Intelligent gas unmanned inspection method and system based on internet of things

Abstract

This invention provides a smart gas unmanned inspection method and system based on the Internet of Things (IoT). The method is executed by a government safety supervision and management platform based on the IoT-based smart gas unmanned inspection system. It includes: acquiring regional data of the managed area; determining, based on the regional data and traffic data of the managed area, whether to designate the managed area as an area to be inspected; in response to designating the managed area as an area to be inspected, determining inspection parameters for the area to be inspected; the inspection parameters are related to at least one of pipeline monitoring equipment, inspection personnel, and unmanned inspection equipment; and sending the inspection parameters to the government safety supervision platform to control at least one of the pipeline monitoring equipment, inspection personnel, and unmanned inspection equipment to complete the inspection of the area to be inspected. Through the aforementioned method, inspections can be completed more effectively and promptly, making the inspection results more reliable and facilitating subsequent troubleshooting.

Description

Technical Field

[0001] This manual relates to the field of gas pipeline inspection, and in particular to a smart unmanned gas pipeline inspection method and system based on the Internet of Things. Background Technology

[0002] As a crucial component of urban infrastructure, the safe and stable operation of gas pipelines directly impacts all aspects of residents' lives and urban development. Regular inspections of gas pipelines to promptly identify and address potential safety hazards are key measures to ensure a safe gas supply. Traditional gas pipeline inspections primarily rely on manual labor, which makes it difficult to guarantee the comprehensiveness and accuracy of the inspections. Furthermore, the difficulty and danger of inspections increase significantly when facing complex environments.

[0003] Therefore, we hope to propose an IoT-based intelligent unmanned gas pipeline inspection method to better complete the inspection of gas pipelines. Summary of the Invention

[0004] The objectives of this invention include: avoiding the problems of insufficient comprehensiveness and accuracy that may exist in manual inspections, and enhancing the ability to cope with inspections in complex environments.

[0005] The invention includes an IoT-based intelligent unmanned gas inspection method. The method includes: acquiring regional data of a managed area from a gas company management platform within a government safety supervision object platform via a government safety supervision sensor network platform; the regional data including at least one of ground image information, macroscopic image information, air data, and environmental data; wherein the gas company management platform acquires the regional data from a gas inspection object platform via a gas company sensor network platform; based on the regional data and traffic data of the managed area, determining whether to identify the managed area as an area to be inspected; in response to identifying the managed area as the area to be inspected, determining inspection parameters for the area to be inspected; the inspection parameters being related to at least one of pipeline monitoring equipment, inspection personnel, and unmanned inspection equipment; sending the inspection parameters to the government safety supervision object platform, through which the government safety supervision object platform further controls at least one of the pipeline monitoring equipment, the inspection personnel, and the unmanned inspection equipment to complete the inspection of the area to be inspected.

[0006] The invention also includes an IoT-based intelligent unmanned gas inspection system, comprising a government safety supervision and management platform, a government safety supervision sensor network platform, a government safety supervision target platform, a gas company sensor network platform, and a gas inspection target platform; the gas inspection target platform includes unmanned inspection equipment; the government safety supervision target platform includes a gas company management platform; the government safety supervision and management platform is configured to: obtain regional data of the managed area from the gas company management platform within the government safety supervision target platform through the government safety supervision sensor network platform, the regional data including ground image information, macro image information, and air quality data. According to at least one of the following: gas company management platform, the gas company sensor network platform obtains the regional data from the gas inspection target platform; based on the regional data and the traffic data of the management area, it determines whether the management area is identified as an area to be inspected; in response to identifying the management area as an area to be inspected, it determines the inspection parameters of the area to be inspected; the inspection parameters are sent to the government safety supervision target platform, and the government safety supervision target platform further controls at least one of the pipeline monitoring equipment, the inspection personnel, and the unmanned inspection equipment to complete the inspection of the area to be inspected.

[0007] The aforementioned methods enable more targeted and timely inspections, resulting in more reliable inspection results and facilitating smooth troubleshooting. The IoT-based smart gas unmanned inspection system can form a closed-loop information operation between various functional platforms and operate in a coordinated and regular manner under the unified management of the gas company's management platform, realizing the informatization and intelligence of smart gas unmanned inspections. Attached Figure Description

[0008] This specification will be further described by way of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not limiting; in these embodiments, the same reference numerals denote the same structures, wherein:

[0009] Figure 1 This is a schematic diagram of the platform structure of an IoT-based smart gas unmanned inspection system according to some embodiments of this specification;

[0010] Figure 2 This is an exemplary flowchart of an IoT-based smart gas unmanned inspection method according to some embodiments of this specification;

[0011] Figure 3 This is a schematic diagram illustrating the determination of the area to be inspected according to some embodiments of this specification;

[0012] Figure 4 This is an exemplary flowchart illustrating the determination of inspection parameters according to some embodiments of this specification.

[0013] Figure labeling: 100 - IoT-based smart gas unmanned inspection system; 110 - Government safety supervision and management platform; 120 - Government safety supervision sensor network platform; 130 - Government safety supervision object platform; 131 - Gas company management platform; 140 - Gas company sensor network platform; 150 - Gas inspection object platform; 310 - Macroscopic image information; 320 - Traffic data; 330 - Dynamic characteristics; 340 - Ground image information; 350 - Environmental data; 360 - Air data; 370 - Risk characteristics; 380 - Facility information; 390 - Facility damage risk; 3100 - Area to be inspected. Detailed Implementation

[0014] To more clearly illustrate the technical solutions of the embodiments in this specification, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are merely some examples or embodiments of this specification. For those skilled in the art, these drawings can be applied to other similar scenarios without creative effort. Unless obvious from the context or otherwise specified, the same reference numerals in the drawings represent the same structures or operations.

