Intelligent monitoring method and system for flow state of gas pipeline

Abstract

The invention relates to the technical field of robustness artificial intelligence, and discloses an intelligent monitoring method and system for the flow state of a gas pipeline, and the method comprises the following steps: carrying out the grid division of a pipeline according to a construction layout diagram of the gas pipeline, and carrying out the leakage danger grade marking of the gas pipeline in each grid unit; for local gas pipelines in the grid units with different danger levels, the intensities of the installed sensor assemblies are different; the sensor assembly is used for collecting gas in the gas pipeline and equipment operation data; sensor data are collected, processed and transmitted through data acquisition and transmission equipment; determining geographical location information of an accident site by using positioning equipment; geographic information data support and path planning are provided by means of a geographic information system device. The system can be suitable for various installation environments and is high in monitoring accuracy.

Description

Technical Field

[0001] The present invention relates to the technical fields of robust artificial intelligence and gas pipeline monitoring, and in particular to a method and system for intelligently monitoring the flow status of a gas pipeline. Background Art

[0002] In the field of natural gas transmission, gas pipeline flow monitoring is a key link to ensure stable and safe gas supply. It provides data support for gas transmission scheduling by monitoring relevant parameters such as gas flow in the gas pipeline, ensuring that natural gas can be stably and efficiently delivered to the user end. At the same time, monitoring and evaluation of the operating status of flow meters and related equipment is also an important guarantee for maintaining the normal operation of the gas transmission system. In the event of an emergency such as a leak, rapid and accurate accident location and reasonable emergency response route planning are crucial to reducing accident hazards and ensuring the safety of personnel and the environment.

[0003] At present, there are some studies involving the monitoring of gas pipeline flow. For example, patent CN113723834A is an intelligent high-level scheduling and operation and maintenance system and method for gas pipeline network. In order to realize the intelligent scheduling of natural gas, the pipeline flow will be monitored as a whole; patent CN119687387A is a working condition analysis method and system for gas pipelines. By constructing a corresponding pipeline analysis model for each gas pipeline, the output pipeline efficiency and friction coefficient changes are output, and relevant thresholds are set to alarm the pipeline operation, thereby improving the accuracy of working condition monitoring.

[0004] However, the existing gas pipeline flow monitoring technology still has many shortcomings. Due to factors such as the remote installation location and complex environment of the gas pipeline, it is difficult to obtain multi-parameter information such as temperature, pressure, and flow in real time, and there is a lack of effective means to predict flow change trends. This makes it difficult to plan gas transmission scheduling in advance. When the flow rate changes suddenly, it is very easy to have insufficient gas supply or abnormal pressure, which seriously threatens the stability and safety of gas supply. Taking the winter gas consumption peak as an example, due to the inability to accurately predict flow changes, some areas may experience gas shortages, affecting the normal lives of residents.

[0005] In terms of monitoring flow meters and related equipment, traditional methods have limitations and cannot fully collect operating data such as vibration, temperature, and pressure fluctuations. At the same time, the lack of equipment health assessment models based on multi-dimensional data makes it difficult to predict equipment failures in advance, resulting in a high risk of sudden equipment failures, which in turn affects the normal operation of gas pipelines. Once equipment fails suddenly, it may cause gas transmission interruptions, causing huge economic losses to enterprises.

[0006] In addition, when emergencies such as gas pipeline leaks occur, existing systems perform poorly in accident location and emergency response.

[0007] In view of the problems of the above-mentioned existing technologies, it is urgent to develop a more advanced gas pipeline flow monitoring technology. Summary of the Invention

[0008] The present invention aims to provide an intelligent monitoring method for the flow state of gas pipelines to solve the problem of large fluctuations in the accuracy rate of the monitoring results of the flow state of gas pipelines.

[0009] To solve the above problems, the present invention adopts the following technical solutions:

[0010] Solution 1: A method for monitoring the flow state of gas pipelines, including the following steps:

[0011] Step 1, divide the pipeline into grids according to the construction layout diagram of the gas pipeline, and mark the leakage risk level for the gas pipeline in each grid unit;

[0012] Step 2, for the local gas pipelines in grid units with different risk levels, the density of the installed sensor components is different;

[0013] Step 3, use the sensor components to collect the gas and equipment operation data in the gas pipeline; collect, process, and transmit the sensor data through the data acquisition and transmission equipment;

[0014] Step 4, use the positioning equipment to determine the geographical location information of the accident site; provide geographical information data through the geographical information system equipment for path planning.

[0015] Preferably, in Step 2, the sensor components include a temperature sensor, a pressure sensor, a flow sensor, and a vibration sensor; the temperature sensor uses a high-precision thermocouple or thermal resistance sensor, the pressure sensor uses a capacitive or strain gauge pressure sensor, and the flow sensor selects an ultrasonic flowmeter or a turbine flowmeter.

[0016] Preferably, in Step 1, the grid division adopts an equal-spacing division method. Based on the pipeline length direction, first perform a horizontal division at an interval of 500 meters; if a pipeline branch situation is encountered during the division process, make a longitudinal adjustment according to the direction and position of the branch.

[0017] Preferably, in Step 1, mark the leakage risk level for the gas pipeline in each grid unit: perform a comprehensive evaluation and marking according to the population density, building density around the pipeline in the grid unit, as well as the material and service life of the pipeline itself;

[0018] If the population density in a grid unit exceeds 5000 people per square kilometer, the building density exceeds 30%, and the pipeline service life exceeds 15 years, mark this grid unit as a high-risk level;

[0019] If the population density within a grid cell is between 2,000 and 5,000 people per square kilometer, the building density is between 10% and 30%, and the pipeline service life is between 10 and 15 years, it is marked as a medium - risk level;

[0020] If the population density within a grid cell is less than 2,000 people, the building density is less than 10%, and the pipeline service life is less than 15 years, mark this grid cell as a low - risk level.

[0021] Preferably, in step two, the density of the sensor components installed in the local gas transmission pipelines within grid cells of different risk levels is different, specifically:

[0022] For grid cells of high - risk level, install a temperature sensor, a pressure sensor, and a flow sensor every 200 meters, and install two vibration sensors on each key device;

[0023] For grid cells of medium - risk level, install a temperature sensor, a pressure sensor, and a flow sensor every 500 meters, and install one vibration sensor on each key device;

[0024] For grid cells of low - risk level, install a temperature sensor, a pressure sensor, and a flow sensor every 1,000 meters, and install one vibration sensor on every two key devices.

