamic programming table, that is, the intersection of the last pipe network operation data time point and the last meteorological data time point. Record the position of this point, which will be the end point of the matching path; start from the lower right corner of the dynamic programming table, check the value of the current position and its possible previous position (upper left corner, left side and top); according to the DTW filling rule, the one with the smallest value among the three positions of upper left corner, left side and top is usually selected as the next point of backtracking. This is because when the DTW algorithm fills the dynamic programming table, the value of each cell is calculated based on the minimum value of its adjacent cells plus the similarity of the current cell. After the next point to be traced back is determined, it is recorded as part of the matching path, which means adding the time point pair of the current position (the time point of the pipeline operation data and the time point of the meteorological data) to the matching path list, moving to the previous position determined in the previous step, and repeating the above process to continue to find and record the points on the backtracking path. During the backtracking process, the previous position that results in the minimum cumulative similarity is always selected; backtracking is continued until the upper left corner (starting point) of the dynamic programming table is reached. In this process, a complete grid path from the lower right corner to the upper left corner is obtained. This path is the final matching path of the time point of the pipeline operation data and the time point of the meteorological data. The final matching path represents the optimal alignment of the time points between the two time series. This path not only takes into account the similarity between the time points, but also ensures the minimization of the overall cumulative similarity through dynamic programming.

[0056] According to the final matching path, the meteorological data time point corresponding to each pipe network operation data time point is determined; for each matched pipe network operation data time point, it is merged with the corresponding meteorological data time point into one record to obtain a fused data set, which specifically includes: Create an empty result list or data frame to store the fused records, starting from the matching path obtained by DTW backtracking. This path is a list of time point pairs (pipeline operation data time points and meteorological data time points). Traverse this list and process each pair of matching time points one by one. For each pair of matching time points, extract all relevant data corresponding to the time point from the pipe network operation data set (such as flow, pressure, etc.), and at the same time, extract all relevant data corresponding to the time point from the meteorological data set (such as temperature, humidity, wind speed, etc.). Merge the data of the extracted pipe network operation data time point with the data of the corresponding meteorological data time point into one record. This can be achieved by creating a new dictionary or data row, which contains all the fields of the corresponding time points in the two data sets. Add the merged record to the previously prepared result list or data frame, and repeat the above steps until all time point pairs in the matching path are traversed. When all matching time point pairs are processed and added to the result list, this list represents the fused data set.

[0057] In an embodiment of the present invention, by matching meteorological data with pipeline network operation data, the relationship between pipeline network operation status and meteorological conditions can be analyzed more accurately. This fused data set helps to reveal the direct impact of meteorological factors on the operation status of the pipeline network, thereby improving the accuracy of pipeline network performance evaluation. Based on the fused data set, decision makers can have a more comprehensive understanding of the operation status of the pipeline network under specific meteorological conditions, so as to make more reasonable resource allocation, maintenance plans and emergency response decisions. Using historical fused data, a more accurate prediction model can be built to predict the operation status of the pipeline network under different meteorological conditions, which helps to prevent potential problems and plan in advance. By analyzing the fused data, the bottlenecks and optimization points of pipeline network operation can be found, thereby improving the operational efficiency of the entire pipeline network. Meteorological conditions are one of the important factors affecting pipeline network operation. Through data fusion, pipeline network risks under severe weather conditions can be identified and evaluated, so that preventive measures can be taken to reduce the possibility of accidents.

[0058] In a preferred embodiment of the present invention, a preliminary configuration scheme is generated according to the prediction results, including: Identify parameters important to the operation of the pipeline network from the prediction results, including: conducting a comprehensive data analysis of the prediction results, including checking the pressure prediction values ​​and flow prediction values ​​of each node and their changing trends over time. By analyzing the data, identify parameters that are critical to the operation of the pipeline network. These key parameters include the pressure peak of a specific node, seasonal changes in flow, or the performance of certain nodes under specific meteorological conditions. Pay special attention to areas that are significantly affected by meteorological conditions (such as temperature, wind speed, and humidity), and record the changes in pipeline network performance in these areas under different meteorological conditions.

[0059] According to the operational needs of gas companies, the configuration plan objectives are set, including: determining the company's operational needs and objectives, which may include improving gas supply stability, reducing energy loss, optimizing operating costs, etc. Based on demand assessment, clear and quantifiable configuration objectives are set. For example, setting the pressure fluctuation range of key nodes, improving the gas supply reliability in specific areas, etc.

