Method, device and equipment for monitoring gas in closed space, medium and program product

Abstract

The invention relates to the technical field of gas monitoring, in particular to a gas monitoring method, device and equipment in a closed space, a medium and a program product. The method comprises the steps that gas monitoring data in a target space is acquired, a gas characteristic parameter matrix is constructed based on the gas monitoring data, the gas characteristic parameter matrix comprises a plurality of target characteristic parameters associated with monitoring requirements, and the target characteristic parameters comprise multi-component gas spectrum data; performing dimension reduction processing on the feature parameter matrix based on a preset dimension reduction algorithm to obtain a low-dimensional feature matrix, the low-dimensional feature matrix comprising a plurality of groups of data points of a target dimension; in response to the condition that the characteristic parameters of the data points exceed a preset concentration threshold value, determining abnormal data points exceeding the concentration threshold value; and generating gas leakage alarm information based on the relative position information of the abnormal data point in the target space. By adopting the method, the reliability and response efficiency of gas monitoring can be improved.

Description

Technical Field

[0001] The present application relates to the field of gas monitoring technology, and in particular to a method, device, equipment, medium and program product for monitoring gas in a confined space. Background Art

[0002] In industrial production, underground operations, warehousing and transportation, the accumulation of harmful gases in confined spaces (such as storage tanks, pipelines, underground mines, and ship cabins) can pose a serious threat to personnel safety and equipment operation. For example, the leakage of flammable gases (such as methane and hydrogen) can cause explosions, while the accumulation of toxic gases (such as carbon monoxide and hydrogen sulfide) can cause poisoning or even death. Therefore, real-time monitoring of gas concentrations in confined spaces and timely warnings when concentrations exceed standards are key to ensuring safe production.

[0003] Conventional gas monitoring technologies primarily rely on fixed or portable gas sensors, such as electrochemical sensors, non-destructive infrared (NDIR) sensors, and catalytic combustion sensors. These sensors can detect the concentration of specific gases and transmit the data to a monitoring system via wired or wireless means, enabling real-time monitoring and alarms.

[0004] However, the current gas monitoring methods have the following technical problems:

[0005] Existing gas monitoring methods have problems such as low monitoring coverage and response delay, resulting in low efficiency of gas monitoring in space, which needs to be optimized. Summary of the Invention

[0006] Based on this, it is necessary to provide a method, device, computer equipment, computer-readable storage medium and computer program product for gas monitoring in a confined space, which can improve the reliability and response efficiency of gas monitoring, in order to address the above technical problems.

[0007] In a first aspect, the present application provides a method for monitoring gas in a confined space. The method comprises:

[0008] Acquiring gas monitoring data within a target space, and constructing a gas characteristic parameter matrix based on the gas monitoring data, wherein the gas characteristic parameter matrix includes a plurality of target characteristic parameters associated with monitoring requirements, and the target characteristic parameters include multi-component gas spectral data;

[0009] Performing dimensionality reduction processing on the feature parameter matrix based on a preset dimensionality reduction algorithm to obtain a low-dimensional feature matrix, wherein the low-dimensional feature matrix includes several groups of data points of the target dimension;

[0010] In response to the presence of a characteristic parameter of the data point exceeding a preset concentration threshold, determining an abnormal data point exceeding the concentration threshold;

[0011] Gas leakage alarm information is generated based on the relative position information of the abnormal data point in the target space.

[0012] In one embodiment, generating gas leakage alarm information based on the relative position information of the abnormal data point in the target space includes:

[0013] Performing cluster analysis on the data points in the low-dimensional feature matrix to determine a data point cluster that satisfies a preset clustering constraint condition, wherein the data point cluster includes a central data point and edge data points whose distance from the central data point is less than a preset neighborhood threshold;

[0014] Constructing a gas distribution cloud map corresponding to the data point cluster based on the central data point and the edge data points;

[0015] A target data point cluster containing the abnormal data point is determined, and a fluid kinematics analysis is performed on the gas distribution cloud map corresponding to the target data point cluster based on a preset analysis algorithm to determine leakage source information associated with the abnormal data point.

[0016] In one embodiment, constructing a gas distribution cloud corresponding to the data point cluster based on the central data point and the edge data point includes:

[0017] Determining a bounding volume geometric model of the gas distribution cloud map based on the edge data points, wherein a preset expansion distance is set between a surface of the bounding volume geometric model and the edge data points;

[0018] The diffusion path of the target gas is predicted based on the gas distribution cloud map and the concentration distribution trend represented by the edge data points.

