Gas safety monitoring system and method based on laser technology and big data

Abstract

The present invention relates to the field of gas safety monitoring technology, and in particular to a gas safety monitoring system and method based on laser technology and big data. The method comprises: determining a gas safety monitoring area, and dividing the gas safety monitoring area into a number of sensitivity monitoring areas according to the diffusion path of the target gas and the gas source center; setting a number of monitoring points in the gas safety monitoring area according to the sensitivity monitoring areas, and performing position distribution on the number of monitoring points; fitting the monitoring point sub-data output by the monitoring points according to historical prevention and control information to obtain gas monitoring information; simulating a gas safety monitoring scenario, and inputting the gas monitoring information into a gas safety detection model, and outputting gas safety detection results. Through the present invention, big data is used to optimize the capabilities of the monitoring and early warning system. By combining laser technology with big data analysis, this technical solution improves the effectiveness of the gas monitoring system in predicting potential leaks and responding in a timely manner.

Description

Technical Field

[0001] The present invention relates to the field of gas safety monitoring technology, and in particular to a gas safety monitoring system and method based on laser technology and big data. Background Art

[0002] In the field of modern industrial and urban safety, gas leakage monitoring and prevention is a key safety measure, especially in the chemical, oil and gas and other industries that handle flammable and explosive gases. The main purpose of the gas safety monitoring system is to detect harmful gas leaks in a timely manner and prevent fires, explosions and other related safety accidents.

[0003] However, existing technologies still face significant limitations and challenges in practical applications. For example, many existing gas monitoring systems often lack the ability to effectively utilize big data to optimize monitoring and early warning systems. These issues limit the effectiveness of gas monitoring systems in predicting potential leaks and responding promptly, thus affecting overall safety management effectiveness.

[0004] The information disclosed in this background technology section is only intended to deepen the understanding of the overall background technology of the present disclosure and should not be regarded as an admission or any form of suggestion that the information constitutes the prior art known to those skilled in the art. Summary of the Invention

[0005] The present invention provides a gas safety monitoring system and method based on laser technology and big data, which can effectively solve the problems in the background technology.

[0006] In order to achieve the above object, the technical solution adopted by the present invention is:

[0007] A gas safety monitoring method based on laser technology and big data, the method comprising:

[0008] Determine a gas safety monitoring area, and divide the gas safety monitoring area into several sensitivity monitoring areas according to the diffusion path and gas source center of the target gas;

[0009] Setting a plurality of monitoring points in the gas safety monitoring area according to the sensitivity monitoring area, and performing position distribution on the plurality of monitoring points to obtain monitoring point distribution information;

[0010] Obtaining historical prevention and control information corresponding to the monitoring point through the monitoring point distribution information, and fitting the monitoring point sub-data output by the monitoring point according to the historical prevention and control information to obtain gas monitoring information;

[0011] A gas safety detection model is established to simulate a gas safety monitoring scenario, and the gas monitoring information is input into the gas safety detection model to output the gas safety detection results.

[0012] Furthermore, the gas safety monitoring area is divided into several sensitivity monitoring areas according to the diffusion path and gas source center of the target gas, including:

[0013] The sensitivity monitoring area includes a high sensitivity area and a low sensitivity area;

[0014] wherein a plurality of laser light sources are used in the high-sensitivity region and each light source is configured to monitor the gas in the high-sensitivity region in real time by selecting a laser wavelength that matches the strong absorption characteristics of the target gas molecules;

[0015] A tunable laser light source is used in the low-sensitivity area to cover the absorption characteristic lines of multiple target gases, and the gas in the low-sensitivity area is monitored in real time by adjusting the wavelength of the laser.

[0016] Furthermore, the multiple laser light sources in the high-sensitivity area use continuous wave lasers, and the tunable laser light source in the low-sensitivity area uses pulsed lasers, and the pulse repetition frequency is set accordingly.

