Digital twin system for detecting and locating natural gas leaks in utility tunnels based on sound source localization

Abstract

We provide a digital twin system for detecting and locating natural gas leaks in utility tunnels based on sound source localization. [Solution] In this system, a methane sensor is placed in the natural gas chamber of a common utility seismic tunnel, and when it detects that the methane concentration has reached a preset threshold, it sends an alarm signal to a mobile unit. The mobile unit autonomously moves to the natural gas leak area in the natural gas chamber based on the alarm signal and collects natural gas leak acoustic signals. The signal collection and location unit performs leak location for the natural gas leak source using a leak acoustic difference algorithm and feeds back the location of the located natural gas leak source to the mobile unit. The mobile unit autonomously moves to the location of the natural gas leak source and transmits the location of the leak source to a data aggregation unit on the common utility seismic tunnel server. The twin system updates the location results in a digital twin model in real time and virtually visualizes the common utility seismic tunnel.

Description

[Technical Field]

[0001] The present invention relates to the field of digital twin technology, and in particular to a digital twin system for detecting and locating natural gas leaks in utility tunnels based on sound source localization. [Background technology]

[0002] A utility tunnel is a form of intensive use of urban underground space, whereby municipal public pipelines (for example, electricity, communications, water supply and drainage, natural gas, etc.) are laid in the same space, thereby realizing efficient resource sharing and maintaining boundaries. However, utility tunnels often pose an extremely high risk in the event of an accident, especially a natural gas leak.

[0003] Natural gas is a flammable and explosive gas, and when accumulated in a confined underground space, it is prone to explosions and fires, resulting in serious property losses and human casualties. Furthermore, natural gas leaks can cause environmental pollution and secondary disasters, further increasing the scope and severity of the accident. Therefore, effective monitoring of utility ducts, especially the prevention and response to natural gas leak accidents, is extremely important.

[0004] Natural gas leaks in utility tunnels can pose a serious safety concern. Most conventional natural gas leak detection methods rely on direct detection using gas sensors, but in complex utility tunnel environments, the detection range of a single sensor is limited and it can be subject to interference from other factors, making it difficult to accurately locate the leak source.

[0005] Therefore, there is an urgent need to provide a technical solution to address the shortcomings of the prior art. Summary of the Invention

[0006] The purpose of the present application is to provide a digital twin system for detecting and locating natural gas leaks in utility tunnels based on sound source localization in order to solve or mitigate the problems existing in the above-mentioned prior art.

[0007] To achieve the above objectives, the present application provides the following technical solutions:

[0008] The present application provides a digital twin system for detecting and locating natural gas leaks in a utility tunnel based on sound source localization, the system comprising: a methane sensor disposed in a natural gas chamber of the utility tunnel, configured to monitor a methane concentration in the natural gas chamber in real time and to transmit an alarm signal when it is determined that the methane concentration in the natural gas chamber has reached a preset threshold; a mobile unit that receives an alarm signal transmitted from the methane sensor and autonomously moves to a natural gas leak area in the natural gas chamber based on the alarm signal; and a signal collection and location unit disposed in the mobile unit and equipped with a microphone array, the microphone array configured to collect natural gas leakage acoustic signals in the natural gas leakage area, and in response to the natural gas leakage acoustic signals, perform leakage location to the position of a natural gas leakage source in the natural gas leakage area using a leakage acoustic difference algorithm using a pre-constructed leakage source location model, feed back the located position of the natural gas leakage source to the mobile unit so that the mobile unit autonomously moves to the position of the corresponding natural gas leakage source, and transmit the position of the natural gas leakage source to a data aggregation unit of a comprehensive utility trench server.

[0009] Preferably, the signal collection and location unit is further configured to process the collected natural gas leakage sound signal based on a wavelet transform Kalman filter method to obtain spectral data of the natural gas leakage sound signal, and determine the location of the natural gas leakage source within the natural gas leakage area based on the obtained spectral data of the natural gas leakage sound signal by the leakage sound difference algorithm.

