A multi-source gas data fusion leak source positioning method and device

Abstract

The application provides a multi-source gas data fusion leakage source positioning method and device, and relates to the technical field of a sensor system. The method comprises the following steps: acquiring multi-source data collected by a sensor system arranged in a target area, wherein the sensor system comprises a plurality of gas sensors and a plurality of environmental sensors, the gas sensors are used for collecting gas concentration data, and the environmental sensors are used for collecting physical environment data; fusing the gas concentration data and the physical environment data, and performing inversion calculation on a leakage process of a leakage gas; determining a leakage source position based on the leakage process and mapping back to a physical structure of a gas pipe network. The application can position the position of gas leakage, thereby improving the disposal efficiency of gas leakage detection.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of sensor systems, in particular to a multi-source gas data fusion leak source positioning method and device. BACKGROUND

[0002] Household gas leakage detection mainly monitors the concentration changes of methane, propane and other combustible gases in indoor air in real time by deploying high-sensitivity gas sensors, identifies leakage events in combination with threshold judgment mechanism, triggers sound-light alarms and links to close electromagnetic valves to cut off gas supply once the detection value exceeds the preset safety concentration threshold, and can report the leakage alarm information to the user terminal or property platform through the wireless communication module to realize rapid response and remote intervention and protect the safety of life and property of users.

[0003] Firstly, at the gas input end, if the gas meter air inlet interface seal fails, the connection is loose, or the pipeline deforms due to foundation settlement, small or intermittent leaks will occur. Secondly, in the gas delivery path, metal pipes may leak due to long-term stress concentration, thermal expansion and contraction, corrosion perforation, or third-party construction disturbance; and soft hose connections have the risks of pipe aging, external force pulling, connection loosening, or interface seal ring failure, especially non-stainless steel corrugated pipes or PVC hoses are more vulnerable. Thirdly, in terms of connection components, such as tees, elbows, valves, quick couplings, etc., if the sealing materials such as rubber gaskets fail due to aging, material incompatibility or improper installation, they will become high-risk points for leakage. At the use terminal, if the gas stove, water heater, wall-mounted furnace, etc. have problems such as gas path system rupture, abnormal opening of the ignition device, failure of the flameout protection, etc., they may also continuously leak gas without obvious sound.

[0004] The existing household gas leakage detection technology generally uses fixed-point gas sensors, which can only monitor the concentration of combustible gases in the air at fixed points and determine whether there is gas leakage through threshold triggering, lacks the ability to perceive the spatial location of the leakage source, and thus although it can issue an alarm in the event of a leak, it cannot provide the specific location of the gas leak, and users need to check each place themselves in the presence of safety hazards, which is not only time-consuming and labor-intensive, but also easy to cause misjudgment and secondary risks, seriously restricting the practicality and disposal efficiency of the detection system. Therefore, a method is needed to locate the position of the gas leak to improve the disposal efficiency of the gas leak detection. SUMMARY

[0005] The present application provides a multi-source gas data fusion leak source positioning method and device, which can locate the position of the gas leak to improve the disposal efficiency of the gas leak detection.

[0006] In a first aspect of the present application, a multi-source gas data fusion leak source positioning method is provided, the method comprising:

[0007] Acquire multi-source data collected by a sensor system deployed in the target area. The sensor system includes multiple gas sensors and multiple environmental sensors. The gas sensors are used to collect gas concentration data, and the environmental sensors are used to collect physical environment data.

[0008] By integrating gas concentration data with physical environment data, the leakage process of the leaked gas is inverted and calculated.

[0009] Based on the leakage process, the location of the leakage source is determined and mapped back to the physical structure of the gas pipeline network.

[0010] Based on the above technical solutions, the preferred method for acquiring multi-source data collected by a sensor system deployed in the target area specifically includes:

[0011] Multiple gas sensors are deployed based on the gas structure topology diagram. The nodes in the gas structure topology diagram correspond to the gas source location, gas delivery path, gas connection location, and gas usage terminal location.

[0012] Multiple environmental sensors are deployed, including temperature sensors, humidity sensors, air pressure sensors, and airflow velocity sensors, which are used to collect temperature data, humidity data, air pressure data, and gas flow velocity data, respectively.

[0013] Based on data collected from multiple gas sensors and multiple environmental sensors, a structured index is established for timestamps, spatial locations, sensor types, and sampling data to form a raw dataset with complete spatiotemporal attributes.

[0014] Based on the above technical solutions, the preferred approach is to integrate gas concentration data and physical environment data to perform inverse calculations on the leakage path of the leaked gas, specifically including:

[0015] Calculate the gas concentration change data based on the gas concentration data in the original dataset;

[0016] Using gas concentration change data as the core observation, a gas diffusion physical model is constructed. The gas diffusion physical model uses a three-dimensional spatial grid as the basic unit, and divides the target area into a regular voxel grid structure. Each grid node in the grid uses temperature data, humidity data, air pressure data, and gas flow velocity data as state variables. Partial differential equations are established to describe the gas diffusion behavior.

[0017] In constructing the physical model of gas diffusion, the free path and thermal motion coefficient of local gas molecules are determined by temperature, humidity and pressure data, thereby calculating the diffusion coefficient of each grid node. The local airflow field is solved based on the airflow velocity data to obtain the velocity vector in each spatial cell. The diffusion coefficient and velocity vector are input into the partial differential equation, and the first evolution sequence of the theoretical concentration field is obtained through numerical solution.

[0018] Based on the above technical solutions, a preferred approach is to determine the location of the leak source based on the leak process and map it back to the physical structure of the gas pipeline network, specifically including:

[0019] Calculate the difference between the gas concentration change data and the first evolution sequence, and construct a residual vector sequence;

[0020] A gradient descent method based on backpropagation is used to perform multiple rounds of gradient updates on the parameters of the source term function of the partial differential equation. The source term function is used to describe the time-varying estimates of the location and intensity of the leakage source, and the residual vector sequence is used as the gradient source for optimizing the objective function of the source term function.

[0021] After each gradient update, the partial differential equation is solved numerically again to update the second evolution sequence of the theoretical concentration field, and the target residual vector is calculated again until the mean residual value is lower than the threshold, and the target residual vector is output.

[0022] Output the target source term function corresponding to the target residual vector, and determine the non-zero distribution interval of the target source term function as the location of the leakage source;

[0023] The location of the leak source is mapped to the gas structure topology to determine the physical location of the leak source.

[0024] Based on the above technical solutions, the preferred method for acquiring multi-source data collected by a sensor system deployed in the target area further includes:

[0025] Multiple gas sensors are deployed based on the gas structure topology diagram. The nodes in the gas structure topology diagram correspond to the gas source location, gas delivery path, gas connection location, and gas usage terminal location.