[0017] Furthermore, obtaining historical prevention and control information corresponding to the monitoring points through the monitoring point distribution information includes:

[0018] Collect and store historical prevention and control information, and pre-process the historical prevention and control information;

[0019] Classify the historical prevention and control information according to the sensitivity monitoring area, and each classification result corresponds to the sensitivity monitoring area one by one;

[0020] In each of the sensitivity monitoring areas, historical prevention and control information that matches the monitoring point distribution information is selected as a trust reference, and a trust value is assigned to each monitoring point in the sensitivity monitoring area according to the classification result;

[0021] The contribution value of each sensitivity monitoring area is obtained through the trust degree assignment.

[0022] Furthermore, deep learning is performed on the pre-processed historical prevention and control information, and the distribution of monitoring points is adjusted based on the deep learning results, including:

[0023] Establishing a gas safety monitoring database for storing and managing the collected historical prevention and control information;

[0024] The pre-processed historical prevention and control information is classified for the first time according to the monitoring scenario, and the results of the first classification are clustered according to the similarity of the monitoring point distribution information to obtain a second classification result;

[0025] Based on the test point distribution information and the second classification results, the historical prevention and control information related to each monitoring point is deeply learned, and the qualified trust degree of the monitoring point is analyzed and calculated through the monitoring results corresponding to the information of each monitoring point;

[0026] Each monitoring point is adjusted based on the qualified confidence level.

[0027] Furthermore, each monitoring point is adjusted based on the qualified confidence, including:

[0028] Determining whether the trustworthiness of the monitoring point information meets the qualified trustworthiness, and if so, retaining the monitoring position of the current monitoring point;

[0029] If not, the monitoring position of the current monitoring point is deleted, and a new monitoring point is selected according to the distribution of the monitoring point distribution information until the selected monitoring point meets the qualified trust level.

[0030] Furthermore, a gas safety detection model is established, including:

[0031] Acquire monitoring scene information, and establish a simulated gas safety monitoring scene based on the monitoring scene information;

[0032] The gas safety detection model accesses the gas safety monitoring database, and calls historical prevention and control information in the gas safety monitoring database that matches the monitoring scenario information according to the first classification, and performs deep learning on the called historical prevention and control information to obtain gas safety detection standards that meet the monitoring scenario;

[0033] The gas monitoring information is input into the gas safety detection model, and the risk level of the gas monitoring information is evaluated according to the gas safety monitoring standard, and a gas safety detection result is output according to the risk level.

[0034] Furthermore, reselecting monitoring points according to the distribution of the monitoring point distribution information includes:

[0035] Based on the gas safety monitoring database, establishing a monitoring point distribution grid within the gas safety monitoring area;

[0036] Entering the monitoring point distribution information into the monitoring point distribution collection and distribution grid to obtain corresponding absolute collection and distribution information;

[0037] Relative collection and dispersion information is set according to the first classification and the second classification results, and the relative collection and dispersion information is fitted with the absolute collection and dispersion information, and the monitoring points are reselected according to the collection and dispersion fitting results.

[0038] A gas safety monitoring system based on laser technology and big data, comprising:

[0039] A monitoring area division module determines a gas safety monitoring area and divides the gas safety monitoring area into several sensitivity monitoring areas according to the diffusion path and gas source center of the target gas;

[0040] A monitoring point distribution module is configured to set a number of monitoring points in the gas safety monitoring area according to the sensitivity monitoring area, and to perform position distribution on the monitoring points to obtain monitoring point distribution information;

[0041] A monitoring information acquisition module, which acquires historical prevention and control information corresponding to the monitoring point through the monitoring point distribution information, and fits the monitoring point sub-data output by the monitoring point according to the historical prevention and control information to obtain gas monitoring information;

[0042] The safety detection result module establishes a gas safety detection model, simulates a gas safety monitoring scenario, inputs the gas monitoring information into the gas safety detection model, and outputs the gas safety detection results.

[0043] Furthermore, the monitoring information acquisition module includes:

[0044] An information preprocessing unit collects and stores historical prevention and control information and preprocesses the historical prevention and control information;

[0045] A regional classification corresponding unit, which classifies the historical prevention and control information according to the sensitivity monitoring area, and each classification result corresponds to the sensitivity monitoring area one by one;

[0046] A trust value assignment unit selects, within each of the sensitivity monitoring areas, historical prevention and control information that matches the monitoring point distribution information as a trust reference, and assigns a trust value to each monitoring point within the sensitivity monitoring area according to the classification result;

[0047] A contribution value acquisition unit is configured to obtain the contribution value of each of the sensitivity monitoring areas through the trust degree assignment.