[0060] Based on the parameters important to the operation of the pipeline network and the set configuration goals, a preliminary configuration plan is constructed; the parameters of the preliminary configuration plan include the pressure set values ​​and flow distribution of the pipeline network nodes; the parameters important to the operation of the pipeline network include the pressure and flow change trends of the key nodes, and the areas affected by meteorological conditions, specifically including: combining the identified key parameters and the set goals, designing a preliminary configuration plan framework, which covers the pressure set values, flow distribution strategies and adjustment measures for different meteorological conditions for each key node in the pipeline network; according to the historical data and forecast results of the key nodes, a reasonable pressure range is set for each node to ensure that these set values ​​can meet the gas supply demand without causing excessive pressure on the pipeline network; according to the flow forecast results and the operational needs of the enterprise, a flow distribution strategy is formulated, which involves adjusting the gas supply in different areas to ensure that the flow can be effectively distributed during peak demand periods or under specific meteorological conditions, and special response measures are formulated for areas affected by meteorological conditions. For example, in hot weather, it may be necessary to increase the gas supply in certain areas to ensure that user needs are met; in extreme weather conditions, it may be necessary to adjust the operation strategy of the pipeline network to ensure safety; use historical data to verify the preliminary configuration plan, check whether the plan can achieve the set goals, and identify possible problems. Based on the results of the simulation test, adjust and optimize the plan, which may involve modifying the pressure set values ​​of certain nodes, adjusting the flow distribution strategy, or improving measures to deal with meteorological conditions.

[0061] In an embodiment of the present invention, by accurately configuring the pressure and flow of the pipeline nodes, unnecessary energy loss can be reduced, thereby improving the operating efficiency of the entire pipeline network. A reasonable configuration scheme can reduce the risk of failure of the pipeline network due to pressure fluctuations or uneven flow, and enhance the stability and reliability of the system; adjusting the flow distribution according to the prediction results can ensure that resources can be effectively utilized and waste can be avoided during peak demand periods or when weather conditions are unfavorable. The pre-planned configuration scheme enables the pipeline network to quickly adjust its operating status when facing emergencies (such as extreme weather, equipment failure), improve response speed and coping capabilities, and extend the service life of the pipeline equipment by reducing unnecessary pressure fluctuations and flow shocks, thereby reducing long-term maintenance costs.

[0062] In a preferred embodiment of the present invention, the parameters of the preliminary configuration scheme are encoded as "genes" through a genetic algorithm, and a set of initial "populations", i.e., multiple possible configuration schemes, are created; the population is iteratively evolved, and in each iteration, the fitness of each individual is evaluated; the corresponding individuals are selected for crossover to generate a new population, and after multiple iterations, the final configuration scheme is obtained, which may include: The parameters of the preliminary configuration scheme (such as the pressure setting value and flow distribution of the pipeline network node) are encoded as "genes" in the genetic algorithm, which is achieved by converting continuous parameter values ​​into discrete binary, integer or floating point number sequences; the parameter set of each configuration scheme (i.e. a set of specific pressure and flow values) is encoded as a "gene string" or "chromosome", representing an individual in the genetic algorithm; based on the scale and complexity of the problem, a set of initial "populations" is randomly generated, each individual is a possible configuration scheme, represented by a randomly generated gene string; ensure that the initial population has sufficient diversity to cover different areas of the solution space, thereby increasing the possibility of finding the global optimal solution; Define a fitness function to evaluate the quality of each individual (i.e., configuration scheme); for each individual in the population, use the fitness function to calculate its fitness value, which will serve as the basis for the probability of the individual being selected in the selection process; according to the fitness value of the individual, use a selection mechanism (such as roulette selection, tournament selection, etc.) to select the individuals that will participate in the next generation of reproduction. Individuals with higher fitness have a greater probability of being selected, and a portion of the individuals with the highest fitness (i.e., elite individuals) can be selectively retained to ensure that they can be directly passed on to the next generation, thereby accelerating the convergence of the algorithm; randomly select a pair of individuals in the population as parents, and randomly determine one or more crossover points, which will be used to exchange the genetic information of both parents. Through the crossover operation, the genetic characteristics of both parents are combined to generate a new individual (i.e., offspring). This new individual inherits certain characteristics of both parents and may have better fitness.

[0063] A smaller mutation probability is set (this probability value is usually very small, such as 0.01 or 0.001, to ensure that mutations do not occur too frequently, thereby maintaining the stability of the population) to introduce new gene mutations during the reproduction process, which helps to increase the diversity of the population and prevent the algorithm from falling into a local optimal solution too early. The gene values ​​of certain individuals are randomly changed with a certain probability to introduce a new search direction. The steps are repeated until the termination condition is met. In each iteration, a new population is generated and its fitness is evaluated to find a better configuration scheme. A maximum number of iterations is set. When the maximum number of iterations is reached or an individual that meets the fitness threshold is found, the algorithm stops running. After the algorithm terminates, the individual with the highest fitness is selected from the current population as the final configuration scheme, and the gene string of the optimal individual is decoded back to the actual parameter value (such as the pressure and flow setting value), and the final configuration scheme is implemented according to these parameters.

