A maintenance management system for gas utility equipment

Abstract

This invention discloses a maintenance and management system for gas facilities and equipment, relating to the field of gas equipment management technology. It includes: an information acquisition module for real-time acquisition of operational data from gas facilities and equipment; a fault-prone equipment identification module for cluster analysis of historical maintenance records to identify fault-prone equipment; an equipment status assessment module for constructing an equipment status assessment model, inputting the real-time acquired operational data from the gas facilities and equipment into the model to obtain the current failure probability of the equipment; a maintenance management module for calculating the maintenance priority of each gas facility and equipment, sorting maintenance tasks from highest to lowest priority, and executing them in the sorted order; and a path planning module for using a path planning algorithm to output optimal path information and executing tasks according to the planned optimal path, thus achieving comprehensive and precise management of gas facilities and equipment.

Description

Technical Field

[0001] This invention relates to the field of gas equipment management technology, specifically to a maintenance and management system for gas facilities and equipment. Background Technology

[0002] With the acceleration of urbanization and the continuous increase in gas consumption, the maintenance of gas facilities and equipment has become increasingly important. Gas facilities and equipment, such as pressure regulating boxes and valve wells, are important components of the urban gas supply system, and their safe and stable operation is directly related to the safety of residents' lives and industrial production.

[0003] Traditional maintenance methods for gas facilities and equipment mainly rely on manual inspections and periodic maintenance. While manual inspections can detect some obvious faults and safety hazards, they are often limited by the experience and sense of responsibility of the inspectors, making it difficult to discover some potential and hidden faults. At the same time, while periodic maintenance can prevent faults from occurring to some extent, the setting of maintenance cycles and contents often lacks scientific basis, resulting in low maintenance efficiency and high maintenance costs.

[0004] Furthermore, with the rapid development of IoT technology, gas facilities and equipment have gradually achieved intelligent monitoring and remote control. By installing various IoT sensors, real-time data on equipment operation and environmental parameters can be collected, providing rich data support for equipment maintenance. However, how to effectively utilize this data to achieve intelligent maintenance of equipment remains an important issue. Summary of the Invention

[0005] (a) Technical problems to be solved To address the shortcomings of existing technologies, this invention provides a maintenance and management system for gas facilities and equipment. Through intelligent and information-based means, it enables real-time monitoring, fault early warning, and maintenance task optimization of gas facilities and equipment, thereby improving maintenance efficiency and safety. This system combines various advanced technologies such as Internet of Things (IoT), data analysis, and path planning algorithms to achieve comprehensive and precise management of gas facilities and equipment, providing strong support for the safe and stable operation of urban gas supply systems.

[0006] (II) Technical Solution To achieve the above objectives, the present invention provides the following technical solution: a maintenance and management system for gas facilities and equipment, comprising: The information collection module assigns a unique identification code to each gas facility and equipment and collects the operating data of the gas facility and equipment in real time. The fault-prone equipment identification module extracts historical maintenance records from the database and uses... K-means++The algorithm performs cluster analysis on historical maintenance records to identify and label equipment prone to failure. The equipment status assessment module constructs an equipment status assessment model. The real-time collected operating data of the gas facility equipment is input into the equipment status assessment model to obtain the current failure probability of the equipment. If the failure probability is greater than 0.5, the equipment is considered to be about to fail. If the failure probability is less than or equal to 0.5, the equipment is considered to be in normal condition. The maintenance management module constructs a network diagram of gas facilities and equipment, calculates the betweenness centrality of each gas facility and equipment, and calculates the maintenance priority of each gas facility and equipment based on the failure probability and whether it is a fault-prone device. According to the maintenance priority of each gas facility and equipment, the maintenance tasks are sorted from largest to smallest and executed in the sorted order. The path planning module obtains a list of all maintenance tasks to be executed and the real-time location information of maintenance personnel. Using the A* path planning algorithm, it takes the current location of the maintenance personnel, the location of the target gas facility and equipment, and map information as input, and outputs the optimal path information to execute the task according to the planned optimal path.

