Natural gas pipeline leakage monitoring system based on NB-IoT technology

Abstract

The present invention discloses a natural gas pipeline leakage monitoring system based on NB-IoT technology, which relates to the field of wireless communications and aims to address the problems of existing natural gas pipeline leakage monitoring systems, which are prone to missed detections and have difficulty in effectively predicting high-leakage areas. The system comprises a data acquisition module, a user terminal, a Beidou positioning module, a cloud platform, and a wireless communication module. The data acquisition module is used to collect natural gas pipeline status data, the Beidou positioning module is used to collect sensor locations, and the pipeline status data and location data are sent to the cloud platform via the wireless communication module. The cloud platform is used to determine whether there are any abnormal pipeline status and send pipeline status information, alarm information, and location information to the user terminal via the wireless communication module. The user terminal is used to visualize pipeline status information and warning information. The cloud platform is also used to predict high-leakage areas in the pipeline based on historical pipeline status data and to redeploy sensor positions based on the results of the high-leakage areas.

Description

Technical Field

[0001] The present invention relates to the field of wireless communication technology, and in particular to a natural gas pipeline leakage monitoring system based on NB-IoT technology. Background Art

[0002] Natural gas is a multi-component, flammable and explosive gas, requiring extremely high safety standards for its storage and transportation. The global natural gas transportation and distribution network is complex and continues to expand. The reliability of natural gas pipeline infrastructure has become a critical requirement. Existing natural gas pipelines are characterized by continuous, closed transmission systems, with natural gas under pressure from transportation, storage, to consumer consumption. Pipeline leaks are a major threat to pipeline network reliability. Regardless of their size, leaks are a significant concern due to their potentially significant impact. These impacts extend beyond downtime and repair costs, potentially including significant resource losses, personal injury, and environmental damage. The risk of leaks is increasing due to factors such as external interference, corrosion, construction defects, material failure, and ground movement, potentially leading to major gas pipeline accidents.

[0003] Leak detection technology is gaining increasing attention as a means of ensuring safe equipment operation. Over the past few decades, considerable effort has been invested in research to mitigate the catastrophic impact of gas leaks. However, simply detecting the presence of a gas leak is insufficient to determine effective countermeasures. Before addressing these issues, it is essential to understand the leak's location and high-risk areas, a key area of research in pipeline reliability assurance. Therefore, timely and accurate identification of pipeline leak sources is of paramount importance.

[0004] Currently, natural gas pipeline leak detection still relies primarily on manual inspections, requiring on-site personnel to conduct individual inspections. This method relies heavily on individual experience and attentiveness, significantly increasing the on-site personnel's workload and the company's maintenance costs, and is not safe, efficient, or reliable. The Internet of Things (IoT) is an extension and expansion of the internet, connecting any object to the internet through information sensing devices. Narrowband Internet of Things (NB-IoT) is one of the most commonly used IoT technologies. Built on cellular networks, it offers wide coverage, massive connectivity, low power consumption, and low cost, and holds great promise for applications in scenarios such as smart monitoring and smart homes. However, natural gas pipeline leak monitoring systems based on NB-IoT technology are still prone to missed detections and struggle to effectively predict high-risk leak areas. Summary of the Invention

[0005] The technical problems to be solved by the present invention are:

[0006] The existing natural gas pipeline leakage monitoring system is prone to missed detections and has difficulty in effectively predicting high-leakage areas.

[0007] The present invention is to solve the above technical problems using the following technical solutions:

[0008] The present invention provides a natural gas pipeline leakage monitoring system based on NB-IoT technology, comprising: a data acquisition module, a user terminal, a Beidou positioning module, a cloud platform, and a wireless communication module; the data acquisition module is used to collect natural gas pipeline status data through sensors, the Beidou positioning module is used to collect the position of the sensor, and the pipeline status data and position data are sent to the cloud platform through the wireless communication module. The cloud platform is used to determine whether there is a status abnormality based on the collected natural gas pipeline status data. If the pipeline has a status abnormality, the pipeline status information, alarm information, and position information are sent to the user terminal through the wireless communication module. The user terminal is used to realize visualization of the pipeline status information and warning information. The cloud platform is also used to predict high-leakage areas of the pipeline based on historical pipeline status data, and redeploy sensor positions according to the results of the high-leakage areas.