[0026] The first time when the gas first arrives at the first sensor is determined based on a set concentration change threshold, and the second time when the gas first arrives at each of the second sensors is determined, wherein the first sensor is any one of the multiple gas sensors, and the second sensor is any one of the multiple gas sensors other than the first sensor.

[0027] Multiple environmental sensors are deployed at each gas sensor location. These environmental sensors include a temperature sensor, a humidity sensor, a pressure sensor, and a gas flow rate sensor, which are used to collect temperature data, humidity data, pressure data, and gas flow rate data, respectively.

[0028] Based on the above technical solutions, the preferred approach is to integrate gas concentration data with physical environment data to perform inverse calculations on the leakage process of the leaked gas, specifically including:

[0029] Based on temperature data, humidity data, air pressure data, and gas flow velocity data, a gas propagation speed function is defined;

[0030] An arrival time constraint equation is constructed based on the gas propagation velocity function. The arrival time constraint equation is used to represent the path propagation time of the gas from the leak source to each second sensor, which is equal to the time difference between the second time and the first time.

[0031] By establishing a set of simultaneous constraint equations for multiple gas sensors using the arrival time constraint equation, the residual functions of each gas sensor are constructed.

[0032] The residual functions of all gas sensors are used to construct a vector-form nonlinear least squares optimization objective function, which takes the estimated location of the leak source and the first time as parameters to be determined, and minimizes the sum of squares of the difference between the path propagation time and the actual arrival time of each node.

[0033] Based on the above technical solutions, a preferred approach is to determine the location of the leak source based on the leak process and map it back to the physical structure of the gas pipeline network, specifically including:

[0034] The nonlinear least squares optimization objective function is solved iteratively. In each iteration, the residual value of the residual function is recalculated based on the current estimated value of the parameter to be solved, and the derivative matrix of the residual function of the parameter to be solved is calculated. The step size is adjusted and updated by constructing the Jacobian matrix and the damping term.

[0035] During multiple iterations of the solution process, if it is determined that the change of the parameter to be solved is less than the set threshold, the estimated location of the leakage source corresponding to the last parameter to be solved is output, and the location of the leakage source is obtained.

[0036] The location of the leak source is mapped to the gas structure topology to determine the physical location of the leak source.

[0037] In a second aspect, the present invention provides a leak source localization device based on multi-source gas data fusion. The device is used to execute a leak source localization method based on multi-source gas data fusion as described above. The device includes an acquisition module, a processing module, and an output module, wherein:

[0038] The acquisition module is used to acquire multi-source data collected by the sensor system deployed in the target area. The sensor system includes multiple gas sensors and multiple environmental sensors. The gas sensors are used to collect gas concentration data, and the environmental sensors are used to collect physical environment data.

[0039] The processing module is used to fuse gas concentration data with physical environment data to perform inverse calculations on the leakage process of the leaked gas;

[0040] The output module is used to determine the location of the leak source based on the leak process and map it back to the physical structure of the gas pipeline network.

[0041] Based on the above technical solutions, preferably, the acquisition module is used to deploy multiple gas sensors according to the gas structure topology map, where the nodes of the gas structure topology map correspond to the gas source location, gas delivery path, gas connection location, and gas usage terminal location.

[0042] The acquisition module is used to deploy multiple environmental sensors, including a temperature sensor, a humidity sensor, a pressure sensor, and a gas velocity sensor, which are used to collect temperature data, humidity data, pressure data, and gas velocity data, respectively.

[0043] The acquisition module is used to create a structured index based on the data collected by multiple gas sensors and multiple environmental sensors, including timestamps, spatial locations, sensor types, and sampling data, to form a raw dataset with complete spatiotemporal attributes.

[0044] Based on the above technical solutions, preferably, the processing module is used to calculate gas concentration change data based on the gas concentration data in the original dataset;

[0045] The processing module is used to construct a gas diffusion physical model with gas concentration change data as the core observation. The gas diffusion physical model uses a three-dimensional spatial grid as the basic unit and divides the target area into a regular voxel grid structure. Each grid node in the grid uses temperature data, humidity data, air pressure data and gas flow velocity data as state variables. The gas diffusion behavior is described by establishing partial differential equations.

[0046] The processing module is used to determine the local gas molecule free path and thermal motion coefficient through temperature, humidity and pressure data during the construction of the gas diffusion physical model, thereby calculating the diffusion coefficient of each grid node, solving the local airflow field based on airflow velocity data, obtaining the velocity vector in each spatial cell, inputting the diffusion coefficient and velocity vector into the partial differential equation, and obtaining the first evolution sequence of the theoretical concentration field through numerical solution.

[0047] Based on the above technical solutions, preferably, the processing module is used to calculate the difference between the gas concentration change data and the first evolution sequence, and to construct a residual vector sequence;

[0048] The processing module is used to perform multiple rounds of gradient updates on the parameters of the source term function of the partial differential equation using the gradient descent method based on the backpropagation mechanism. The source term function is used to describe the time-varying estimate of the location and intensity of the leakage source, and the residual vector sequence serves as the gradient source for optimizing the objective function of the source term function.

[0049] The processing module is used to re-numerically solve the partial differential equation after each round of gradient update, update the second evolution sequence of the theoretical concentration field, and recalculate the target residual vector until the mean residual value is lower than the threshold, and then output the target residual vector.

[0050] The output module is used to output the target source term function corresponding to the target residual vector, and to determine the non-zero distribution interval of the target source term function as the location of the leakage source.

[0051] The output module is used to map the location of the leak source to the gas structure topology map, thereby determining the physical location of the leak source.

[0052] Based on the above technical solutions, preferably, the root acquisition module is used to deploy multiple gas sensors according to the gas structure topology map, where the gas structure topology map nodes correspond to the gas source location, gas delivery path, gas connection location, and gas usage terminal location;

[0053] The acquisition module is used to determine the first time when the gas first arrives at the first sensor based on a set concentration change threshold, and to determine the second time when the gas first arrives at each of the second sensors, wherein the first sensor is any one of the multiple gas sensors, and the second sensor is any one of the multiple gas sensors other than the first sensor.

[0054] The acquisition module is used to deploy multiple environmental sensors at each gas sensor location. The environmental sensors include a temperature sensor, a humidity sensor, a pressure sensor, and a gas flow rate sensor, which are used to collect temperature data, humidity data, pressure data, and gas flow rate data, respectively.

[0055] Based on the above technical solutions, preferably, the processing module is used to define a gas propagation speed function based on temperature data, humidity data, air pressure data, and gas flow velocity data;

[0056] The processing module is used to construct the arrival time constraint equation based on the gas propagation speed function. The arrival time constraint equation is used to represent the path propagation time of the gas from the leak source to each second sensor, which is equal to the time difference between the second time and the first time.