[0015] It should be understood that the terms “system,” “device,” “unit,” and / or “module” used herein are one way to distinguish different components, elements, parts, sections, or assemblies at different levels. However, if other terms can achieve the same purpose, they may be replaced by other expressions.

[0016] Flowcharts are used in this specification to illustrate the operations performed by the system according to embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed in exact order. Instead, the steps can be processed in reverse order or simultaneously. Furthermore, other operations can be added to these processes, or one or more steps can be removed from them.

[0017] Figure 1 This is a schematic diagram of the platform structure of an IoT-based smart gas unmanned inspection system, as shown in some embodiments of this specification.

[0018] In some embodiments, such as Figure 1 As shown, the IoT-based smart gas unmanned inspection system 100 may include a government safety supervision and management platform 110, a government safety supervision sensor network platform 120, a government safety supervision object platform 130, a gas company sensor network platform 140, and a gas inspection object platform 150.

[0019] The Government Safety Supervision and Management Platform 110 refers to a comprehensive management platform for the government to process and supervise information.

[0020] In some embodiments, the government safety supervision and management platform 110 is configured to execute an IoT-based smart gas unmanned inspection method. For details of this method, please refer to the relevant description later in this specification.

[0021] In some embodiments, the government security supervision and management platform 110 may be configured on a processor and / or server used by the government, which may process data and / or information obtained from other platforms and execute program instructions based on such data, information and / or processing results to perform one or more functions described in this specification.

[0022] In some embodiments, the government security supervision and management platform 110 can interact with the government security supervision object platform 130 through the government security supervision sensor network platform 120.

[0023] The government security supervision sensor network platform 120 refers to the connection platform that enables interaction between the government security supervision management platform 110 and the government security supervision object platform 130, and is configured as a communication device and / or server.

[0024] In some embodiments, the government security supervision sensor network platform 120 can be configured as a communication network or gateway, etc., and can realize the functions of sensing and communication of perception information and sensing and communication of control information.

[0025] The government safety supervision platform 130 refers to a platform for generating government regulatory information and executing control information. In some embodiments, the government safety supervision platform 130 includes a gas company management platform 131.

[0026] In some embodiments, the government safety supervision object platform 130 interacts upward with the government safety supervision sensor network platform 120 and downward with the gas company sensor network platform 140.

[0027] Gas company management platform 131 refers to a comprehensive management platform for gas company information.

[0028] The gas company sensor network platform 140 refers to a platform that manages the sensor information of the gas company. In some embodiments, the gas company sensor network platform can be configured as a communication network or a gateway, etc.

[0029] In some embodiments, the gas company's sensor network platform 140 interacts with the government's safety supervision platform 130 and the gas inspection platform 150.

[0030] The gas inspection platform 150 refers to the functional platform for the gas company to generate sensing information and execute control information. In some embodiments, the gas inspection platform 150 includes unmanned inspection equipment.

[0031] Unmanned inspection equipment refers to inspection equipment that does not require human operation. In some embodiments, unmanned inspection equipment may include, but is not limited to, drones, unmanned vehicles, and their mounted environmental monitoring equipment, gas monitoring equipment, sensors, image acquisition equipment, and / or laser point cloud equipment.

[0032] In some embodiments of this specification, the IoT-based smart gas unmanned inspection system can form an information operation closed loop between various functional platforms and operate in a coordinated and regular manner under the unified management of the gas company's management platform, thereby realizing the informatization and intelligence of smart gas unmanned inspection.

[0033] In some embodiments, when implementing an IoT-based smart gas unmanned inspection method, the government safety supervision and management platform can obtain regional data of the managed area from the gas company management platform in the government safety supervision object platform through the government safety supervision sensor network platform; based on the regional data and traffic data of the managed area, determine whether to identify the managed area as an area to be inspected; in response to identifying the managed area as an area to be inspected, determine the inspection parameters of the area to be inspected; send the inspection parameters to the government safety supervision object platform, and further control at least one of pipeline monitoring equipment, inspection personnel, and unmanned inspection equipment through the government safety supervision object platform to complete the inspection of the area to be inspected.

[0034] Figure 2 This is an exemplary flowchart of an IoT-based smart gas unmanned inspection method according to some embodiments of this specification.

[0035] like Figure 2 As shown, process 200 includes the following steps. In some embodiments, process 200 may be executed by a government security regulatory management platform 110.

[0036] Step 210: Obtain the regional data of the management area.

[0037] The management area is the area defined by dividing the region where the gas pipeline network is located.

[0038] In some embodiments, the government security supervision and management platform can be divided into multiple management areas based on pre-set standards. For example, it can be divided according to the different management personnel.

[0039] Regional data is data that reflects regional information within a managed area. In some embodiments, regional data includes at least one of ground imagery information, macroscopic imagery information, air data, and environmental data.

[0040] Ground image information is image data that reflects the surface information of the managed area. For example, ground image information may include data representing surface undulations, etc. In some embodiments, ground image information may be represented by point cloud data and / or images, etc.

[0041] Macroscopic image information refers to image data that reflects the overall situation of the managed area. For example, macroscopic image information may include data reflecting the environment and human geography of the managed area.

[0042] Air data is data that reflects air conditions. For example, air data may include, but is not limited to, the composition and concentration of gases in the air.

[0043] Environmental data are data that reflect environmental conditions. For example, environmental data may include, but is not limited to, temperature and humidity.

[0044] In some embodiments, ground image information and macroscopic image information can be acquired by image acquisition devices installed in the gas inspection target platform, and air data and environmental data can be acquired by sensors installed in the gas inspection target platform, and the aforementioned data can be transmitted to the gas company management platform through the gas company's sensor network platform.