[0009] Furthermore, the data acquisition module includes a plurality of collectors, each of which is connected to a temperature sensor, a pressure sensor and a humidity sensor.

[0010] Furthermore, the wireless communication module is a NB-IOT module, and the communication protocol between the NB-IOT module and the cloud platform is the MQTT protocol.

[0011] Furthermore, the cloud platform is configured with a data anomaly analysis model, a pipeline pressure state prediction model, and a leakage-prone area prediction model;

[0012] The data anomaly analysis model is based on the isolation forest algorithm and is used to determine whether there are anomalies in the pipeline status data;

[0013] The pipeline state prediction model is based on an LSTM network, which takes the collected time series pressure data as input and the pipeline pressure at the next moment as output, and is used to predict whether the pipeline pressure at the next moment is abnormal;

[0014] The high-leakage area prediction model is based on the K-means clustering algorithm and is used to predict the high-leakage area of the pipeline based on the historical status data of the pipeline, providing a basis for redeploying the sensor position.

[0015] Furthermore, the function implementation process of the data anomaly analysis model is as follows:

[0016] For the data set X={x 1, x 2,.., x n}, where each data point x i By pressure x 1. Temperature x 2 and humidity x 3. Determine the number of isolation trees T and the size of each subsample n ;

[0017] For each subsample, an isolation tree is constructed and the data points are calculated. x i In the t The path length in an isolation tree is h t ( x i ), the expected length of the path is:

[0018] ;

[0019] in T is the number of isolation trees;

[0020] Calculating anomaly scores s ( x i ):

[0021] ;

[0022] in, c ( n ) is the average path length, for n data points, whose values are:

[0023] ;

[0024] in, H ( n ) is the n harmonic numbers;

[0025] like Greater than the first threshold , then the data point is considered to be an outlier;

[0026] Furthermore, the function implementation process of the leakage high-incidence area prediction model is as follows:

[0027] For the pipeline history dataset X={ x 1, x 2,.., x n}, the data point x iDivided into k clusters, and its objective function is:

[0028] ;

[0029] in S i It is i The set of data points in a cluster, μ i It is i The center of a cluster is calculated as follows:

[0030] ;

[0031] if Greater than the second threshold , it is determined to be a high-risk leakage area.

[0032] Furthermore, the first threshold The value of is 0.7~0.8, the second threshold The value is: 0.5~1.

[0033] Compared with the prior art, the present invention has the following beneficial effects:

[0034] The present invention uses NB-IOT technology to achieve efficient transmission of sensor data, combined with cloud-based intelligent analysis to quickly detect abnormal patterns in pipeline status. Through real-time, intelligent monitoring, the identification time of leakage accidents is shortened from several hours of traditional manual inspections to several minutes, ensuring that problems can be discovered and handled at an early stage. The present invention uses predictive maintenance functions to provide early warnings of potential failure risks and avoid the occurrence of sudden leakage accidents. The use of forest algorithms and K-means clustering algorithms to form data-driven decisions reduces false alarm and missed alarm rates, and by predicting high-incidence locations of pipeline leakage, optimizes the deployment of sensor devices, and provides strong guarantees for the safe operation of pipelines. In addition, the present invention improves the convenience of management. Staff do not need to frequently travel to the site, and can view data and warning information in real time through the cloud platform or local QT interface, significantly reducing manpower investment and operation and maintenance costs.