[0057] The processing module is used to establish a set of simultaneous constraint equations for multiple gas sensors through the arrival time constraint equation, and to construct the residual function of each gas sensor.

[0058] The processing module is used to construct a vector-form nonlinear least squares optimization objective function using the residual functions of all gas sensors. The nonlinear least squares optimization objective function takes the estimated location of the leak source and the first time as parameters to be determined, and minimizes the sum of squares of the difference between the path propagation time and the actual arrival time of each node.

[0059] Based on the above technical solutions, the preferred processing module is used to iteratively solve the nonlinear least squares optimization objective function. In each iteration, the residual value of the residual function is recalculated based on the current estimated value of the parameter to be solved, and the derivative matrix of the residual function of the parameter to be solved is calculated. The step size is adjusted and updated by constructing the Jacobian matrix and the damping term.

[0060] The processing module is used to output the estimated leakage source location corresponding to the last parameter during multiple iterations of the solution process if it is determined that the change of the parameter to be solved is less than a set threshold, so as to obtain the leakage source location.

[0061] The output module is used to map the location of the leak source to the gas structure topology map, thereby determining the physical location of the leak source.

[0062] In a third aspect of the invention, an electronic device is provided, including a processor, a memory, a user interface, and a network interface, wherein the memory is used to store instructions, the user interface and the network interface are both used to communicate with other devices, and the processor is used to execute the instructions stored in the memory to cause the electronic device to perform the method as described in any of the preceding embodiments.

[0063] In a fourth aspect, the present invention provides a computer-readable storage medium storing instructions that, when executed, perform the method as described in any of the preceding claims.

[0064] In summary, one or more technical solutions provided in the embodiments of the present invention have at least the following technical effects or advantages:

[0065] 1. This invention constructs a multi-source fusion modeling system with gas concentration changes as the core observation and physical environment state as the propagation constraint. It combines partial differential diffusion equations to invert the leakage path and accurately solves the source term function based on gradient optimization mechanism. Finally, it realizes the quantitative identification of the spatial location of the leakage source and the mapping of the pipeline structure. This not only significantly improves the spatial perception capability and positioning accuracy of gas leakage detection, but also greatly enhances the system's robust analytical capability against complex diffusion behavior under environmental disturbances. Thus, it achieves an efficient closed loop from leakage perception to structural positioning, improving the timeliness, safety and intelligence of leakage handling.

[0066] 3. This invention introduces a time-difference observation mechanism based on abrupt concentration response, and constructs a gas propagation velocity function by combining environmental variables such as temperature, humidity, air pressure, and gas flow rate. This forms a refined spatiotemporal propagation constraint model, and based on this, establishes a nonlinear least-squares optimization framework to iteratively calculate the spatial location and occurrence time of the leak source. Finally, the results are mapped to a gas structure topology map, achieving quantitative location of the source point by reverse calculation from the dynamic gas diffusion process. This significantly improves the accuracy and dynamic adaptability of gas leak location, possessing technical advantages such as rapid response, algorithm stability, and strong physical interpretability, enhancing the intelligence level and practical safety performance of leak detection systems. Attached Figure Description

[0067] Figure 1 This is a flowchart illustrating a method for locating leak sources using multi-source gas data fusion, as disclosed in an embodiment of the present invention.

[0068] Figure 2 This is a schematic diagram of a leak source location device based on multi-source gas data fusion disclosed in an embodiment of the present invention;

[0069] Figure 3 This is a schematic diagram of the structure of an electronic device disclosed in an embodiment of the present invention.

[0070] Explanation of reference numerals in the attached drawings: 201, acquisition module; 202, processing module; 203, output module; 301, processor; 302, communication bus; 303, user interface; 304, network interface; 305, memory. Detailed Implementation

[0071] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments.

[0072] In the description of the embodiments of the present invention, words such as "for example" or "for instance" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as "for example" or "for instance" in the embodiments of the present invention should not be construed as being more preferred or advantageous than other embodiments or designs. Rather, the use of words such as "for example" or "for instance" is intended to present the relevant concepts in a specific manner.

[0073] In the description of the embodiments of the present invention, the term "multiple" means two or more. For example, multiple systems means two or more systems, and multiple screen terminals means two or more screen terminals. Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the indicated technical features. Thus, a feature defined with "first" or "second" may explicitly or implicitly include one or more of that feature. The terms "comprising," "including," "having," and variations thereof all mean "including but not limited to," unless otherwise specifically emphasized.

[0074] Existing household gas leak detection technologies primarily rely on the fixed deployment of high-sensitivity gas sensors to monitor changes in the concentration of combustible gases such as methane and propane in the air in real time. Combined with threshold judgment mechanisms, these technologies trigger alarms and gas shut-off linkages. While this enables timely response and remote early warning for leak events, the lack of ability to identify the spatial location of the leak source means that accurate location information cannot be provided after an alarm is triggered. This forces users to conduct manual investigations in environments with safety risks, which can easily lead to misjudgments and secondary hazards, severely impacting actual handling efficiency. This limitation is particularly evident in complex leak scenarios such as gas input seal failure, aging pipelines along the delivery path, aging seals on connecting components, or abnormal terminal equipment. These factors highlight the technical limitations of traditional fixed-point monitoring solutions in terms of leak tracing capabilities.

[0075] This embodiment discloses a leak source localization method based on multi-source gas data fusion, referring to... Figure 1 This includes the following steps S110-S130:

[0076] S110: Acquire multi-source data collected by sensor systems deployed in the target area.

[0077] S120 integrates gas concentration data with physical environment data to perform inversion calculations on the leakage process of leaked gas.

[0078] S130, based on the leakage process, determines the location of the leakage source and maps it back to the physical structure of the gas pipeline network.

[0079] The leak source localization method based on multi-source gas data fusion disclosed in this invention is applied to a server. The server includes, but is not limited to, electronic devices such as mobile phones, tablets, wearable devices, and PCs (Personal Computers), and can also be a backend server running a leak source localization method based on multi-source gas data fusion. The server can be implemented using a standalone server or a server cluster composed of multiple servers.

[0080] In the first embodiment, acquiring multi-source data collected by a sensor system deployed in the target area specifically includes: deploying multiple gas sensors according to a gas structure topology map, where each node in the gas structure topology map corresponds to the location of the gas source, the gas delivery path, the location of the gas connection point, and the location of the gas user terminal; deploying multiple environmental sensors, including temperature sensors, humidity sensors, air pressure sensors, and airflow velocity sensors, which are used to collect temperature data, humidity data, air pressure data, and gas flow velocity data, respectively; and establishing a structured index for timestamps, spatial locations, sensor types, and sampling data based on the data collected by the multiple gas sensors and multiple environmental sensors to form a raw dataset with complete spatiotemporal attributes.

