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

Abstract

The invention discloses a natural gas pipeline leakage monitoring system based on an NB-IoT (Narrow Band Internet of Things) technology, relates to the field of wireless communication, and aims to solve the problems that an existing natural gas pipeline leakage monitoring system is easy to leak and is difficult to effectively predict a leakage high-incidence area. Comprising a data acquisition module, a user side, a Beidou positioning module, a cloud platform and a wireless communication module, the data collection module is used for collecting natural gas pipeline state data, the Beidou positioning module is used for collecting the position of a sensor, the pipeline state data and position data are sent to the cloud platform through the wireless communication module, and the cloud platform is used for judging whether the pipeline state is abnormal or not. Pipeline state information, alarm information and position information are sent to the user side through the wireless communication module, the user side is used for achieving visualization of the pipeline state information and the alarm information, and the cloud platform is further used for predicting a leakage high-incidence area of the pipeline based on historical state data of the pipeline and redeploying the position of the sensor according to a result of the leakage high-incidence area.

Description

Technical Field

[0001] The present invention relates to the technical field of wireless communication, and more particularly, 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, and its storage and transportation safety requirements are very high. The global natural gas transportation and distribution network is very complex and still expanding. The reliability of natural gas pipeline infrastructure has become a key requirement. The characteristics of existing natural gas pipelines are as follows: The gas transmission pipeline system is a continuous and closed transportation system; from transportation, storage to user use, natural gas is in a pressurized state. The occurrence of pipeline leakage is the main factor threatening the reliability of the pipeline network. Due to the possible huge impact, pipeline leakage is an important issue regardless of the size of the leakage. These impacts go beyond the costs involved in downtime and maintenance costs, and may include a large amount of resource losses, and may also include personal injuries and environmental disasters. Due to the influence of factors such as external interference, corrosion, construction defects, material failures, and ground movement, the risk of leakage is increasing, and even major gas pipeline accidents may be triggered.

[0003] Leak detection technology, as a way to ensure the safe operation of equipment, is gradually attracting people's attention. In the past few decades, in order to offset the catastrophic effects of gas leakage, a considerable amount of effort has been invested in researching gas leak detection technology. However, simply revealing the existence of gas leakage is not enough to determine effective countermeasures. Before determining the solution measures, information such as the location of the leakage and high-risk leakage areas must be known. These works are also the research focus in the field of pipeline reliability assurance. Therefore, it is of great practical significance to detect and accurately locate the leakage source of the pipeline in a timely manner.

[0004] At present, the leakage detection of natural gas pipelines still mainly relies on manual inspections. This method requires the duty personnel to go to the site for one-by-one inspections, which largely depends on personal experience and carefulness, greatly increasing the workload of the duty personnel and the maintenance cost of the enterprise, and is not safe, efficient, and reliable enough. The Internet of Things is a product that extends and expands on the basis of the Internet, connecting any item to the Internet through information sensing devices. Narrow band internet of things (NB-IoT) is one of the currently commonly used Internet of Things technologies, built on a cellular network, with characteristics such as wide coverage, massive connections, low power consumption, and low cost, and has good application prospects in scenarios such as intelligent monitoring and smart homes. The natural gas pipeline leakage monitoring system based on NB-IoT technology is still prone to problems such as missed detections and difficulties in effectively predicting high-leakage areas. Summary of the Invention

[0005] The technical problem to be solved by the present invention is: In the existing natural gas pipeline leakage monitoring system, problems such as missed detection and difficulty in effectively predicting high-leakage areas are likely to occur.

[0006] The technical solution adopted by the present invention to solve the above technical problems: 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 positions of the sensors, 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 judge whether there is an abnormal status according to the collected natural gas pipeline status data. If the pipeline has an abnormal status, 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 the pipeline status information and early warning information. The cloud platform is also used to predict the high-leakage areas of the pipeline based on the historical pipeline status data, and redeploy the positions of the sensors according to the results of the high-leakage areas.

[0007] Further, the data acquisition module includes a plurality of collectors, and each collector is connected with a temperature sensor, a pressure sensor, and a humidity sensor.

[0008] Further, 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.