[0045] In some embodiments, the government safety supervision and management platform can obtain regional data of the managed area from the gas company management platform within the government safety supervision object platform through the government safety supervision sensor network platform. The gas company management platform can obtain regional data from the gas inspection object platform through the gas company sensor network platform.

[0046] Step 220: Based on the regional data and traffic data of the managed area, determine whether to designate the managed area as an area to be inspected.

[0047] Traffic data is data that reflects traffic conditions. For example, traffic data may include, but is not limited to, road traffic flow.

[0048] In some embodiments, the government's safety monitoring and management platform may obtain traffic data through external platforms, such as traffic monitoring centers or map service providers.

[0049] The area to be inspected refers to the management area that needs to be inspected.

[0050] In some embodiments, the government safety supervision and management platform can determine the gas leakage situation in the management area based on air data, determine the traffic flow in the management area based on traffic data, determine the surface undulation of the management area based on ground image information, determine the building density and road density based on macro image information, and determine the temperature and humidity based on environmental data; and determine whether to identify the management area as an area to be inspected based on at least one of the following: gas leakage situation, traffic flow, surface undulation data, building density, road density, temperature and humidity.

[0051] Gas leak information reflects the presence of a gas leak. If the percentage of gas contained in the air of a managed area exceeds a certain threshold, a gas leak is considered to exist in that area. This threshold can be determined based on prior experience.

[0052] Surface relief data reflects the elevation characteristics of a region and may include the elevation of at least one point within the managed area.

[0053] Building density is data reflecting the building footprint, which can be determined based on the percentage of building area in the total area of ​​the managed area.

[0054] Road density is data that reflects the density of road distribution and can be determined based on the length of roads per unit area in the managed region.

[0055] In some embodiments, determining whether to identify a managed area as an area to be inspected includes at least one stage of determination.

[0056] For example, a government safety supervision and management platform can make a first-stage judgment based on the gas leak situation in the managed area. If a gas leak is found in the managed area, the managed area is designated as an area to be inspected; if no gas leak is found, the second-stage judgment is initiated.

[0057] For example, the government safety supervision and management platform can conduct a second-stage judgment based on traffic flow, surface undulation data, building density, and road density of the managed area. The second-stage judgment includes whether at least one of the following conditions is met: traffic flow exceeding a flow threshold, surface undulation data variance exceeding an undulation threshold, building density exceeding a building density threshold, road density exceeding a road density threshold, temperature exceeding a temperature threshold, and humidity exceeding a humidity threshold. If the managed area meets more than N of the aforementioned conditions, it is designated as an area to be inspected. Here, N is an integer greater than 1 and not greater than 6, which can be determined according to actual needs. The traffic flow threshold, undulation threshold, building density threshold, road density threshold, temperature threshold, and humidity threshold can be determined based on prior experience and / or actual needs.

[0058] In some embodiments, the government safety supervision and management platform can also determine the dynamic characteristics of the management area based on macroscopic image information and traffic data; determine the risk characteristics of gas pipelines in the management area based on ground image information, environmental data, air data, and dynamic characteristics; determine the facility damage risk based on the risk characteristics and facility information of gas-related facilities; and determine the management area as an area to be inspected in response to the facility damage risk meeting preset conditions. For more detailed specifications, please refer to this specification. Figure 3 And its related descriptions.

[0059] Step 230: In response to determining the management area as the area to be inspected, determine the inspection parameters for the area to be inspected.

[0060] Inspection parameters are parameters used to guide the inspection process. In some embodiments, inspection parameters are associated with at least one of pipeline monitoring equipment, inspection personnel, and unmanned inspection equipment.

[0061] In some embodiments, in response to identifying a managed area as an area to be inspected, the government safety supervision and management platform can determine inspection parameters based on preset rules. These preset rules may include: when the managed area is identified as an area to be inspected in the first stage of the assessment, determining at least one of the second data acquisition parameters of the unmanned inspection device and the dispatch instructions corresponding to the inspection personnel; and when the managed area is identified as an area to be inspected in the second stage of the assessment, determining at least one monitoring device to be activated and its monitoring frequency.

[0062] The second acquisition parameter is used to instruct the unmanned inspection equipment to hover and monitor above the gas pipeline to acquire air data. The second acquisition parameter may include, but is not limited to, at least one of path and hovering time. The path may be determined based on the distribution of gas pipelines in the area to be inspected, and the hovering time may be determined based on prior experience. In some embodiments, the hovering time is also related to the number of downstream users of the gas pipeline; the more downstream users, the longer the hovering time.

[0063] A dispatch instruction is a command used to instruct inspectors to monitor gas pipelines. In some embodiments, the government safety supervision and management platform can determine whether there is a gas leak in the managed area based on air data obtained by unmanned inspection equipment based on a second collection parameter. In response to the presence of gas leaks at one or more locations, the government safety supervision and management platform can generate a dispatch instruction based on the coordinates of the leak locations and send it to the terminal corresponding to the inspector to arrange for the appropriate inspector to conduct an inspection.

[0064] "Monitoring equipment to be activated" refers to pipeline monitoring equipment that needs to be turned on. In some embodiments, the government safety supervision and management platform can determine the monitoring equipment to be activated based on the value of N used in the second-stage judgment and the level of the pipeline monitoring equipment. For example, the government safety supervision and management platform can activate pipeline monitoring equipment sequentially from highest to lowest level. The larger the value of N, the more stringent the second-stage judgment, and the smaller the number of pipeline monitoring equipment activated at this time.

[0065] The level of pipeline monitoring equipment is positively correlated with the importance of the data it acquires. The importance of data can be determined using frequent term algorithms based on indicators related to historical incidents. For example, if a large number of historical incidents are related to a particular indicator, then that indicator is considered important.

[0066] Monitoring frequency refers to the frequency of data collection from pipeline monitoring equipment or gas pipelines. Monitoring frequency is negatively correlated with the number of monitoring devices to be activated.