[0010] TIFF0007748766000002.tif21170

number

[0011] TIFF0007748766000004.tif28170

number

number

[0012] TIFF0007748766000007.tif24170

number

[0013] TIFF0007748766000009.tif59170

number

[0014] Preferably, the digital twin system further includes a physical simulation model of the comprehensive utility tunnel constructed according to physical parameters of the comprehensive utility tunnel, The training data set of the leakage source location model is constructed based on the simulated positions of the natural gas leakage sources in the physical simulation model and the corresponding time delay difference simulation data, and the simulated positions of the natural gas leakage sources in the physical simulation model and the corresponding time delay difference simulation data are obtained by using the physical simulation model to simulate natural gas leakage acoustic signals at the positions of different natural gas leakage sources in the common seismic tunnel, and determining the time delay difference simulation data at which the simulated signals in the physical simulation model reach any pair of microphone simulation sensors.

[0015] TIFF0007748766000011.tif40170

[0016] TIFF0007748766000012.tif44170

[0017] TIFF0007748766000013.tif37170

number

number

[0018] In an embodiment of the present application, in a digital twin system for detecting and locating natural gas leaks in a common utility tunnel based on sound source localization, a methane sensor is disposed in a natural gas chamber of the common utility tunnel, and monitors the methane concentration in the natural gas chamber in real time. When it detects that the methane concentration in the natural gas chamber has reached a predetermined threshold, it sends an alarm signal to a mobile unit. The mobile unit receives the alarm signal transmitted from the methane sensor and autonomously moves to the natural gas leak area in the natural gas chamber based on the alarm signal. A signal collection and localization unit is disposed in the mobile unit, and the signal collection and localization unit is provided with a microphone array to collect natural gas leakage sound signals in the natural gas leakage area. In accordance with the natural gas leakage sound signals, leak localization is performed on the location of the natural gas leak source in the natural gas leakage area using a leakage sound difference algorithm. The location of the located natural gas leak source is fed back to the mobile unit, and the mobile unit autonomously moves to the location of the corresponding natural gas leak source and sends the location of the natural gas leak source to the data aggregation unit of the common utility tunnel server.

[0019] This allows the microphone array to monitor the natural gas leak acoustic signals and accurately locate the source of the natural gas leak from the difference in acoustic waves, overcoming the problems of conventional gas sensors, such as their limited detection range in complex environments and their susceptibility to interference. This enables the timely, rapid, and accurate detection of natural gas leaks in utility tunnels, assisting in the accurate location of the source of the natural gas leak and effectively shortening the accident response time. [Brief explanation of the drawings]

[0020] The drawings in the specification that form a part of this application are intended to provide a further understanding of the application, and the illustrative examples and descriptions thereof are intended to interpret the application and are not intended to unduly limit the application.

[0021] [Figure 1]FIG. 1 is a scenario schematic diagram of a digital twin system for detecting and localizing natural gas leaks in utility tunnels based on sound source localization according to some embodiments of the present application. [Figure 2] FIG. 1 is a technical principle diagram of a digital twin system for detecting and localizing natural gas leaks in utility tunnels based on sound source localization according to some embodiments of the present application. [Figure 3] 1 is a flowchart of detecting natural gas leaks in utility tunnels based on sound source localization according to some embodiments of the present application; [Figure 4] FIG. 1 is a design diagram of a digital twin frame architecture according to some embodiments of the present application. [Figure 5] FIG. 2 is a two-dimensional spectrum diagram after wavelet transformation according to some embodiments of the present application. [Figure 6] FIG. 2 is a one-dimensional spectrum diagram after wavelet transformation according to some embodiments of the present application. DETAILED DESCRIPTION OF THE INVENTION

[0022] The present invention will be described in detail below in conjunction with examples and with reference to the drawings. Each example is provided by way of interpretation of the present application and is not intended to limit the present application. In fact, it will be apparent to those skilled in the art that modifications and variations can be made to the present application without departing from the scope or spirit of the present application. For example, features shown or described as part of one embodiment can be used in another embodiment to produce yet another embodiment. All other embodiments that can be obtained by a person skilled in the art based on the embodiments of the present invention should fall within the scope of protection of the present invention.

[0023] Currently, conventional gas sensors are prone to interference when monitoring natural gas leaks in complex utility tunnels, resulting in inaccurate location of natural gas leak sources. In response to this problem, this application proposes a digital twin system for detecting and locating natural gas leaks in utility tunnels based on sound source localization, which uses a microphone array to accurately locate the location of natural gas leaks through sound wave analysis technology, thereby timely and accurately locating the location of natural gas leak sources in complex utility tunnel environments.

