Environmental change alarm system
By constructing a three-dimensional dynamic model and dynamic interactive field of the underground environment, the accuracy problem of identifying underground environmental changes and risk assessment is solved, and comprehensive monitoring of the underground environmental status and risk warning are achieved.
Patent Information
- Application Number
- CN202511069505.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-07-31
- Publication Date
- 2025-09-23
AI Technical Summary
When facing complex security threats, the existing underground environmental abnormality alarm system has problems such as false alarms, missed alarms, inaccurate risk assessment and insufficient risk prediction, making it difficult to effectively identify the abnormality propagation mechanism and evolution law.
By collecting multi-source fluctuation data in the well in real time, a three-dimensional dynamic model is constructed, the three-dimensional dynamic molecular matrix and dynamic interaction field are determined, and a model for monitoring the abnormal movement of the underground environment is established to conduct quantitative risk assessment and abnormal warning.
It achieves comprehensive, intuitive and dynamic visualization of the underground environmental status, improves the perception and analysis capabilities of complex environmental coupling changes and abnormal behaviors, and improves the reliability of the abnormal movement identification model and the accuracy of the alarm system.
Smart Images
Figure CN120688280A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of environmental abnormality alarm, and more specifically, to an environmental abnormality alarm system. Background Art
[0002] In recent years, underground environmental monitoring technology has developed rapidly. As a key technology for ensuring underground safety, the environmental anomaly alarm system realizes real-time monitoring of underground environmental parameters and risk warning by integrating multi-source sensor networks, digital twin modeling and intelligent analysis algorithms. In existing technologies, advanced alarm systems usually have functions such as three-dimensional dynamic modeling, multi-physics field coupling analysis and intelligent risk assessment. They can automatically identify environmental anomalies, assess risk levels, and issue early warning signals in a timely manner, thereby effectively preventing the occurrence of safety accidents. In actual applications, such systems achieve accurate characterization of the dynamic interaction effects of the underground environment by constructing a three-dimensional dynamic molecular matrix and combining the joint analysis of multiple physical fields such as temperature field, stress field, and seepage field, significantly improving the accuracy and timeliness of safety monitoring.
[0003] However, existing technologies still require further improvement in alarm systems. First, due to the strong nonlinearity and time-varying nature of the underground environment, the system is prone to false alarms and missed alarms, such as misjudging normal environmental fluctuations as safety hazards or failing to promptly identify potential major risks. Second, when it comes to the fusion processing of multi-source heterogeneous data, existing systems struggle to accurately distinguish the coupling relationships between different parameters, resulting in inaccurate risk assessments. Furthermore, when it comes to anomaly root cause analysis and risk prediction, traditional methods often lack a deep understanding of the propagation mechanisms and evolutionary patterns of anomalies, making it difficult to provide reliable support for emergency decision-making. In particular, when faced with complex safety threats such as abnormal gas accumulation and signs of water inrush, existing systems still have significant deficiencies in risk quantification accuracy and warning timeliness. Therefore, establishing a more reliable model for identifying underground environmental anomalies and conducting risk quantification assessments based on dynamic interactive fields to improve the accuracy of alarm systems has become a key challenge that needs to be addressed. Summary of the Invention
[0004] The present application provides an environmental anomaly alarm system that can establish a more reliable underground environmental anomaly identification model and perform risk quantification assessment based on a dynamic interactive field to improve the accuracy of the alarm system.
[0005] In a first aspect, the present application provides an environmental abnormality alarm system, characterized in that the alarm system comprises:
[0006] A model building module, configured to collect multi-source fluctuation data of the downhole environment in real time and build a three-dimensional dynamic model of the downhole environment based on the multi-source fluctuation data;
[0007] A field determination module is used to determine a three-dimensional dynamic molecular matrix of the downhole environment based on the three-dimensional dynamic model of the downhole environment, and determine a dynamic interaction field of the downhole environment through the three-dimensional dynamic molecular matrix;
[0008] a matrix determination module, configured to establish a downhole environment abnormality monitoring model based on the dynamic interaction field of the downhole environment, perform abnormality monitoring based on the downhole environment abnormality monitoring model to obtain an abnormality data matrix, and determine downhole risk assessment data based on the abnormality data matrix;
[0009] The alarm module is used to quantify the risk according to the downhole risk assessment data, thereby obtaining the abnormal risk level of the downhole environment, and to issue an abnormal warning according to the abnormal risk level.