[0007] Furthermore, various IoT sensors are installed on gas facility equipment. RFID Tags, including pressure sensors, temperature sensors, gas leak detection sensors, and vibration sensors; utilize installed IoT sensors to collect real-time operational data from gas facility equipment. RFID The information of the label is transmitted through RFID The reading device reads and transmits data; through... GIS The software labels and records the geographical location information of the equipment, and associates and integrates the geographical location information of the gas facility equipment with the identification code and sensor data of the gas facility equipment.

[0008] Furthermore, use K-means++ The algorithm performs cluster analysis on historical maintenance records, specifically including: S1: Use K-means++ Algorithm Initialization K Cluster centers; S2: Calculate the result for each data point. K The distance between each cluster center is used to assign data points to the nearest cluster center. The distance calculation formula is as follows: ,in, d This represents the distance from a data point to its cluster center. Indicates the first i The coordinates of each data point Indicates the first k The coordinates of the cluster centers; S3: Recalculate the center of each cluster, using the average of all data points in each cluster as the new cluster center. The calculation formula is as follows: ,in, n Clustering The number of data points in the middle, Indicates the first k One cluster, The coordinates of the new cluster centers; S4: Repeat steps S2 and S3 until the cluster centers no longer change or the preset number of iterations is reached.

[0009] Furthermore, operational data of gas facilities and equipment are acquired, including but not limited to pressure, temperature, gas leak detection, and vibration. Feature values ​​are extracted from the operational data, including but not limited to pressure change rate, temperature fluctuation range, gas leak rate, and vibration intensity. A logistic regression model is used to construct an equipment condition assessment model, and the operational data of the gas facilities and equipment is used as a training set to train the equipment condition assessment model.

[0010] Further, equipment condition assessment model: ,in, P Indicates the probability of failure. e It is a natural constant. z This represents the linear part of the evaluation model. Represents the intercept term. Represents the characteristic coefficients. Indicates the extracted feature values. m Indicates the number of eigenvalues.

[0011] Furthermore, by using GIS technology, gas facilities and equipment and their connections are accurately marked on a map to form a network diagram of gas facilities and equipment. Nodes in the network diagram represent gas facilities and equipment, and edges represent the connections between gas facilities and equipment. The betweenness centrality of each node is calculated using the following formula: ,in, Represents a node v betweenness centrality, Indicates from node s To the node t The number of shortest paths, Indicates from node s To the node t The shortest path passes through the nodes v The quantity.

[0012] Furthermore, the betweenness centrality, failure probability, and whether it is a fault-prone device for each gas facility are obtained. The maintenance priority of each gas facility is calculated. Based on the maintenance priority of each gas facility, the maintenance tasks are sorted from highest to lowest and executed in the sorted order.

[0013] Furthermore, the formula for calculating maintenance priority is as follows: ,in, Indicates the first j Maintenance priority for individual gas facilities and equipment Indicates the first j Betweenness centrality of individual gas facilities and equipment Indicates the first j The probability of failure of individual gas facility equipment Indicates the first j Is the gas facility equipment prone to failure? No, Therefore, , as well as This represents the weighting coefficient.

[0014] Further, choose A* The path planning algorithm defines its objective function as minimizing the total path length from the current location to the target gas facility and back. A* Heuristic function of the algorithm: ,in, f(q) Represents a node q Total cost g(q) Indicates the distance from the starting point to the node. q The actual cost h(q) Indicates from node q Heuristic cost estimation to the destination.

[0015] Furthermore, the system inputs the current location of the maintenance personnel, the location of the target gas facility and equipment, and map information. The algorithm then calculates the optimal path from the starting point to the destination and outputs the optimal path information, including the path length and the nodes traversed. The maintenance personnel then execute the task according to the planned optimal path.