[0025] Preferably, step four further includes using the time - series prediction model algorithm to predict the flow change trend. The time - series prediction model algorithm is the ARIMA (AutoRegressive Integrated Moving Average) model. Use the 3 - standard - deviation method to remove outliers, normalize the data to the [0, 1] interval, determine that the order of the AR term is 2, the differencing order is 1, the order of the MA term is 1, and predict the flow for the next 24 hours at 1:00 am every day.

[0026] Preferably, use the equipment health assessment model algorithm to evaluate the equipment health status. The equipment health assessment model algorithm is the support vector machine, use the radial basis kernel function as the kernel function, extract vibration amplitude, frequency, temperature change rate, pressure fluctuation standard deviation, etc. from the operation data as feature vectors, analyze the equipment operation data every 1 hour, and issue a warning when the predicted probability of equipment failure within the next 24 hours exceeds 50%.

[0027] Preferably, step four further includes using the equipment health assessment model algorithm to evaluate the equipment health status. The equipment health assessment model algorithm is the support vector machine, use the radial basis kernel function as the kernel function, extract vibration amplitude, frequency, temperature change rate, pressure fluctuation standard deviation, etc. from the operation data as feature vectors, analyze the equipment operation data every 1 hour, and issue a warning when the predicted probability of equipment failure within the next 24 hours exceeds 50%.

[0028] The advantages of this solution are as follows:

[0029] The method of the present invention can accurately monitor the flow state of gas transmission pipelines. By dividing the grid to mark the danger level, reasonably arranging sensors to collect multi-parameter data, combining multiple algorithms to predict the flow rate, evaluate the equipment, and plan the emergency route, intelligent and efficient monitoring is achieved, ensuring gas supply safety and reducing accident risks and losses.

[0030] In addition, in the field of gas transmission pipeline flow state monitoring, there are significant essential differences between the traditional monitoring method and the solution of the present invention.

[0031] In terms of the types of monitoring equipment, the types of monitoring equipment used in the traditional method are single. Traditional monitoring often only focuses on the monitoring of the flow rate, and lacks sufficient attention to the monitoring of key data such as vibration, temperature, and pressure fluctuations during the operation of flow meters and related equipment, and does not equip corresponding comprehensive sensor equipment for data collection. This is because the traditional monitoring concept is relatively limited and does not fully recognize the importance of these multi-dimensional data for accurately evaluating the equipment operation status and predicting faults. In contrast, the solution of the present invention fully considers the complexity and multi-factor correlation of equipment operation, and sets up various types of sensors. By comprehensively arranging different types of sensors, all-round collection of equipment operation data is realized, providing sufficient data support for subsequent accurate analysis and evaluation.

[0032] Even if the traditional method can achieve comprehensive configuration in terms of the types of monitoring equipment, there are still problems in the effectiveness of data collection. Due to technical limitations or lack of systematic layout planning, traditional monitoring equipment is difficult to effectively solve the contradiction between the comprehensiveness and timeliness of data collection. In order to reduce the data collection and transmission volume, the data collection frequency of traditional equipment may not meet the requirements of real-time monitoring and trend analysis, and the long interval time causes some important transient data to be missed. In contrast, the solution of the present invention has obvious advantages in data collection. The data collector has a multi-channel data collection function, can be well compatible with different types of sensors, collects sensor data every 10 seconds, and performs simple data filtering processing to remove obvious noise data, ensuring the accuracy and timeliness of the collected data. At the same time, through the wireless transmission module, using advanced communication technologies such as 4G, 5G or LoRa, and giving priority to using 5G to ensure high-speed and stable transmission of data to the data processing center, realizing real-time monitoring and dynamic analysis of the equipment operation status.

[0033] In terms of equipment health assessment, the traditional method lacks an equipment health assessment model built based on multi-dimensional data. Due to the inability to comprehensively collect data and the even greater difficulty in effectively integrating and analyzing this data, the traditional method cannot establish a scientific and accurate equipment health assessment system and is difficult to predict equipment failures in advance. In contrast, the solution of the present invention uses the Support Vector Machine (SVM) algorithm to extract feature vectors that can reflect the equipment health status from multi-dimensional operation data such as vibration, temperature, and pressure fluctuations collected, such as the amplitude and frequency of vibration, the change rate of temperature, and the standard deviation of pressure fluctuations. Based on this, an equipment health assessment model is constructed. By training the model with a large amount of historical data to improve its accuracy, it can analyze the equipment operation data every hour and predict the probability of equipment failure within the next 24 hours. If the probability exceeds 50%, an early warning is issued, and maintenance is arranged in advance, greatly reducing the risk of sudden equipment failures, ensuring the normal operation of the gas transmission pipeline, and avoiding gas transmission interruptions and economic losses caused by equipment failures.

[0034] More importantly, the traditional monitoring method is designed based on an ideal scenario and does not distinguish between gas transmission pipelines in different installation environments but uses the same monitoring method. This results in a higher monitoring accuracy for gas transmission pipelines whose actual installation environment is closer to the ideal scenario, causing the accuracy rate of the gas transmission pipeline flow monitoring results to fluctuate greatly in different actual installation environments under the traditional monitoring method. The present solution effectively solves this problem and can maintain a high monitoring accuracy rate in various actual installation environments.

[0035] Solution Two: The present invention also provides an intelligent monitoring system for the flow state of a gas transmission pipeline, including a central processor, and a division standard module, a sensor assembly, a data acquisition and transmission device, a positioning device, and a geographic information system device that are respectively connected to the central processor;

[0036] The division standard module is used to divide the pipeline into grids and mark the leakage risk levels according to the construction layout diagram of the gas transmission pipeline;

[0037] The sensor assembly is used to collect the gas and equipment operation data inside the gas transmission pipeline;

[0038] The data acquisition and transmission device is used to collect, process, and transmit the sensor data;

[0039] The positioning device is used to determine the geographical location information of the accident site;

[0040] The geographic information system device is used to provide geographic information data support and path planning;

[0041] The central processing unit controls the grid division standard module to perform grid division and risk level annotation according to a preset strategy, and receives the data transmitted by the sensor components in the corresponding grid through the data acquisition and transmission device according to the risk level of the grid unit; when the central processing unit determines that there is an accident in a certain grid unit based on the sensor data of the grid unit, it determines the accident location through the positioning device, and then uses the geographic information system to plan the optimal emergency route.