[0067] In some embodiments, the government safety supervision and management platform can also determine the inspection priority of the area to be inspected based on the surface maintenance plan and traffic planning information of the management area; and determine the inspection parameters based on the inspection priority, the management resource data of the management area, and historical maintenance data. For more detailed instructions, please refer to this specification. Figure 4 And its related descriptions.

[0068] Step 240: Send the inspection parameters to the government's safety supervision platform to control at least one of the pipeline monitoring equipment, inspection personnel, and unmanned inspection equipment to complete the inspection of the area to be inspected.

[0069] In some embodiments, the government safety supervision and management platform can send inspection parameters to the government safety supervision object platform, and further control at least one of the pipeline monitoring equipment, inspection personnel and unmanned inspection equipment through the government safety supervision object platform to complete the inspection of the area to be inspected.

[0070] For example, in response to the management area being identified as an area to be inspected during the first stage of judgment, the government safety supervision and management platform can send the second collection parameters to the unmanned inspection equipment, control the unmanned inspection equipment to hover and monitor along the gas pipeline according to the second collection parameters; and determine whether there is a gas leak location based on the data obtained by the unmanned inspection equipment. If there is a gas leak location, a dispatch instruction is sent to the terminal corresponding to the inspection personnel to instruct the inspection personnel to conduct manual inspection.

[0071] In response to the management area being identified as an area to be inspected during the second phase of assessment, the government safety supervision and management platform can send the monitoring equipment to be activated and the monitoring frequency to the pipeline monitoring equipment, so as to control the relevant pipeline monitoring equipment to acquire data from the gas pipeline according to the monitoring frequency. At this time, the government safety supervision and management platform can also send the monitoring equipment to be activated and the monitoring frequency to the terminal corresponding to the inspection personnel to synchronize relevant information.

[0072] In some embodiments of this specification, the government safety supervision and management platform can determine whether the managed area needs to be inspected based on regional data, and when inspection is required, it can determine appropriate inspection parameters to complete the inspection of the area to be inspected. This allows for more targeted and timely inspections, making the inspection results more reliable and facilitating smooth troubleshooting in the future.

[0073] Figure 3 This is a schematic diagram illustrating the determination of the area to be inspected according to some embodiments of this specification.

[0074] In some embodiments, such as Figure 3 As shown, the government safety supervision and management platform can determine the dynamic characteristics 330 of the management area based on macroscopic image information 310 and traffic data 320; determine the risk characteristics 370 of gas pipelines in the management area based on ground image information 340, environmental data 350, air data 360, and dynamic characteristics 330; determine the facility damage risk 390 based on the risk characteristics 370 and facility information 380 of gas auxiliary facilities; and determine the management area as an area to be inspected 3100 when the facility damage risk 390 meets the preset conditions.

[0075] For more information on ground imagery, macroscopic imagery, air data, environmental data, managed areas, and areas awaiting inspection, please refer to [link to relevant documentation]. Figure 2 The corresponding description.

[0076] Dynamic characteristics refer to relevant parameters that measure surface pressure. Dynamic characteristics can be used to reflect the impact of construction activities (scale, noise levels), traffic, and pedestrian flow on surface pressure.

[0077] In some embodiments, the government safety supervision and management platform determines dynamic characteristics based on macroscopic image information and traffic data through various methods. For example, the government safety supervision and management platform can determine dynamic characteristics based on the positive correlation between macroscopic image information, traffic data, and dynamic characteristics using a preset formula. For example, the preset formula is shown in formula (1) below:

[0078] (1)

[0079] in, Indicates dynamic characteristics, This represents the building density in macroscopic image information. This indicates the road density in macroscopic image information. This represents the average traffic flow on the road. , , It is a parameter of order of magnitude. , , It can be based on experience presets or by system default settings.

[0080] In some embodiments, the government safety supervision and management platform can determine dynamic characteristics based on macroscopic image information, traffic data, noise information and vibration information in the management area.

[0081] Noise information refers to information related to the noise characteristics of a managed area. For example, noise information may include the noise frequencies of multiple noise sources.

[0082] Vibration information refers to information related to the vibration characteristics of a managed area. For example, vibration information may include the vibration frequencies of multiple vibrations.

[0083] In some embodiments, dynamic characteristics are positively correlated with macroscopic image information, traffic data, noise information, and vibration information in the management area. The government safety supervision and management platform can determine dynamic characteristics based on macroscopic image information, traffic data, noise information, and vibration information in the management area using a preset formula. For example, the preset formula is shown in formula (2) below:

[0084] (2)

[0085] in, This represents the average noise frequency of multiple noise sources. This represents the average vibration frequency of multiple vibrations. , It is a parameter of order of magnitude. , It can be based on experience presets or by system default settings.

[0086] The resonance caused by sound waves and the energy they carry can affect the condition of the Earth's surface, causing vibrations, etc.

[0087] In some embodiments of this specification, the influence of noise and vibration on dynamic characteristics is considered, which helps to determine dynamic characteristics more accurately, thereby ensuring the accuracy of subsequent data such as risk characteristics and improving the efficiency of determining the area to be inspected.

[0088] Risk characteristics refer to data related to the risks associated with gas pipelines in a managed area. In some embodiments, risk characteristics include risk type and risk intensity.

[0089] Risk types include active risks and passive risks. Active risks refer to risks related to the gas pipeline itself, such as risks caused by pipeline aging and disrepair; passive risks refer to risks caused by external pressure, interference, etc.

[0090] Risk intensity is data that characterizes the likelihood of a gas pipeline posing a risk.

[0091] In some embodiments, the government safety supervision and management platform can determine the risk characteristics of gas pipelines in the management area based on ground image information, environmental data, air data, and dynamic features.