[0016] A method for maintenance and management of gas facilities and equipment includes the following steps: Step 1: Assign a unique identification code to each gas facility and collect its operating data in real time; Step 2: Retrieve historical maintenance records from the database, using... K-means++ The algorithm performs cluster analysis on historical maintenance records to identify and label equipment prone to failure. Step 3: Construct an equipment status assessment model. Input the real-time collected operating data of the gas facility equipment into the equipment status assessment model to obtain the current failure probability of the equipment. If the failure probability is greater than 0.5, the equipment is considered to be about to fail. If the failure probability is less than or equal to 0.5, the equipment is considered to be in normal condition. Step 4: Construct a network diagram of gas facility equipment, calculate the betweenness centrality of each gas facility equipment, and calculate the maintenance priority of each gas facility equipment based on the failure probability and whether it is a fault-prone device. According to the maintenance priority of each gas facility equipment, sort the maintenance tasks from largest to smallest and execute them in the sorted order. Step 5: Obtain the list of all maintenance tasks to be executed and the real-time location information of maintenance personnel. Using the A* path planning algorithm, input the current location of the maintenance personnel, the location of the target gas facility and equipment, and map information, and output the optimal path information. Execute the task according to the planned optimal path.

[0017] (III) Beneficial Effects This invention provides a maintenance and management system for gas facilities and equipment, which has the following beneficial effects: (1) By constructing an equipment status assessment model and training it with equipment status data from historical maintenance records, the probability of equipment failure can be predicted more accurately, which helps relevant personnel to take timely measures to avoid the occurrence or expansion of failures, thereby ensuring the safe operation of gas facilities.

[0018] (2) By constructing a network diagram of gas facility equipment, managers can quickly understand the overall structure of the equipment network. Using the betweenness centrality algorithm, the equipment that plays a key role in the network can be identified. By combining the failure probability of the equipment and whether it is a faulty equipment, the maintenance priority of each equipment can be more accurately assessed, and maintenance tasks can be performed in order of priority to ensure that limited maintenance resources are used most reasonably.

[0019] (3) By constructing an equipment status assessment model and training it with equipment status data from historical maintenance records, the probability of equipment failure can be predicted more accurately, which helps relevant personnel to take timely measures to avoid the occurrence or expansion of failures, thereby ensuring the safe operation of gas facilities.

[0020] (4) The optimal path calculated by the path planning algorithm enables maintenance personnel to quickly reach the task location, reducing the time spent on the road and thus improving the efficiency of the overall maintenance work. It takes into account factors such as the actual road network and obstacles, avoids unnecessary detours, and further shortens the path length. Attached Figure Description

[0021] Figure 1This is a schematic diagram of the maintenance and management system for gas facilities and equipment according to the present invention; Figure 2 This is a schematic diagram of the gas facility equipment network of the present invention; Figure 3 This is a schematic diagram illustrating the steps of the maintenance and management method for gas facilities and equipment according to the present invention. Detailed Implementation

[0022] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0023] Please see Figure 1 - Figure 2 This invention provides a maintenance and management system for gas facility equipment, comprising: an information acquisition module, a fault-prone equipment identification module, an equipment status assessment module, a maintenance management module, and a route planning module; wherein, The information acquisition module assigns a unique identifier to each device and collects the device's operating data and environmental parameters in real time. Specifically, a unique QR code is generated for each key piece of equipment such as a gas pressure regulating box and valve well through a dedicated identification code generation system. This QR code is then printed and affixed to a prominent location on the equipment. Based on the type of equipment and operational requirements, appropriate sensor models and installation locations are selected. Various IoT sensors, including pressure sensors, temperature sensors, gas leak detection sensors, and vibration sensors, are installed on the equipment. Appropriate RFID tag models are selected and affixed to suitable locations on the equipment to ensure that the reading range of the RFID tags can cover the surrounding area of ​​the equipment, so as to facilitate the rapid reading of equipment information during inspections and maintenance. By utilizing installed IoT sensors, real-time data collection of equipment operation and environmental parameters is achieved. Information from RFID tags is read and transmitted through dedicated RFID reading devices. GIS software or platforms are used to mark and record the geographical location information of the equipment (such as latitude and longitude coordinates). At the same time, the geographical location information of the equipment is associated and integrated with other information of the equipment (such as identification codes, sensor data, etc.) so as to intuitively display the distribution and status of the equipment on a map. Based on the equipment's operating specifications and safety standards, and combined with historical data and expert experience, an emergency threshold is set for the data collected by each sensor. When the sensor data exceeds or falls below the set emergency threshold, an emergency maintenance task is triggered. A notification mechanism is configured after the emergency maintenance task is triggered, and relevant personnel are promptly notified for handling via SMS, email, APP push, etc. For example, for pressure sensors, a maximum pressure threshold and a minimum pressure threshold can be set. When the equipment pressure exceeds or falls below these thresholds, an emergency maintenance task will be automatically triggered.