[0081] Specifically, during the deployment phase, the first step is to spatially deploy gas sensors based on the gas structure topology diagram within the residence. This topology diagram is a directed graph representing the connections between various components of the gas supply system. These components include the gas source location, gas delivery path, gas connection points, and gas usage terminals. Each node represents a key functional location, and each edge represents a pipeline connection. Based on this topology diagram, gas sensors are deployed at each node location to ensure coverage of all critical areas through which gas flows or where leaks may occur, forming a logically complete spatial observation network. For example, in a typical residential scenario, four gas sensor nodes can be deployed at the main gas valve, near the gas inlet of the kitchen stove, at the bend in the exposed pipe on the kitchen wall, and at the water heater connection, respectively covering the source point, the straight path, the connection point, and the usage terminal.

[0082] Subsequently, environmental sensors are deployed to simultaneously collect temperature, humidity, air pressure, and gas velocity data. Temperature sensors measure air temperature using thermocouples or thermistors; humidity sensors reflect relative humidity using capacitive or resistive sensing units; air pressure sensors measure atmospheric pressure changes using piezoresistive MEMS structures; and air velocity sensors acquire local airflow velocity using hot-wire anemometers or ultrasonic anemometers. All environmental and gas sensors are spatially co-located or adjacent to each other to ensure direct overlap in their observation areas, enabling spatial matching and response coupling in subsequent data fusion modeling.

[0083] During the data acquisition phase, all sensors are uniformly configured with a local timestamp recording mechanism with millisecond-level accuracy. Simultaneously, spatial encoding is performed based on the physical installation location number and the indoor floor plan coordinate system. The data collected by each sensor includes: sensor type identifier, timestamp, spatial coordinates, and the current sampled value, forming a structured quadruple. These quadruples are then standardized to construct a data structure with time as the primary index and spatial location and sensor type as secondary indices, ensuring complete spatiotemporal consistency of the data. For example, if a gas sensor node located at the water heater interface collects a concentration value of 180 ppm at 10:00:00 on July 25, 2025, the original dataset would be recorded as: {Type: Gas Sensor, Location: Node H1, Time: 2025-07-25 10:00:00, Concentration Value: 180 ppm}. This, along with the temperature sensor record at the same time, forms multi-channel observation data at the same location, providing a unified data input foundation for subsequent leak modeling, path inversion, and source location. The entire process established a unified description framework for multi-source heterogeneous data, opening up data pathways for spatial modeling and intelligent identification of gas leaks.

[0084] In one possible implementation, gas concentration data and physical environment data are integrated to perform inverse calculations on the leakage path of the leaked gas. Specifically, this includes: calculating gas concentration change data based on the gas concentration data in the original dataset; constructing a gas diffusion physical model using the gas concentration change data as the core observation, wherein the gas diffusion physical model uses a three-dimensional spatial grid as the basic unit, dividing the target area into a regular voxel grid structure, and each grid node within the grid uses temperature data, humidity data, air pressure data, and gas velocity data as state variables, and describing the gas diffusion behavior by establishing partial differential equations; in the process of constructing the gas diffusion physical model, the local gas molecule free path and thermal motion coefficient are determined by temperature data, humidity data, and air pressure data, thereby calculating the diffusion coefficient of each grid node, solving the local airflow field based on airflow velocity data to obtain the velocity vector in each spatial unit, inputting the diffusion coefficient and velocity vector into the partial differential equations, and obtaining the first evolution sequence of the theoretical concentration field through numerical solution.

[0085] Specifically, firstly, after forming the original dataset, gas concentration change data needs to be extracted from the gas concentration data collected by the gas sensors. Gas concentration change data refers to the rate of change of the gas concentration value at a certain spatial node over time, reflecting the diffusion dynamics of a leak event. Using each gas sensor node as a reference, the gas concentration increment within adjacent sampling time intervals is calculated and normalized to form a differential concentration sequence. Let the gas sensor node... In time The concentration value Then the change in its gas concentration is:

[0086]

[0087] The aforementioned difference sequence is used to characterize the degree of abrupt changes in local gas concentration and is an important observation for determining the gas propagation front and diffusion path.

[0088] Next, a physical model of gas diffusion is constructed using gas concentration change data as the core driving factor. The entire target region is divided into a regular voxel grid structure, with each cubic grid serving as a three-dimensional discrete unit. Each voxel grid node is defined to have complete physical state variables, including temperature data. Humidity data air pressure data With airflow velocity data Partial differential equations are introduced into this spatial grid field to describe the propagation behavior of the gas in space and time, and convection-diffusion type control equations are used to describe the gas concentration. The dynamic evolutionary relationship:

[0089]

[0090] Wherein, diffusion coefficient Characterizing the thermal diffusivity of molecules, flow velocity vector It characterizes the convective diffusion trend driven by macroscopic airflow. The source term function is used to describe the time-varying estimates of the location and intensity of the leakage source. This governing equation is a class of second-order partial differential equations, with the first term being the diffusion term and the second term being the convection term, describing the diffusion behavior of gas under non-uniform thermal fields and airflow disturbances.

[0091] To obtain the diffusion coefficient, it is necessary to estimate the mean free path of gas molecules and the diffusion constant by combining local temperature, humidity, and air pressure parameters. Diffusion coefficient This can be given by the following empirical formula:

[0092]

[0093] in, Boltzmann's constant, The gas dynamic viscosity coefficient, The effective radius of a gas molecule, This is the humidity adjustment coefficient. This is a function of air pressure. The higher the temperature, the lower the air pressure, and the lower the humidity, the greater the diffusion coefficient and the stronger the gas diffusion ability.

[0094] Flow velocity vector An interpolation field is constructed using airflow velocity sensor data and building spatial boundary conditions. Three-dimensional airflow velocity components are estimated at each grid node using linear interpolation or the finite volume method. If the wind speed value at each sensor node is... The corresponding position is Then, multi-point weighted interpolation is used to construct the velocity value at the center position of each voxel:

[0095]

[0096] The diffusion coefficients and velocity vector fields at all spatial grid points are input into the governing equations, and an implicit Crank-Nicolson difference scheme is used for numerical solution, with a time step set to [value missing]. The space step size is The objective is to determine the theoretical concentration values ​​for all grid nodes at the next time step, thus forming a concentration field evolution sequence. .

[0097] In this embodiment, the source term function is used not only to describe the existence of a leak source, but also to quantify its leakage rate and diffusion range. Mathematically, it means that during the theoretical concentration evolution process, the model actively injects gas at a specified spatial location to simulate the continuous release of gas in a real leak scenario. Physically, it can be understood as the "source strength function" of the leak point.