[0019] In one embodiment, acquiring gas monitoring data in the target space and constructing a gas characteristic parameter matrix based on the gas monitoring data includes:

[0020] Acquiring the gas monitoring data based on a plurality of sensor groups distributed in the target space, wherein the sensor groups include several types of gas sensors for different gas types;

[0021] The method further comprises:

[0022] Acquiring facility distribution information within the target space, and constructing a facility geometric model matching the facility target space based on the facility distribution information;

[0023] Several groups of leakage sources are preset in the facility geometric model space, gas diffusion simulation is performed based on the facility leakage sources and the facility geometric model, and the layout information of the sensor group in the target space is determined based on the results of the gas diffusion simulation, wherein the layout information includes downstream position information of the leakage source and position information of the airflow stagnation area.

[0024] In one embodiment, presetting a plurality of groups of leakage sources in the facility geometric model space, performing a gas diffusion simulation based on the facility leakage sources and the facility geometric model, and determining the layout information of the sensor group in the target space based on the results of the gas diffusion simulation includes:

[0025] Traversing and deleting component structures in the facility geometric model, performing the gas diffusion simulation on the deleted facility geometric model, and determining correlation parameters between the component structures and gas diffusion motion based on the simulation results;

[0026] The target component structures whose correlation parameters are lower than a preset threshold value in the facility geometric model are removed to obtain a simplified facility geometric model.

[0027] In one embodiment, presetting a plurality of groups of leakage sources in the facility geometric model space, performing a gas diffusion simulation based on the facility leakage sources and the facility geometric model, and determining the layout information of the sensor group in the target space based on the results of the gas diffusion simulation includes:

[0028] Setting a mover model that matches the real scene and corresponding action information in the facility geometric model, wherein the mover model is used to represent the dynamic operating facilities and moving objects in the target space;

[0029] The mover model is controlled to perform a gas diffusion simulation in the facility geometric model based on the motion information, so as to introduce a disturbance factor of the mover model into the gas diffusion simulation.

[0030] In a second aspect, the present application also provides a device for monitoring gas in a confined space. The device comprises:

[0031] A monitoring data module is used to obtain gas monitoring data in the target space and construct a gas characteristic parameter matrix based on the gas monitoring data. The gas characteristic parameter matrix includes a number of target characteristic parameters associated with the monitoring requirements, and the target characteristic parameters include multi-component gas spectral data;

[0032] A feature dimensionality reduction module is used to perform dimensionality reduction processing on the feature parameter matrix based on a preset dimensionality reduction algorithm to obtain a low-dimensional feature matrix, wherein the low-dimensional feature matrix includes several groups of data points of the target dimension;

[0033] an abnormality monitoring module, configured to, in response to a characteristic parameter of the data point exceeding a preset concentration threshold, determine an abnormal data point exceeding the concentration threshold;

[0034] The abnormality alarm module is used to generate gas leakage alarm information based on the relative position information of the abnormal data point in the target space.

[0035] In one embodiment, the abnormal alarm module includes:

[0036] A cluster analysis module, configured to perform cluster analysis on the data points in the low-dimensional feature matrix to determine a data point cluster that satisfies a preset clustering constraint condition, wherein the data point cluster includes a central data point and edge data points whose distance from the central data point is less than a preset neighborhood threshold;

[0037] A distribution cloud map module, configured to construct a gas distribution cloud map corresponding to the data point cluster based on the central data point and the edge data points;

[0038] The leakage source matching module is used to determine the target data point cluster where the abnormal data point exists, perform fluid kinematic analysis on the gas distribution cloud map corresponding to the target data point cluster based on a preset analysis algorithm, and determine the leakage source information associated with the abnormal data point.

[0039] In one embodiment, the distribution cloud map module includes:

[0040] a bounding volume model module, configured to determine a bounding volume geometric model of the gas distribution cloud map based on the edge data points, wherein a preset expansion distance is set between a surface of the bounding volume geometric model and the edge data points;

[0041] The diffusion prediction module is used to predict the diffusion path of the target gas based on the gas distribution cloud map and the concentration distribution trend represented by the edge data points.