[0042] Preferably, the installation density of the sensor components is adjusted according to the leakage risk level of the grid unit, and the number and type of sensors installed in grid units with different risk levels are different; the leakage risk levels include high risk level, medium risk level and low risk level; for grid units with a high risk level, a temperature sensor, a pressure sensor and a flow sensor are installed every 200 meters, and two vibration sensors are installed on each key device; for grid units with a medium risk level, a temperature sensor, a pressure sensor and a flow sensor are installed every 500 meters, and one vibration sensor is installed on each key device; for grid units with a low risk level, a temperature sensor, a pressure sensor and a flow sensor are installed every 1000 meters, and one vibration sensor is installed on every two key devices.

[0043] The advantages of the present invention are as follows:

[0044] The present invention constructs a comprehensive and efficient monitoring system for the flow state of gas transmission pipelines. By scientifically and reasonably dividing grids according to the construction layout diagram of gas transmission pipelines and annotating the leakage risk level based on factors such as the population density, building density, pipeline material and service life around the pipeline, the risk degree of different regions can be accurately identified. Based on the differential installation of sensor components according to the risk level, various sensors are densely installed in high-risk areas, such as installing temperature, pressure and flow sensors every 200 meters and two vibration sensors on key devices; moderately installed in medium-risk areas; and reasonably sparsely installed in low-risk areas, realizing the optimal allocation of resources, ensuring the strict monitoring of high-risk areas and avoiding resource waste in low-risk areas, effectively improving the pertinence and economy of monitoring. The present invention can be applied to various installation environments with high monitoring accuracy. It can quickly and accurately determine the accident location, can formulate the optimal emergency response route in combination with the surrounding geographical information and traffic conditions, has high emergency handling efficiency, wide application range, and will not affect the fluctuation of the monitoring effect accuracy due to the change of the pipeline installation environment.

[0045] In terms of data processing and application, the sensor component collects the gas and equipment operation data in the gas transmission pipeline in real time. The data collection and transmission equipment efficiently collects, processes, and transmits the data to ensure the timeliness and accuracy of the data. The positioning equipment quickly determines the accident location with the help of the GPS / Beidou positioning module. The geographic information system equipment uses the GIS server and software platform to provide geographic information data support and path planning, greatly improving the emergency response efficiency and being able to quickly control the scope of the accident impact. In addition, through in-depth analysis of the collected data, abnormal pipeline operations are detected in a timely manner and alarms are given, further ensuring the safe operation of the gas transmission pipeline.

[0046] In addition, the present invention breaks through the limitations of traditional gas transmission pipeline monitoring methods. Due to industry practices, traditional monitoring often regards the installation environment as an ideal environment that meets the installation requirements, lacking accurate assessment of the pipeline risks in the installation environment area and targeted monitoring. It only focuses on the monitoring of all gas transmission pipelines inside the pipeline, ignoring the impact of the installation environment on the pipeline use. The present invention innovatively introduces the concepts of grid division and risk level marking, breaking away from the technical bias of only monitoring the pipeline itself, and realizing the refined management of the pipeline and its actual installation area as a whole. The method of differentially installing sensor components according to different risk levels is pioneering in the industry, effectively solving the problems of reasonable resource allocation and accurate monitoring. At the same time, the deep integration of positioning technology, geographic information system and gas transmission pipeline monitoring has achieved a qualitative leap in emergency response path planning, which is more scientific and efficient compared with traditional emergency response methods. This design of multi-technology integration and multi-link innovation solves many long-existing problems in the field of gas transmission pipeline monitoring, provides new ideas and methods for the industry development, and has outstanding creativity. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 It is a flowchart of the method of the present invention.

[0048] Figure 2 It is a logic block diagram of the system of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0049] The following is a further detailed description through specific embodiments:

[0050] As shown in the Figure 1 drawing: The gas transmission pipeline flow state monitoring method includes the following steps:

[0051] S1 Divide the pipeline into grids according to the construction layout drawing of the gas transmission pipeline, and mark the leakage risk level for the gas transmission pipeline in each grid unit;

[0052] According to the grid division and annotation strategy preset in the central processing unit, the pipeline is divided into grids based on the construction layout diagram of the gas transmission pipeline: The equal-spacing division method is adopted. Taking the pipeline length direction as the reference, the horizontal division is first carried out at intervals of 500 meters. During the division process, pipeline branch situations will be encountered. At this time, longitudinal adjustments are made according to the branch direction and position. For example, if a branch pipeline appears within the horizontally divided interval and the length of the branch pipeline exceeds 200 meters, then longitudinal division is carried out at the branch to form independent grid units. This can ensure the integrity and independence of each grid unit, and avoid areas with missed monitoring or repeated monitoring. Through this division method, the entire gas transmission pipeline system can be divided into multiple grid units that are convenient for management and monitoring, providing a clear area division for subsequent risk level annotation and sensor installation.

[0053] For the gas transmission pipeline within each grid unit, leakage risk level annotation is carried out: Comprehensive evaluation and annotation are carried out according to factors such as the population density, building density around the pipeline within the grid unit, as well as the pipeline material and service life. Data on population density and building density within each grid unit are obtained through the statistical department, and at the same time, the pipeline construction materials and service life are determined by referring to the pipeline construction materials. If the population density within a grid unit exceeds 5000 people per square kilometer, the building density exceeds 30%, and the pipeline service life exceeds 15 years, then this grid unit is marked as a high-risk level. This is because in areas with dense population and buildings, once a pipeline leak occurs, the possible casualties and property losses may be very serious, and the possibility of leakage of pipelines with a longer service life is relatively high. When the population density is between 2000 - 5000 people per square kilometer, the building density is between 10% - 30%, and the pipeline service life is between 10 - 15 years, it is marked as a medium-risk level. In other cases, that is, grid units with low population density, small building density, and short pipeline service life are marked as low-risk levels. This annotation method can more accurately reflect the leakage risk degree of the pipeline within each grid unit, providing an important basis for formulating subsequent monitoring strategies.

[0054] S2 For local gas pipelines in grid units of different hazard levels, the density of installed sensor components is different; for grid units of high hazard levels, in order to monitor the pipeline status more timely and accurately and improve the timeliness of leak detection, a temperature sensor, a pressure sensor and a flow sensor are installed every 200 meters, and two vibration sensors are installed on each key equipment (such as valves, compressors, etc.). Such high-density sensor installation can more comprehensively obtain the temperature, pressure, flow changes of gas in the pipeline and the vibration of the equipment, and can quickly detect abnormal changes. For grid units of medium hazard levels, a temperature sensor, a pressure sensor and a flow sensor are installed every 500 meters, and a vibration sensor is installed on each key equipment. This installation density can not only meet the basic monitoring needs of pipeline operation status, but also control costs to a certain extent. For grid units of low hazard levels, a temperature sensor, a pressure sensor and a flow sensor are installed every 1000 meters, and a vibration sensor is installed on every two key equipment. While ensuring the necessary monitoring of pipelines in low-risk areas, avoid excessive installation of sensors to cause waste of resources. By adjusting the sensor installation density according to the hazard level, rational use of resources is achieved, and the cost-effectiveness of the monitoring system is improved while ensuring the safe operation of the gas pipeline.