[0035] The system presented in this invention significantly improves accuracy, real-time performance, and safety, not only increasing pipeline management efficiency but also providing a new solution for intelligent management of natural gas pipelines. The application of this system will effectively drive the industry toward intelligent and efficient development, providing strong technical support for ensuring pipeline operation safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 This is a schematic diagram of the structure of a natural gas pipeline leakage monitoring system based on NB-IoT technology in an embodiment of the present invention;

[0037] Figure 2 Schematic diagram of the hardware of the embedded system in an embodiment of the present invention;

[0038] Figure 3 This is a diagram showing a cloud platform for a natural gas pipeline leakage monitoring system according to an embodiment of the present invention;

[0039] Figure 4 The local QT pipeline leakage monitoring interface in the embodiment of the present invention is displayed

[0040] Figure 5 This is the overall structure of the natural gas pipeline leakage monitoring system based on NB-IoT technology in an embodiment of the present invention. DETAILED DESCRIPTION

[0041] In order to enable those skilled in the art to better understand the present invention, exemplary embodiments or examples of the present invention will be described below with reference to the accompanying drawings. Obviously, the described embodiments or examples are only some of the embodiments or examples of the present invention, and not all of them. Based on the embodiments or examples of the present invention, all other embodiments or examples obtained by those skilled in the art without creative work should fall within the scope of protection of the present invention.

[0042] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0043] Specific implementation plan one: The present invention provides a natural gas pipeline leakage monitoring system based on NB-IoT technology, including: a data acquisition module, a user terminal, a Beidou positioning module, a cloud platform and a wireless communication module; the data acquisition module is used to collect natural gas pipeline status data through sensors, the Beidou positioning module is used to collect the position of the sensor, and the pipeline status data and position data are sent to the cloud platform through the wireless communication module. The cloud platform is used to determine whether there is a state abnormality based on the collected natural gas pipeline status data. If the pipeline has a state abnormality, the pipeline status information, alarm information, and position information are sent to the user terminal through the wireless communication module. The user terminal is used to realize the visualization of pipeline status information and warning information. The cloud platform is also used to predict high-incidence areas of the pipeline based on the historical status data of the pipeline, and redeploy the sensor position according to the results of the high-incidence areas of the leakage.

[0044] The monitoring system also includes a control module, which is used to convert the analog data signal of the pipeline status collected by the collection module into a digital data signal, and send the converted pipeline status data and position data to the cloud platform through the wireless communication module.

[0045] Specific implementation plan 2: The data acquisition module includes multiple data collectors, each of which is connected to a star instrument pressure transmitter and a DHT11 temperature and humidity sensor. The pressure transmitter is used to collect the internal pressure of the pipeline, and the DHT11 temperature and humidity sensor is used to collect the temperature and humidity around the pipeline. This implementation plan is otherwise the same as specific implementation plan 1.

[0046] Specific implementation scheme three: The wireless communication module is an NB-IOT module, and the communication protocol between the NB-IOT module and the cloud platform is the MQTT protocol. This implementation scheme is otherwise the same as the specific implementation scheme two.

[0047] Specific implementation plan 4: The cloud platform is configured with a data anomaly analysis model, a pipeline pressure state prediction model, and a leakage high-incidence area prediction model;

[0048] The data anomaly analysis model is based on the isolation forest algorithm and is used to determine whether there are anomalies in the pipeline status data;

[0049] The pipeline state prediction model is based on an LSTM network, which takes the collected time series pressure data as input and the pipeline pressure at the next moment as output, and is used to predict whether the pipeline pressure at the next moment is abnormal;

[0050] The high-leakage area prediction model is based on the K-means clustering algorithm and is used to predict high-leakage areas of the pipeline based on the historical state data of the pipeline, providing a basis for redeploying sensor locations. The rest of this embodiment is the same as the specific embodiment three.