[0024] By assigning a unique identifier to each device and installing IoT sensors to collect operational data and environmental parameters in real time, real-time monitoring of device status is achieved. This real-time monitoring capability enables the system to promptly detect abnormal conditions in the devices, thereby triggering emergency maintenance tasks. This avoids potential delays and omissions that may occur with traditional manual inspections and periodic maintenance methods, improving the accuracy and timeliness of maintenance.

[0025] The fault-prone equipment identification module extracts historical maintenance records from the database and uses... K-means++ The algorithm performs cluster analysis on historical maintenance records to identify and label equipment prone to failure. Specifically, historical maintenance records are extracted from the database. These records should include, but are not limited to, maintenance time, maintenance type (such as preventive maintenance, corrective maintenance, etc.), cause of failure, equipment or components involved, maintenance personnel, maintenance cost, and post-maintenance status. The extracted data is cleaned to remove duplicate, erroneous, or incomplete data records to ensure the accuracy and consistency of the data. use K-means++ The algorithm performs cluster analysis on historical maintenance records, specifically including the following steps: S1: Select an appropriate number of clusters based on the quantity and distribution of historical maintenance records. K For example, use visualization tools such as scatter plots, histograms, or box plots to observe the distribution and characteristics of the data, noting whether there are multiple obvious groups in the data, such as certain equipment types or fault types occurring frequently. Based on the observation of the data distribution and domain knowledge, initially select an initial value (e.g., ...). K =3) as the number of clusters, used K-means++ Algorithm Initialization K There are 10 cluster centers, which are randomly selected, but the distribution of data points is taken into account during the selection process to ensure that the distance between the initial centers is as far as possible; S2: Calculate the result for each data point. KThe data points are then assigned to the nearest cluster centers based on the distance between them. The Euclidean distance can be used to calculate the distance from each data point to its nearest cluster center. For two-dimensional data points and cluster centers, the formula for calculating the Euclidean distance is: ,in, d This represents the distance from a data point to its cluster center. Indicates the first i The coordinates of each data point Indicates the first k The coordinates of the cluster centers; S3: Recalculate the center of each cluster, using the average of all data points in each cluster as the new cluster center. The formula for calculating the new cluster center for each cluster is as follows: ,in, n Clustering The number of data points in the middle, Indicates the first k One cluster, The coordinates of the new cluster centers; S4: Repeat steps S2 and S3 until the cluster centers no longer change or the preset number of iterations is reached; The silhouette coefficient is used to evaluate the quality of the clustering results. If the clustering results are not ideal (such as low clustering quality index or unstable clustering results), the K value is adjusted and steps S1 to S4 are repeated. When the clustering results are stable and the quality index is high, the final K value is determined.

[0026] Based on the clustering results, the total number of failures for all devices in each cluster is counted. The devices in the cluster with the most failures are marked as fault-prone devices. This is achieved by adding a new field or label to the database so that these devices or components can be given priority attention and handling during subsequent maintenance.

[0027] Cluster analysis of historical maintenance records can identify equipment or components that frequently fail. These equipment or components are marked as fault-prone equipment, allowing for focused attention and priority handling during subsequent maintenance. This helps optimize the allocation of maintenance resources, ensures that critical equipment and components receive timely and effective maintenance, and reduces downtime and repair costs caused by equipment failures.