[0092] For example, a government safety supervision and management platform can determine whether the temperature in environmental data is greater than a temperature threshold, whether the humidity is greater than a humidity threshold, or whether the dynamic characteristics are greater than a dynamic threshold. If any of the above three conditions are met, the risk type can be determined to be a passive risk; otherwise, it is an active risk.

[0093] For example, a government safety supervision and management platform can determine the intensity of risk based on the judgment results of at least one assessment item regarding ground image information, environmental data, air data, and dynamic characteristics. These assessment items include: a) judging from ground image information that the variance of surface undulation is greater than an undulation threshold; b) judging from environmental data that the temperature is greater than a temperature threshold; c) judging from environmental data that the humidity is greater than a humidity threshold; d) judging from air data that there is a gas leak in the managed area; e) judging from traffic data that the average traffic flow on roads in the managed area is greater than a traffic flow threshold; and f) judging from dynamic characteristics that the dynamic characteristics are greater than a dynamic threshold.

[0094] For example, the government's safety supervision and management platform can determine the risk intensity based on the initial risk level and the aforementioned judgment results using a preset formula. The preset formula is shown in formula (3) below:

[0095] (3)

[0096] in, Indicates the intensity of risk. Indicates the initial risk level. This indicates the number of items in the evaluation that meet the criteria. Among them, It can be preset by staff based on experience or set by system default.

[0097] Among them, the temperature threshold, humidity threshold, dynamic threshold, fluctuation threshold, and flow threshold are preset critical values ​​for temperature, humidity, dynamic characteristics, variance of fluctuation, and average flow rate of the road, respectively. The temperature threshold, humidity threshold, dynamic threshold, fluctuation threshold, and flow threshold can be preset by staff based on experience or set by system default.

[0098] In some embodiments, the government safety supervision and management platform can determine the estimated dynamic characteristics of the management area within a preset future time period based on environmental data and dynamic characteristics using a first prediction model; determine the estimated air data of the management area within a preset future time period based on air data and environmental data using a second prediction model; and determine the risk characteristics of the management area based on ground image information, estimated dynamic characteristics, and estimated air data using a third prediction model.

[0099] A preset future time period refers to a predetermined period of time in the future. For example, 0.5 hours in the future, 1 hour in the future, etc.

[0100] Predicted dynamic characteristics refer to relevant parameters that measure surface pressure within a predetermined future time period.

[0101] Predicted air quality data refers to data related to air characteristics within a predetermined future time period.

[0102] In some embodiments, the first prediction model can be a machine learning model. For example, a neural network (NN) model or other trained machine learning model.

[0103] In some embodiments, the input to the first prediction model includes environmental data and dynamic features, and the output includes the estimated dynamic features of the managed area within a preset future time period.

[0104] In some embodiments, the first prediction model can be obtained in various ways, such as by training with a large number of first training samples bearing a first label. A set of first training samples includes sample environment data and sample dynamic features from a historical first time period, and the corresponding first label includes sample dynamic features from a historical second time period. The historical first time period is earlier than the historical second time period.

[0105] For example, the government safety supervision and management platform can obtain historical environmental data and historical dynamic characteristics of the historical management area in the first historical period as the first training sample, and obtain the dynamic characteristics of the historical management area in the second historical period as the first label corresponding to the first training sample.

[0106] The government safety supervision and management platform can input the first training sample into the initial first prediction model and obtain its output; based on the first label and the output of the initial first prediction model, a first loss function is constructed; based on the first loss function, the parameters of the initial first prediction model are iteratively updated; until the iteration termination condition is met, training is complete, and a trained first prediction model is obtained. The iteration termination condition may include the convergence of the first loss function or the number of iterations reaching a threshold.

[0107] In some embodiments, the second prediction model can be a machine learning model. For example, a neural network (NN) model or other trained machine learning model.

[0108] In some embodiments, the inputs of the second prediction model include air data and environmental data, and the output includes estimated air data for the managed area within a preset future time period.

[0109] In some embodiments, the second prediction model can be obtained in various ways, such as by training with a large number of second training samples with second labels. A set of second training samples includes sample air data and sample environment data from a historical first time period, and the corresponding second labels include sample air data from a historical second time period.

[0110] The process of obtaining the second training sample and the second label is similar to that of obtaining the first training sample and the first label. The training process of the second prediction model is similar to that of the first prediction model. Please refer to the relevant explanations above.

[0111] In some embodiments, the inputs to the first prediction model further include surface maintenance planning and traffic planning information for the management area; the inputs to the second prediction model further include pipeline monitoring parameters of pipeline monitoring equipment in the management area.

[0112] Surface maintenance planning refers to information related to changes to the surface within a managed area. For example, it may involve addressing sinkholes or other surface maintenance or repairs in a specific area of ​​the managed area.

[0113] Traffic planning information refers to information related to the control of roads within a managed area. For example, it may include situations where a road in the managed area needs maintenance and is temporarily closed, or other situations requiring traffic control.

[0114] Pipeline monitoring parameters refer to the types of pipeline information that need to be obtained through monitoring. In some embodiments, pipeline monitoring parameters can be determined based on the type of pipeline monitoring equipment. For example, when the pipeline monitoring equipment is a temperature sensor, the pipeline monitoring parameter is temperature; when the pipeline monitoring equipment is a humidity sensor, the pipeline monitoring parameter is humidity.

[0115] In some embodiments, when the input to the first prediction model further includes surface maintenance planning and traffic planning information of the management area, the first training samples also include sample surface maintenance planning and sample traffic planning information; when the input to the second prediction model further includes pipeline monitoring parameters of pipeline monitoring equipment in the management area, the second training samples also include sample pipeline monitoring parameters.