[0010] In this embodiment, multi-source fluctuation data of the downhole environment is collected in real time through a distributed multi-modal sensor array.
[0011] In this embodiment, the multimodal sensor array is distributedly deployed according to environmental parameters, geological parameters, equipment status, and personnel location data.
[0012] In this embodiment, constructing a three-dimensional dynamic model of the downhole environment using the multi-source fluctuation data specifically includes:
[0013] Performing spatiotemporal synchronization on the multi-source fluctuation data to obtain spatiotemporal synchronized multi-source fluctuation data;
[0014] The multi-source fluctuation data after time and space synchronization are input into the lightweight digital twin engine for rendering, thereby obtaining a three-dimensional dynamic model of the underground environment.
[0015] In this embodiment, determining the three-dimensional dynamic molecular matrix of the downhole environment according to the downhole three-dimensional dynamic model specifically includes:
[0016] The three-dimensional space of the downhole is gridded, and the three-dimensional dynamic model of the downhole is associated with the grid coordinates, thereby obtaining a three-dimensional dynamic molecular matrix of the downhole environment.
[0017] In this embodiment, the three-dimensional dynamic molecular matrix is a multi-dimensional data structure for storing downhole environmental information.
[0018] In this embodiment, determining the dynamic interaction field of the downhole environment through the three-dimensional dynamic molecular matrix specifically includes:
[0019] Jointly simulate multiple physical fields in the downhole environment to obtain the interaction effects of the physical fields in the downhole environment;
[0020] The three-dimensional dynamic molecular matrix and the physical field interaction effect are coupled and simulated to obtain the dynamic interaction field of the downhole environment.
[0021] In this embodiment, the dynamic interaction field is a physical field used to characterize the multi-dimensional dynamic coupling effect of the complex underground environment.
[0022] In this embodiment, abnormality monitoring is performed according to the underground environment abnormality monitoring model to obtain an abnormality data matrix, which specifically includes:
[0023] The underground environment abnormality monitoring model is used to monitor the abnormality of the underground environment in real time to obtain abnormality data of the underground environment;
[0024] All abnormal points in the dynamic interaction field are determined by using abnormal data of the downhole environment, and the data of all abnormal points are processed to obtain an abnormal data matrix.
[0025] In this embodiment, determining downhole risk assessment data according to the abnormal data matrix specifically includes:
[0026] Identifying the root cause of the abnormality through the abnormality data matrix, and performing risk prediction based on the root cause of the abnormality to obtain risk prediction data;
[0027] The risk diffusion path is marked according to the risk prediction data to obtain risk diffusion path data, and the risk assessment data is determined through the risk prediction data and the risk diffusion path data.
[0028] The technical solutions provided by the embodiments disclosed in this application have the following beneficial effects:
[0029] The model building module collects multi-source fluctuation data of the downhole environment in real time, and constructs a three-dimensional dynamic model of the downhole environment through the multi-source fluctuation data; the field determination module determines the three-dimensional dynamic molecular matrix of the downhole environment according to the three-dimensional dynamic model of the downhole environment, and determines the dynamic interaction field of the downhole environment through the three-dimensional dynamic molecular matrix; the matrix determination module establishes a downhole environment anomaly monitoring model according to the dynamic interaction field of the downhole environment, performs anomaly monitoring according to the downhole environment anomaly monitoring model, obtains an anomaly data matrix, and determines downhole risk assessment data according to the anomaly data matrix; the alarm module quantifies risks according to the downhole risk assessment data, and then obtains the anomaly risk level of the downhole environment, and performs abnormal warnings according to the anomaly risk level.