[0042] In one embodiment, the monitoring data module includes:

[0043] a sensor group module, configured to obtain the gas monitoring data based on a plurality of sensor groups distributed in the target space, wherein the sensor groups include several types of gas sensors for different gas types;

[0044] The device further comprises:

[0045] a facility distribution model module, configured to obtain facility distribution information within the target space and construct a facility geometric model matching the facility target space based on the facility distribution information;

[0046] A diffusion simulation module is used to preset several groups of leakage sources in the facility geometric model space, perform gas diffusion simulation based on the facility leakage sources and the facility geometric model, and determine the layout information of the sensor group in the target space based on the results of the gas diffusion simulation, wherein the layout information includes the downstream position information of the leakage source and the position information of the airflow stagnation area.

[0047] In one embodiment, the diffusion simulation module includes:

[0048] a structural correlation module, configured to traverse and delete component structures in the facility geometric model, perform the gas diffusion simulation on the deleted facility geometric model, and determine correlation parameters between the component structures and the gas diffusion motion based on the simulation results;

[0049] The model simplification module is used to remove the target component structures whose correlation parameters are lower than a preset threshold value in the facility geometric model to obtain a simplified facility geometric model.

[0050] In one embodiment, the diffusion simulation module includes:

[0051] A mover model module, configured to set a mover model that matches the real scene and corresponding motion information in the facility geometric model, wherein the mover model is used to characterize the dynamic operating facilities and moving objects in the target space;

[0052] A disturbance simulation module is used to control the mover model to perform gas diffusion simulation in the facility geometric model based on the action information, so as to introduce a disturbance factor of the mover model into the gas diffusion simulation.

[0053] In a third aspect, the present application further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, it implements the steps of the method for monitoring gas in a confined space as described in any embodiment of the first aspect.

[0054] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method for monitoring gas in a confined space as described in any one of the embodiments of the first aspect.

[0055] In a fifth aspect, the present application further provides a computer program product, comprising a computer program that, when executed by a processor, implements the steps of the method for monitoring gas in a confined space as described in any one of the embodiments of the first aspect.

[0056] The above-mentioned method, apparatus, computer device, storage medium, and computer program product for monitoring gas in a confined space can achieve the following beneficial effects corresponding to the technical problems in the background technology by deducing the technical features in the claims:

[0057] The present application provides a method for monitoring gas in a confined space, comprising: obtaining gas monitoring data in a target space, constructing a gas characteristic parameter matrix based on the gas monitoring data, wherein the gas characteristic parameter matrix includes several target characteristic parameters associated with monitoring requirements, wherein the target characteristic parameters include multi-component gas spectral data; performing dimensionality reduction processing on the characteristic parameter matrix based on a preset dimensionality reduction algorithm to obtain a low-dimensional characteristic matrix, wherein the low-dimensional characteristic matrix includes several groups of data points of the target dimension; in response to the characteristic parameter of the data point exceeding a preset concentration threshold, determining an abnormal data point exceeding the concentration threshold; and generating a gas leak alarm based on the relative position information of the abnormal data point in the target space. In implementation, a terminal obtains gas monitoring data, and by integrating data from sensors at different locations into a gas characteristic parameter matrix, it helps to analyze different types of monitoring parameters in the gas characteristic parameter matrix, avoids the limitations of analyzing data from a single sensor, and helps to provide comprehensive monitoring data. Subsequently, the gas characteristic parameter matrix is ​​subjected to dimensionality reduction processing, which helps to eliminate redundant data, reduce the complexity of calculation, and enable the calculation to focus on core risk indicators, thereby helping to enhance the sensitivity of abnormal monitoring and highlight the main concentration mutation characteristics among a large number of parameters. The terminal then uses preset thresholds to identify abnormal data points and locate the leak source. This helps isolate abnormal data points and eliminate noise, allowing calculations to be tailored to the abnormal data, improving the efficiency and accuracy of anomaly location. Ultimately, the generation of alarm information enables response and handling of gas anomalies, improving the safety of facilities and personnel within the target space. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following briefly introduces the drawings required for use in the embodiments of the present application or related technical descriptions. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying any creative work.