[0009] Further, the cloud platform is configured with a data anomaly analysis model, a pipeline pressure status prediction model, and a high-leakage area prediction model; The data anomaly analysis model is based on the isolation forest algorithm and is used to determine whether there is an anomaly in the pipeline status data; The pipeline status prediction model is based on the LSTM network, takes the pressure data of the collected time series as the input, and takes the pipeline pressure at the next moment as the output, and is used to predict whether there is an anomaly in the pipeline pressure at the next moment; The high-leakage area prediction model is based on the K-means clustering algorithm and is used to predict the high-leakage areas of the pipeline based on the historical pipeline status data, providing a basis for redeploying the positions of the sensors.

[0010] Further, 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 xi Composed of 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, construct an isolation tree and calculate the data point x i in the t th isolation tree with a path length of h t ( x i ), and the expected value of the path length is: ; where T is the number of isolation trees; Calculate the anomaly score s ( x i ): ; where, c ( n ) is the average value of the path length. For n data points, its value is: ; where, H ( n ) is the n th harmonic number; If is greater than the first threshold , then the data point is considered an outlier; Furthermore, the functional implementation process of the leakage high - incidence area prediction model is as follows: For the pipeline historical dataset X = { x 1, x 2,.., x n}, divide the data point x i into k clusters, and its objective function is: ; where S i is the set of data points in the i th cluster, μ i is the center of the i th cluster, and its calculation formula is: ; If is greater than the second threshold , it is determined as a high-leakage area.

[0011] Furthermore, the value of the first threshold is 0.7 - 0.8, and the value of the second threshold is 0.5 - 1.

[0012] Compared with the prior art, the beneficial effects of the present invention are as follows: The present invention realizes the efficient transmission of sensor data through NB-IoT technology, combines cloud intelligent analysis to quickly detect abnormal patterns of pipeline status, and through real-time and intelligent monitoring, shortens the identification time of leakage accidents from several hours of traditional manual inspections to several minutes, ensuring that problems can be discovered and handled in the early stage. The present invention provides early warnings of potential failure risks through predictive maintenance functions, avoiding the occurrence of sudden leakage accidents. Using the forest algorithm and K-means clustering algorithm to form data-driven decision-making reduces false alarm and missed alarm rates, and optimizes the deployment of sensor devices by predicting high-leakage locations of pipelines, providing strong guarantees for the safe operation of pipelines. In addition, the present invention improves the convenience of management. Staff do not need to frequently go to the site, and can view data and warning information in real time through the cloud platform or local QT interface, greatly reducing labor input and operation and maintenance costs.

[0013] The system of the present invention has been significantly improved in terms of accuracy, real-time performance, and security. It not only improves the efficiency of pipeline management, but also provides a new solution for the intelligent management of natural gas pipelines. The application of this system will effectively promote the industry to develop towards the direction of intelligence and high efficiency, providing strong technical support for ensuring the safe operation of pipelines. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 is a schematic structural diagram of a natural gas pipeline leakage monitoring system based on NB-IoT technology in an embodiment of the present invention; Figure 2 is a schematic hardware diagram of an embedded system in an embodiment of the present invention; Figure 3 is a display diagram of the cloud platform of the natural gas pipeline leakage monitoring system in an embodiment of the present invention; Figure 4 is a display of the local QT pipeline leakage monitoring interface in an embodiment of the present invention Figure 5 is the overall structure of a natural gas pipeline leakage monitoring system based on NB-IoT technology in an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0015] To enable those skilled in the art to better understand the solution of the present invention, the exemplary embodiments or examples of the present invention will be described below in conjunction with the accompanying drawings. Obviously, the described embodiments or examples are only a part of the embodiments or examples of the present invention, rather than all of them. Based on the embodiments or examples in the present invention, all other embodiments or examples obtained by those of ordinary skill in the art without creative efforts shall fall within the scope of protection of the present invention.

[0016] To make the above objects, features, and advantages of the present invention more obvious and understandable, the following will describe the specific embodiments of the present invention in detail with reference to the accompanying drawings.