[0030] It can be seen that in this application, first, by collecting multi-source fluctuation data of the downhole environment in real time and constructing a three-dimensional dynamic model of the downhole environment, it is possible to achieve a comprehensive, intuitive and dynamic visualization expression of the complex downhole environmental state, and more accurately capture the subtle characteristics and spatiotemporal evolution laws of environmental anomalies; then, the three-dimensional dynamic molecular matrix is determined through the three-dimensional dynamic model of the downhole environment, and a dynamic interactive field is constructed based on the matrix, which can achieve a comprehensive characterization of the spatial structure of the downhole environment and the changes in multi-source physical fields, and significantly improve the perception and interpretation of the coupled changes and abnormal behaviors of the complex environment. Analysis capability; secondly, by establishing a downhole environmental anomaly monitoring model based on the dynamic interactive field of the downhole environment, and performing anomaly monitoring and risk assessment based on the downhole environmental anomaly monitoring model, it is possible to achieve comprehensive perception and accurate characterization of the multi-source anomaly characteristics of the complex downhole environment, thereby identifying the root cause of the anomaly and the risk propagation path; finally, by quantifying the risk based on the downhole risk assessment data, and then determining the anomaly risk level of the downhole environment, and performing abnormal warnings based on the risk level, it is possible to effectively improve the reliability of the downhole environmental anomaly identification model, thereby improving the accuracy of the alarm system.
[0031] In summary, the technical solution adopted in this application can establish a more reliable underground environmental anomaly identification model and perform risk quantification assessment based on the dynamic interaction field to improve the accuracy of the alarm system. BRIEF DESCRIPTION OF THE DRAWINGS
[0032] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following is a brief introduction to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.
[0033] Figure 1 This is a module structure diagram of an environmental abnormality alarm system provided by this application;
[0034] Figure 2 is an exemplary flow chart for determining a dynamic interaction field of a downhole environment provided by the present application;
[0035] Figure 3 It is an exemplary flow chart for determining an abnormal data matrix provided by this application. DETAILED DESCRIPTION
[0036] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.
[0037] The embodiment of the present application provides an environmental anomaly alarm system, the core of which is to collect multi-source fluctuation data of the downhole environment in real time through a model construction module, and construct a three-dimensional dynamic model of the downhole environment through the multi-source fluctuation data; the field determination module determines the three-dimensional dynamic molecular matrix of the downhole environment according to the three-dimensional dynamic model of the downhole environment, and determines the dynamic interaction field of the downhole environment through the three-dimensional dynamic molecular matrix; the matrix determination module establishes a downhole environmental anomaly monitoring model according to the dynamic interaction field of the downhole environment, performs anomaly monitoring according to the downhole environmental anomaly monitoring model, obtains an anomaly data matrix, and determines downhole risk assessment data according to the anomaly data matrix; the alarm module quantifies the risk according to the downhole risk assessment data, and then obtains the anomaly risk level of the downhole environment, and performs abnormal warning according to the anomaly risk level. The above scheme can establish a more reliable downhole environmental anomaly identification model, and perform risk quantification assessment based on the dynamic interaction field to improve the accuracy of the alarm system.
[0038] In order to better understand the above technical solution, the following will be described in detail with reference to the accompanying drawings and specific implementation methods. Figure 1 As shown in FIG. 1 , this figure is a module structure diagram of an environmental abnormality alarm system according to this embodiment of the present application. The alarm system includes: a model building module 100, a field determination module 200, a matrix determination module 300, and an alarm module 400, which are described as follows:
[0039] The model building module 100 is used to collect multi-source fluctuation data of the downhole environment in real time, and build a three-dimensional dynamic model of the downhole environment based on the multi-source fluctuation data.
[0040] In this embodiment, multi-source fluctuation data of the downhole environment are collected in real time through a distributed multi-modal sensor array; in specific implementation, first, multiple groups of intelligent sensor nodes can be deployed in key areas underground, each node integrating multiple high-precision sensors, and then the integrated high-precision sensors are used to collect data on the downhole environment in real time; it should be noted that in this application, the multi-modal sensor array can be distributedly deployed according to environmental parameters, geological parameters, equipment status and personnel positioning data. For example, the multi-modal sensor array can be distributedly deployed in areas with significant air flow (tunnels, air shafts), rock crushing areas, key equipment concentration areas (elevators, fans, pump stations) and operating areas, so that multi-source fluctuation data of the downhole environment can be collected in real time, wherein the multi-source fluctuation data includes downhole environmental parameter data, downhole geological parameter data, equipment status data and personnel positioning data.