[0024] The digital twin system is designed hierarchically, dividing it into physical, data, algorithm, and function layers. The physical layer includes physical entities and logical rules. The physical entities are the actual utility trench facility and the natural gas transmission pipeline contained within it, and the logical rules define the operating methods and behavioral rules of these physical objects in the digital twin system. The logical layer ensures that the system can accurately map real-world physical conditions and serves as the basis for the digital twin system data.

[0025] The data layer is responsible for collecting and managing fixed data from physical spaces and real-time sensor data, including environmental data from utility tunnels, methane sensor data, and leak detection data, ensuring that the algorithm layer can process and analyze based on accurate and timely data. The algorithm layer uses technologies such as deep learning, signal processing, and noise reduction to analyze and calculate the raw data provided by the data layer. Deep learning models are used to identify the characteristics of natural gas leaks, which, combined with signal processing technology, improve the accuracy of data analysis and enable accurate localization of the leak source.

[0026] Specifically, the functional layer includes leak warnings, visualization of utility tunnel data, and location of leak sources. By performing real-time monitoring and data analysis, the functional layer visually displays the status of natural gas in utility tunnels, issues an alarm when an abnormality is detected, and localizes the leak location, allowing for timely action.

[0027] Specifically, the utility tunnel server uses Blender to model the utility tunnel's experimental modules and various sensors, obtaining virtual models of various objects on the experimental platform. Materials are then applied to the virtual models using a shader, and finally a texture map is obtained by baking, and the texture map corresponding to the virtual model is imported into Unity3D. A digital twin system is constructed in Unity3D, and the model positions are set in Unity3D based on the geometric relationships between the various virtual models.

[0028] As shown in Figures 1 to 6, the digital twin system for detecting and locating natural gas leaks in utility tunnels based on sound source localization includes a methane sensor, a mobile unit, and a signal collection and localization unit. The methane sensors are placed in the natural gas chamber of the utility tunnel, with one methane sensor placed every 15 meters according to pipeline construction in the urban underground utility tunnel, allowing real-time monitoring of the methane concentration in the natural gas chamber. The natural gas chamber is the space inside the utility tunnel where the natural gas pipeline is located.

[0029] Below, with reference to Figure 3, the process of detecting natural gas leaks in utility tunnels based on sound source localization will be explained in conjunction with the configuration of a digital twin system.

[0030] In step S101, if a natural gas leak occurs in the pipeline, the methane sensor monitors that the methane concentration in the natural gas chamber reaches a preset threshold, and then sends an alarm signal for natural gas leakage.

[0031] In step S102, the mobile unit receives the alarm signal transmitted from the methane sensor and autonomously moves to the natural gas leak area within the natural gas chamber based on the alarm signal. An autonomous navigation mobile robot is employed as the mobile unit, and is capable of autonomously moving within the utility tunnel. Specifically, the mobile robot is equipped with a wireless communication module connected to the utility tunnel's internal network, and the alarm signal is quickly transmitted to the mobile unit via the internal network communication. The alarm signal also includes the number and coordinate information of the methane sensor that issued the alarm signal, and indicates the area where a leak may be occurring.

[0032] The mobile robot is equipped with a built-in laser radar for position synchronization, map construction, and obstacle avoidance, and the corresponding driver package is installed and the laser radar node rplidar_ros is launched. The mobile robot uses a Raspberry Pi as the master chip, communicates with ROS via the serial port, controls the mobile robot's chassis using the rosserial or ros_control package, controls the mobile robot's linear and angular velocity by issuing cmd_vel in ROS, provides the mobile robot with action-based path planning based on the move_base method, and realizes the mobile robot's path navigation through a planner for global path planning and local real-time planning.

[0033] In addition, two types of cost maps, globable_costmap and local_planner, are introduced to the mobile robot to represent the weights of obstacles and routes, and sensors can detect the surrounding environment in real time and dynamically adjust the direction of travel to avoid obstacles. Multiple cruising points are set, and a ROS node is created that sequentially accesses these cruising points through the ROS navigation stack and repeatedly sends multiple target points to move_base. After receiving an alarm signal, the mobile robot launches automatic navigation and quickly travels to the area where a potential leak is occurring. In addition, in the event of a natural gas leak, multiple methane sensors may issue alarm signals simultaneously. Based on the alarm signal, it can only be determined that a natural gas leak has occurred in the area where the methane sensors are located, but the exact location of the leak cannot be determined.