[0048] The technical solution of the present invention can achieve the following technical effects:

[0049] This technology effectively addresses the limitations and challenges of existing gas safety monitoring systems in practical applications, especially the ability to effectively utilize big data to optimize monitoring and early warning systems. By combining laser technology with big data analysis, this technical solution improves the effectiveness of gas monitoring systems in predicting potential leaks and responding promptly. First, the solution makes monitoring more targeted and systematic by accurately dividing the monitoring area and setting up multiple sensitivity monitoring areas. Second, by utilizing big data analysis of historical prevention and control information and monitoring point data, the understanding of gas behavior patterns is enhanced, improving prediction accuracy.

[0050] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0052] Figure 1 This is a flow chart of a gas safety monitoring method based on laser technology and big data;

[0053] Figure 2 A schematic diagram of the process for dividing several sensitive monitoring areas;

[0054] Figure 3 A flowchart for obtaining historical prevention and control information corresponding to monitoring points;

[0055] Figure 4 This is a structural diagram of the gas safety monitoring system based on laser technology and big data. DETAILED DESCRIPTION

[0056] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0057] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this invention pertains. The terms used in this specification are for the purpose of describing specific embodiments only and are not intended to limit the invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0058] Example 1

[0059] like Figure 1 As shown, this application provides a gas safety monitoring method based on laser technology and big data, the method comprising:

[0060] S10: Determine the gas safety monitoring area and divide the gas safety monitoring area into several sensitivity monitoring areas according to the diffusion path and gas source center of the target gas;

[0061] S20: setting a number of monitoring points in the gas safety monitoring area according to the sensitivity monitoring area, and performing position distribution on the number of monitoring points to obtain monitoring point distribution information;

[0062] S30: Obtain historical prevention and control information corresponding to the monitoring point through the monitoring point distribution information, and fit the monitoring point sub-data output by the monitoring point according to the historical prevention and control information to obtain gas monitoring information;

[0063] S40: Establish a gas safety detection model, simulate a gas safety monitoring scenario, input gas monitoring information into the gas safety detection model, and output gas safety detection results.

[0064] Specifically, first, based on the industrial facilities or storage locations where gas may be present, the gas safety monitoring area that needs to be monitored is determined, and based on the determined gas diffusion path and gas source center, the gas safety monitoring area is divided into different sensitivity monitoring areas. The division of each monitoring area is based on the potential risk and impact range of gas leakage. An appropriate number of monitoring points are deployed in each sensitivity monitoring area to ensure that key areas can be covered and gas leaks can be detected in real time. The specific location distribution of monitoring points can be optimized according to wind direction, building layout, and staff activity areas to enhance monitoring effectiveness. Current gas concentration data is collected through established monitoring points and compared and analyzed with historical prevention and control information stored in the database. Big data analysis techniques such as time series analysis and cluster analysis are used to fit the monitoring point sub-data to obtain accurate gas monitoring information. A gas safety detection model is constructed. This model integrates laser technology and big data analysis results to simulate actual monitoring scenarios. Based on historical prevention and control information, evaluation criteria are generated to assess possible risks. These results can also be obtained through feedback from historical monitoring information, including potential leak point locations, predicted leak concentrations, and recommended emergency response measures.

[0065] The technical solution of the present invention effectively addresses the limitations and challenges of existing gas safety monitoring systems in practical applications, especially the problem of effectively utilizing big data to optimize the ability of monitoring and early warning systems. By combining laser technology with big data analysis, this technical solution improves the effectiveness of gas monitoring systems in predicting potential leaks and responding promptly.

[0066] Further, if Figure 2 As shown in the figure, the gas safety monitoring area is divided into several sensitivity monitoring areas according to the diffusion path of the target gas and the gas source center, including:

[0067] S11: Sensitivity monitoring areas include high sensitivity areas and low sensitivity areas;

[0068] S12: wherein a plurality of laser light sources are used in the high-sensitivity area, and each light source selects a laser wavelength that matches the strong absorption characteristics of the target gas molecules to monitor the gas in the high-sensitivity area in real time;

[0069] S13: A tunable laser light source is used in the low-sensitivity area to cover the absorption characteristic lines of multiple target gases. The wavelength of the laser is adjusted to monitor the gas in the low-sensitivity area in real time.