[0116] In some embodiments of this specification, the input of the first prediction model takes into account some municipal construction information, such as surface maintenance planning and traffic planning information, which can take into account the pressure changes of buried gas pipelines due to macroscopic changes; the input of the second prediction model takes into account pipeline monitoring parameters, which can rely on more data when predicting whether gas leaks will occur in the future, making the final result more accurate.

[0117] In some embodiments, the third prediction model can be a machine learning model. For example, a neural network (NN) model or other trained machine learning model.

[0118] In some embodiments, the inputs to the third prediction model include ground image information, estimated dynamic features, and estimated air data, and the output includes risk characteristics of the managed area.

[0119] In some embodiments, the third prediction model can be obtained through various methods. For example, it can be obtained by training with a large number of third training samples with third labels. A set of third training samples includes sample ground image information, sample dynamic features, and sample air data from a historical second time period, and the corresponding third labels include sample risk features from a historical third time period. The historical second time period is earlier than the historical third time period.

[0120] For example, the government safety supervision and management platform can obtain historical ground image information, historical dynamic features, and historical air data of the historical management area in the second historical period as a set of third training samples, and determine the historical risk characteristics of the historical management area in the third historical period as the corresponding third label.

[0121] The government's safety supervision and management platform can statistically analyze accidents that occurred in the historical management area during the third historical time period, determine the type of historical accident based on the type of accident occurrence, and use the ratio of the time elapsed between the accident occurrence and the current time to a preset time threshold as the historical risk intensity; thereby determining the historical risk characteristics. The preset time threshold can be represented by the average time interval between the occurrence of this type of accident in historical data. If no accident occurs during the third time period, the third tag is marked as 0.

[0122] The training process of the third prediction model is similar to that of the first prediction model, as can be found in the relevant explanation above.

[0123] In some embodiments of this specification, considering the inherent uncertainty of risk characteristics, machine learning models are used to predict future risk situations, enabling advance control and providing preventative measures against potential risks to reduce losses.

[0124] Gas ancillary facilities refer to various auxiliary equipment and structures related to gas transmission, distribution, and use. For example, gas ancillary facilities include pressure regulating equipment and metering devices.

[0125] Facility information refers to relevant information that characterizes the features / attributes of gas-related facilities. For example, facility information may include, but is not limited to, the type of gas-related facility and its geographical coordinates.

[0126] Facility damage risk is data that characterizes the likelihood of damage to gas-related facilities.

[0127] In some embodiments, the government safety supervision and management platform can determine the risk of facility damage through various methods based on risk characteristics and facility information of gas-related facilities. For example, if the risk type is an active risk, the government safety supervision and management platform can determine the risk intensity as a risk of facility damage; if the risk type is a passive risk, the government safety supervision and management platform can determine the risk of facility damage based on the correlation between the risk of facility damage and the risk intensity.

[0128] For example, the government safety supervision and management platform can determine the facility damage risk based on the positive correlation between risk intensity and facility damage risk using a preset formula. The preset formula is shown in formula (4) below:

[0129] (4)

[0130] in, Indicates the risk of facility damage. Indicates the intensity of risk. This indicates the risk coefficient. The range is between 0 and 1. It can be preset by staff based on experience, or, It can be represented by the ratio of the number of times gas-related facilities malfunction in passive risk to the total number of times passive risk occurred in historical data.

[0131] In some embodiments, the government safety supervision and management platform can determine the risk of facility damage based on risk characteristics and critical values ​​of gas-related facilities.

[0132] Facility criticality value is data that characterizes the criticality of gas-related facilities. The higher the facility criticality value, the more critical the gas-related facility. In some embodiments, facility criticality value is positively correlated with the number of downstream branches of the gas-related facility and the timeliness of maintenance.

[0133] The number of downstream branches refers to the number of pipelines branching off from the current gas ancillary facilities towards end users or other gas pipelines.

[0134] Maintenance timeliness is data that characterizes the speed at which maintenance is carried out on gas-related facilities. Maintenance timeliness is negatively correlated with the average time from fault detection to maintenance completion.

[0135] In some embodiments, if the risk type is an active risk, the government safety supervision and management platform can determine the risk intensity as the facility damage risk; if the risk type is a passive risk, the facility damage risk is positively correlated with the facility critical value and the risk intensity.

[0136] In some embodiments of this specification, when the risk type is passive risk, it is also necessary to consider the critical value of the gas auxiliary facilities. The more important the facility, the higher the risk of damage to the corresponding facility should be, so that it can receive more attention, so that the area to be inspected can be more accurate, and damage can be detected in time when the area to be inspected is inspected for subsequent processing.

[0137] Preset conditions refer to the pre-defined criteria used to determine whether a managed area is a region to be inspected. In some embodiments, preset conditions are related to a risk threshold. A preset condition could be that the risk of damage to facilities in the managed area exceeds a risk threshold.

[0138] The risk threshold refers to the maximum pre-defined risk of facility damage.

[0139] In some embodiments, the risk threshold is related to gas delivery data for the managed area.

[0140] Gas delivery data refers to data related to gas pipelines within a managed area. In some embodiments, gas delivery data includes pipeline class, end-user type, etc.

[0141] The pipeline class is determined by the number of end users connected to the pipeline. The more end users, the higher the pipeline class.

[0142] End-user type refers to the type of user associated with gas usage. For example, end-user types include commercial users, government users, and individual users.

[0143] In some embodiments, the risk threshold is related to gas delivery data for the managed area. For example, the risk threshold is positively correlated with pipeline grade. As another example, the risk threshold for commercial and government users is higher than that for individual users.

[0144] In some embodiments of this specification, the higher the pipeline grade, the more important the pipeline is, and the more strictly the risks need to be controlled. Furthermore, considering the types of end users, commercial users and government users, who have a wider impact, require more stringent risk control compared to individual users. Strict risk control is conducive to timely response to changes in the pipeline and reducing losses.