[0034] In step S103, the signal collection and localization unit provided in the autonomous navigation mobile robot detects acoustic waves generated by natural gas leakage and collects natural gas leakage acoustic signals after the mobile robot moves to the potential leakage area based on the alarm signal. Specifically, the signal collection and localization unit is provided with a microphone array to collect natural gas leakage acoustic signals in the natural gas leakage area. Here, collecting natural gas leakage acoustic signals using a circularly arranged microphone array improves the spatial resolution of the natural gas leakage acoustic signals, enhances the omnidirectional sensing capability of natural gas leakage acoustic signals in utility tunnels, and can effectively capture acoustic signals propagating from different directions in complex environments.

[0035] In step S104, the signal collection and location unit locates the location of the natural gas leakage source through acoustic wave difference.

[0036] TIFF0007748766000016.tif30170

number

[0037] TIFF0007748766000018.tif19170

[0038] TIFF0007748766000019.tif33170

[0039] TIFF0007748766000020.tif40170

[0040] TIFF0007748766000021.tif17170

[0041] TIFF0007748766000022.tif32170

number

[0042] TIFF0007748766000024.tif19170

number

[0043] TIFF0007748766000026.tif47170

[0044] TIFF0007748766000027.tif64170

[0045] TIFF0007748766000028.tif19170

number

[0046] TIFF0007748766000030.tif49170

[0047] TIFF0007748766000031.tif32170

number

[0048] In this application, the acoustic simulation tool Roomsimove is used to set the propagation path of natural gas leakage sound waves, including multipath reflection and sound absorption characteristics, based on the physical parameters of the utility tunnel (e.g., wall material, size, etc.), and natural gas leakage sound sources are installed at different positions to generate acoustic signals from the different sound sources. The sound source signals include pulse signals and noise and are used to simulate sound sources in a real environment. Specifically, a physical simulation model of the utility tunnel is constructed based on the physical parameters of the utility tunnel, and natural gas leakage sound signals are simulated at the locations of different natural gas leak sources within the utility tunnel.

[0049] Next, the time delay difference simulation data of the simulation signal in the physical simulation model arriving at any pair of microphone simulation sensors is determined, and a training dataset for the leak source localization model is constructed based on the simulated location of the natural gas leak source in the physical simulation model and the corresponding time delay difference simulation data. Specifically, the arrival time delay difference of the simulation signal when it arrives at each pair of microphone simulation sensors is calculated, and the time delay difference simulation data is recorded as input features for training the leak source localization model. The simulated location of the natural gas leak source corresponding to each simulation signal is recorded as output labels for training the leak source localization model.

[0050] TIFF0007748766000033.tif56170

[0051] TIFF0007748766000034.tif35170

[0052] The convolutional layer is then connected to a max pooling layer after processing to reduce the dimensionality of the data and highlight key features. The feature sequence extracted by the convolutional layer is then transmitted to a recurrent neural network (LSTM), which captures the temporal dependencies in the time series through the recurrent layer. This allows the LSTM unit to learn the relationships between multiple frames of data, further improving the accuracy of localization.

[0053] TIFF0007748766000035.tif19170

[0054] TIFF0007748766000036.tif36170

[0055] Here, the mean square error loss function is expressed by the following Equation 6.

number

[0056] The detection evaluation index of the leakage source localization model is determined according to the following Equation 7.

number

[0057] TIFF0007748766000039.tif58170

[0058] TIFF0007748766000040.tif62170

[0059] TIFF0007748766000041.tif10170

number

[0060] TIFF0007748766000043.tif91170

[0061] TIFF0007748766000044.tif38170

[0062] In step S105, the mobile unit autonomously moves to the location of the specific natural gas leak source.

[0063] Specifically, when the signal collection and location unit locates a natural gas leak source in a utility tunnel, it feeds back the location of the located natural gas leak source to the mobile unit, and the mobile unit autonomously moves to the location of the corresponding natural gas leak source.