[0070] As a preferred embodiment of the above, within the determined gas safety monitoring area, the monitoring area is divided into different sensitivity monitoring areas according to the possible diffusion path and gas source center of the target gas. In this embodiment, these areas are divided into high-sensitivity areas and low-sensitivity areas according to the sensitivity of identifying gases that threaten safety. The high-sensitivity area generally includes the direct surrounding areas of the gas storage and processing facilities, while the low-sensitivity area may be an area farther away or with better ventilation conditions, where the leakage impact is smaller. Multiple laser light sources are deployed in the high-sensitivity area, and each laser light source selects a laser wavelength that matches the strong absorption characteristics of the target gas molecules, that is, the target gas is identified one-to-one to improve the identification accuracy. For the low-sensitivity area, a tunable laser light source is used for gas monitoring. This type of laser light source can cover the absorption characteristic lines of multiple target gases and can adjust the laser wavelength according to real-time monitoring needs. This allows the system to flexibly respond to various types of gas leaks and realize the ability of one device to monitor multiple gases, thereby reducing equipment costs and operation and maintenance complexity.

[0071] Furthermore, the multiple laser light sources in the high-sensitivity area use continuous wave lasers, and the tunable laser light source in the low-sensitivity area uses pulsed lasers, and the pulse repetition frequency is set accordingly.

[0072] On the basis of the above embodiment, multiple continuous wave laser light sources are deployed in high-sensitivity areas. These light sources are specifically used for intensive monitoring of high-risk environments such as the core operating areas or storage areas of chemical plants. The continuous wave laser light source can provide stable and continuous laser output, making monitoring more continuous and accurate. At the same time, a laser light source that matches the strong absorption characteristic wavelength of the target gas molecules is selected to ensure that trace gas leaks can be accurately detected even in complex environments. This method can capture small changes in gas concentration in real time, quickly trigger alarms and initiate countermeasures; for low-sensitivity areas, pulsed laser light sources are selected. Pulsed laser light sources can cover a larger monitoring area and are suitable for monitoring low-risk or remote areas. These light sources can effectively reduce the energy consumption of the equipment and reduce the impact on the environment by emitting short high-energy laser pulses. The appropriate pulse repetition frequency is set to adapt to the environmental conditions and gas detection requirements of the monitoring area, ensuring that the pulsed laser can be quickly switched and adjusted on the absorption characteristic lines of different gases, thereby flexibly responding to the detection of multiple gases.

[0073] Further, if Figure 3 As shown, the historical prevention and control information corresponding to the monitoring points is obtained through the monitoring point distribution information, including:

[0074] S31: Collect and store historical prevention and control information, and pre-process the historical prevention and control information;

[0075] S32: Classify historical prevention and control information according to the sensitivity monitoring area, and each classification result corresponds to a sensitivity monitoring area one by one;

[0076] S33: In each sensitivity monitoring area, historical prevention and control information that matches the distribution information of monitoring points is selected as a trust reference, and trust values ​​are assigned to each monitoring point in the sensitivity monitoring area based on the classification results;

[0077] S34: Obtain the contribution value of each sensitivity monitoring area through trust assignment.

[0078] In this embodiment, the system needs to collect all historical prevention and control information related to gas safety, which may include past gas monitoring data, accident records, implemented safety measures and their effects, etc., and may also include monitoring point control information implemented for some specific monitoring scenarios; these data are collected and stored in a database for further analysis and reference. At the same time, these historical data are preprocessed to clean the noise and irrelevant information in the data to ensure the accuracy and reliability of subsequent analysis. The preprocessed historical prevention and control information is classified according to the sensitivity monitoring area. This classification process takes into account the specific environmental factors and historical gas leakage conditions of each area to ensure that each classification result can accurately correspond to the corresponding sensitivity monitoring area. In each sensitivity monitoring area, the historical prevention and control information that best matches it is selected as a trust reference based on the monitoring point distribution information. Based on these trust references, a trust value is assigned to each monitoring point. The trust value is assigned based on the relevance and accuracy of the historical data, and the contribution and reliability of each monitoring point to the current monitoring strategy are evaluated. For example, monitoring points that have detected leaks multiple times in history will gain a higher degree of trust; by comprehensively analyzing the trust of monitoring points in each sensitivity monitoring area, the comprehensive contribution value of each area is calculated. This contribution value reflects the importance and reliability of the area in the overall gas safety monitoring system, providing a basis for formulating targeted safety strategies and resource allocation.