[0098] The source term function usually satisfies the following condition: when Located in the spatial region of the leak source and time During the leakage stage, It takes a non-zero value; at other locations or times, it is zero or approximately zero. For steady-state leakage events, the source term function can be modeled as the product of a spatial Gaussian distribution and a time constant function:

[0099]

[0100] in Indicates the leakage intensity. Indicates the estimated location of the leak source. Indicates the diffusion scale of the leak area. This is a time indication function that controls the range of leakage duration.

[0101] In leakage path inversion and leakage source localization, the source term function is also a key parameter to be optimized. By comparing the residuals of the model-simulated concentration field and the sensor-measured concentration field, and by performing inverse optimization on the spatial location and intensity parameters in the source term function, the parameters can be continuously adjusted. The form of the source term function allows the theoretical concentration field to approximate the measured concentration field, thereby enabling the joint inference of the spatial location and temporal characteristics of the leakage source. In other words, the source term function is not only the input to the diffusion equation but also the core inversion object in the leakage tracing process.

[0102] This theoretical concentration evolution sequence serves as a physical fit to the actual gas diffusion process, providing a comparable analytical benchmark for subsequent leak source location inversion, path reconstruction, and time-based source tracing. Through the above modeling process, the gas diffusion trend can be accurately characterized under thermal and airflow disturbances with a real physical background, enabling numerically controllable simulation of the leak process.

[0103] In one possible implementation, based on the leakage process, the location of the leakage source is determined and mapped back to the physical structure of the gas pipeline network. Specifically, this includes: calculating the difference between gas concentration change data and the first evolution sequence to construct a residual vector sequence; employing a gradient descent method based on backpropagation to perform multiple rounds of gradient updates on the parameters of the source term function of the partial differential equation, where the source term function describes the time-varying estimate of the leakage source location and intensity, and the residual vector sequence serves as the gradient source for optimizing the objective function of the source term function; after each round of gradient updates, the partial differential equation is numerically solved again to update the second evolution sequence of the theoretical concentration field, and the target residual vector is calculated again until the mean residual value is below a threshold, at which point the target residual vector is output; the target source term function corresponding to the target residual vector is output, and the non-zero distribution interval of the target source term function is determined as the leakage source location; the leakage source location is mapped to the gas structure topology map, thereby determining the physical location of the leakage source.

[0104] Specifically, firstly, the first evolution sequence has been obtained in the theoretical simulation stage, namely the simulated concentration field obtained by inputting the current source term function parameter values ​​into the gas diffusion partial differential equation. Simultaneously, a gas concentration change data sequence was constructed based on the raw concentration data collected by the gas sensor. This data sequence consists of actual observations at spatially discrete locations and time points. The two sequences are compared point-by-point at the same grid nodes and time points to construct a residual vector sequence:

[0105]

[0106] in This represents the error between the simulated concentration and the measured concentration at each sampling point. This residual vector serves as the source for gradient calculation during the optimization process, used to measure whether the parameters of the current source term function are reasonable.

[0107] Next, regarding the source term function in the partial differential equation for gas diffusion... ,in A loss function is constructed for the set of parameters including the leak location, leak intensity, and diffusion scale. Represents the sum of squares of all residuals:

[0108]

[0109] Gradient descent using backpropagation optimizes the parameters of the source function. The partial derivatives of the loss function with respect to the parameters are calculated via automatic differentiation.

[0110]

[0111] Then set the learning rate Perform iterative updates:

[0112]

[0113] After each parameter update, the new source function will be... The data is input into the diffusion partial differential equation, and a numerical solution is performed again to obtain the updated theoretical concentration field. The residual vector is then recalculated. This iterative process continues until the mean of the objective function residuals satisfies the set convergence condition, namely:

[0114]

[0115] in This represents the total number of sampling points. This is the residual convergence threshold.

[0116] After convergence is complete, output the corresponding source term function at this point. The continuum formed by the non-zero regions in the spatial location of the source term function is defined as the spatial distribution region of the leakage source. In other words, if there exist spatial points... satisfy If this non-zero value persists across multiple time steps, then this point will be included in the leakage source estimation set.

[0117] Finally, the estimated spatial coordinates of the leakage source are... Mapping to the gas structure topology map, the spatial matching mechanism is used to find the topology map node identifier that is closest to its location, and the structure number mapping of the leak source in the actual gas pipeline physical structure is completed. For example, if the leak source location result is matched to the node "Connection Interface J7", then this node is the identification result of the physical location of the leak source.

[0118] In the second embodiment, acquiring multi-source data collected by a sensor system deployed in the target area further includes: deploying multiple gas sensors according to a gas structure topology map, where nodes in the gas structure topology map correspond to the gas source location, gas delivery path, gas connection location, and gas usage terminal location; determining the first time when the gas first arrives at the first sensor based on a set concentration change threshold, and determining the second time when the gas first arrives at each of the second sensors, wherein the first sensor is any one of the multiple gas sensors, and the second sensor is any one of the multiple gas sensors other than the first sensor; and deploying multiple environmental sensors at each gas sensor location, including a temperature sensor, a humidity sensor, a pressure sensor, and a gas flow rate sensor, for collecting temperature data, humidity data, pressure data, and gas flow rate data, respectively.

[0119] Specifically, in practical implementation, the first step is to construct a gas structure topology map based on the physical structure information of the indoor gas supply system. This topology map is a directed graph structure, with nodes corresponding to key locations in the physical pipeline network, including gas source locations (such as the main inlet valve or gas meter), main sections of the gas delivery path, gas connection locations (such as tees, elbows, and interface connections), and gas usage terminal locations (such as stoves, water heaters, and wall-mounted boilers). Each node has clear spatial coordinates and forms topological edges through pipeline connections. Based on this topology map, multiple gas sensors are deployed at the aforementioned key nodes, ensuring that the gas sensors spatially cover the starting point, transmission process, key connection points, and end consumption points of gas flow. This ensures that if a leak occurs in any link, a corresponding node can provide an immediate response. For example, in the kitchen, four gas sensors are installed below the gas meter, in the middle of the exposed pipe, at the interface valve, and at the gas inlet of the stove.

[0120] Following a gas leak, gas sensors continuously monitor the concentration of gas in the air at a preset sampling frequency. To capture the spatial propagation of the leaking gas front, the system presets a concentration abrupt change threshold, for example, 100 ppm. When any gas sensor detects a sudden increase in its concentration from a stable background concentration and exceeds this threshold for the first time, this moment is recorded as the initial arrival time of the gas at that sensor. This time serves as a time reference point for the actual leak path. The gas sensor that is triggered first is defined as the first sensor, and its trigger time is defined as the first time T1. Other gas sensors that are not triggered first are defined as the second sensors, and their initial arrival times are defined as the second time T. iThis set of time data serves as the key input for subsequent diffusion path time difference inversion. For example, if the sensor below the gas meter reaches the mutation threshold first, and its initial mutation time is recorded as 10:00:12, with other times being 10:00:15, 10:00:20, and 10:00:26, then this sequence forms a time chain of gas propagation.