[0145] In some embodiments, the government safety supervision and management platform can compare the risk of facility damage with a risk threshold. If the risk of facility damage is greater than the risk threshold, it is determined that the preset conditions are met and the management area is identified as an area to be inspected.

[0146] In some embodiments of this specification, by calculating the dynamic and risk characteristics of the management area, the accuracy of the identified facility damage risks can be improved, thereby identifying the areas to be inspected. This is beneficial for dispatching staff to repair areas with risks and for investigating risks caused by facility failures, which can reduce the waste of resources in investigating other failures not caused by facilities.

[0147] Figure 4 This is an exemplary flowchart illustrating the determination of inspection parameters according to some embodiments of this specification.

[0148] In some embodiments, in response to identifying a management area as an area to be inspected, the inspection parameters for the area to be inspected are determined, including: obtaining surface maintenance planning, traffic planning information, management resource data of the area to be inspected, and historical maintenance data of gas pipelines in the area to be inspected from the government safety supervision and management platform; determining the inspection priority of the area to be inspected based on the surface maintenance planning and traffic planning information; and determining the inspection parameters based on the inspection priority, management resource data, and historical maintenance data.

[0149] In some embodiments, such as Figure 4 As shown, process 400 includes the following steps. Process 400 can be executed by the government's security supervision and management platform.

[0150] Step 410: Obtain surface maintenance planning information, traffic planning information, management resource data of the area to be inspected, and historical maintenance data of gas pipelines in the area to be inspected from the government safety supervision and management platform.

[0151] Management resource data refers to data related to the resource characteristics of the area to be inspected. For example, management resource data may include the number of maintenance personnel, the number of standby resources, etc. The number of standby resources includes the number of standby facilities that are auxiliary facilities for gas supply.

[0152] In some embodiments, the government safety supervision and management platform can obtain surface maintenance planning, traffic planning information and management resource data of the area to be inspected in real time via the network, and store them in the government safety supervision and management platform for use when needed.

[0153] Historical maintenance data refers to relevant data on the maintenance performed on gas pipelines in the area to be inspected during a historical period. For example, historical maintenance data may include the time of maintenance and the type of incident that occurred during maintenance.

[0154] Accident type refers to the type of malfunction that occurs in the gas pipeline. For example, accident types include gas pipeline rupture, valve damage, etc.

[0155] In some embodiments, after a gas pipeline malfunctions, the maintenance data generated during the repair is uploaded to the government's safety supervision and management platform for storage, so that it can be retrieved from the government's safety supervision and management platform when needed.

[0156] Step 420: Based on surface maintenance planning and traffic planning information, determine the inspection priority of the area to be inspected.

[0157] For information on surface maintenance planning and transportation planning, please refer to [link / reference]. Figure 3 The corresponding description.

[0158] Inspection priority is a hierarchical standard used to guide the order of inspections and resource allocation for multiple areas to be inspected. Inspection priority is related to the importance of the area to be inspected; the more important the area, the higher the inspection priority.

[0159] In some embodiments, the government safety supervision and management platform can determine the inspection priority of the area to be inspected through various methods based on surface maintenance planning and traffic planning information. For example, the government safety supervision and management platform can determine whether the area to be inspected is in both surface maintenance planning and traffic planning information. If it is in both, the inspection priority is the highest; if it is only in surface maintenance planning, the inspection priority is the second highest; if it is only in traffic planning information, the inspection priority is the third highest; and if it is not in either, the inspection priority is the lowest.

[0160] In some embodiments, inspection priority is also related to facility critical values ​​for gas ancillary facilities within the area to be inspected. More information on gas ancillary facilities and facility critical values ​​can be found at [link to relevant documentation]. Figure 3 The corresponding description.

[0161] In some embodiments, the inspection priority is positively correlated with the facility criticality value of gas ancillary facilities in the area to be inspected.

[0162] In some embodiments of this specification, the importance of gas auxiliary facilities is considered when setting inspection priorities, which can increase the priority of areas where more critical pipelines are located, so that resources can be allocated effectively.

[0163] Step 430: Determine inspection parameters based on inspection priority, management resource data, and historical maintenance data.

[0164] In some embodiments, the government safety supervision and management platform can determine inspection parameters based on inspection priorities, management resource data, and historical maintenance data.

[0165] For example, for areas with high inspection priority, if management resources are limited, inspection parameters include using unmanned inspection equipment; if management resources are abundant, inspection parameters include dispatching inspection personnel. For areas with low inspection priority, if management resources are limited, inspection parameters include using unmanned inspection equipment; if management resources are abundant, inspection parameters include using pipeline monitoring equipment.

[0166] In some embodiments, the government safety supervision and management platform can determine the probability of an accident based on candidate inspection parameters, inspection priorities, management resource data, and historical maintenance data through a probability prediction model; and determine the inspection parameters based on the accident probability.

[0167] Candidate inspection parameters refer to parameters that are considered as alternative inspection parameters.

[0168] In some embodiments, the government safety supervision and management platform can obtain candidate inspection parameters based on historical inspection parameters. For example, the platform can count the frequency of each historical inspection parameter in historical data and select a preset number of historical inspection parameters with the highest frequency as candidate inspection parameters. The preset number is determined according to actual needs.

[0169] Accident probability refers to the probability of an accident occurring in the area to be inspected.

[0170] A probabilistic prediction model is a model used to determine the probability of an accident. In some embodiments, the probabilistic prediction model is a machine learning model. For example, a neural network (NN) model or other trained machine learning model.

[0171] In some embodiments, the inputs to the probabilistic prediction model include candidate inspection parameters, inspection priorities, management resource data, and historical maintenance data for the area to be inspected, and the output includes the probability of an accident.