[0079] Furthermore, deep learning is performed on the pre-processed historical prevention and control information, and the distribution of monitoring points is adjusted based on the deep learning results, including:

[0080] Establish a gas safety monitoring database to store and manage collected historical prevention and control information;

[0081] The pre-processed historical prevention and control information is classified for the first time according to the monitoring scenario, and the results of the first classification are clustered according to the similarity of the monitoring point distribution information to obtain the second classification results;

[0082] Based on the test point distribution information and the second classification results, deep learning is performed on the historical prevention and control information related to each monitoring point. The qualified trust level of the monitoring point is analyzed and calculated through the monitoring results corresponding to the information of each monitoring point.

[0083] Adjustments are made to each monitoring point based on the qualified confidence level.

[0084] As a preferred embodiment of the above, by fine-tuning and learning the historical prevention and control information, dynamic adjustment of the monitoring points is achieved to improve the accuracy and efficiency of the gas monitoring system. The specific implementation steps are: first, a gas safety monitoring database is constructed to store and manage all collected historical prevention and control information, including but not limited to past gas leakage data, historical records of monitoring points, previous emergency response effects and related environmental parameter data. The establishment of the database ensures the systematicness and queryability of the data, and also provides systematic data support for deep learning of big data. The pre-processed historical prevention and control information in the database is first classified according to different monitoring scenarios. For example, it can be classified according to factors such as gas type, leakage level, seasonal changes, etc., and then the results of the first classification are classified according to the monitoring point. The similarity of the distribution information is clustered to obtain a more detailed second classification result. This step helps identify which monitoring points show similar monitoring results under similar conditions through cluster analysis, and performs deep learning analysis based on the distribution information of each monitoring point and its corresponding second classification result. Through deep learning, the system can learn from historical prevention and control information and predict the performance and reliability of each monitoring point, and then analyze and calculate the qualified trust of each point, and make necessary adjustments to the monitoring points based on the calculated qualified trust. The adjustments may include changing the location of certain points, adding new monitoring points, or removing poorly performing points. The goal of this step is to optimize the entire monitoring network, ensure that each monitoring point can play its role to the greatest extent in its location, and improve the efficiency and response speed of the entire gas monitoring system.

[0085] Furthermore, adjustments are made to each monitoring point based on the qualified trust level, including:

[0086] Determine whether the trust level of the monitoring point information meets the qualified trust level. If so, retain the monitoring position of the current monitoring point;

[0087] If it does not meet the requirements, the monitoring location of the current monitoring point will be deleted, and a new monitoring point will be selected based on the distribution of the monitoring point information until the selected monitoring point meets the qualified trust level.

[0088] On the basis of the above implementation mode, the system evaluates the historical performance of each monitoring point according to the deep learning results obtained in the above steps, and calculates the trust of each point. The trust is determined based on the accuracy, reliability and consistency of the monitoring data of the monitoring point in the past. The trust reflects the expected performance of the monitoring point in future operations. The system compares the trust of each monitoring point with the preset qualified trust threshold. If the trust of the monitoring point reaches or exceeds this threshold, the monitoring point is considered qualified and can continue to be monitored at the current location. This ensures that each point in the monitoring network can be effectively Perform its monitoring tasks; for those monitoring points whose trust does not reach the qualified threshold, the system will perform an adjustment procedure. First, the current monitoring points are deleted. Next, the monitoring points are reselected based on the distribution of the monitoring point information. The distribution analysis takes into account the geographical characteristics, environmental conditions and historical leakage data of the target area to ensure that the newly selected monitoring points can more effectively cover high-risk areas. The newly selected monitoring points are evaluated for trust again. If the trust of the new point still does not reach the threshold, the adjustment process is repeated and a new location is selected. This process continues until the trust of all monitoring points reaches the required qualified standard.