[0064] The calculation formula of the fitness function is: ; in, is the fitness value, the larger the value, the better the configuration scheme; is the economic cost of running the network; is the penalty item for violating the constraints of the pipeline network operation; , , and is the weight coefficient, which is used to balance the influence of each item; represents the actual pressure value of the i-th node; represents the target pressure value of the i-th node; Indicates the total number of nodes in the network, used to measure the deviation between the network node pressure and the target pressure. The smaller the deviation, the higher the fitness. Indicates The actual flow value of the pipeline; Indicates The target flow value of the pipeline; Represents the total number of pipes in the pipe network.

[0065] ; in, Indicates The construction cost per unit length of the pipeline; represents the length of the kth pipeline; Indicates The unit time operating cost of each device; Indicates The operating time of each device; Indicates the total number of pipes in the network; Represents the total number of devices in the pipe network.

[0066] ; in, represents the maximum allowable pressure of the ith node; Indicates The maximum allowable flow of each pipeline is set to penalize the configuration scheme that violates the operation constraints of the pipeline network. The higher the degree of violation, the greater the penalty and the lower the fitness. represents the actual pressure value of the i-th node; Indicates The actual flow value of the pipeline; n represents the total number of nodes in the pipeline network; m represents the total number of pipelines in the pipeline network; i represents the index of the node, with a value range of 1≤i≤n, which is used to traverse all nodes in the pipeline network; Represents the index of the pipeline, with a value range of 1≤j≤m, and is used to traverse all pipelines in the network.

[0067] The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. An analysis system for gas enterprise operation management, characterized in that: include: The data acquisition module is used to obtain the operating parameters of key nodes of the gas transmission and distribution network, the gas consumption data of the user terminal and the meteorological data of the environmental monitoring point in real time and pre-process them to obtain pre-processed data; A data processing module, for generating a three-dimensional model of a gas transmission and distribution network using preprocessed data; Based on the three-dimensional model, the machine learning prediction model is used to predict the future operation status of the gas transmission and distribution network to obtain the prediction results, which include the layout of the network, the location of key nodes, and the relationship with meteorological conditions; based on the prediction results, a preliminary configuration plan is generated; The optimization module is used to encode the parameters of the preliminary configuration scheme as "genes" through the genetic algorithm and create a set of initial "populations", that is, multiple possible configuration schemes; iteratively evolve the population, and in each iteration, evaluate the fitness of each individual; select the corresponding individuals for crossover to generate a new population, and after multiple iterations, obtain the final configuration scheme.

2. The analysis system for gas enterprise operation management according to claim 1, characterized in that: Using preprocessed data, a 3D model of the gas transmission and distribution network is generated, including: Each pipe network node is regarded as a particle, and the position of the particle is initialized as a combination of two-dimensional coordinates and elevation data. A velocity vector is assigned to each particle, and the initial velocity is set to zero, indicating the moving direction and speed of the particle in three-dimensional space. Define the fitness function, which is used to evaluate the position of each particle, that is, the node in the three-dimensional space; In each iteration, the fitness value of each particle is evaluated according to the fitness function, and the speed and position of the particle are updated. After the iteration of the particle swarm optimization algorithm is completed, the final optimized particle position is mapped to the three-dimensional space to determine the position of each node in the three-dimensional coordinate system; Create a 3D pipe network element model, including pipes, valves and joints, based on the position of each node in the 3D coordinate system and known pipe information; According to the actual connection relationship between the pipe network elements, the various elements are assembled into a three-dimensional pipe network model.

3. The analysis system for gas enterprise operation management according to claim 2, characterized in that: Based on the three-dimensional model, the machine learning prediction model is used to predict the future operation status of the gas transmission and distribution network to obtain the prediction results. The prediction results include the layout of the pipeline network, the location of key nodes, and the relationship with meteorological conditions, including: Extract the pipe network layout information from the 3D model, including the length, diameter, material and connection method of the pipes; determine and extract the key node locations in the pipe network, which are branch points, control valves or pressure regulating stations; Acquire and process historical operating data of key nodes, including pressure, flow and temperature data; Obtain real-time meteorological data related to gas transmission and distribution from environmental monitoring points, including temperature, humidity, wind speed and direction, so that the real-time meteorological data can be matched with the timestamps of the pipeline network operation data; The network layout information and key node location data extracted from the 3D model are integrated with the historical operation data to form a preliminary data set; The meteorological data are fused with the preliminary data set so that the pipeline network operation data at each time point correspond to the corresponding meteorological conditions to obtain a fused data set; Preprocess the fused data set and divide the preprocessed data set into a training set, a validation set, and a test set; Use the training set to train the neural network model, and adjust the hyperparameters of the neural network model to optimize the performance of the neural network model; use the validation set to evaluate the performance of the neural network model during the training process to obtain the final prediction model; Input the current three-dimensional model data and real-time environmental meteorological data into the final prediction model to obtain the predicted operating status of each key node of the pipeline network in the future, including the predicted values ​​of pressure and flow.