[0051] Specific implementation plan 5: The function implementation process of the data anomaly analysis model is as follows:

[0052] For the data set X={ x 1, x 2,.., x n}, where each data point x i By pressure x 1. Temperature x 2 and humidity x 3. Determine the number of isolation trees T and the size of each subsample n ; Normalize the data to [0,1] to eliminate the influence of different dimensions;

[0053] For each subsample, an isolation tree is constructed and the data points are calculated. x i In the t The path length in an isolation tree is ht ( x i ), the expected length of the path is:

[0054] ;

[0055] in T is the number of isolation trees;

[0056] Calculating anomaly scores s ( x i ):

[0057] ;

[0058] in, c ( n ) is the average path length, for n data points, whose values are:

[0059] ;

[0060] in, H ( n ) is the n harmonic number; approximately: ,

[0061] like Greater than the first threshold , then the data point is considered to be an outlier;

[0062] Using the Isolation Forest algorithm, this invention can quickly and accurately detect abnormal patterns in pressure, temperature, and humidity data, enabling real-time monitoring and early warning of natural gas pipeline leaks. This method not only improves the real-time and accuracy of monitoring but also reduces false positives and missed alerts, providing a strong guarantee for the safe operation of natural gas pipelines and enabling measures to be taken. This implementation plan is otherwise identical to Specific Implementation Plan 4.

[0063] Specific implementation plan six: The function realization process of the pipeline state prediction model is: the collected time series pressure data x t , in the input layer, the time series pressure data x t Input into the LSTM network, data is processed in the LSTM layer to capture long-term dependencies in the time series; the output of the LSTM unit Indicates time t The hidden state of t Information learned at all previous time steps in, is the cell state, and are the hidden state and cell state of the previous time step respectively; the output of the LSTM layer Passed to a fully connected layer (or dense layer) to predict the pipeline state at the next time step T+1 ;according to Output the data. is the weight matrix, is the bias term; the formula is concretely: .

[0064] if If the preset range is exceeded, an early warning is triggered. The rest of this implementation plan is the same as the specific implementation plan five.

[0065] Specific implementation plan seven: The functional implementation process of the leakage high-incidence area prediction model is as follows:

[0066] The K-means clustering algorithm is used to analyze high-incidence areas of leakage and optimize sensor deployment locations.

[0067] For the pipeline history dataset X={ x 1, x 2,.., x n}, the data point x i Divided into k clusters, and the goal is to minimize the sum of squared errors within the clusters:

[0068] ;

[0069] in S i It is i The set of data points in a cluster, μ i It is i The center of a cluster is calculated as follows:

[0070] ;

[0071] if Greater than the second threshold , it is determined to be a high-risk area for leakage. The rest of this implementation plan is the same as the specific implementation plan six.

[0072] Specific implementation plan eight: the first threshold The value of is 0.7~0.8, the second threshold The value of is: 0.5~1. The rest of this implementation plan is the same as the specific implementation plan seven.

[0073] The monitoring system of the present invention uses the NB-IOT data transmission system to realize the interactive data transmission between the cloud platform pipeline leakage monitoring system and the local pipeline, collects and generates the pipeline leakage monitoring system display data through sensors, and uses the NB-IOT data transmission system to transmit it to the cloud platform pipeline leakage detection system in real time, and then uses Python programming technology to generate the QT interface of the local natural gas pipeline monitoring platform to import the data from the cloud platform to the local end for log generation and data visualization. At the same time, the cloud pre-trained model can be loaded to support local reasoning while predicting the life status of the pipeline and detecting abnormal pressure, temperature and humidity of the pipeline. The staff remotely controls the pipeline leakage monitoring system through the NB-IOT data transmission system, so that the staff does not need to go to the location of the sensor for on-site operation, thereby improving the convenience and real-time performance of the pipeline leakage monitoring system and meeting the applicability of the pipeline leakage monitoring system to different display occasions.

[0074] like Figures 1 to 5 As shown, the monitoring system of the present invention adopts a modular approach, and the overall structure is divided into four layers: perception layer, network layer, platform layer and application layer.