[0089] Furthermore, the establishment of a gas safety detection model includes:

[0090] Obtain monitoring scene information and establish a simulated gas safety monitoring scene based on the monitoring scene information;

[0091] The gas safety detection model is connected to the gas safety monitoring database and, based on the first classification, calls historical prevention and control information in the gas safety monitoring database that matches the monitoring scenario information. It also conducts deep learning on the called historical prevention and control information to obtain gas safety detection standards that meet the monitoring scenario.

[0092] The gas monitoring information is input into the gas safety detection model, and the risk level of the gas monitoring information is evaluated according to the gas safety monitoring standard, and the gas safety detection results are output according to the risk level.

[0093] In this embodiment, the system needs to obtain detailed information about the current monitoring scenario, including but not limited to gas type, environmental conditions, historical leakage events and related facility layout. This information helps to establish an accurate simulated gas safety monitoring scenario to ensure that the gas safety detection model can reflect the characteristics of the actual monitoring environment. This model will simulate different gas leakage and diffusion situations, as well as the effects of different safety measures. The model is established based on physical and chemical laws of gas behavior, as well as data collected in previous experiments and actual operations. The gas safety detection model is connected to the gas safety monitoring database and calls historical prevention and control information that matches the current monitoring scenario, which includes data collected under similar environments and conditions. These historical data are deep-learned and processed, and advanced machine learning algorithms are used to analyze data patterns to obtain gas safety detection standards applicable to the current monitoring scenario. The real-time monitored gas monitoring information is input into the gas safety detection model. The model will evaluate the risk level of this information based on the safety detection standards previously learned. According to the risk level, the system will output gas safety detection results, which may include alarms, safety notifications, and specific measures that need to be taken.

[0094] Furthermore, the monitoring points are reselected based on the distribution of monitoring point information, including:

[0095] Based on the gas safety monitoring database, a monitoring point distribution grid is established within the gas safety monitoring area;

[0096] Enter the monitoring point distribution information into the monitoring point distribution collection and distribution grid to obtain the corresponding absolute collection and distribution information;

[0097] The relative collection and dispersion information is set according to the results of the first and second classifications, and the relative collection and dispersion information is fitted with the absolute collection and dispersion information. The monitoring points are reselected based on the collection and dispersion fitting results.

[0098] As a preferred embodiment of the above, a monitoring point distribution collection and distribution grid is established in the gas safety monitoring area. The grid is a virtual, structured spatial grid system used to map and analyze the spatial distribution of monitoring points. The establishment of the grid is based on geographic information system technology, which can accurately represent the position of each monitoring point in the physical space. The existing monitoring point distribution information is entered into the monitoring point distribution collection and distribution grid. By systematically managing the spatial positions of the monitoring points, the corresponding position of each monitoring point in the collection and distribution grid is obtained. This step can be achieved by importing the geographic coordinate data of the monitoring points to ensure that the location information of each monitoring point is accurately recorded and analyzed. According to the previous data analysis results, especially the first Based on the second classification results, relative distribution information is set for each monitoring point. The relative distribution information reflects the importance and functionality of the monitoring point relative to other points. For example, some points may be more critical in monitoring specific types of gases or under specific environmental conditions. This information will be used to optimize the distribution of monitoring points to more effectively cover the monitoring area. The entered absolute distribution information will be fitted with the set relative distribution information. The monitoring points will be evaluated and reselected based on this distribution fitting result. During the fitting process, the system will evaluate the deviation between the actual distribution effect of each monitoring point and the ideal distribution model, so as to determine which monitoring points need to be adjusted or whether new points need to be added to improve the coverage efficiency and monitoring quality of the monitoring network.