[0041] In this embodiment, the three-dimensional dynamic model of the underground environment can be constructed by using the multi-source fluctuation data in the following manner:
[0042] Performing spatiotemporal synchronization on the multi-source fluctuation data to obtain spatiotemporal synchronized multi-source fluctuation data;
[0043] The multi-source fluctuation data after time and space synchronization are input into the lightweight digital twin engine for rendering, thereby obtaining a three-dimensional dynamic model of the underground environment.
[0044] In specific implementation, first, the multi-source fluctuation data can be synchronized in time and space, that is, a unified time base (such as Beidou / GPS time or local high-precision timing system) can be used to align the timestamps of various types of data in the multi-source fluctuation data, and the spatial coordinates corresponding to various types of data in the multi-source fluctuation data can be mapped to a spatial model, thereby marking the spatial coordinates of various types of data in the multi-source fluctuation data. The above method can achieve the time and space synchronization of multi-source fluctuation data, thereby obtaining the multi-source fluctuation data after time and space synchronization; then, the multi-source fluctuation data after time and space synchronization can be input into the lightweight digital twin engine for rendering, so that a three-dimensional model containing downhole environmental parameter data, downhole geological parameter data, equipment status data and personnel positioning data can be generated, that is, a three-dimensional dynamic model of the downhole environment. The lightweight digital twin engine selected in this application adopts the Unity3D real-time rendering framework.
[0045] It should be noted that by collecting multi-source fluctuation data of the downhole environment in real time and constructing a three-dimensional dynamic model of the downhole environment, a comprehensive, intuitive and dynamic visual expression of the complex downhole environmental state can be achieved. This not only effectively makes up for the problems of information isolation, response lag and insufficient spatial perception of traditional monitoring methods, but also enables the deep integration of multi-source heterogeneous data such as environment, equipment, geology and personnel. Based on the three-dimensional dynamic model, the subtle features and spatiotemporal evolution laws of environmental anomalies can be more accurately captured, providing real, continuous and multi-dimensional support data for the establishment of a more reliable downhole environmental anomaly identification model. The field determination module 200 is used to determine the three-dimensional dynamic molecular matrix of the downhole environment based on the three-dimensional dynamic model of the downhole environment, and to determine the dynamic interaction field of the downhole environment through the three-dimensional dynamic molecular matrix.
[0046] In this embodiment, the three-dimensional dynamic molecular matrix of the downhole environment can be determined based on the downhole three-dimensional dynamic model in the following manner:
[0047] The three-dimensional space of the downhole is gridded, and the three-dimensional dynamic model of the downhole is associated with the grid coordinates, thereby obtaining a three-dimensional dynamic molecular matrix of the downhole environment.
[0048] In specific implementation, first, based on the three-dimensional space of the downhole environment, certain rules can be used to divide the space into multiple small units, that is, gridding. The purpose of gridding is to convert the complex three-dimensional space environment into a structured grid system to facilitate data management and analysis. In this application, the downhole three-dimensional space can be gridded into multiple 0.5m×0.5m×0.5m cubic grid units; then, the downhole three-dimensional dynamic model can be associated with the grid coordinates, so as to obtain a three-dimensional dynamic molecular matrix of the downhole environment, wherein the three-dimensional dynamic molecular matrix is a multidimensional data structure for storing downhole environment information. The three-dimensional dynamic molecular matrix contains the downhole environmental spatial information and environmental parameters of each grid cell at the corresponding moment. In actual implementation, each grid cell has a clear spatial coordinate, through which the position of the grid cell can be accurately found in the downhole three-dimensional dynamic model. The environmental parameters corresponding to the grid cell (such as gas concentration, temperature, humidity, etc.) are dynamically updated and bound to the grid cell. The data in each grid cell not only includes spatial information, but also needs to be bound to time information (for example, the data value at a certain moment). As time changes, a matrix that is dynamically updated in time and space is formed, that is, a three-dimensional dynamic molecular matrix.
[0049] Preferably, in this embodiment, reference Figure 2 As shown in FIG. 1 , this figure is an exemplary flow chart for determining the dynamic interaction field of the downhole environment in an embodiment of the present application. In this embodiment, determining the dynamic interaction field of the downhole environment by the three-dimensional dynamic molecular matrix can be implemented by the following steps:
[0050] In step S21, a joint simulation is performed on multiple physical fields in the downhole environment to obtain the interaction effect of the physical fields in the downhole environment;
[0051] In step S22, a coupling simulation is performed on the three-dimensional dynamic molecular matrix and the physical field interaction effect to obtain a dynamic interaction field of the downhole environment.