[0075] The function of the perception layer is to collect information about the pressure, temperature, humidity and location of the equipment in the pipeline through sensors and monitors, and then transmit the data to the network layer after integration. Figure 2 As shown, specifically including:

[0076] Step S1: Use the star instrument pressure transmitter to collect pipeline pressure data, the DHT11 temperature and humidity sensor to measure the temperature and humidity in the environment, and the GPS / Beidou positioning system to record the sensor position;

[0077] Step S2: To prevent excessive data transmission from being detrimental to data storage, during the data collection process, the pressure sensor, temperature and humidity sensor, and GPS / Beidou positioning system are controlled to collect data at a frequency of once every 5 minutes.

[0078] Step S3: Using an RS-485 communication circuit, the circuit uses the MAX3485FESA chip to convert the serial port level into the RS-485 interface level; the STM32 main control chip controls interrupt 1 to obtain the pipeline pressure data on the RS-485 bus through the Modbus-RTU communication protocol, reads the temperature and humidity data around the device and obtains the latitude and longitude location information of the device, packages the obtained data into JSON, and transmits the data to the network layer.

[0079] The DHT11 digital sensor integrates a composite sensor for temperature and humidity acquisition and digital signal output, using a single-wire serial interface. This allows for simple connection and convenient data collection. The Xingyi CYYZ18 pressure transmitter outputs an RS-485 digital signal with a measurement range of 0 to 3.5 MPa and a test accuracy of 0.25% FS.

[0080] The network layer uses cellular networks and the MQTT network protocol to upload processed data to the cloud platform server. Specifically, it includes:

[0081] Step S1: The transmission technology uses the BC20 module that integrates NB-IOT and GNSS dual systems. This chip can not only use NB-IOT for data upload, but also use the global navigation satellite system for device positioning;

[0082] Step S2: The communication protocol uses the cellular network and MQTT protocol to upload the processed data to the cloud platform server. The data is uploaded in a subscription / distributed mode to ensure the reliability and real-time performance of the transmission.

[0083] like Figure 3 As shown in the figure, the functions of the platform layer are designed based on the ONENET Internet of Things platform. The product equipment management is established using the Internet of Things platform, and the real-time data monitoring platform is established using the data visualization in its application development platform. The staff can view it through the WEB terminal;

[0084] The function of the application layer is to realize data visualization through the local QT interface, such as Figure 4 As shown, it includes pressure trend, temperature and humidity display and map positioning, and supports offline running of pre-trained models; specifically, it includes:

[0085] Step S1, interface design, using Python programming technology combined with pyqt5 to develop QT interface;

[0086] Step S2: Data visualization, supporting real-time display of pressure trend graphs, temperature and humidity change curves, and map positioning information, while generating an operation log;

[0087] Step S3: Offline analysis: users can load pre-trained models for local data analysis to meet the needs of use in an off-network environment.

[0088] The modular structure makes the natural gas pipeline leak monitoring system easier to manage. Each layer collaborates with the others to complete the required functions of the entire system. Because NB-IoT does not automatically activate the Packet Data Protocol (PDP), the main control chip sends AT commands via UART2 to activate the PDP context, allowing the device to log in to the PS domain and enable data flow across the network. Registration with the OneNET IoT cloud platform is performed via AT commands. The main control chip packages the acquired data into JSON format and uses AT commands to control the NB-IoT module to upload the data to the pipeline leak monitoring system via the MQTT protocol. This method parses access requests from the NB-IoT transmission system to determine the terminal identity information of the transmission system and further determines whether the NB-IoT has access rights to the pipeline leak monitoring system. This ensures that only NB-IoT data transmission systems with appropriate access rights can access the pipeline leak monitoring system, preventing illegal use of the NB-IoT data transmission system's data transmission bandwidth and improving the efficiency and security of the NB-IoT data transmission system's data transmission bandwidth.