[0121] To ensure spatiotemporal consistency in the modeling of the diffusion physical environment at each gas sensor node, a set of environmental sensors is deployed at each gas sensor node. These sensors include a temperature sensor for real-time acquisition of local thermal environment data during gas diffusion, a humidity sensor to reflect the influence of water vapor content on the viscosity of gas molecules, a pressure sensor to monitor the modulation effect of local atmospheric pressure on gas density and diffusion path, and a gas velocity sensor to quantify the wind speed and convection effects on gas propagation at that location. This set of sensors collaboratively constitutes a physical parameter field for regulating gas diffusion behavior. For example, at the node below the stove, a set of MEMS temperature sensors (sampling range -20°C to 85°C), capacitive humidity sensors (accuracy ±2%RH), piezoresistive pressure sensors (0.1 kPa accuracy), and hot-wire gas velocity sensors (0.05 m / s resolution) are installed simultaneously with the gas sensors. This node will generate a five-channel spatiotemporally aligned raw data record at every moment, achieving a complete fusion monitoring of gas response and physical environment dynamics, providing a complete input for leak location and path inversion.

[0122] In one possible implementation, gas concentration data and physical environment data are integrated to perform inverse calculations on the leakage process of the leaked gas. Specifically, this includes: defining a gas propagation velocity function based on temperature, humidity, air pressure, and gas flow rate data; constructing arrival time constraint equations based on the gas propagation velocity function, which represent the path propagation time of the gas from the leak source location to each second sensor, equal to the time difference between the second time and the first time; establishing a system of simultaneous constraint equations for multiple gas sensors using the arrival time constraint equations to construct the residual functions of each gas sensor; and constructing a vector-form nonlinear least squares optimization objective function using the estimated leak source location and the first time as parameters to be determined, minimizing the sum of squares of the differences between the path propagation time and the actual arrival time at each node.

[0123] Specifically, in this embodiment, it is first necessary to combine the temperature data, humidity data, air pressure data, and gas flow velocity data collected by the environmental sensor to establish a gas propagation velocity function at the location of the gas sensor. This is used to estimate the average path velocity of gas propagating from the leak source to each gas sensor. This propagation velocity function is an empirical modeling result of the complex physical field, established based on diffusion theory and convection coupling mechanisms, and can be constructed, for example, in the following form:

[0124]

[0125] in This represents the macroscopic airflow convection velocity measured by the airflow velocity sensor. These are the fitting coefficients. Boltzmann's constant, The kinetic viscosity coefficient of the gas. , These are the adjustment factors for humidity and air pressure, respectively, thereby quantifying the coupled influence of the local environment on molecular thermal diffusion and macroscopic gas migration velocity.

[0126] Next, the arrival time constraint equations for the gas propagation path are constructed. Let the predicted location of the leak source be... , No. The gas sensor locations are as follows: The gas propagation distance is the Euclidean distance:

[0127]

[0128] The path propagation time is:

[0129]

[0130] The propagation time is constrained from the observed actual time difference, and the time difference is defined as... ,in For the first The second time of a gas sensor To obtain the constraint equations immediately:

[0131]

[0132] The equation is established on all the second sensors, forming a multivariate nonlinear simultaneous constraint system.

[0133] Furthermore, each constraint equation is constructed as a residual function, representing the deviation between the theoretical propagation time and the observation time. The 1st... The residual functions are:

[0134]

[0135] Based on this, all residual functions are summarized to form a nonlinear least squares optimization objective function:

[0136]

[0137] The objective function uses the three-dimensional coordinates of the leak source location. With the first time For the variables to be optimized, a high-precision nonlinear optimization algorithm (such as the Levenberg-Marquardt method) is used to iteratively solve the problem until the squared deviation between the propagation time of all paths and the observation time difference is minimized.

[0138] In one possible implementation, the location of the leak source is determined based on the leakage process and mapped back to the physical structure of the gas pipeline network. Specifically, this includes: iteratively solving the nonlinear least squares optimization objective function; in each iteration, recalculating the residual value of the residual function based on the current estimated value of the parameter to be solved, and calculating the derivative matrix of the residual function for the parameter to be solved; adjusting the update step size by constructing the Jacobian matrix and damping term; if the change of the parameter to be solved is determined to be less than a set threshold during multiple iterations, the estimated location of the leak source corresponding to the last parameter to be solved is output to obtain the location of the leak source; and mapping the location of the leak source to the gas structure topology map to determine the physical location of the leak source.

[0139] Specifically, in the parameter optimization process of leakage source inversion, a nonlinear least squares optimization method is used to iteratively solve the objective function, with the Levenberg-Marquardt method chosen to balance convergence speed and numerical stability. In each iteration, the estimated values ​​of the current parameters to be determined, i.e., the three-dimensional location parameters of the leakage source, are used. With the parameter of leakage start time Recalculate all residual function values, in the form of:

[0140]

[0141] Simultaneously, the partial derivative matrix of the residual function with respect to all parameters to be determined is constructed to obtain the Jacobian matrix. Each row represents the corresponding number. The residual function of each sensor The partial derivatives are used to linearly approximate the gradient distribution in the local region of the current solution space. The parameter update direction for the current iteration step is defined. satisfy:

[0142]

[0143] in This is a column vector consisting of all current residual function values. The damping coefficient controls the adjustment of the iteration step size. The identity matrix is ​​used to prevent divergence caused by ill-conditioned Jacobian matrices near singular points in the parameter space. If the sum of squared residuals decreases after the current iteration, then reduce [the value]. Relax the constraints; if the residuals increase, then increase the constraint. Increase the regularization penalty to converge to a local minimum.

[0144] As the iteration process progresses, the system continuously updates the parameter estimates. And continuously calculate the residual vector and Jacobian matrix for the new round. When the parameter change occurs between two consecutive iterations... Less than the set convergence threshold (For example, set to) If the combined threshold of meters and seconds is reached, the iteration is considered to have converged, the optimization process is terminated, and the output of the last round of parameters is used as the final estimation result to obtain the location of the leakage source.

[0145]

[0146] After estimating the spatial location of the leak source, these physical coordinates need to be mapped onto the gas structure topology diagram. All functional nodes in the gas structure topology diagram have been spatially labeled and numbered, including gas source nodes, transmission path nodes, connection nodes, and end-user nodes. The mapping process is based on the principle of spatial proximity, using a minimum distance matching method to match the estimated location with the set of nodes in the topology diagram. Calculate the Euclidean distance:

[0147]

[0148] Selecting makes Minimum node number The corresponding physical structural location serves as the physical location result of the leak source, completing the mapping from the mathematical solution to the gas pipeline network structural identifier. For example, if If the source of the leak is closest to the node "Connection Interface J12", then the structural location corresponding to node J12 will be identified as the source of the leak, which can be used for subsequent maintenance intervention or automatic response mechanisms.