[0059] Figure 1 A diagram of an application environment of a method for monitoring gas in a confined space according to an embodiment;

[0060] Figure 2 This is a schematic diagram of a first flow chart of a method for monitoring gas in a confined space in one embodiment;

[0061] Figure 3 is a second flow chart of a method for monitoring gas in a confined space in another embodiment;

[0062] Figure 4 A third flow chart of a method for monitoring gas in a confined space in another embodiment;

[0063] Figure 5 is a schematic diagram of a fourth flow chart of a method for monitoring gas in a confined space in another embodiment;

[0064] Figure 6 is a fifth flow chart of a method for monitoring gas in a confined space in another embodiment;

[0065] Figure 7 is a sixth flow chart of a method for monitoring gas in a confined space in another embodiment;

[0066] Figure 8 This is a structural block diagram of a gas monitoring device in a confined space according to an embodiment;

[0067] Figure 9 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0068] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0069] This application proposal is based on research on the following issues, specifically:

[0070] Conventional gas monitoring technologies primarily rely on fixed or portable gas sensors, such as electrochemical sensors, non-destructive infrared (NDIR) sensors, and catalytic combustion sensors. These sensors can detect the concentration of specific gases and transmit the data to a monitoring system via wired or wireless means, enabling real-time monitoring and alarms.

[0071] However, the current gas monitoring methods have the following technical problems:

[0072] Existing gas monitoring methods have problems such as low monitoring coverage and response delay, resulting in low efficiency of gas monitoring in space, which needs to be optimized.

[0073] Based on this, the embodiment of the present application provides a method for monitoring gas in a confined space, which can be applied to Figure 1In the application environment shown, the sensor group is used to monitor the gas in the target space and upload the acquired data to the terminal for processing. The terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can be smart speakers, smart TVs, smart air conditioners, smart car devices, projectors, etc.

[0074] In one embodiment, Figure 2 As shown, a method for monitoring gas in a confined space is provided. Figure 1 The following steps are used as an example to illustrate the terminal in the figure:

[0075] Step 202: Acquire gas monitoring data in the target space, and construct a gas characteristic parameter matrix based on the gas monitoring data.

[0076] The gas characteristic parameter matrix includes several target characteristic parameters associated with monitoring requirements, and the target characteristic parameters include multi-component gas spectrum data.

[0077] For example, multiple sensor groups, such as a multispectral gas sensor array (e.g., a TDLAS tunable laser spectrometer), can be deployed within the target space to collect spectral absorption data of multiple gases (e.g., CH4, CO2, H2S, etc.) in real time. The terminal can integrate the data from sensors at different locations into a gas characteristic parameter matrix with the dimensions [number of sensors × gas type × time series].

[0078] Step 204: Perform dimensionality reduction processing on the feature parameter matrix based on a preset dimensionality reduction algorithm to obtain a low-dimensional feature matrix.

[0079] The low-dimensional feature matrix includes several groups of data points of target dimensions.

[0080] For example, the dimensionality reduction algorithm may include principal component analysis (PCA), t-SNE, or UMAP algorithm, etc. The terminal may integrate or delete some elements in the multidimensional feature matrix through the dimensionality reduction algorithm, thereby reducing the multidimensional matrix to a target dimension.

[0081] Step 206: In response to the presence of a characteristic parameter of the data point exceeding a preset concentration threshold, determining an abnormal data point exceeding the concentration threshold.

[0082] For example, the terminal can perform cluster analysis (such as DBSCAN) on the reduced-dimensional data points, marking outliers that exceed a threshold (such as principal component 1 > 1.0). Then, combined with the sensor location information, the backpropagation algorithm is used to calculate the coordinates of the leak source (for example, outlier point S2 is located in the northeast corner of the space).

[0083] Step 208: Generate gas leakage alarm information based on the relative position information of the abnormal data point in the target space.

[0084] Among them, gas leakage alarm information may include leaked gas type, concentration, diffusion trend prediction information, etc.

[0085] In the above-mentioned method for monitoring gas in a confined space, reasonable deduction is performed in combination with the technical features in the embodiment to achieve the beneficial effect of solving the technical problems raised in the background technology:

[0086] The present application provides a method for monitoring gas in a confined space, comprising: obtaining gas monitoring data in a target space, constructing a gas characteristic parameter matrix based on the gas monitoring data, wherein the gas characteristic parameter matrix includes several target characteristic parameters associated with monitoring requirements, wherein the target characteristic parameters include multi-component gas spectral data; performing dimensionality reduction processing on the characteristic parameter matrix based on a preset dimensionality reduction algorithm to obtain a low-dimensional characteristic matrix, wherein the low-dimensional characteristic matrix includes several groups of data points of the target dimension; in response to the characteristic parameter of the data point exceeding a preset concentration threshold, determining an abnormal data point exceeding the concentration threshold; and generating a gas leak alarm based on the relative position information of the abnormal data point in the target space. In implementation, a terminal obtains gas monitoring data, and by integrating data from sensors at different locations into a gas characteristic parameter matrix, it helps to analyze different types of monitoring parameters in the gas characteristic parameter matrix, avoids the limitations of analyzing data from a single sensor, and helps to provide comprehensive monitoring data. Subsequently, the gas characteristic parameter matrix is ​​subjected to dimensionality reduction processing, which helps to eliminate redundant data, reduce the complexity of calculation, and enable the calculation to focus on core risk indicators, thereby helping to enhance the sensitivity of abnormal monitoring and highlight the main concentration mutation characteristics among a large number of parameters. The terminal then uses preset thresholds to identify abnormal data points and locate the leak source. This helps isolate abnormal data points and eliminate noise, allowing calculations to be tailored to the abnormal data, improving the efficiency and accuracy of anomaly location. Ultimately, the generation of alarm information enables response and handling of gas anomalies, improving the safety of facilities and personnel within the target space.

[0087] In one embodiment, Figure 3 As shown, step 208 includes:

[0088] Step 302: performing cluster analysis on the data points in the low-dimensional feature matrix to determine data point clusters that meet preset clustering constraints.

[0089] The data point cluster includes a central data point and edge data points whose distance from the central data point is less than a preset neighborhood threshold.

[0090] For example, the terminal can cluster data points based on density characteristics, pre-setting a neighborhood threshold based on the diffusion characteristics of a specific gas. The terminal can iterate over each data point, determine the neighborhood range of each point based on the neighborhood threshold, and then identify the number of data points within the neighborhood range of that point. If the number meets the preset threshold, the point is selected as the center data point, and the data points within the neighborhood are selected as edge data points. This allows clustering without pre-determining the morphological characteristics of the data point clusters, enabling monitoring and analysis of various gas leak types.

[0091] Step 304: constructing a gas distribution cloud map corresponding to the data point cluster based on the central data point and the edge data points.

[0092] For example, the terminal can interpolate data points within a cluster, such as using Kriging or inverse distance weighting (IDW), to generate a continuous concentration distribution surface. The terminal can then overlay a spatial structure model (such as a CAD map), annotating the center point (red), edge points (yellow), and concentration gradients (shades of dark). Ultimately, a visual gas distribution cloud map is formed.

[0093] Step 306: Determine the target data point cluster containing the abnormal data point, perform fluid kinematic analysis on the gas distribution cloud map corresponding to the target data point cluster based on a preset analysis algorithm, and determine leakage source information associated with the abnormal data point.

[0094] For example, the terminal can calculate the gas diffusion velocity vector based on the concentration gradient represented by the gas distribution cloud map, track it in reverse along the velocity field, and iteratively solve the coordinates of possible leakage sources in combination with the positions of spatial obstacles (such as pipes and walls). Through Bayesian reasoning, it integrates multi-cluster cloud map information and outputs the confidence level of the leakage source (such as "the probability of leakage at the valve port is 82%").

[0095] In this embodiment, by constructing a gas distribution cloud map and performing kinematic reverse tracing, the leakage source can be located and analyzed, which helps to improve the effect of gas monitoring.

[0096] In one embodiment, Figure 4 As shown, step 304 includes:

[0097] Step 402: Determine a bounding volume geometric model of the gas distribution cloud map based on the edge data points, wherein a preset expansion distance is set between the surface of the bounding volume geometric model and the edge data points.

[0098] The expansion distance may refer to the minimum spacing distance between the surface of the bounding volume geometric model and the data point, and the expansion distance may be determined by technicians based on the diffusion rate of the associated gas.

[0099] Exemplarily, the terminal may use an algorithm such as the Quickhull algorithm or the α-shape algorithm to calculate the minimum convex hull of edge data points to form an initial bounding volume; and extrapolate the expansion distance along the normal direction of the convex hull surface to generate a conservative safety boundary.

[0100] Step 404: Predicting the diffusion path of the target gas based on the gas distribution cloud map and the concentration distribution trend represented by the edge data points.

[0101] For example, the terminal can use the bounding volume geometry model, gas distribution cloud map and environmental parameters as input, and implement velocity field modeling, streamline tracking and diffusion path probability evaluation through prediction algorithms, and finally obtain a high-probability diffusion path to achieve diffusion prediction.