[0028] The equipment status assessment module constructs an equipment status assessment model. Real-time collected equipment operation data is input into the equipment status assessment model to obtain the current failure probability of the equipment. If the failure probability is greater than 0.5, the equipment is considered to be about to fail. If the failure probability is less than or equal to 0.5, the equipment is considered to be in normal condition. Specifically, the system acquires operational data from key equipment such as pressure regulating boxes and valve wells, including parameters such as pressure, temperature, gas leak detection, and vibration. The operational data is preprocessed, including noise removal and missing value filling. Feature values ​​that reflect the operating status of the equipment, such as pressure change rate, temperature fluctuation range, gas leak rate, and vibration intensity, are extracted from the preprocessed data. A logistic regression model was chosen as the basis for the equipment condition assessment model. Equipment condition data (such as normal operation and failure) from historical maintenance records was used as the training set to train the model. The output of the logistic regression model is a probability value between 0 and 1, representing the probability of equipment failure. The formula is: ,in, P Indicates the probability of failure. e It is a natural constant. z This represents the linear part of the evaluation model. Represents the intercept term. Represents the characteristic coefficients. Indicates the extracted feature values. m Indicates the number of eigenvalues; The real-time collected equipment operation data is input into the trained equipment status assessment model to obtain the current failure probability of the equipment. If the failure probability is greater than 0.5, the equipment is considered to be about to fail. If the failure probability is less than or equal to 0.5, the equipment is considered to be in normal condition. By constructing an equipment condition assessment model and training it with equipment condition data from historical maintenance records, the probability of equipment failure can be predicted more accurately. This helps relevant personnel take timely measures to prevent the occurrence or escalation of failures, thereby ensuring the safe operation of gas facilities.

[0029] The maintenance management module constructs a network diagram of gas facility equipment, calculates the betweenness centrality of each device, and calculates the maintenance priority of each device by combining the failure probability and whether it is a fault-prone device. Based on the maintenance priority of each device, the maintenance tasks are sorted from largest to smallest and executed in the sorted order. Specifically, using GIS technology, gas facilities and equipment (such as pressure regulating boxes, valve wells, etc.) and their connections (such as pipelines) are accurately marked on a map to form a gas facility and equipment network diagram. Nodes in the network diagram represent equipment, and edges represent the connections between equipment (such as pipelines). The betweenness centrality algorithm is used to identify key nodes. Betweenness centrality measures the importance of a node as a "bridge" in the network, i.e., how many pairs of nodes a node lies on the shortest path between them. The formula is as follows: ,in, Represents a node v betweenness centrality, Indicates from nodes To the node t The number of shortest paths, Indicates from node s To the node t The shortest path passes through the nodes v Quantity; Obtain the betweenness centrality, failure probability, and whether it is a fault-prone device for each device. Calculate the maintenance priority for each device. Based on the maintenance priority of each device, sort the maintenance tasks from highest to lowest, and execute the maintenance tasks in the sorted order. The formula for calculating the maintenance priority is as follows: ,in, Indicates the first j Maintenance priority for each device Indicates the first j Betweenness centrality of each device Indicates the first j The probability of failure of each device Indicates the first j Is it a device prone to failure? No, Therefore, , as well as Indicates the weighting coefficient; It should be noted that the sum of the weighting coefficients should be 1, that is... The specific value of the weighting coefficient should be determined based on the actual situation, equipment type, system requirements, and maintenance strategy. For example, if betweenness centrality has a significant impact on system stability, or if it is desirable to prioritize the protection of equipment that plays a critical role in the network, then the weighting coefficient can be adjusted accordingly. If the system is particularly sensitive to failure probability, or if you want to prioritize devices with a high failure probability, then you can set it to a higher level. If setting it to a high level is crucial for identifying equipment prone to failure, or if you want to focus specifically on equipment known to be prone to malfunction, then you can... Set too high; By constructing a network diagram of gas facility equipment, managers can quickly understand the overall structure of the equipment network. Using the betweenness centrality algorithm, they can identify equipment that plays a key role in the network. By combining the failure probability of the equipment and information on whether it is a fault-prone equipment, they can more accurately assess the maintenance priority of each equipment and execute maintenance tasks in order of priority, ensuring that limited maintenance resources are used most rationally.

[0030] The path planning module obtains a list of all maintenance tasks to be executed and the real-time location information of maintenance personnel. Using the A* path planning algorithm, it outputs the optimal path information and executes the tasks according to the planned optimal path.