[0055] S3 uses sensor components to collect gas and equipment operation data in the gas pipeline; collects, processes and transmits sensor data through data acquisition and transmission equipment;

[0056] S4 uses positioning equipment to determine the geographical location information of the accident site; and uses geographic information system equipment to provide geographic information data support and path planning.

[0057] In the step of collecting data by the sensor assembly, the temperature sensor uses a high-precision thermocouple or thermal resistor sensor, the pressure sensor uses a capacitive or strain gauge pressure sensor, the flow sensor uses an ultrasonic flowmeter or a turbine flowmeter, and the vibration sensor is installed on the flowmeter and related equipment. Appropriate sensors are selected for different data types to ensure the accuracy and reliability of data collection.

[0058] In the step of transmitting data by the data acquisition and transmission device, the wireless transmission module preferentially uses 5G technology. If the 5G signal coverage is poor, it automatically switches to 4G or LoRa. The data collector performs simple data filtering on the collected data. The stability of data transmission is ensured, and the data quality is improved through data filtering, providing reliable data for subsequent analysis.

[0059] The positioning device is a GPS / Beidou positioning module, which is installed on key facilities along the pipeline every 2000 meters. The devices carried by emergency response vehicles and personnel are also equipped with corresponding positioning modules. This ensures that the accident location can be quickly and accurately determined in case of an emergency, thus gaining time for emergency rescue.

[0060] In the described Geographic Information System (GIS) device, the GIS server stores and manages geographic information data, which is updated at least once a month; the GIS software platform provides a visual operation interface for loading, analyzing geographic information data, and implementing route planning. This guarantees the accuracy and timeliness of geographic information, facilitating intuitive operation by operators and enhancing the scientific nature of emergency response.

[0061] The method for monitoring the flow state of the gas transmission pipeline further includes steps of predicting the flow change trend using the time series prediction model algorithm, evaluating the equipment health status using the equipment health assessment model algorithm, and planning the emergency response route using the emergency response route planning algorithm. Through the application of multiple algorithms, multi-faceted monitoring and management of the flow state of the gas transmission pipeline are realized, enhancing the intelligence and effectiveness of the monitoring system.

[0062] The time series prediction model algorithm is ARIMA (Autoregressive Integrated Moving Average Model). The 3-sigma method is used to remove outliers, and the data is normalized to the interval [0, 1]. Through multiple experiments and cross-validation, the order of the AR term is determined to be 2, the differencing order is 1, and the order of the MA term is 1. The flow for the next 24 hours is predicted at 1 am every day. Through scientific data processing and precise model settings, the flow prediction accuracy is improved, providing an accurate basis for gas transmission scheduling.

[0063] The equipment health assessment model algorithm is Support Vector Machine (SVM). The radial basis kernel function is used as the kernel function. Vibration amplitude, frequency, temperature change rate, standard deviation of pressure fluctuation, etc. are extracted from the operation data as feature vectors. The operation data of the equipment is analyzed every 1 hour. When the probability of the equipment failing within the next 24 hours exceeds 50%, a warning is issued. This effectively evaluates the equipment health status, timely discovers potential failure risks, facilitates arranging maintenance in advance, and ensures the normal operation of the pipeline.

[0064] The emergency response route planning algorithm is the Dijkstra algorithm. The geographic information data in the GIS server is converted into a graph data structure, and the passing time of different sections is calculated according to the actual road conditions as the weight of the edge. The optimal emergency route is planned within 1 minute after receiving the accident alarm information. By using an efficient algorithm and accurate geographic information, the optimal emergency route is quickly planned, improving the emergency response efficiency and reducing accident losses.

[0065] As Figure 2As shown in the figure, the gas pipeline flow state monitoring system in the present invention includes a central processor, and components respectively connected to the central processor: a division standard module for dividing the pipeline into grids according to the construction layout drawing of the gas pipeline and marking the leakage risk level, a sensor assembly, a data acquisition and transmission device, a positioning device, and a geographic information system device;

[0066] The sensor assembly is used to collect gas and equipment operation data in the gas pipeline; the data acquisition and transmission device is used to collect, process, and transmit sensor data; the positioning device is used to determine the geographical location information of the accident site; the geographic information system device is used to provide geographical information data support and path planning. By setting the division standard module and combining with other components, the whole process monitoring from pipeline risk level division, data acquisition and transmission to accident positioning and emergency planning is realized, improving the systematicness and comprehensiveness of gas pipeline monitoring.

[0067] The installation density of the sensor assembly is adjusted according to the leakage risk level of the grid unit, and the number and type of sensors installed in grid units with different risk levels are different. Adjusting the sensor installation targeted according to the risk level, reasonably allocating resources, focusing on monitoring in high-risk areas, improving the monitoring efficiency and accuracy, and at the same time avoiding waste of resources caused by excessive installation in low-risk areas.

[0068] The division standard module includes a grid division unit and a risk level marking unit; the grid division unit is used to divide the pipeline into grids according to the construction layout drawing of the gas pipeline, and the risk level marking unit is used to mark the leakage risk level of the gas pipeline in each grid unit. Modularizing the division and marking functions makes the system structure clearer, easier to implement and manage, and is conducive to improving the accuracy and standardization of division and marking.

[0069] For grid units with a high risk level, one temperature sensor, one pressure sensor, and one flow sensor are installed every 200 meters, and two vibration sensors are installed on each key device; for grid units with a medium risk level, one temperature sensor, one pressure sensor, and one flow sensor are installed every 500 meters, and one vibration sensor is installed on each key device; for grid units with a low risk level, one temperature sensor, one pressure sensor, and one flow sensor are installed every 1000 meters, and one vibration sensor is installed on every two key devices. Clearly defining the installation density of sensors under different risk levels, encrypting the installation in high-risk areas, can more timely and accurately monitor the pipeline status in high-risk areas; reasonably installing in medium- and low-risk areas according to the risk degree, while ensuring the monitoring effect, optimizing resource allocation, and reducing the monitoring cost.