[0064] Each comprehensive utility tunnel server may be provided with a corresponding data aggregation unit and fire alarm unit, and when the signal collection and location unit locates a natural gas leakage source in the utility tunnel, the location of the natural gas leakage source can be further transmitted to the data aggregation unit and fire alarm unit of the comprehensive utility tunnel server, allowing countermeasures to be taken in a timely manner.

[0065] In this application, a Bluetooth module is used for data transmission, ensuring stable data transmission, real-time performance, and strong interference resistance in a complex utility tunnel environment. After the location of the natural gas leak source is located, the location information and natural gas sensor data are quickly transmitted via the Bluetooth module to the data aggregation unit of the utility tunnel server, i.e., the control center server, and recorded in a MySQL database. This not only ensures the completeness and accuracy of the data, but also significantly shortens the response time for accident handling and reduces the possibility of secondary disasters.

[0066] The data collected by all sensors in the utility tunnel is transmitted to a data aggregation unit, stored in a MySQL database, and then transmitted to the digital twin system. The digital twin system acquires and processes this data in real time to dynamically construct the location of the leak source. During this process, a high degree of synchronization is maintained between the virtual model of the digital twin system and the physical device. If the location of the leak source in the physical system changes, the virtual model is updated in real time, ensuring consistency in leak source prediction and monitoring.

[0067] The digital twin system may further include an output unit capable of visually outputting the predicted location of the leak source and issuing a leak alarm.

[0068] In step S106, the output unit of the digital twin system can visualize the leak localization process, display the location of the leak source, and provide an alarm.

[0069] As an example, the predicted location of the leak source is visually displayed through the Unity3D platform. The data transmitted via Bluetooth is accessed in Unity3D, and real-time access to Bluetooth data is enabled based on the installation of InTheHand.Bluetooth through the NuGet package manager. Then, the SerialPort class is used to communicate with the Bluetooth device. The data fed back from Bluetooth (the location of the natural gas leak source) is analyzed, and the corresponding mobile robot position in Unity is updated.

[0070] Drag and drop a UI-Text object into the positionText field in the Canvas tool to display the mobile robot's position data in real time. That is, use the UI-Text component in the Canvas tool to update the coordinate information of the leak source in real time, allowing the system operator to clearly see the location and movement trajectory of the leak source in three-dimensional space. By combining the Xcharts graphic component with a MySQL database, the digital twin system can display the internal data of the utility sewer in graph form. By calling the Mysql.Connector and XchartsAPI, the leak data in the database is visually displayed.

[0071] Various digital charts are built in Unity3D through the Xcharts plugin, and connected to database data using dynamic links. Mysql.Data.dll is imported into the Unity Assets folder. Then, a C# script is created to use the MySQL Connector and the API provided by Xcharts to connect the chart's data source to the real-time data in MySQL. SQL is queried using command.CommandText, and database information is obtained using the render.Read() method. Finally, the chart's data source is changed to the real-time data in the MySQL database using data.Add(serieData) to form a natural gas detection digital twin system.

[0072] In describing the present invention, the terms "one embodiment," "some embodiments," "example," "embodiment," or "some examples" mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, general references to the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0073] The above is only a preferred embodiment of the present application, and is not intended to limit the present application. Those skilled in the art can make various modifications and variations to the present application. As long as they do not deviate from the spirit and principle of the present application, any modifications, equivalent replacements, improvements, etc. should all be included within the protection scope of the present application.

Claims

【Request 1】 【Number】 [Equation 1] [Equation 2] [Equation 3] [Equation 4] [Equation 5]

2. Further comprising a physical simulation model of the general utility tunnel constructed according to physical parameters of the general utility tunnel; 2. The digital twin system for detecting and locating natural gas leaks in comprehensive utility tunnels based on sound source localization described in claim 1, characterized in that the training data set of the leak source localization model is constructed based on the simulated positions of the natural gas leak sources in the physical simulation model and the corresponding time delay difference simulation data, and the simulated positions of the natural gas leak sources in the physical simulation model and the corresponding time delay difference simulation data are obtained by using the physical simulation model to simulate natural gas leak acoustic signals at different natural gas leak source positions in the comprehensive utility tunnel and determining the time delay difference simulation data at which the simulated signals in the physical simulation model reach any pair of microphone simulation sensors.

3.

4. 【Request 5】 【Number】 [Equation 6]

Images