[0031] Specifically, obtain a list of all maintenance tasks to be executed, including task location (latitude and longitude coordinates), task type, urgency, and other information, and obtain the real-time location information of maintenance personnel through GPS or other positioning technologies; Select the A* path planning algorithm, set the algorithm parameters such as search range, number of iterations, mutation rate, etc., and define the objective function of path planning, which is to minimize the total path length of the maintenance personnel from the current location to the target device and back (or to the next task point). The heuristic function of the A* algorithm is as follows: Where f(q) represents the total cost of node q, g(q) represents the actual cost from the starting point to node q, and h(q) represents the heuristically estimated cost from node q to the destination (such as Euclidean distance). Input the starting point (the current location of the maintenance personnel), the ending point (the location of the target device), and map information (including road network, obstacles, etc.). Run the algorithm to calculate the optimal path from the starting point to the ending point and output the optimal path information, including the path length, nodes passed (intersections, road segments), etc. The maintenance personnel execute the task according to the planned optimal path. The optimal path calculated by the A* algorithm allows maintenance personnel to quickly reach the task location, reducing travel time and improving the overall efficiency of maintenance work. It takes into account factors such as the actual road network and obstacles, avoiding unnecessary detours and further shortening the path length.

[0032] Please see Figure 3 The present invention also provides a method for maintenance and management of gas facilities and equipment, comprising the following steps: Step 1: Assign a unique identification code to each gas facility and collect its operating data in real time; Step 2: Retrieve historical maintenance records from the database, using... K-means++ The algorithm performs cluster analysis on historical maintenance records to identify and label equipment prone to failure. Step 3: Construct an equipment status assessment model. Input the real-time collected operating data of the gas facility equipment into the equipment status assessment model to obtain the current failure probability of the equipment. If the failure probability is greater than 0.5, the equipment is considered to be about to fail. If the failure probability is less than or equal to 0.5, the equipment is considered to be in normal condition. Step 4: Construct a network diagram of gas facility equipment, calculate the betweenness centrality of each gas facility equipment, and calculate the maintenance priority of each gas facility equipment based on the failure probability and whether it is a fault-prone device. According to the maintenance priority of each gas facility equipment, sort the maintenance tasks from largest to smallest and execute them in the sorted order. Step 5: Obtain the list of all maintenance tasks to be executed and the real-time location information of maintenance personnel. Using the A* path planning algorithm, input the current location of the maintenance personnel, the location of the target gas facility and equipment, and map information, and output the optimal path information. Execute the task according to the planned optimal path.

[0033] In the application, the various formulas mentioned are all calculated by removing dimensions and taking their numerical values. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The coefficients in the formulas are set by those skilled in the art according to the actual situation.

[0034] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented in software, the above embodiments can be implemented, in whole or in part, as a computer program product. Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, and combinations thereof. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution.

[0035] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0036] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application.

Claims

1. A maintenance management system for gas utility equipment, characterized by: include: The information collection module assigns a unique identification code to each gas facility and equipment and collects the operating data of the gas facility and equipment in real time. A failure-prone device identification module extracts historical maintenance records from a database, uses K-means++ an algorithm to perform cluster analysis on the historical maintenance records, identifies failure-prone devices, and labels them; The equipment status assessment module constructs an equipment status assessment model. The real-time collected operating data of the gas facility equipment is input into the equipment status assessment model to obtain the current failure probability of the equipment. If the failure probability is greater than 0.5, the equipment is considered to be about to fail. If the failure probability is less than or equal to 0.5, the equipment is considered to be in normal condition. The maintenance management module constructs a network diagram of gas facilities and equipment, calculates the betweenness centrality of each gas facility and equipment, and calculates the maintenance priority of each gas facility and equipment based on the failure probability and whether it is a fault-prone device. According to the maintenance priority of each gas facility and equipment, the maintenance tasks are sorted from largest to smallest and executed in the sorted order. The path planning module obtains a list of all maintenance tasks to be executed and the real-time location information of maintenance personnel. Using the A* path planning algorithm, it takes the current location of the maintenance personnel, the location of the target gas facility and equipment, and map information as input, and outputs the optimal path information to execute the task according to the planned optimal path.