[0070] The grid division unit adopts an equal spacing division method, with the pipeline length direction as the benchmark, and is divided horizontally at a spacing of 500 meters, and then adjusted vertically according to the branching of the pipeline to ensure the integrity and independence of each grid unit. The method of equal spacing division combined with pipeline branch adjustment is simple and easy to implement and can effectively cover the entire gas pipeline, ensuring the scientificity and rationality of grid division, and facilitating subsequent hazard level marking and monitoring work.

[0071] The hazard level labeling unit labels the hazard level according to factors such as the population density, building density, and the material and service life of the pipeline itself around the grid unit; grid units with a population density of more than 5,000 people per square kilometer, a building density of more than 30%, and a pipeline service life of more than 15 years are labeled as high hazard levels; grid units with a population density between 2,000 and 5,000 people per square kilometer, a building density between 10% and 30%, and a pipeline service life of 10-15 years are labeled as medium hazard levels; other situations are labeled as low hazard levels. The hazard level labeling is performed by comprehensively considering a variety of factors related to leakage hazards, so that the labeling results can better reflect the actual risks and provide an accurate basis for the targeted installation of sensors and the formulation of emergency measures.

[0072] The data acquisition and transmission equipment includes a data collector and a wireless transmission module; the data collector has a multi-channel data acquisition function, is compatible with different types of sensor interfaces, and performs preliminary processing and caching on the collected data; the wireless transmission module is used to transmit the data processed by the data collector to the data processing center. The multi-channel compatibility and preprocessing functions of the data collector ensure the compatibility and preliminary quality of data acquisition, and the wireless transmission module realizes remote data transmission, ensuring that the data is delivered to the processing center in time for analysis.

[0073] The positioning device is a GPS / Beidou positioning module, which is installed on key facilities and emergency response equipment along the pipeline. The mature positioning technology is used to ensure that the accident location can be quickly and accurately determined when an accident occurs, providing key location information for subsequent emergency rescue.

[0074] The geographic information system equipment includes a GIS server and a GIS software platform; the GIS server is used to store and manage geographic information data, and the GIS software platform is used to load and analyze geographic information data and implement path planning. The GIS server and software platform cooperate with each other to provide rich geographic information data support, realize scientific path planning by loading and analyzing data, and improve the efficiency and scientificity of emergency response.

[0075] The gas transmission pipeline flow state monitoring system also includes a data analysis and processing module, which is used to deeply analyze the data collected by the sensors, judge whether the pipeline operation state is normal, and issue an alarm when abnormal. Adding the data analysis and processing module realizes the in-depth mining of the collected data, timely discovers the abnormal pipeline operation, issues an alarm, and provides more reliable support for ensuring the safe operation of the gas transmission pipeline.

[0076] The specific implementation process is as follows:

[0077] The gas transmission pipeline flow state monitoring system in the present invention includes:

[0078] (I) System composition

[0079] 1. Sensor assembly:

[0080] Temperature sensor: Select high-precision thermocouple or thermal resistance sensors, such as K-type thermocouples, and install them at key nodes of the gas transmission pipeline for real-time collection of the temperature data of the gas in the pipeline. These key nodes include positions prone to temperature changes such as elbows and branches of the pipeline, and one is installed every 500 meters to ensure comprehensive monitoring of the temperature distribution in the pipeline.

[0081] Pressure sensor: Adopt capacitive or strain gauge pressure sensors, which can accurately measure the gas pressure in the pipeline, and install them at different positions of the pipeline to ensure comprehensive monitoring of the pressure distribution. One pressure sensor is installed at the starting end, every 1000 meters in the middle section, and at the end of the pipeline.

[0082] Flow sensor: Ultrasonic flowmeter or turbine flowmeter can be selected, and its measurement principle is used to accurately obtain the gas flow information, and it is installed at positions such as the starting end, middle section, and end of the pipeline. By installing flow sensors at these positions, the flow data at different positions can be compared in real time to timely discover abnormal flow conditions.

[0083] Vibration sensor: Such as an acceleration sensor, which is installed on the flowmeter and related equipment to monitor the vibration of the equipment in real time for equipment health status assessment. One vibration sensor is installed on each flowmeter and key related equipment.

[0084] 2. Data acquisition and transmission equipment:

[0085] Data collector: Collect data from various sensors, have multi-channel data acquisition functions, be compatible with different types of sensor interfaces, and perform preliminary processing and caching of the collected data. The data collector collects sensor data every 10 seconds and performs simple data filtering processing to remove obvious noise data.

[0086] Wireless Transmission Module: Utilize wireless communication technologies such as 4G, 5G, or LoRa to transmit the data processed by the data collector to the data processing center, achieving remote data transmission. Preferentially use 5G technology to ensure high-speed and stable data transmission. If the 5G signal coverage is poor, it will automatically switch to 4G or LoRa.

[0087] 3. Positioning Device:

[0088] GPS / Beidou Positioning Module: Installed on key facilities along the pipeline and emergency response equipment. In case of an emergency, it can quickly determine the geographical location information of the accident site. Install a GPS / Beidou positioning module on key facilities along the pipeline every 2000 meters, and the equipment carried by emergency response vehicles and personnel is also equipped with corresponding positioning modules.

[0089] 4. Geographic Information System (GIS) Equipment:

[0090] GIS Server: Store and manage a large amount of geographic information data, including terrain, roads, buildings, etc., providing data support for emergency response route planning. Regularly update the geographic information data to ensure its accuracy and timeliness, and update it at least once a month.

[0091] GIS Software Platform: Provide a visual operation interface, capable of loading and analyzing geographic information data, and realizing functions such as path planning. Through this platform, operators can intuitively view geographic information and perform emergency route planning operations.

[0092] 5. Central Processing Unit: Adopt Kunpeng 920 processor or i.MX series chips pre-stored with various subsequent algorithm applications.

[0093] (2) Algorithm Applications

[0094] 1. Time Series Prediction Model Algorithm - ARIMA (Autoregressive Integrated Moving Average Model):

[0095] Data Preprocessing: Clean and normalize multi-dimensional data such as historical flow data, seasonal changes, upstream and downstream gas consumption demands, etc., removing outliers and noise interference. Use the 3-sigma method to remove outliers and normalize the data to the [0, 1] interval.

[0096] Model Training: Utilize the processed data to capture the trend, seasonality, and randomness characteristics of the data through the autoregressive (AR), differencing (I), and moving average (MA) terms of the ARIMA model, and determine the model parameters. Through multiple experiments and cross-validation, determine the optimal model parameters, such as the order of the AR term is 2, the differencing order is 1, and the order of the MA term is 1.