[0089] The core board mainly includes the power supply part, the main control chip part, and the signal acquisition part. The power supply part is a 12 / 24V voltage input with an EMC protection circuit to prevent the power supply end from being struck by lightning and surges, and can suppress common-mode and differential-mode interference. It is equipped with LMR14030SDDAR and ASM1117 voltage regulator chips to provide 5V and 3.3V power for the acquisition part and the main control chip; the main control part uses the STM32L151RCT6 chip, which has low power consumption and is equipped with high- and low-speed external crystal oscillators, download circuits, and serial ports; the signal acquisition part mainly includes the RS485 interface and AD acquisition port. The RS485 interface circuit uses the MAX3485EESA signal conversion chip, which has lightning protection, surge protection, and anti-interference capabilities. AD acquisition is mostly 4-20mA current signal, and the signal AD acquisition is achieved through a voltage divider circuit. The two acquisition methods can be selected according to sensor requirements.

[0090] Although the present invention is disclosed as above, the scope of protection disclosed by the present invention is not limited thereto. Those skilled in the art of the present invention may make various changes and modifications without departing from the spirit and scope of the present invention, and these changes and modifications will fall within the scope of protection of the present invention.

Claims

1. A natural gas pipeline leakage monitoring system based on NB-IoT technology, characterized in that: include: A data acquisition module, a user terminal, a Beidou positioning module, a cloud platform, and a wireless communication module; the data acquisition module is used to collect natural gas pipeline status data through sensors, the Beidou positioning module is used to collect the location of the sensor, and the pipeline status data and location data are sent to the cloud platform via the wireless communication module. The cloud platform is used to determine whether there is a status anomaly based on the collected natural gas pipeline status data. If there is a pipeline status anomaly, the pipeline status information, alarm information, and location information are sent to the user terminal via the wireless communication module. The user terminal is used to realize the visualization of pipeline status information and warning information. The cloud platform is also used to predict high-leakage areas of the pipeline based on historical pipeline status data and redeploy sensor positions according to the results of the high-leakage areas; The cloud platform is equipped with a data anomaly analysis model, a pipeline pressure state prediction model, and a leakage high-incidence area prediction model; The data anomaly analysis model is based on the isolation forest algorithm and is used to determine whether there are anomalies in the pipeline status data; The pipeline pressure state prediction model is based on an LSTM network, which takes the collected time series pressure data as input and the pipeline pressure at the next moment as output, and is used to predict whether the pipeline pressure at the next moment is abnormal; The high-leakage area prediction model is based on the K-means clustering algorithm and is used to predict the high-leakage area of the pipeline based on the historical status data of the pipeline, providing a basis for redeploying the sensor position; The data acquisition module includes multiple collectors, each of which is connected to a temperature sensor, a pressure sensor and a humidity sensor; The wireless communication module is an NB-IOT module, and the communication protocol between the NB-IOT module and the cloud platform is the MQTT protocol; The functional implementation process of the data anomaly analysis model is as follows: For the data set X={ x 1, x 2,.., x n }, where each data point x i By pressure x 1. Temperature x 2 and humidity x 3. Determine the number of isolation trees T and the size of each subsample n ; For each subsample, an isolation tree is constructed and the data points are calculated. x i In the t The path length in an isolation tree is h t ( x i ), the expected length of the path is: ； in T is the number of isolation trees; Calculating anomaly scores s ( x i ): ； in, c ( n ) is the average path length, for n data points, whose values are: ； in, H ( n ) is the n harmonic numbers; like Greater than the first threshold , then the data point is considered to be an outlier.

2. The natural gas pipeline leakage monitoring system based on NB-IoT technology according to claim 1 is characterized in that: The functional implementation process of the leakage high-incidence area prediction model is as follows: For the pipeline history dataset X={ x 1, x 2,.., x n }, the data point x i Divided into k clusters, and its objective function is: ； in S i It is i The set of data points in a cluster, μ i It is i The center of a cluster is calculated as follows: ； if Greater than the second threshold , it is determined to be a high-risk leakage area.

3. The natural gas pipeline leakage monitoring system based on NB-IoT technology according to claim 2 is characterized in that: The first threshold The value of is 0.7~0.8, the second threshold The value is: 0.5~1.

Images