4. The analysis system for gas enterprise operation management according to claim 3, characterized in that: The meteorological data are fused with the preliminary data set so that the network operation data at each time point corresponds to the corresponding meteorological conditions to obtain a fused data set, including: Determine the number of time points of pipeline operation data, set to M; determine the number of time points of meteorological data, set to N; create a two-dimensional matrix with M rows and N columns to store the similarities between time points; Initially, all elements in the matrix are set to a default value; For each time point of the pipe network operation data, set it to i; for each time point of the meteorological data, set it to j; set the initial distance to 0 at the upper left corner of the DTW matrix, i.e. the starting point; set the first row and the first column of the DTW matrix to infinity, indicating the unreachability between the starting point and the remaining points; starting from the first time point i of the pipe network operation data and the first time point j of the meteorological data, gradually traverse all pairs of time points; for each pair of time points (i, j), extract the corresponding pipe network operation data parameters and meteorological data parameters; calculate the Euclidean distance between the pipe network operation data parameters and the meteorological data parameters; According to the Euclidean distance between the pipe network operation data parameters and the meteorological data parameters and the values ​​of the adjacent cells filled in the DTW matrix, the value of the current cell is updated and moved to the next time point pair until all time point pairs are traversed; The final Euclidean distance value is found at the lower right corner of the DTW matrix, i.e. the end point, which represents the similarity between the entire pipeline network operation data sequence and the entire meteorological data sequence; Fill the similarity between i and j into the corresponding position of the two-dimensional matching matrix, i.e., row i, column j; create a dynamic programming table of the same size as the two-dimensional matching matrix; starting from the upper left corner, gradually fill each element in the dynamic programming table, and the value of each element represents the minimum cumulative similarity from the starting point to the current position; Update the value of the current position according to the minimum cumulative similarity of the previous position and the similarity of the current position, starting from the lower right corner of the dynamic planning table and gradually backtracking to the upper left corner. During the backtracking process, record the grid path passed, which is the final matching path between the pipe network operation data time point and the meteorological data time point; According to the final matching path, determine the meteorological data time point corresponding to each pipe network operation data time point; For each matched pipe network operation data time point, it is merged with the corresponding meteorological data time point into one record to obtain a fused data set.

5. The analysis system for gas enterprise operation management according to claim 4, characterized in that: Based on the prediction results, a preliminary configuration plan is generated, including: Identify parameters important to the operation of the network from the prediction results; Set the goals of the configuration plan according to the operational needs of the gas company; Construct a preliminary configuration plan based on the parameters important to the operation of the pipeline network and the set configuration goals.

6. The analysis system for gas enterprise operation management according to claim 5, characterized in that: The parameters of the preliminary configuration plan include the pressure set points and flow distribution of the pipeline network nodes.

7. The analysis system for gas enterprise operation management according to claim 6, characterized in that: Parameters important to pipeline network operation include pressure at key nodes, flow rate trends, and areas affected by meteorological conditions.

8. An analysis method for gas enterprise operation management, characterized in that: The method is used to execute the system according to any one of claims 1 to 7, and the method comprises: Real-time acquisition of operating parameters of key nodes of the gas transmission and distribution network, gas consumption data of user terminals, and meteorological data of environmental monitoring points, and pre-processing to obtain pre-processed data; Using the preprocessed data, a three-dimensional model of the gas transmission and distribution network is generated; based on the three-dimensional model, a machine learning prediction model is used to predict the future operation status of the gas transmission and distribution network to obtain prediction results, including the layout of the network, the location of key nodes, and the relationship with meteorological conditions; based on the prediction results, a preliminary configuration plan is generated; The parameters of the preliminary configuration scheme are encoded as "genes" through the genetic algorithm, and an initial set of "populations", that is, multiple possible configuration schemes, are created; the population is iteratively evolved, and in each iteration, the fitness of each individual is evaluated; the corresponding individuals are selected for crossover to generate a new population, and after multiple iterations, the final configuration scheme is obtained.

9. A computing device, characterized in that include: one or more processors; A storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement the method according to claim 8.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a program, which implements the method according to claim 8 when executed by a processor.

Images