[0102] In this embodiment, the terminal converts discrete point clouds into computable geometric entities, providing a computational domain for subsequent physical simulations. It also considers diffusion, convection, and environmental disturbances, approximating real complex scenarios, and providing confidence intervals for diffusion paths, which helps to achieve hierarchical management of diffusion risks.

[0103] In one embodiment, Figure 5 As shown, step 202 includes:

[0104] Step 502: Acquire the gas monitoring data based on several sensor groups distributed in the target space, where the sensor groups include several types of gas sensors for different gas types.

[0105] Exemplarily, the sensor group may include electrochemical (such as H2S), infrared (such as CO2), catalytic combustion (such as CH4) and other sensors, covering the target gas spectrum.

[0106] The method further comprises:

[0107] Step 504: Acquire the facility distribution information in the target space, and construct a facility geometric model that matches the facility target space based on the facility distribution information.

[0108] Step 506: Preset several groups of leakage sources in the facility geometric model space, perform gas diffusion simulation based on the facility leakage sources and the facility geometric model, and determine the layout information of the sensor group in the target space based on the results of the gas diffusion simulation, wherein the layout information includes the downstream position information of the leakage source and the position information of the airflow stagnation area.

[0109] For example, the terminal can preset a virtual leak source at a leak-prone point (such as a valve or flange), set a leak rate (e.g., CH4@0.1kg / s), and configure simulation conditions such as ambient temperature, humidity, and spatial boundaries. The resulting simulation results include a concentration field time series, airflow streamlines, and stagnant zone identification (vortex core area). Furthermore, the terminal can increase simulation weights for facility areas with a high historical leak frequency.

[0110] In this embodiment, the terminal couples geometric models, fluid simulation, and sensor deployment into a system engineering, which helps to optimize the spatial configuration of the sensor network and provides reliability assurance for gas monitoring in high-risk environments.

[0111] In one embodiment, Figure 6 As shown, step 506 includes:

[0112] Step 602: traverse and delete the component structures in the facility geometric model, perform the gas diffusion simulation on the deleted facility geometric model, and determine the correlation parameters between the component structures and the gas diffusion movement based on the simulation results.

[0113] Step 604: removing the target component structures whose correlation parameters are lower than a preset threshold value in the facility geometric model to obtain a simplified facility geometric model.

[0114] In this embodiment, the terminal can delete structures irrelevant to gas dispersion in the model through simulation, thereby simplifying the model and improving the efficiency of simulation operations.

[0115] In one embodiment, Figure 7 As shown, step 506 includes:

[0116] Step 702: Setting a mover model that matches the real scene and corresponding action information in the facility geometric model, wherein the mover model is used to represent the dynamic operating facilities and moving objects in the target space.

[0117] Step 704: Based on the motion information, the mover model is controlled to perform a gas diffusion simulation in the facility geometric model, so as to introduce a disturbance factor of the mover model into the gas diffusion simulation.

[0118] The actuator model can include an AGC car, a robotic arm, and other components, as well as a model of a person moving within the scene. The person can be placed along a movement path marked by a technician, and their walking trajectory generated based on a probabilistic model. The terminal can also simulate the motion of the actuator model based on a mixed mode of preset paths and random behavior.

[0119] In this embodiment, by adding a mover model, it is helpful to introduce the disturbance factor caused by the movement of the mover model in the scene into the gas diffusion simulation, thereby improving the reliability of the simulation results.

[0120] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0121] Based on the same inventive concept, embodiments of the present application also provide a confined space gas monitoring device for implementing the aforementioned confined space gas monitoring method. The solution provided by this device is similar to the solution described in the aforementioned method. Therefore, the specific limitations of one or more of the following embodiments of the confined space gas monitoring device can be found in the aforementioned limitations of the confined space gas monitoring method and are not further elaborated here.

[0122] In one embodiment, Figure 8 As shown, a gas monitoring device in a confined space is provided, comprising: a monitoring data module, a feature dimension reduction module, an abnormality monitoring module and an abnormality alarm module, wherein:

[0123] A monitoring data module is used to obtain gas monitoring data in the target space and construct a gas characteristic parameter matrix based on the gas monitoring data. The gas characteristic parameter matrix includes a number of target characteristic parameters associated with the monitoring requirements, and the target characteristic parameters include multi-component gas spectral data;

[0124] A feature dimensionality reduction module is used to perform dimensionality reduction processing on the feature parameter matrix based on a preset dimensionality reduction algorithm to obtain a low-dimensional feature matrix, wherein the low-dimensional feature matrix includes several groups of data points of the target dimension;

[0125] an abnormality monitoring module, configured to, in response to a characteristic parameter of the data point exceeding a preset concentration threshold, determine an abnormal data point exceeding the concentration threshold;

[0126] The abnormality alarm module is used to generate gas leakage alarm information based on the relative position information of the abnormal data point in the target space.