[0052] In specific implementation, first, multiple physical fields in the downhole environment can be jointly simulated, that is, typical physical fields (gas diffusion field, temperature field, humidity field, wind flow field, geological stress field and electromagnetic field) existing in the downhole environment are input into a multi-physics field simulation platform (such as COMSOL, ANSYS) for multi-field joint solution to obtain the interaction characteristics and effects of each physical field, thereby obtaining the physical field interaction effect in the downhole environment, wherein the physical field interaction effect represents the strong correlation and coupling effect between different physical fields in the downhole environment; then, the three-dimensional dynamic molecular matrix and the physical field interaction effect can be coupled simulated to obtain the dynamic interaction field of the downhole environment, wherein the dynamic interaction field is a physical field used to characterize the multi-dimensional dynamic coupling effect of the complex downhole environment. The three-dimensional dynamic molecular matrix and the physical field interaction effect can be used as the boundary conditions of the physical field model, and the physical field model can be fused and iteratively updated through the simulation algorithm to realize the dynamic coupling between the three-dimensional dynamic molecular matrix and the physical field interaction effect, thereby obtaining the dynamic interaction field of the downhole environment, which can reflect the coupling effect and real-time evolution law between the physical fields in the downhole environment.
[0053] It should be noted that by determining the three-dimensional dynamic molecular matrix through the three-dimensional dynamic model of the downhole environment and constructing a dynamic interaction field based on the matrix, a comprehensive characterization of the spatial structure of the downhole environment and the changes in multi-source physical fields can be achieved. The dynamic interaction field effectively integrates environmental parameters, physical field effects and spatial distribution characteristics, significantly improving the perception and analysis capabilities of complex environmental coupling changes and abnormal behaviors, and helping to establish a more accurate, dynamic and adaptive environmental anomaly identification model, and achieving accurate prediction of the diffusion path, impact range and evolution trend of hazardous sources, thereby greatly improving the sensitivity, accuracy and response time of the downhole environmental anomaly alarm system, and effectively supporting the high reliability and scientific decision-making of downhole safety monitoring and intelligent early warning.
[0054] The matrix determination module 300 is used to establish a downhole environment anomaly monitoring model based on the dynamic interaction field of the downhole environment, perform anomaly monitoring based on the downhole environment anomaly monitoring model, obtain an anomaly data matrix, and determine downhole risk assessment data based on the anomaly data matrix.
[0055] In this embodiment, a downhole environment anomaly monitoring model is established based on the dynamic interactive field of the downhole environment. In specific implementation, first, it is necessary to clarify the modeling principles of the downhole environment anomaly monitoring model, namely multi-dimensional data drive (physical quantity + spatial position + time series), multi-field coupling perception (joint monitoring and feature fusion), anomaly behavior identification (change amplitude + change rate + abnormal characteristics) and risk evolution tracking (spatial diffusion + time development); then, the key monitoring objects and indicators of the downhole environment anomaly monitoring model can be defined. For example, when the key monitoring object is temperature, the indicator can be the temperature mutation rate; finally, anomaly identification criteria can be established (for example, anomaly threshold setting, anomaly pattern recognition and multi-field coupling response rules), and anomaly monitoring and early warning logic can be established, so that a downhole environment anomaly monitoring model can be obtained, which can monitor and display the three-dimensional distribution of abnormal areas in real time.
[0056] Preferably, in this embodiment, reference Figure 2 As shown in FIG. 1 , this figure is an exemplary flow chart for determining an abnormal data matrix in an embodiment of the present application. In this embodiment, abnormal monitoring is performed based on the downhole environment abnormality monitoring model, and obtaining the abnormal data matrix can be specifically achieved by the following steps:
[0057] In step S31, the underground environment abnormality monitoring model is used to monitor the underground environment abnormality in real time to obtain underground environment abnormality data;
[0058] In step S32, all abnormal points in the dynamic interaction field are determined by the abnormal data of the downhole environment, and the data of all abnormal points are processed to obtain an abnormal data matrix.