[0149] This embodiment also discloses a leak source location device based on multi-source gas data fusion, referring to... Figure 2 The device includes an acquisition module 201, a processing module 202, and an output module 203. It is used to execute any of the above-described multi-source gas data fusion leak source localization methods, wherein:

[0150] The acquisition module 201 is used to acquire multi-source data collected by a sensor system deployed in the target area. The sensor system includes multiple gas sensors and multiple environmental sensors. The gas sensors are used to collect gas concentration data, and the environmental sensors are used to collect physical environment data.

[0151] The processing module 202 is used to fuse gas concentration data and physical environment data to perform inverse calculations on the leakage process of the leaked gas.

[0152] Output module 203 is used to determine the location of the leak source based on the leak process and map it back to the physical structure of the gas pipeline network.

[0153] In one possible implementation, the acquisition module 201 is used to deploy multiple gas sensors according to a gas structure topology map, where the nodes of the gas structure topology map correspond to the gas source location, gas delivery path, gas connection location, and gas usage terminal location.

[0154] The acquisition module 201 is used to deploy multiple environmental sensors, including a temperature sensor, a humidity sensor, a pressure sensor, and a gas flow rate sensor, which are used to collect temperature data, humidity data, pressure data, and gas flow rate data, respectively.

[0155] The acquisition module 201 is used to establish a structured index for timestamps, spatial locations, sensor types and sampling data based on data collected by multiple gas sensors and multiple environmental sensors, forming a raw dataset with complete spatiotemporal attributes.

[0156] In one possible implementation, the processing module 202 is used to calculate gas concentration change data based on the gas concentration data in the original dataset.

[0157] The processing module 202 is used to construct a gas diffusion physical model with gas concentration change data as the core observation. The gas diffusion physical model uses a three-dimensional spatial grid as the basic unit and divides the target area into a regular voxel grid structure. Each grid node in the grid uses temperature data, humidity data, air pressure data and gas flow velocity data as state variables, and describes the gas diffusion behavior by establishing partial differential equations.

[0158] The processing module 202 is used to determine the local gas molecule free path and thermal motion coefficient through temperature data, humidity data and air pressure data during the construction of the gas diffusion physical model, thereby calculating the diffusion coefficient of each grid node, solving the local airflow field based on airflow velocity data, obtaining the velocity vector in each spatial cell, inputting the diffusion coefficient and velocity vector into the partial differential equation, and obtaining the first evolution sequence of the theoretical concentration field through numerical solution.

[0159] In one possible implementation, the processing module 202 is used to calculate the difference between the gas concentration change data and the first evolution sequence, and construct a residual vector sequence.

[0160] The processing module 202 is used to perform multiple rounds of gradient updates on the parameters of the source term function of the partial differential equation using the gradient descent method based on the backpropagation mechanism. The source term function is used to describe the time-varying estimate of the location and intensity of the leakage source, and the residual vector sequence serves as the gradient source for optimizing the objective function of the source term function.

[0161] The processing module 202 is used to re-numerically solve the partial differential equation after each round of gradient update, update the second evolution sequence of the theoretical concentration field, and recalculate the target residual vector until the mean residual value is lower than the threshold, and then output the target residual vector.

[0162] The output module 203 is used to output the target source term function corresponding to the target residual vector, and to determine the non-zero distribution interval of the target source term function as the location of the leakage source.

[0163] Output module 203 is used to map the location of the leak source to a gas structure topology map, thereby determining the physical location of the leak source.

[0164] In one possible implementation, the root acquisition module 201 is used to deploy multiple gas sensors according to a gas structure topology map, where the gas structure topology map nodes correspond to the gas source location, gas delivery path, gas connection location, and gas usage terminal location.

[0165] The acquisition module 201 is used to determine the first time when the gas first arrives at the first sensor based on a set concentration change threshold, and to determine the second time when the gas first arrives at each of the second sensors, wherein the first sensor is any one of the multiple gas sensors, and the second sensor is any one of the multiple gas sensors other than the first sensor.

[0166] The acquisition module 201 is used to deploy multiple environmental sensors at each gas sensor location. The environmental sensors include a temperature sensor, a humidity sensor, a pressure sensor, and a gas flow rate sensor, which are used to collect temperature data, humidity data, pressure data, and gas flow rate data, respectively.

[0167] In one possible implementation, the processing module 202 is used to define a gas propagation speed function based on temperature data, humidity data, air pressure data, and gas flow rate data.

[0168] The processing module 202 is used to construct an arrival time constraint equation based on the gas propagation speed function. The arrival time constraint equation is used to represent the path propagation time of the gas from the leak source location to each second sensor, which is equal to the time difference between the second time and the first time.

[0169] The processing module 202 is used to establish a set of simultaneous constraint equations for multiple gas sensors through the arrival time constraint equation, and to construct the residual function of each gas sensor.

[0170] The processing module 202 is used to construct a vector-form nonlinear least squares optimization objective function using the residual functions of all gas sensors. The nonlinear least squares optimization objective function takes the estimated location of the leak source and the first time as parameters to be determined, and minimizes the sum of squares of the difference between the path propagation time of each node and the actual arrival time.

[0171] In one possible implementation, the processing module 202 is used to iteratively solve the nonlinear least squares optimization objective function. In each iteration, the residual value of the residual function is recalculated based on the current estimated value of the parameter to be solved, and the derivative matrix of the residual function of the parameter to be solved is calculated. The step size is adjusted and updated by constructing the Jacobian matrix and the damping term.

[0172] The processing module 202 is used to output the estimated leakage source location corresponding to the last parameter during multiple iterations of the solution process if it is determined that the change of the parameter to be solved is less than a set threshold, thereby obtaining the leakage source location.

[0173] Output module 203 is used to map the location of the leak source to a gas structure topology map, thereby determining the physical location of the leak source.

[0174] It should be noted that the above embodiments of the apparatus are only illustrated by the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the apparatus and method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process can be found in the method embodiments, which will not be repeated here.

[0175] This embodiment also discloses an electronic device, referring to... Figure 3 The electronic device may include: at least one processor 301, at least one communication bus 302, user interface 303, network interface 304, and at least one memory 305.

[0176] The communication bus 302 is used to enable communication between these components.

[0177] The user interface 303 may include a display screen and a camera. Optionally, the user interface 303 may also include a standard wired interface and a wireless interface.

[0178] The network interface 304 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface).