[0017] Specific Embodiment 1: 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 positions of the sensors, 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 an abnormal status based on the collected natural gas pipeline status data. If there is an abnormal status in the pipeline, 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 visualize the pipeline status information and early warning information. The cloud platform is also used to predict the high-leakage areas of the pipeline based on the historical pipeline status data, and redeploy the positions of the sensors according to the results of the high-leakage areas.

[0018] The monitoring system further includes a control module, which is used to convert the analog data signal of the pipeline status collected by the acquisition 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.

[0019] Specific Embodiment 2: The data acquisition module includes multiple collectors, and each collector 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. Other parts of this embodiment are the same as those of Specific Embodiment 1.

[0020] Specific Embodiment 3: 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. Other parts of this embodiment are the same as those of Specific Embodiment 2.

[0021] Specific Embodiment 4: The cloud platform is configured with a data anomaly analysis model, a pipeline pressure status prediction model, and a high-leakage 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 status prediction model is based on the LSTM network. Taking the pressure data of the collected time series as the input and the pipeline pressure at the next moment as the output, it is used to predict whether there are anomalies in the pipeline pressure at the next moment; The leakage high-incidence area prediction model is based on the K-means clustering algorithm and is used to predict the leakage high-incidence area of the pipeline based on the pipeline historical status data, providing a basis for redeploying the sensor positions. Other parts of this implementation plan are the same as those of the specific implementation plan three.

[0022] Specific implementation plan five: 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 is composed of 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 between [0, 1] to eliminate the influence of different dimensions; For each subsample, construct an isolation tree and calculate the path length of the data point x i in the t th isolation tree as ht ( x i ). The expected value of the path length is: ; where T is the number of isolation trees; Calculate the anomaly score s ( x i ): ; where, c ( n ) is the average value of the path lengths. For n data points, its value is: ; where, H ( n ) is the n th harmonic number; approximately: , If is greater than the first threshold , the data point is considered an outlier; Using the Isolation Forest algorithm, the present invention can quickly and accurately detect abnormal patterns in pressure and temperature / humidity data, thereby realizing real-time monitoring and early warning of natural gas pipeline leaks. This method not only improves the real-time performance and accuracy of monitoring, but also reduces the false alarm and missed alarm rates, providing strong guarantee for the safe operation of natural gas pipelines, and measures have been taken. Other aspects of this implementation scheme are the same as those of the fourth specific implementation scheme.

[0023] Specific implementation scheme six: The functional implementation process of the pipeline state prediction model is as follows: The collected time series pressure data x t , in the input layer, the time series pressure data x t is input into the LSTM network, and data processing is performed in the LSTM layer to capture long-term dependencies in the time series; the output of the LSTM unit represents the hidden state at time t , which contains information learned from all previous time steps from t ; Among them, is the cell state, and are the hidden state and cell state of the previous time step respectively; the output of the LSTM layer is transmitted to a fully connected layer (or a dense layer) for predicting the pipeline state at the next time step T+1 ; data output is performed according to . Among them, is the weight matrix, is the bias term; the formula is specifically: .

[0024] If exceeds the preset range, an early warning is triggered. Other aspects of this implementation scheme are the same as those of the fifth specific implementation scheme.

[0025] Specific implementation scheme seven: The functional implementation process of the leakage high-incidence area prediction model is as follows: Use the K-means clustering algorithm to analyze the high-incidence areas of leaks and optimize the deployment locations of sensors.

[0026] For the pipeline historical data set X={ x 1, x 2,.., x n}, the data point x i is divided into ka cluster, with the goal of minimizing the sum of the squared errors within the cluster: ; where S i is the set of data points in the i -th cluster, μ i is the center of the i -th cluster, and its calculation formula is: ; If is greater than the second threshold , it is determined as a high-leakage area. Other parts of this implementation plan are the same as those of Specific Implementation Plan VI.

[0027] Specific Implementation Plan VIII: The value of the first threshold is 0.7 - 0.8, and the value of the second threshold is 0.5 - 1. Other parts of this implementation plan are the same as those of Specific Implementation Plan VII.