[0099] Example 2

[0100] Based on the same inventive concept as the gas safety monitoring method based on laser technology and big data in the aforementioned embodiment, the present invention also provides a gas safety monitoring system based on laser technology and big data, such as Figure 4 As shown, the system includes:

[0101] The monitoring area division module determines the gas safety monitoring area and divides the gas safety monitoring area into several sensitive monitoring areas according to the diffusion path and gas source center of the target gas;

[0102] The monitoring point distribution module sets a number of monitoring points in the gas safety monitoring area according to the sensitivity monitoring area, and distributes the positions of the monitoring points to obtain the monitoring point distribution information;

[0103] The monitoring information acquisition module obtains the historical prevention and control information corresponding to the monitoring point through the monitoring point distribution information, and fits the monitoring point sub-data output by the monitoring point according to the historical prevention and control information to obtain gas monitoring information;

[0104] The safety detection result module establishes a gas safety detection model, simulates the gas safety monitoring scenario, inputs the gas monitoring information into the gas safety detection model, and outputs the gas safety detection results.

[0105] The above-mentioned adjustment system in the present invention can effectively implement a gas safety monitoring method based on laser technology and big data. The technical effects that can be achieved are as described in the above-mentioned embodiments and will not be repeated here.

[0106] The monitoring information acquisition module includes:

[0107] Information preprocessing unit, which collects and stores historical prevention and control information and preprocesses the historical prevention and control information;

[0108] The regional classification corresponding unit classifies historical prevention and control information according to the sensitivity monitoring area, and each classification result corresponds to a sensitivity monitoring area one by one;

[0109] The trust assignment unit selects historical prevention and control information that matches the distribution information of monitoring points in each sensitivity monitoring area as a trust reference, and assigns trust to each monitoring point in the sensitivity monitoring area based on the classification results;

[0110] The contribution value acquisition unit obtains the contribution value of each sensitivity monitoring area through trust assignment.

[0111] Similarly, the above-mentioned optimization schemes for the system can also respectively achieve the corresponding optimization effects of the method in Example 1, which will not be repeated here.

[0112] Although the present application has been described with reference to specific features and embodiments thereof, it is apparent that various modifications and combinations may be made thereto without departing from the spirit and scope of the present application. Accordingly, this specification and drawings are merely illustrative of the present application as defined herein and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, those skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, the present application is intended to include such modifications and variations as fall within the scope of the present application and its equivalents.

Claims

1. A gas safety monitoring method based on laser technology and big data, characterized in that: The method comprises: Determine the gas safety monitoring area and divide it into several sensitivity monitoring areas according to the diffusion path and gas source center of the target gas, including: The sensitivity monitoring area includes a high sensitivity area and a low sensitivity area; wherein a plurality of laser light sources are used in the high-sensitivity region and each light source is configured to monitor the gas in the high-sensitivity region in real time by selecting a laser wavelength that matches the strong absorption characteristics of the target gas molecules; A tunable laser light source is used in the low-sensitivity area to cover the absorption characteristic lines of multiple target gases, and the gas in the low-sensitivity area is monitored in real time by adjusting the wavelength of the laser; The multiple laser light sources in the high-sensitivity area use continuous wave lasers, and the tunable laser light source in the low-sensitivity area uses pulsed lasers, and the pulse repetition frequency is set accordingly; Setting a plurality of monitoring points in the gas safety monitoring area according to the sensitivity monitoring area, and performing position distribution on the plurality of monitoring points to obtain monitoring point distribution information; Obtaining historical prevention and control information corresponding to the monitoring point through the monitoring point distribution information, and fitting the monitoring point sub-data output by the monitoring point according to the historical prevention and control information to obtain gas monitoring information, including: collecting and storing historical prevention and control information, preprocessing the historical prevention and control information, performing deep learning on the preprocessed historical prevention and control information, and adjusting the distribution of the monitoring points through the deep learning results, including: Establishing a gas safety monitoring database for storing and managing the collected historical prevention and control information; The pre-processed historical prevention and control information is classified for the first time according to the monitoring scenario, and the results of the first classification are clustered according to the similarity of the monitoring point distribution information to obtain a second classification result; Based on the monitoring point distribution information and the second classification results, the historical prevention and control information related to each monitoring point is deeply learned, and the qualified trust degree of the monitoring point is analyzed and calculated through the monitoring results corresponding to the information of each monitoring point; Adjusting each monitoring point based on the qualified confidence level; A gas safety detection model is established to simulate a gas safety monitoring scenario, and the gas monitoring information is input into the gas safety detection model to output the gas safety detection results.