[0127] In one embodiment, the abnormal alarm module includes:

[0128] A cluster analysis module, configured to perform cluster analysis on the data points in the low-dimensional feature matrix to determine a data point cluster that satisfies a preset clustering constraint condition, wherein the data point cluster includes a central data point and edge data points whose distance from the central data point is less than a preset neighborhood threshold;

[0129] A distribution cloud map module, configured to construct a gas distribution cloud map corresponding to the data point cluster based on the central data point and the edge data points;

[0130] The leakage source matching module is used to determine the target data point cluster where the abnormal data point exists, perform fluid kinematic analysis on the gas distribution cloud map corresponding to the target data point cluster based on a preset analysis algorithm, and determine the leakage source information associated with the abnormal data point.

[0131] In one embodiment, the distribution cloud map module includes:

[0132] a bounding volume model module, configured to determine a bounding volume geometric model of the gas distribution cloud map based on the edge data points, wherein a preset expansion distance is set between a surface of the bounding volume geometric model and the edge data points;

[0133] The diffusion prediction module is used to predict the diffusion path of the target gas based on the gas distribution cloud map and the concentration distribution trend represented by the edge data points.

[0134] In one embodiment, the monitoring data module includes:

[0135] a sensor group module, configured to obtain the gas monitoring data based on a plurality of sensor groups distributed in the target space, wherein the sensor groups include several types of gas sensors for different gas types;

[0136] The device further comprises:

[0137] a facility distribution model module, configured to obtain facility distribution information within the target space and construct a facility geometric model matching the facility target space based on the facility distribution information;

[0138] A diffusion simulation module is used to preset several groups of leakage sources in the facility geometric model space, perform gas diffusion simulation based on the facility leakage sources and the facility geometric model, and determine the layout information of the sensor group in the target space based on the results of the gas diffusion simulation, wherein the layout information includes the downstream position information of the leakage source and the position information of the airflow stagnation area.

[0139] In one embodiment, the diffusion simulation module includes:

[0140] a structural correlation module, configured to traverse and delete component structures in the facility geometric model, perform the gas diffusion simulation on the deleted facility geometric model, and determine correlation parameters between the component structures and the gas diffusion motion based on the simulation results;

[0141] The model simplification module is used to remove the target component structures whose correlation parameters are lower than a preset threshold value in the facility geometric model to obtain a simplified facility geometric model.

[0142] In one embodiment, the diffusion simulation module includes:

[0143] A mover model module, configured to set a mover model that matches the real scene and corresponding motion information in the facility geometric model, wherein the mover model is used to characterize the dynamic operating facilities and moving objects in the target space;

[0144] A disturbance simulation module is used to control the mover model to perform gas diffusion simulation in the facility geometric model based on the action information, so as to introduce a disturbance factor of the mover model into the gas diffusion simulation.

[0145] Each module in the aforementioned confined space gas monitoring device may be implemented in whole or in part through software, hardware, or a combination thereof. Each module may be embedded in or independent of a processor in a computer device in hardware form, or may be stored in a computer device memory in software form, so that the processor can call and execute the corresponding operations of each module.

[0146] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 9As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected via a system bus, and the communication interface, the display unit and the input device are connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a gas monitoring method in a confined space is implemented. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device casing, or an external keyboard, touchpad or mouse.

[0147] Those skilled in the art will understand that Figure 9 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0148] In one embodiment, a computer device is further provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps in the above method embodiments when executing the computer program.

[0149] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0150] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0151] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of relevant countries and regions.

[0152] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processor involved in the various embodiments provided herein may be, but are not limited to, a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, and the like.