[0028] The monitoring system of the present invention uses the NB-IOT data transmission system to realize the data interaction and transmission between the cloud platform pipeline leakage monitoring system and the local pipeline. Through sensors, the data for the pipeline leakage monitoring system is collected and generated, and then transmitted to the cloud platform pipeline leakage detection system in real time by using the NB-IOT data transmission system. Then, by using PYTHON programming technology, the QT interface of the natural gas pipeline monitoring platform at the local end is generated to import the data from the cloud platform to the local end for log generation and data visualization display. At the same time, the pre-trained model on the cloud can be loaded to support local inference while predicting the life status of the pipeline and detecting abnormalities in pipeline pressure, temperature, and humidity. The staff can remotely control the pipeline leakage monitoring system through the NB-IOT data transmission system, so that there is no need for the staff to go to the location of the sensor for on-site operation, 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.

[0029] As Figures 1 to 5 shown, the monitoring system of the present invention adopts a modular method, and the overall structure is divided into four layers: the perception layer, the network layer, the platform layer, and the application layer.

[0030] The function of the perception layer is to collect the pipeline pressure, temperature, humidity, and device location information through sensors and monitors, and then transmit the data to the network layer after integration. As Figure 2 shown, it specifically includes: Step S1: Use a star instrument pressure transmitter to collect pipeline pressure data, a DHT11 temperature and humidity sensor to measure the temperature and humidity in the environment, and a GPS / Beidou positioning system to record the sensor location; Step S2: To prevent excessive data transmission from being unfavorable to data storage, during the data acquisition process, control the pressure sensor, temperature and humidity sensor, and GPS / Beidou positioning system to collect data at a frequency of once every 5 minutes. Step S3: Use an RS-485 communication circuit. The circuit uses a MAX3485FESA chip to convert the serial port level into an 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, read the temperature and humidity data around the device, and obtain the longitude and latitude position information of the device, package the obtained data into JSON, and transmit the data to the network layer.

[0031] The DHT11 digital sensor integrates a composite sensor for temperature and humidity acquisition and digital signal output, and adopts a single-wire serial method. It is simple to connect and convenient to collect. The signal output of the Xingyi CYYZ18 pressure transmitter is an RS-485 digital signal, with a range of 0~3.5 MPa and a test accuracy of 0.25%FS.

[0032] The function of the network layer is to upload the processed data to the cloud platform server using the cellular network and the MQTT network protocol; specifically including: Step S1: The transmission technology uses a BC20 module integrating NB-IOT and GNSS dual systems. This chip can not only upload data using NB-IOT, but also locate the device using the global navigation satellite system. Step S2: The communication protocol uses the cellular network and the MQTT protocol to upload the processed data to the cloud platform server, and uploads the data through the subscription / distributed mode to ensure the reliability and real-time performance of the transmission.

[0033] As Figure 3 shown, the function of the platform layer is designed based on the ONENET Internet of Things platform. The Internet of Things platform is used to establish product device management, and a real-time monitoring platform for data is established using data visualization in its application development platform. Staff can view it through the WEB side. The function of the application layer is to realize data visualization through the local QT interface. As Figure 4 shown, it includes pressure trend, temperature and humidity display, and map positioning, and at the same time supports offline operation of the pre-trained model; specifically including: Step S1: Interface design, using Python programming technology combined with pyqt5 to develop a QT interface. Step S2: Data visualization, supporting real-time display of pressure trend charts, temperature and humidity change curves, and map positioning information, and generating operation logs at the same time. Step S3: Offline analysis. The user can load the pre-trained model for local data analysis to meet the usage requirements in a network-free environment.

[0034] The modular structure makes the natural gas pipeline leakage monitoring system easier to manage. Each layer cooperates with other layers to complete the functions required by the entire system. Since the NB-IOT does not have the function of automatically activating the Packet Data Protocol (PDP), the main control chip needs to send AT commands through UART2 to activate the PDP context, enabling the device terminal to log in to the PS domain, thereby realizing data circulation between networks. Register through AT commands on the OneNET Internet of Things cloud platform. The main control chip packs the acquired data into JSON and uses AT commands to control the NB-IoT module to upload the data to the pipeline leakage monitoring system through the MQTT protocol. Through the above method, the access request from the NB-IOT transmission system is parsed and processed to determine the terminal identity information of the transmission system, and further determine whether the NB-IOT has the access permission to the pipeline leakage monitoring system, ensuring that only the NB-IOT data transmission system with corresponding access permission can intervene in the pipeline leakage monitoring system, avoiding the illegal misuse of the data transmission bandwidth of the NB-IOT data transmission system, and improving the data transmission bandwidth usage efficiency and usage security of the NB-IOT data transmission system.