[0059] In specific implementation, first, the downhole environment anomaly monitoring model can be used to monitor the anomalies of the downhole environment in real time, that is, to continuously receive real-time multi-source fluctuation data (environmental parameters, equipment status, personnel location, physical field characteristics, etc.) from multi-modal sensors, and then rely on the downhole environment anomaly monitoring model to conduct real-time analysis on the collected multi-source fluctuation data. According to the anomaly judgment rules preset in the downhole environment anomaly monitoring model, the anomaly events in the downhole environment can be automatically identified, so that the anomaly data of the downhole environment can be obtained, wherein the anomaly data includes the time when the anomaly occurs in the downhole environment, the anomaly location (spatial coordinates / grid number), the anomaly type (gas, temperature, pressure, vibration, etc.) and the anomaly characteristic parameters (amplitude). degree, rate, abnormal index); then, all abnormal points in the dynamic interaction field can be determined through the abnormal data of the downhole environment, that is, the spatial coordinates of the abnormal data are marked in the dynamic interaction field, and the marked spatial coordinate points are used as abnormal points. All abnormal points in the dynamic interaction field can be obtained in the above manner; finally, the data of all abnormal points can be processed, that is, for all the identified abnormal points, the relevant feature data corresponding to each abnormal point are extracted, and the relevant feature data are uniformly standardized and normalized to facilitate subsequent analysis, so that the abnormal data can be expressed in a matrix according to the spatial position, time series and feature dimension to form an abnormal data matrix.
[0060] In this embodiment, the downhole risk assessment data may be determined according to the abnormal data matrix in the following manner:
[0061] Identifying the root cause of the abnormality through the abnormality data matrix, and performing risk prediction based on the root cause of the abnormality to obtain risk prediction data;
[0062] The risk diffusion path is marked according to the risk prediction data to obtain risk diffusion path data, and the risk assessment data is determined through the risk prediction data and the risk diffusion path data.
[0063] In specific implementation, first, the root cause of the abnormality can be identified based on the abnormal data matrix, that is, an in-depth correlation analysis is conducted on various related feature data in the abnormal data matrix, and data mining, cause-effect tracing, expert knowledge base and other methods are used, combined with historical cases and physical mechanism models, to identify the logical or physical coupling relationship between abnormal events, so as to determine the core inducement or main controlling factor of the abnormality, that is, the root cause of the abnormality; then, risk prediction can be carried out based on the root cause of the abnormality, that is, the underground risk knowledge base and prediction algorithm are called to predict the future risk situation based on the characteristics of the root cause of the abnormality, thereby forming structured risk prediction data, wherein the risk prediction data includes the location of the risk source, the risk type, the risk Risk intensity, evolution trend and potential impact radius; secondly, the risk diffusion path can be marked according to the risk prediction data to obtain risk diffusion path data, that is, the risk prediction data can be input into the dynamic interaction field for simulation, so that the abnormal diffusion or migration path can be obtained, and the spatial trajectory of the abnormal diffusion path can be calibrated in the three-dimensional dynamic model of the underground environment to form the risk diffusion path data, wherein the risk diffusion path data includes the diffusion direction, diffusion speed and the coordinates of the affected blocks; finally, the risk assessment data can be determined through the risk prediction data and the risk diffusion path data, that is, the data set composed of the risk prediction data and the risk diffusion path data is combined as the risk assessment data.
[0064] It should be noted that by establishing an underground environmental anomaly monitoring model based on the dynamic interactive field of the underground environment, and conducting anomaly monitoring and risk assessment based on the underground environmental anomaly monitoring model, it is possible to achieve comprehensive perception and accurate characterization of the multi-source anomaly characteristics of the complex underground environment. It can not only dynamically capture and monitor various abnormal fluctuations in the underground environment in real time, but also deeply analyze the spatial distribution, evolution laws and interaction mechanisms of anomaly events through the construction of anomaly data matrix, thereby identifying the root causes of anomalies and risk propagation paths, providing the alarm system with more accurate risk identification, more reliable warning triggering conditions and more intelligent response strategies, and significantly enhancing the accuracy, timeliness and active prevention and control capabilities of the underground safety early warning system.
[0065] The alarm module 400 is used to quantify the risk based on the downhole risk assessment data, thereby obtaining the abnormal risk level of the downhole environment, and to issue an abnormal warning based on the abnormal risk level.