2. The maintenance and management system for gas facilities and equipment according to claim 1, characterized in that: Installing various IoT sensors on gas facility equipment and RFID Tags, IoT sensors include pressure sensors, temperature sensors, gas leak detection sensors, and vibration sensors; by using the installed IoT sensors, real-time operational data of gas facility equipment is collected. RFID The information of the label is transmitted through RFID The reading device reads and transmits data; through... GIS The software labels and records the geographical location information of the equipment, and associates and integrates the geographical location information of the gas facility equipment with the identification code and sensor data of the gas facility equipment.

3. The maintenance and management system for gas facilities and equipment according to claim 1, characterized in that: use K- means++ The algorithm performs cluster analysis on historical maintenance records, specifically including: S1: Use K-means++ Algorithm Initialization K Cluster centers; S2: Calculate the result for each data point. K The distance between each cluster center is used to assign data points to the nearest cluster center. The distance calculation formula is as follows: ,in, d This represents the distance from a data point to its cluster center. Indicates the first i The coordinates of each data point Indicates the first k The coordinates of the cluster centers; S3: Recalculate the center of each cluster, using the average of all data points in each cluster as the new cluster center. The calculation formula is as follows: ,in, n Clustering The number of data points in the middle, Indicates the first k One cluster, The coordinates of the new cluster centers; S4: Repeat steps S2 and S3 until the cluster centers no longer change or the preset number of iterations is reached.

4. The maintenance and management system for gas facilities and equipment according to claim 1, characterized in that: Acquire operational data of gas facilities and equipment, including but not limited to pressure, temperature, gas leak detection, and vibration; extract feature values ​​from the operational data, including but not limited to pressure change rate, temperature fluctuation range, gas leak rate, and vibration intensity; construct an equipment condition assessment model using a logistic regression model; and train the equipment condition assessment model using the operational data of the gas facilities and equipment as a training set.

5. The maintenance and management system for gas facilities and equipment according to claim 4, characterized in that: Equipment condition assessment model: ,in, P Indicates the probability of failure. e It is a natural constant. z This represents the linear part of the evaluation model. Represents the intercept term. Represents the characteristic coefficients. Indicates the extracted feature values. m Indicates the number of eigenvalues.

6. The maintenance and management system for gas facilities and equipment according to claim 1, characterized in that: Using GIS technology, gas facilities and equipment and their connections are marked on a map to form a gas facility and equipment network diagram. Nodes in the network diagram represent gas facilities and equipment, and edges represent the connections between gas facilities and equipment. The betweenness centrality of each node is calculated using the following formula: ,in, Represents a node v betweenness centrality, Indicates from node s To the node t The number of shortest paths, Indicates from node s To the node t The shortest path passes through the nodes v The quantity.

7. The maintenance and management system for gas facilities and equipment according to claim 6, characterized in that: Obtain the betweenness centrality, failure probability, and whether it is a fault-prone device for each gas facility. Calculate the maintenance priority for each gas facility. Sort the maintenance tasks from highest to lowest priority based on the maintenance priority of each gas facility and execute the maintenance tasks in the sorted order.

8. The maintenance and management system for gas facilities and equipment according to claim 7, characterized in that: The formula for calculating maintenance priority is as follows: ,in, Indicates the first j Maintenance priority for individual gas facilities and equipment Indicates the first j Betweenness centrality of individual gas facilities and equipment Indicates the first j The probability of failure of individual gas facility equipment Indicates the first j Is the gas facility equipment prone to failure? No, Therefore, , as well as This represents the weighting coefficient.

9. The maintenance and management system for gas facilities and equipment according to claim 1, characterized in that: choose A* The path planning algorithm defines its objective function as minimizing the total path length from the current location to the target gas facility and back. A* Heuristic function of the algorithm: ,in, f(q) Represents a node q Total cost g(q) Indicates the distance from the starting point to the node. q The actual cost h(q) Indicates from node q Heuristic cost estimation to the destination.

10. A maintenance and management system for gas facilities and equipment according to claim 9, characterized in that: Input the current location of the maintenance personnel, the location of the target gas facility and equipment, and map information. Run the algorithm to calculate the optimal path from the starting point to the destination, and output the optimal path information, including the path length and the nodes passed through. The maintenance personnel perform the task according to the planned optimal path.

Images