[0153] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0154] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A method for monitoring gas in a confined space, characterized in that: The method comprises: Acquiring gas monitoring data within a target space, and constructing a gas characteristic parameter matrix based on the gas monitoring data, wherein the gas characteristic parameter matrix includes a plurality of target characteristic parameters associated with monitoring requirements, and the target characteristic parameters include multi-component gas spectral data; Performing dimensionality reduction processing on the feature parameter matrix based on a preset dimensionality reduction algorithm to obtain a low-dimensional feature matrix, wherein the low-dimensional feature matrix includes several groups of data points of the target dimension; In response to the presence of a characteristic parameter of the data point exceeding a preset concentration threshold, determining an abnormal data point exceeding the concentration threshold; Gas leakage alarm information is generated based on the relative position information of the abnormal data point in the target space.

2. The method according to claim 1, characterized in that The generating of gas leakage alarm information based on the relative position information of the abnormal data point in the target space includes: Performing cluster analysis on the data points in the low-dimensional feature matrix to determine a data point cluster that satisfies a preset clustering constraint condition, wherein the data point cluster includes a central data point and edge data points whose distance from the central data point is less than a preset neighborhood threshold; Constructing a gas distribution cloud map corresponding to the data point cluster based on the central data point and the edge data points; A target data point cluster containing the abnormal data point is determined, and a fluid kinematics analysis is performed on the gas distribution cloud map corresponding to the target data point cluster based on a preset analysis algorithm to determine leakage source information associated with the abnormal data point.

3. The method according to claim 2, characterized in that The constructing of a gas distribution cloud corresponding to the data point cluster based on the central data point and the edge data point includes: Determining a bounding volume geometric model of the gas distribution cloud map based on the edge data points, wherein a preset expansion distance is set between a surface of the bounding volume geometric model and the edge data points; The diffusion path of the target gas is predicted based on the gas distribution cloud map and the concentration distribution trend represented by the edge data points.

4. The method according to claim 1, wherein Acquiring gas monitoring data in the target space and constructing a gas characteristic parameter matrix based on the gas monitoring data includes: Acquiring the gas monitoring data based on a plurality of sensor groups distributed in the target space, wherein the sensor groups include several types of gas sensors for different gas types; The method further comprises: Acquiring facility distribution information within the target space, and constructing a facility geometric model matching the facility target space based on the facility distribution information; Several groups of leakage sources are preset in the facility geometric model space, gas diffusion simulation is performed based on the facility leakage sources and the facility geometric model, and the layout information of the sensor group in the target space is determined based on the results of the gas diffusion simulation, wherein the layout information includes downstream position information of the leakage source and position information of the airflow stagnation area.

5. The method according to claim 4, characterized in that Presetting a plurality of groups of leakage sources in the facility geometric model space, performing a gas diffusion simulation based on the facility leakage sources and the facility geometric model, and determining the layout information of the sensor group in the target space based on the result of the gas diffusion simulation includes: Traversing and deleting component structures in the facility geometric model, performing the gas diffusion simulation on the deleted facility geometric model, and determining correlation parameters between the component structures and gas diffusion motion based on the simulation results; The target component structures whose correlation parameters are lower than a preset threshold value in the facility geometric model are removed to obtain a simplified facility geometric model.

6. The method according to claim 4, characterized in that Presetting a plurality of groups of leakage sources in the facility geometric model space, performing a gas diffusion simulation based on the facility leakage sources and the facility geometric model, and determining the layout information of the sensor group in the target space based on the result of the gas diffusion simulation includes: Setting a mover model that matches the real scene and corresponding action information in the facility geometric model, wherein the mover model is used to represent the dynamic operating facilities and moving objects in the target space; The mover model is controlled to perform a gas diffusion simulation in the facility geometric model based on the motion information, so as to introduce a disturbance factor of the mover model into the gas diffusion simulation.

7. A gas monitoring device in a confined space, characterized in that: The device comprises: A monitoring data module is used to obtain gas monitoring data in the target space and construct a gas characteristic parameter matrix based on the gas monitoring data. The gas characteristic parameter matrix includes a number of target characteristic parameters associated with the monitoring requirements, and the target characteristic parameters include multi-component gas spectral data; A feature dimensionality reduction module is used to perform dimensionality reduction processing on the feature parameter matrix based on a preset dimensionality reduction algorithm to obtain a low-dimensional feature matrix, wherein the low-dimensional feature matrix includes several groups of data points of the target dimension; an abnormality monitoring module, configured to, in response to a characteristic parameter of the data point exceeding a preset concentration threshold, determine an abnormal data point exceeding the concentration threshold; The abnormality alarm module is used to generate gas leakage alarm information based on the relative position information of the abnormal data point in the target space.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images