[0066] In specific implementation, a risk quantification model can be constructed. The risk quantification model used in this application is a convolutional neural network model based on deep learning. The convolutional neural network model based on deep learning is used to perform feature extraction and pattern recognition on the risk assessment data of the downhole environment, and automatically learn the nonlinear relationship between risk factors, thereby realizing the comprehensive quantification of environmental abnormality risks and risk level prediction, that is, the downhole risk assessment data is input into the risk quantification model for risk quantification, thereby obtaining the abnormal risk level of the downhole environment.
[0067] In this embodiment, the abnormality warning may be performed according to the abnormal risk level in the following manner, namely,
[0068] Obtain a pre-defined risk level table;
[0069] An abnormality warning strategy is generated based on the abnormal risk level and a pre-set risk level table.
[0070] In specific implementation, first, a risk level table can be pre-set based on expert knowledge and historical experience; then, an abnormality warning strategy can be generated based on the abnormal risk level and the pre-set risk level table, for example:
[0071] When the abnormal risk level is at Level I risk in the risk level table, it is necessary to continuously collect and record data on the underground environment and conduct routine monitoring of environmental changes (such as temperature, humidity, and gas concentration). There is no need for immediate warning. Only the risk data is updated on the monitoring interface. No intervention is required to maintain the current status.
[0072] When the risk level of abnormal movement is at Level II risk in the risk level table, it is necessary to strengthen monitoring of the underground environment, issue reminders, conduct inspections, monitor key areas through real-time data, increase the frequency of inspections, and regularly push risk warnings to underground workers.
[0073] When the risk level of abnormal movement is at Level III in the risk level table, it is necessary to focus on monitoring the underground environment, initiate risk prevention and control measures, start the evacuation of personnel and ventilation equipment adjustment in high-risk areas, conduct self-inspections on all key equipment underground, confirm the safety status of the equipment, enhance emergency preparedness, respond quickly, and send emergency information to all relevant personnel to ensure that preventive measures are taken in the shortest time possible.
[0074] When the risk level of abnormal movement is at Level IV in the risk level table, an emergency warning of the underground environment is required, and a full range of real-time monitoring systems, including temperature, pressure, gas concentration, etc., must be immediately activated. Advanced risk prediction models must be used to provide early warning of possible diffusion paths and intensities, and emergency plans must be immediately activated to evacuate personnel, shut down equipment, and perform emergency ventilation. Based on the risk diffusion path data, the safe evacuation of personnel in relevant areas must be ensured, and the emergency command system must be activated to dispatch all emergency resources.
[0075] It should be noted that by quantifying risks based on downhole risk assessment data, and then determining the risk level of the downhole environment, and issuing abnormal warnings based on the risk level, the reliability of the downhole environment anomaly identification model can be effectively improved. Risk assessment can more accurately reflect the real-time status of the downhole environment, detect potential dangers in a timely manner, and improve the accuracy of the alarm system.
[0076] It can be seen that in this application, first, by collecting multi-source fluctuation data of the downhole environment in real time and constructing a three-dimensional dynamic model of the downhole environment, it is possible to achieve a comprehensive, intuitive and dynamic visualization expression of the complex downhole environmental state, and more accurately capture the subtle characteristics and spatiotemporal evolution laws of environmental anomalies; then, the three-dimensional dynamic molecular matrix is determined through the three-dimensional dynamic model of the downhole environment, and a dynamic interactive field is constructed based on the matrix, which can achieve a comprehensive characterization of the spatial structure of the downhole environment and the changes in multi-source physical fields, and significantly improve the perception and interpretation of the coupled changes and abnormal behaviors of the complex environment. Analysis capability; secondly, by establishing a downhole environmental anomaly monitoring model based on the dynamic interactive field of the downhole environment, and performing anomaly monitoring and risk assessment based on the downhole environmental anomaly monitoring model, it is possible to achieve comprehensive perception and accurate characterization of the multi-source anomaly characteristics of the complex downhole environment, thereby identifying the root cause of the anomaly and the risk propagation path; finally, by quantifying the risk based on the downhole risk assessment data, and then determining the anomaly risk level of the downhole environment, and performing abnormal warnings based on the risk level, it is possible to effectively improve the reliability of the downhole environmental anomaly identification model, thereby improving the accuracy of the alarm system.