[0097] Prediction Application: Use the trained ARIMA model to predict the trend of flow rate changes within the next 24 hours, providing a basis for gas transmission scheduling. A prediction is made once at 1:00 am every day, and the prediction results are used for the gas transmission scheduling arrangement of the day.

[0098] 2. Equipment Health Assessment Model Algorithm - Support Vector Machine (SVM):

[0099] Feature Extraction: Extract feature vectors that can reflect the health status of the equipment from the operation data (vibration, temperature, pressure fluctuations, etc.) of the flow meters and related equipment collected. For example, extract the amplitude and frequency of vibration, the change rate of temperature, the standard deviation of pressure fluctuations, etc. as feature vectors.

[0100] Model Training: Use the extracted feature vectors as input and the health status of the equipment (normal, faulty, etc.) as labels, and use the support vector machine algorithm for training to construct an equipment health assessment model. The radial basis kernel function is used as the kernel function of the SVM, and it is trained with a large amount of historical data to improve the accuracy of the model.

[0101] Fault Prediction: By analyzing the feature vectors of the real-time collected equipment operation data, use the trained SVM model to predict possible faults of the equipment. Analyze the equipment operation data once every hour to predict the probability of the equipment having a fault within the next 24 hours. If the probability exceeds 50%, an early warning is issued.

[0102] 3. Emergency Response Route Planning Algorithm - Dijkstra Algorithm:

[0103] Data Preparation: Convert the geographical information data in the GIS server into a graph data structure. Nodes represent geographical locations, edges represent road connection relationships, and corresponding weights (such as distance, travel time, etc.) are assigned to the edges. According to the actual road conditions, calculate the travel time of different road sections and use it as the weight of the edge.

[0104] Algorithm Execution: In case of an emergency, with the accident location as the starting point and the emergency rescue target location as the ending point, use the Dijkstra algorithm to search for the shortest path in the graph data structure, that is, the optimal emergency response route. When receiving the accident alarm information, the system automatically starts this algorithm and plans the optimal emergency route within 1 minute.

[0105] The present invention has shown significant superiority in the field of gas pipeline flow state monitoring. In terms of system composition, a sensor assembly including temperature, pressure, flow, and vibration sensors has been carefully designed, and its selection and installation location have been scientifically planned. For example, K-type thermocouples are installed at key nodes of the pipeline every 500 meters to ensure comprehensive and accurate collection of multi-parameter data; data acquisition and transmission equipment work together, the data collector collects and filters data every 10 seconds, and the wireless transmission module automatically switches the network according to the signal to ensure stable data transmission; the positioning equipment uses the GPS / Beidou positioning module to achieve precise positioning, and key facilities along the pipeline are installed every 2,000 meters, and emergency equipment is also equipped synchronously; in GIS equipment, the GIS server updates geographic information data every month, and the GIS software platform provides visual operation and path planning functions.

[0106] In terms of algorithm application, the ARIMA model is used to predict flow. The data is processed by the 3-times standard deviation method, and the parameters of AR=2, I=1, and MA=1 are determined through multiple experiments. The flow rate for the next 24 hours is predicted at 1 a.m. every day to provide a reliable basis for gas transmission scheduling. The SVM algorithm is used to build an equipment health assessment model, and the radial basis kernel function is used to extract characteristic vectors such as vibration amplitude. The equipment is evaluated every hour, and an early warning is issued when the probability of failure exceeds 50%. The Dijkstra algorithm is used to plan emergency routes, and the geographic information is converted into a graph data structure. The actual travel time is used as the weight to plan the optimal emergency route within 1 minute.

[0107] These technical features work together to solve the problems of the existing technology's inability to obtain multiple parameters in real time, difficulty in predicting flow trends, insufficient equipment failure warnings, and low emergency response efficiency. They achieve real-time monitoring of multiple parameters, accurate flow prediction, equipment health assessment, and efficient emergency response. Compared with traditional technologies, these technical features have made substantial breakthroughs and significant progress, fully demonstrating the advanced nature of the present invention.

[0108] Example 1

[0109] Assume that the system of the present invention is applied to a section of gas pipeline located in the suburbs of a city. There are a certain number of factories and residential areas around the area, with a medium population density, a building density of about 20%, and a service life of the pipeline of 12 years. It is judged that the grid unit where this section of pipeline is located is of medium risk level.

[0110] System construction:

[0111] According to the installation requirements of the sensor components, 5 K-type thermocouple temperature sensors, 3 capacitive pressure sensors, 3 ultrasonic flow sensors and 4 acceleration vibration sensors are installed at the key nodes of the pipeline. At the elbows and branches of the pipeline, a K-type thermocouple temperature sensor is installed every 500 meters; at the starting end, middle section every 1000 meters and the end of the pipeline, a capacitive pressure sensor is installed respectively; an acceleration vibration sensor is installed on each flowmeter and key related equipment. Such an installation layout meets the monitoring requirements of medium-risk pipelines and can effectively monitor the operating status of the pipeline at a reasonable cost.

[0112] Install 1 data collector, ensure its correct connection with various sensors, configure a wireless transmission module, and use the 5G network to connect to the data processing center to ensure the efficiency and stability of data transmission.

[0113] Install 3 GPS / Beidou positioning modules on the key facilities along the pipeline, and also equip the emergency response vehicles and personnel equipment with corresponding positioning modules to quickly locate the accident site in case of emergency.

[0114] Build a GIS server to store the detailed geographical information data of the area, and install a GIS software platform to provide data support for the emergency response route planning.

[0115] Data collection and processing:

[0116] The data collector collects data from various sensors at a set time interval (10 seconds), and performs preliminary processing and caching. Through such frequent data collection, subtle changes in the pipeline operation parameters can be captured in a timely manner.

[0117] The collected historical flow data, seasonal change data and upstream and downstream gas consumption demand data are cleaned and normalized according to the requirements of data preprocessing to provide high-quality data for subsequent model training.

[0118] Model training and application:

[0119] Use the processed data to train an ARIMA model, and determine the model parameters (AR = 2, I = 1, MA = 1) through multiple experiments. Use the trained model to predict the flow rate in the next 24 hours. The prediction results show that the flow rate will increase significantly from 9 am to 12 pm the next day. According to this prediction, the gas transmission scheduling is adjusted in advance to increase the gas source supply, avoiding the situation of insufficient gas supply. In the medium-risk area, accurate flow rate prediction is crucial for ensuring stable gas supply, and adjusting the gas source supply in advance effectively avoids possible gas shortage problems.