[0035] The core board mainly includes a power supply part, a main control chip part, and a signal acquisition part. The power supply part has a voltage input of 12 / 24V and is equipped with an EMC protection circuit to prevent lightning strikes and surges at the power supply end, and can suppress common-mode and differential-mode interference. It is equipped with LMR14030SDDAR and ASM1117 voltage regulator chips to supply 5V and 3.3V to 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, a download circuit, and a serial port; the signal acquisition part mainly includes an RS485 interface and an AD acquisition port. The RS485 interface circuit uses the MAX3485EESA signal conversion chip, which has the ability to prevent lightning strikes, surges, and interference. The AD acquisition is mostly 4-20mA current signals, and the signal AD acquisition is realized through a voltage division circuit. The two acquisition methods can be selected according to the sensor requirements.

[0036] Although the present invention is disclosed as above, the protection scope of the present invention is not limited thereto. Those skilled in the art of the present invention can make various changes and modifications without departing from the spirit and scope of the present invention, and these changes and modifications will all fall within the protection scope of the present invention.

Claims

1. A natural gas pipeline leakage monitoring system based on NB-IoT technology, characterized in that, 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 positions of the sensors, 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 an abnormal status based on the collected natural gas pipeline status data. If there is an abnormal status in the pipeline, 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 visualize the pipeline status information and early warning information. The cloud platform is also used to predict the high-leakage areas of the pipeline based on the historical pipeline status data, and redeploy the positions of the sensors according to the results of the high-leakage areas; The cloud platform is configured with a data anomaly analysis model, a pipeline pressure status prediction model, and a high-leakage 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 status prediction model is based on the LSTM network, takes the pressure data of the collected time series as the input, and the pipeline pressure at the next moment as the output, and is used to predict whether there is an anomaly in the pipeline pressure at the next moment; The high-leakage area prediction model is based on the K-means clustering algorithm and is used to predict the high-leakage areas of the pipeline based on the historical pipeline status data, providing a basis for redeploying the positions of the sensors.

2. The natural gas pipeline leakage monitoring system based on NB-IoT technology according to claim 1, characterized in that, The data acquisition module includes multiple collectors, and each collector is connected with a temperature sensor, a pressure sensor, and a humidity sensor.

3. The natural gas pipeline leakage monitoring system based on NB-IoT technology according to claim 2, characterized in that, 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.

4. The natural gas pipeline leakage monitoring system based on NB-IoT technology according to claim 3, wherein The functional implementation process of the data anomaly analysis model is: For the dataset X = { x 1, x 2,.., x n }, where each data point x i is composed of pressure x 1, temperature x 2, and humidity x 3, determine the number of isolation trees T and the size of each subsample n ; Construct an isolation tree for each subsample and calculate the data points x i The path length in the t th isolation tree is h t ( x i ), and the expected value of the path length is: ； wherein T is the number of isolation trees; Calculate anomaly score s ( x i ): ； wherein, c ( n ) is the average value of the path length, and for n data points, its value is: ； Among them, H ( n ) is the n th harmonic number; If is greater than the first threshold , then this data point is considered an outlier.

5. The natural gas pipeline leakage monitoring system based on NB-IoT technology according to claim 4, wherein The functional implementation process of the high-leakage area prediction model is: For the pipeline historical dataset X = { x 1, x 2,.., x n }, divide the data points x i into k clusters, and its objective function is: ； wherein S i is the i set of data points in the μ i is the center of the i cluster, and its calculation formula is: ； If is greater than a second threshold , it is determined as a high leakage prone area.

6. The natural gas pipeline leakage monitoring system based on NB-IoT technology according to claim 5, characterized in that, The first threshold takes a value of 0.7 to 0.8, and the second threshold takes a value of: 0.5 to 1.

Images