[0179] The processor 301 may include one or more processing cores. The processor 301 connects to various parts of the server using various interfaces and lines, and performs various server functions and processes data by running or executing instructions, programs, code sets, or instruction sets stored in memory 305, and by calling data stored in memory 305. Optionally, the processor 301 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). The processor 301 may integrate one or a combination of several of the following: Central Processing Unit (CPU), Graphics Processing Unit (GPU), and modem. The CPU primarily handles the operating system, user interface, and applications. The GPU is responsible for rendering and drawing the content required for display. The modem handles wireless communication. It is understood that the modem may also not be integrated into the processor 301 and may be implemented as a separate chip.

[0180] The memory 305 may include random access memory (RAM) or read-only memory. Optionally, the memory may include a non-transitory computer-readable storage medium. The memory 305 may be used to store instructions, programs, code, code sets, or instruction sets. The memory 305 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the various method embodiments described above, etc. The data storage area may store data involved in the various method embodiments described above. Optionally, the memory 305 may also be at least one storage device located remotely from the aforementioned processor 301. As a computer storage medium, the memory 305 may include an operating system, a network communication module, a user interface 303 module, and an application program for a leak source location method based on multi-source gas data fusion.

[0181] exist Figure 3In the illustrated electronic device, the user interface 303 is primarily used to provide an input interface for the user and to acquire user-input data. The processor 301 can be used to call an application program stored in the memory 305 that represents a leak source location method based on multi-source gas data fusion. When executed by one or more processors 301, the electronic device performs one or more methods as described in the above embodiments.

[0182] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that the present invention is not limited to the described order of actions, as some steps can be performed in other orders or simultaneously according to the present invention. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to the present invention.

[0183] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0184] In the several embodiments provided by this invention, it should be understood that the disclosed apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some service interface; the indirect coupling or communication connection between apparatuses or units may be electrical or other forms.

[0185] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0186] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0187] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory 305 and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned memory 305 includes various media capable of storing program code, such as a USB flash drive, external hard drive, magnetic disk, or optical disk.

[0188] The present invention also discloses a computer-readable storage medium storing instructions. When executed by one or more processors 301, these instructions cause an electronic device to perform one or more methods as described in the above embodiments.

[0189] The above are merely exemplary embodiments of this disclosure and should not be construed as limiting the scope of this disclosure. Any equivalent changes and modifications made in accordance with the teachings of this disclosure shall still fall within the scope of this disclosure. Those skilled in the art will readily conceive of other embodiments of this disclosure upon considering the specification and the disclosure of practical truths. This invention is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not described in this disclosure. The specification and embodiments are to be considered exemplary only, and the scope and spirit of this disclosure are defined by the claims.

Claims

1. A multi-source gas data fusion leak source positioning method, characterized in that, The method comprises: acquiring multi-source data collected by a sensor system arranged in a target area, wherein the sensor system comprises a plurality of gas sensors for collecting gas concentration data and a plurality of environmental sensors for collecting physical environment data; fusing the gas concentration data and the physical environment data to perform inversion calculation on a leakage process of a leakage gas; based on the leakage process, determining a leakage source position and mapping it back to a physical structure of a gas pipe network. The acquisition of the multi-source data collected by the sensor system arranged in the target area further comprises: deploying a plurality of the gas sensors according to a gas structure topology map, wherein nodes of the gas structure topology map correspond to gas source positions, gas transmission paths, gas connection position and gas use terminal positions; determining a first time at which a gas initially reaches a first sensor and a second time at which the gas initially reaches each second sensor based on a set concentration mutation threshold, wherein the first sensor is any one of the plurality of the gas sensors, and the second sensor is any one of the plurality of the gas sensors except the first sensor; deploying a plurality of the environmental sensors at each of the positions of the gas sensors, wherein the environmental sensors comprise temperature sensors, humidity sensors, air pressure sensors and air flow speed sensors for collecting temperature data, humidity data, air pressure data and gas flow speed data respectively; The fusion of the gas concentration data and the physical environment data to perform inversion calculation on the leakage process of the leakage gas further comprises: defining a gas propagation speed function based on the temperature data, the humidity data, the air pressure data and the gas flow speed data; constructing an arrival time constraint equation based on the gas propagation speed function, wherein the arrival time constraint equation is used to represent a path propagation time of the gas from the leakage source position to each of the second sensors, which is equal to a time difference between the second time and the first time; establishing a simultaneous constraint equation set for the plurality of the gas sensors through the arrival time constraint equation, and constructing a residual function of each of the gas sensors; constructing a vector-form nonlinear least squares optimization objective function through the residual functions of all the gas sensors, wherein the nonlinear least squares optimization objective function takes the estimated leakage source position and the first time as to-be-solved parameters, and minimizes a sum of squares of differences between each node path propagation time and actual arrival time.

2. The method according to claim 1, wherein, The determination of the leakage source position based on the leakage process and the mapping back to the physical structure of the gas pipe network further comprises: iteratively solving the nonlinear least squares optimization objective function, wherein in each iteration solving process, a residual value of the residual function is recalculated according to a current estimated value of the to-be-solved parameters, a derivative matrix of the to-be-solved parameters is calculated, and a step length is updated through construction of a Jacobian matrix and a damping term adjustment; in the plurality of iteration solving processes, if it is determined that a change of the to-be-solved parameters is less than a set threshold, an estimated leakage source position corresponding to a last to-be-solved parameter is output, and the leakage source position is obtained. mapping the leak source position to the gas structure topology, thereby determining the physical location of the leak source.

3. A multi-source gas data fusion leak source positioning device, characterized in that, The device is used for performing the multi-source gas data fusion leak source positioning method according to any one of claims 1-2, and the device comprises an acquisition module (201), a processing module (202) and an output module (203), wherein: The acquisition module (201) is configured to acquire multi-source data collected by a sensor system arranged in a target area, wherein the sensor system comprises a plurality of gas sensors and a plurality of environmental sensors, the gas sensors are configured to collect gas concentration data, and the environmental sensors are configured to collect physical environment data. The processing module (202) is configured to fuse the gas concentration data and the physical environment data, and perform inversion calculation on a leak process of a leaked gas. The output module (203) is configured to determine a leak source position based on the leak process, and map back to a physical structure of a gas pipe network.

4. An electronic device, comprising: The electronic device comprises a processor (301), a communication bus (302), a user interface (303), a network interface (304) and a memory (305), the memory (305) is configured to store instructions, the user interface (303) and the network interface (304) are configured to communicate with other devices, the communication bus (302) is configured to realize connection and communication between components in the electronic device, and the processor (301) is configured to execute the instructions stored in the memory (305) to enable the electronic device to perform the method according to any one of claims 1-2.

5. A computer readable storage medium, characterized in that, The computer readable storage medium stores instructions, when the instructions are executed, the method according to any one of claims 1-2 is performed.

Images