2. The gas safety monitoring method based on laser technology and big data according to claim 1 is characterized in that the historical prevention and control information corresponding to the monitoring point is obtained through the monitoring point distribution information, including: Classify the historical prevention and control information according to the sensitivity monitoring area, and each classification result corresponds to the sensitivity monitoring area one by one; In each of the sensitivity monitoring areas, historical prevention and control information that matches the monitoring point distribution information is selected as a trust reference, and a trust value is assigned to each monitoring point in the sensitivity monitoring area according to the classification result; The contribution value of each sensitivity monitoring area is obtained through the trust degree assignment.

3. The gas safety monitoring method based on laser technology and big data according to claim 1, characterized in that: Adjustments are made to each monitoring point based on the qualified confidence level, including: Determining whether the trustworthiness of the monitoring point information meets the qualified trustworthiness, and if so, retaining the monitoring position of the current monitoring point; If not, the monitoring position of the current monitoring point is deleted, and a new monitoring point is selected according to the distribution of the monitoring point distribution information until the selected monitoring point meets the qualified trust level.

4. The gas safety monitoring method based on laser technology and big data according to claim 1, characterized in that: Establish a gas safety detection model, including: Acquire monitoring scene information, and establish a simulated gas safety monitoring scene based on the monitoring scene information; The gas safety detection model accesses the gas safety monitoring database, and calls historical prevention and control information in the gas safety monitoring database that matches the monitoring scenario information according to the first classification, and performs deep learning on the called historical prevention and control information to obtain gas safety detection standards that meet the monitoring scenario; The gas monitoring information is input into the gas safety detection model, and the risk level of the gas monitoring information is evaluated according to the gas safety monitoring standard, and a gas safety detection result is output according to the risk level.

5. The gas safety monitoring method based on laser technology and big data according to claim 3 is characterized in that: Reselecting monitoring points according to the distribution of the monitoring point information includes: Based on the gas safety monitoring database, establishing a monitoring point distribution grid within the gas safety monitoring area; Entering the monitoring point distribution information into the monitoring point distribution collection and distribution grid to obtain corresponding absolute collection and distribution information; Relative collection and dispersion information is set according to the first classification and the second classification results, and the relative collection and dispersion information is fitted with the absolute collection and dispersion information, and the monitoring points are reselected according to the collection and dispersion fitting results.

6. A gas safety monitoring system based on laser technology and big data, using the gas safety monitoring method based on laser technology and big data as claimed in claim 1, characterized in that: The system comprises: A monitoring area division module determines a gas safety monitoring area and divides the gas safety monitoring area into several sensitivity monitoring areas according to the diffusion path and gas source center of the target gas; A monitoring point distribution module is configured to set a number of monitoring points in the gas safety monitoring area according to the sensitivity monitoring area, and to perform position distribution on the monitoring points to obtain monitoring point distribution information; A monitoring information acquisition module, which acquires historical prevention and control information corresponding to the monitoring point through the monitoring point distribution information, and fits the monitoring point sub-data output by the monitoring point according to the historical prevention and control information to obtain gas monitoring information; The safety detection result module establishes a gas safety detection model, simulates a gas safety monitoring scenario, inputs the gas monitoring information into the gas safety detection model, and outputs the gas safety detection results.

7. The gas safety monitoring system based on laser technology and big data according to claim 6 is characterized in that: The monitoring information acquisition module includes: An information preprocessing unit collects and stores historical prevention and control information and preprocesses the historical prevention and control information; A regional classification corresponding unit, which classifies the historical prevention and control information according to the sensitivity monitoring area, and each classification result corresponds to the sensitivity monitoring area one by one; A trust value assignment unit selects, within each of the sensitivity monitoring areas, historical prevention and control information that matches the monitoring point distribution information as a trust reference, and assigns a trust value to each monitoring point within the sensitivity monitoring area according to the classification result; A contribution value acquisition unit is configured to obtain the contribution value of each of the sensitivity monitoring areas through the trust degree assignment.

Images