[0077] In summary, the technical solution adopted in this application can establish a more reliable underground environmental anomaly identification model and perform risk quantification assessment based on the dynamic interaction field to improve the accuracy of the alarm system.
[0078] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0079] Those skilled in the art will appreciate that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium, including a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.
[0080] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.
Claims
1. An environmental abnormality alarm system, characterized in that: The alarm system comprises: A model building module, configured to collect multi-source fluctuation data of the downhole environment in real time and build a three-dimensional dynamic model of the downhole environment based on the multi-source fluctuation data; A field determination module is used to determine a three-dimensional dynamic molecular matrix of the downhole environment based on the three-dimensional dynamic model of the downhole environment, and determine a dynamic interaction field of the downhole environment through the three-dimensional dynamic molecular matrix; a matrix determination module, configured to establish a downhole environment abnormality monitoring model based on the dynamic interaction field of the downhole environment, perform abnormality monitoring based on the downhole environment abnormality monitoring model to obtain an abnormality data matrix, and determine downhole risk assessment data based on the abnormality data matrix; The alarm module is used to quantify the risk according to the downhole risk assessment data, thereby obtaining the abnormal risk level of the downhole environment, and to issue an abnormal warning according to the abnormal risk level.
2. The environmental abnormality alarm system according to claim 1, characterized in that: Multi-source fluctuation data of the downhole environment is collected in real time through a distributed multi-modal sensor array.
3. The environmental abnormality alarm system according to claim 2, characterized in that: The multimodal sensor array is distributedly deployed according to environmental parameters, geological parameters, equipment status and personnel positioning data.
4. The environmental abnormality alarm system according to claim 1, characterized in that: Constructing a three-dimensional dynamic model of the underground environment using the multi-source fluctuation data specifically includes: Performing spatiotemporal synchronization on the multi-source fluctuation data to obtain spatiotemporal synchronized multi-source fluctuation data; The multi-source fluctuation data after time and space synchronization are input into the lightweight digital twin engine for rendering, thereby obtaining a three-dimensional dynamic model of the underground environment.
5. The environmental abnormality alarm system according to claim 1, characterized in that: Determining the three-dimensional dynamic molecular matrix of the downhole environment according to the downhole three-dimensional dynamic model specifically includes: The three-dimensional space of the downhole is gridded, and the three-dimensional dynamic model of the downhole is associated with the grid coordinates, thereby obtaining a three-dimensional dynamic molecular matrix of the downhole environment.
6. The environmental abnormality alarm system according to claim 1, characterized in that: The three-dimensional dynamic molecular matrix is a multi-dimensional data structure for storing downhole environmental information.
7. The environmental abnormality alarm system according to claim 1, characterized in that: Determining the dynamic interaction field of the downhole environment through the three-dimensional dynamic molecular matrix specifically includes: Jointly simulate multiple physical fields in the downhole environment to obtain the interaction effects of the physical fields in the downhole environment; The three-dimensional dynamic molecular matrix and the physical field interaction effect are coupled and simulated to obtain the dynamic interaction field of the downhole environment.
8. The environmental abnormality alarm system according to claim 1, characterized in that: The dynamic interaction field is a physical field used to characterize the multi-dimensional dynamic coupling effect of the complex underground environment.
9. The environmental abnormality alarm system according to claim 1, characterized in that: According to the underground environment abnormality monitoring model, abnormality monitoring is performed to obtain an abnormality data matrix specifically including: The underground environment abnormality monitoring model is used to monitor the abnormality of the underground environment in real time to obtain abnormality data of the underground environment; All abnormal points in the dynamic interaction field are determined by using abnormal data of the downhole environment, and the data of all abnormal points are processed to obtain an abnormal data matrix.
10. The environmental abnormality alarm system according to claim 1, characterized in that: Determining downhole risk assessment data based on the abnormal data matrix specifically includes: Identifying the root cause of the abnormality through the abnormality data matrix, and performing risk prediction based on the root cause of the abnormality to obtain risk prediction data; The risk diffusion path is marked according to the risk prediction data to obtain risk diffusion path data, and the risk assessment data is determined through the risk prediction data and the risk diffusion path data.