[0120] Collect operation data such as vibration, temperature, and pressure fluctuations of flow meters and related equipment, extract feature vectors, and train an SVM device health assessment model. During operation, by analyzing the feature vectors of device operation data in real time, it is found that the vibration amplitude of a certain flow meter is abnormal, and the SVM model predicts that there is a 75% probability of a fault in this flow meter within the next 24 hours. Maintenance personnel are promptly arranged to inspect and maintain this flow meter, avoiding gas transmission interruption caused by sudden equipment failures. This device health assessment and fault warning based on multi-dimensional data can effectively reduce the risks brought by equipment failures in medium-risk level pipeline monitoring and ensure the stable operation of the pipeline.

[0121] Emergency response simulation:

[0122] Suppose a leak occurs at a certain location in the pipeline, and the GPS / Beidou positioning module quickly determines the geographical location information of the accident site.

[0123] The system takes the accident site as the starting point and the nearby emergency rescue station as the end point, and uses the Dijkstra algorithm to plan the emergency response route in the GIS software platform. The optimal route planned avoids traffic congestion sections and densely populated areas, enabling emergency rescue vehicles to reach the accident scene in the shortest time and effectively controlling the scope of the accident impact. In areas such as the outskirts of the city, quickly planning an emergency route that avoids densely populated areas and congested sections is of great significance for reducing accident hazards and ensuring personnel safety.

[0124] Advantages of this embodiment:

[0125] Flow monitoring and scheduling optimization: In the medium-risk level pipeline area in the outskirts of the city, by reasonably installing sensors, multi-parameter data can be collected in real time without additional hardware costs. Using the ARIMA model to accurately predict the flow change trend and adjusting the gas transmission scheduling in advance effectively guarantees the gas supply stability and meets the gas consumption needs of factories and residents in this area.

[0126] Device fault warning and maintenance: For the sensor layout of medium-risk level pipelines, comprehensively collect device operation data, and accurately evaluate the device health status with the help of the SVM model. Timely discover potential faults in the flow meter and arrange maintenance to avoid gas transmission interruption, improve the pipeline operation reliability, and reduce the economic losses that may be caused by equipment failures.

[0127] Efficient emergency response: In the complex traffic and population environment in the outskirts of the city, with the help of the positioning module and GIS technology, quickly plan an emergency route that avoids congestion and densely populated areas, enabling emergency rescue vehicles to quickly reach the accident scene, effectively controlling the scope of the accident impact, and ensuring the safety of personnel and the surrounding environment.

[0128] Embodiment 2

[0129] An application test was carried out on a gas transmission pipeline located in a mountainous area. The terrain of this area is complex and the population is sparse. There are basically no large buildings around the pipeline. The service life of the pipeline is 8 years. After judgment, the grid unit where this section of the pipeline is located is of low risk level.

[0130] System deployment:

[0131] Install 8 K-type thermocouple temperature sensors, 5 strain gauge pressure sensors, 4 turbine flow sensors and 6 vibration sensors. On the pipeline, install a K-type thermocouple temperature sensor, a strain gauge pressure sensor and a turbine flow sensor every 1000 meters; install a vibration sensor on every two key devices. This installation method meets the basic monitoring requirements of low-risk level pipelines while avoiding resource waste caused by over-installation.

[0132] Deploy data collectors and wireless transmission modules, and use 4G network for data transmission (the 5G signal in this area is unstable) to ensure that data can be stably transmitted to the data processing center.

[0133] Install 5 GPS / Beidou positioning modules to ensure that key facilities and emergency equipment along the pipeline have positioning functions, so as to accurately obtain location information in case of emergencies.

[0134] Configure a GIS server and software platform to store geographical information data of this area containing complex terrains (mountains, rivers, etc.) and provide geographical data support for emergency response.

[0135] Data processing and model operation:

[0136] The data collector normally collects data. After cleaning and normalizing the collected multi-dimensional data, train the ARIMA model (finally determine AR = 3, I = 1, MA = 2). Use this model to predict the flow change trend in the next week and provide a reference for long-term gas transmission scheduling. The prediction results show that the flow will decrease significantly due to the shutdown of downstream industrial users on weekends. According to this, adjust the gas transmission plan, reduce the gas source supply, and save costs. In the low-risk level mountain pipeline, long-term flow prediction helps to reasonably arrange the gas source supply and improve the operation efficiency.

[0137] Use the collected equipment operation data to train the SVM equipment health assessment model. In daily monitoring, through model analysis, it is found that the temperature change rate and pressure fluctuation of a compressor are abnormal, and it is predicted that it may malfunction within the next 48 hours. Arrange maintenance personnel in advance to prepare repair tools and spare parts, and carry out repairs before the equipment fails, ensuring the normal operation of the gas transmission pipeline. Even in the low-risk level area, equipment health monitoring can effectively prevent failures and ensure the stable operation of the pipeline.

[0138] Emergency Handling Practice:

[0139] When a pipeline leakage accident occurs, the positioning module determines the accident location. Due to the complex terrain in this area, the geographical information data in the GIS server plays an important role. The system uses the Dijkstra algorithm to plan the emergency response route, comprehensively considering factors such as terrain and road traffic conditions, and plans an optimal route that bypasses mountains and avoids rivers. The emergency rescue personnel quickly reach the accident scene along this route and quickly complete the repair work, reducing the accident losses. In the complex mountain terrain, accurate emergency route planning can improve the rescue efficiency and reduce the losses caused by accidents.

[0140] Advantages of this embodiment:

[0141] Flow Monitoring and Scheduling Optimization: For mountain pipelines with a low risk level, sensors are reasonably arranged for data collection. The ARIMA model is used to predict the flow changes, providing an accurate basis for long-term gas transmission scheduling, achieving a reasonable configuration of gas sources, and saving operation costs.

[0142] Equipment Failure Warning and Maintenance: Based on the sensor installation plan for low-risk pipelines, the operation data of the equipment is effectively collected. The SVM model is used to timely detect potential compressor failures and arrange maintenance in advance, ensuring the normal operation of the pipeline, reducing unnecessary equipment maintenance costs and the risk of gas transmission interruption.

[0143] High-efficiency Emergency Response: Under the complex mountain terrain conditions, an emergency route that bypasses mountains and rivers is planned with the help of positioning and GIS technologies, enabling rescue personnel to quickly reach the accident scene and efficiently complete the repair work, minimizing the accident losses to the greatest extent and ensuring the normal operation of the gas transmission pipeline.

[0144] The above are only embodiments of the present invention. Specific technical solutions and / or common knowledge such as characteristics well known in the art are not described in detail herein. It should be noted that for those skilled in the art, without departing from the technical solution of the present invention, several deformations and improvements can still be made, which should also be regarded as the protection scope of the present invention, and these will not affect the implementation effect of the present invention and the practicality of the patent. The protection scope required by this application should be subject to the content of its claims, and the specific implementation manners described in the specification can be used to explain the content of the claims.

Claims

1. A method for intelligently monitoring the flow status of a gas pipeline, characterized in that: The following steps are involved: Step 1: divide the pipeline into grids according to the gas pipeline construction layout diagram, and mark the leakage hazard level of the gas pipeline in each grid unit; Step 2: for local gas pipelines in grid cells of different hazard levels, different densities of installed sensor components are used; Step 3: Use sensor components to collect gas and equipment operation data in the gas pipeline; collect, process and transmit sensor data through data acquisition and transmission equipment; Step 4: Use positioning equipment to determine the geographical location information of the accident site; The geographic information data is provided by the geographic information system equipment for route planning.

2. The method for intelligently monitoring the flow status of a gas pipeline according to claim 1, characterized in that: In step 2, the sensor assembly includes a temperature sensor, a pressure sensor, a flow sensor and a vibration sensor; the temperature sensor adopts a high-precision thermocouple or thermistor sensor, the pressure sensor adopts a capacitive or strain gauge pressure sensor, and the flow sensor selects an ultrasonic flowmeter or a turbine flowmeter.

3. The method for intelligently monitoring the flow status of a gas pipeline according to claim 2, characterized in that: In step one, the grid is divided into equal intervals, based on the length of the pipeline. First, it is divided horizontally at intervals of 500 meters. If a pipeline branch is encountered during the division process, vertical adjustments are made based on the direction and position of the branch.

4. The method for intelligently monitoring the flow status of a gas pipeline according to claim 3, characterized in that: In step 1, the leakage hazard level of the gas pipeline in each grid unit is marked: a comprehensive assessment is performed based on the population density and building density around the pipeline in the grid unit, as well as the material and service life of the pipeline itself; If the population density in a grid cell exceeds 5,000 people per square kilometer, the building density exceeds 30%, and the age of the pipeline exceeds 15 years, the grid cell will be marked as a high-risk level; If the population density in a grid cell is between 2,000 and 5,000 people per square kilometer, the building density is between 10% and 30%, and the service life of the pipeline is 10-15 years, it is marked as a medium risk level; If the population density in a grid unit is less than 2,000, the building density is less than 10%, and the pipeline age is less than 15 years, the grid unit will be marked as a low risk level.

5. The method for intelligently monitoring the flow status of a gas pipeline according to claim 4, characterized in that: In step 2, the density of sensor components installed in the local gas pipelines in the grid units of different hazard levels is different as follows: For grid cells with high risk levels, a temperature sensor, a pressure sensor, and a flow sensor are installed every 200 meters, and two vibration sensors are installed on each key equipment; For grid cells with medium hazard levels, a temperature sensor, a pressure sensor, and a flow sensor are installed every 500 meters, and a vibration sensor is installed on each key equipment; For grid units with low hazard levels, a temperature sensor, a pressure sensor and a flow sensor are installed every 1,000 meters, and a vibration sensor is installed on every two key devices.

6. The method for intelligently monitoring the flow status of a gas pipeline according to claim 5, characterized in that: Step four also includes using a time series prediction model algorithm to predict traffic change trends. The time series prediction model algorithm is an ARIMA differential autoregressive moving average model, which uses a 3-times standard deviation method to remove outliers, normalizes the data to the [0,1] interval, determines that the AR term order is 2, the difference order is 1, and the MA term order is 1, and predicts the traffic for the next 24 hours at 1 a.m. every day.

7. The method for intelligently monitoring the flow status of a gas pipeline according to claim 5, characterized in that: Step four also includes evaluating the health status of the equipment using an equipment health assessment model algorithm. The equipment health assessment model algorithm is a support vector machine that uses a radial basis kernel function as a kernel function to extract vibration amplitude, frequency, temperature change rate, pressure fluctuation standard deviation, etc. from the operating data as feature vectors. The equipment operating data is analyzed every hour, and an early warning is issued when it is predicted that the probability of failure of the equipment within the next 24 hours exceeds 50%.

8. The method for intelligently monitoring the flow status of a gas pipeline according to claim 5, characterized in that: In step 4, an emergency response route is planned using an emergency response route planning algorithm. The emergency response route planning algorithm is a Dijkstra algorithm, which converts geographic information data in the GIS server into a graph data structure, calculates the travel time of different road sections as the weight of the edge according to actual road conditions, and plans the optimal emergency route within 1 minute after receiving the accident alarm information.

9. An intelligent monitoring system for gas pipeline flow status, characterized in that: It includes a central processing unit, and a division standard module, a sensor component, a data acquisition and transmission device, a positioning device, and a geographic information system device respectively connected to the central processing unit; The division standard module is used to divide the pipeline into grids and mark the leakage risk level according to the gas pipeline construction layout diagram; The sensor assembly is used to collect gas and equipment operation data in the gas pipeline; The data acquisition and transmission equipment is used to collect, process and transmit sensor data; The positioning device is used to determine the geographical location information of the accident location; The GIS equipment is used to provide geographic information data support and route planning; The central processing unit controls the division standard module to perform grid division and hazard level marking according to a preset strategy, and receives data from the sensor components in the corresponding grid through the data acquisition and transmission equipment according to the hazard level of the grid unit; when the central processing unit determines that an accident exists in a grid based on the sensor data of a grid unit, the accident location is determined by the positioning device, and then the optimal emergency route is planned using the geographic information system.

10. The gas pipeline flow status intelligent monitoring system according to claim 9, characterized in that: The installation density of the sensor assembly is adjusted according to the leakage hazard level of the grid unit, and the number and type of sensors installed in the grid units of different hazard levels are different; the leakage hazard level includes high hazard level, medium hazard level and low hazard level; for the grid units of the high hazard level, a temperature sensor, a pressure sensor and a flow sensor are installed every 200 meters, and two vibration sensors are installed on each key device; for the grid units of the medium hazard level, a temperature sensor, a pressure sensor and a flow sensor are installed every 500 meters, and a vibration sensor is installed on each key device; for the grid units of the low hazard level, a temperature sensor, a pressure sensor and a flow sensor are installed every 1000 meters, and a vibration sensor is installed on every two key devices.

Images