[0172] In some embodiments, the probabilistic prediction model can be obtained by training an initial probabilistic prediction model based on a large number of fourth training samples with fourth labels. A set of fourth training samples includes sample inspection parameters, sample inspection priorities for sample areas to be inspected, sample management resource data, and sample maintenance data of gas pipelines in the sample areas to be inspected. The corresponding fourth labels include the sample accident probability corresponding to the sample areas to be inspected.

[0173] For example, the government safety supervision and management platform can obtain historical inspection parameters, historical inspection priorities of historical areas to be inspected, historical management resource data, and historical maintenance data of gas pipelines in historical areas to be inspected as the fourth training sample, and use the probability of subsequent actual accidents as the fourth label corresponding to the fourth training sample.

[0174] The probability of a subsequent actual accident refers to the probability of an accident occurring within the execution time of the historical inspection parameters. Execution time refers to the time required to complete the inspection using the inspection parameters. In some embodiments, the government safety supervision and management platform can statistically analyze the frequency of subsequent actual accidents within the execution time of a certain historical inspection parameter in historical data, calculate the ratio of this frequency to the execution time, normalize this ratio, and determine the result as the probability of a subsequent actual accident. Normalization refers to the process of converting the ratio of frequency to execution time into a value between 0 and 1.

[0175] The training process of the probabilistic prediction model is similar to that of the first prediction model, as described above.

[0176] In some embodiments, the government security supervision and management platform can split the sample dataset according to a preset ratio to obtain a training set, a validation set, and a test set; and train the initial probability prediction model based on the training set, validation set, and test set to obtain the probability prediction model.

[0177] The preset ratio refers to the pre-defined proportions of the training set, validation set, and test set. For example, the preset ratio could be an 8:1:1 ratio of the number of samples in the training set, validation set, and test set.

[0178] In some embodiments, the preset ratio can be pre-set by the government security supervision and management platform based on default settings or prior experience.

[0179] In some embodiments, the government security supervision and management platform can split the sample dataset according to a preset ratio to obtain a training set, a validation set, and a test set.

[0180] The splitting method can include sampling statistics, which may include, but is not limited to, random sampling and stratified sampling. In some embodiments, the gas company management platform can also split the sample dataset in other ways.

[0181] In some embodiments, the training set is a dataset used to tune the learning parameters of the model during training. Learning parameters include weights, biases, and other parameters. The validation set is a dataset used to tune the hyperparameters of the model during training. Hyperparameters include the number of network layers, the number of network nodes, the number of iterations, and the learning rate, etc. The test set is a dataset used to evaluate the performance of the final model.

[0182] The training set, validation set, and test set obtained by splitting the data do not have any data overlap, that is, there is no duplicate data between any two of the training set, validation set, and test set.

[0183] In some embodiments, the government security supervision and management platform can train an initial probability prediction model based on a training set, a validation set, and a test set to obtain a prediction model.

[0184] The training process includes multiple stages. One stage of training includes: inputting the training set into the initial probability prediction model; constructing a loss function based on the fourth label and the output of the initial probability prediction model; updating the parameters of the initial probability prediction model through multiple iterations based on the loss function; during the aforementioned training process, validating the trained initial probability prediction model using a validation set based on a pre-set validation frequency; adjusting the initial learning rate or the learning rate during the training process of the initial probability prediction model after this round of training based on the validation results; when preset conditions are triggered, testing the obtained prediction model using a test set to evaluate the performance of the obtained prediction model; executing multiple stages of training, and using the prediction model with the best performance as the trained prediction model.

[0185] There are several strategies for adjusting the learning rate, such as learning rate decay, learning rate warm-up, cyclic learning rate adjustment, and adaptive learning rate adjustment algorithms.

[0186] The preset conditions may include one or more of the following: the number of iterations reaches a threshold, the loss function converges, or the value of the loss function is less than a preset threshold.

[0187] The above example of model training using training, validation, and test sets is merely an illustration. Other procedures well-known to those skilled in the art can also be used when training models based on training, validation, and test sets.

[0188] In some embodiments, the sample dataset can be randomly divided into multiple sets of sample data. Each set of sample data can be divided into a training set, a validation set, and a test set according to the aforementioned preset ratio. The government safety supervision and management platform can train the initial probability prediction model based on the multiple sets of divided sample data.

[0189] In some embodiments, the learning rate corresponding to a set of sample data is related to the number of sample maintenance data in that set of sample data; the larger the number of sample maintenance data, the larger the learning rate corresponding to that set of sample data. Here, a large number of sample maintenance data refers to a large number of maintenance records in a set of sample data.

[0190] In some embodiments of this specification, training based on training sets, validation sets, and test sets can yield a more suitable probabilistic prediction model, which is beneficial for improving the robustness of the probabilistic prediction model and preventing overfitting. The more historical maintenance data there is, the higher the uncertainty of pipeline accidents in the area to be inspected, and the more important the area to be inspected. By increasing the learning rate of the sample data corresponding to the area to be inspected, the accuracy and efficiency of the probabilistic prediction model in making predictions can be improved.

[0191] In some embodiments, the input to the probabilistic prediction model also includes pipeline monitoring parameters of the pipeline monitoring equipment in the area to be inspected.

[0192] For more information on pipeline monitoring parameters, please refer to [link / reference]. Figure 3 The corresponding description.

[0193] When the input to the probabilistic prediction model also includes pipeline monitoring parameters, the sample dataset also includes sample pipeline monitoring parameters.

[0194] In some embodiments of this specification, the input of the probability prediction model also considers pipeline monitoring parameters. Its essence lies in taking into account the specific conditions of the pipeline, which can fit the actual condition of the pipeline. By taking into account the loss of the pipeline by the gas inside the pipeline, the determined accident probability is more comprehensive and accurate.

[0195] In some embodiments of this specification, by assessing the probability of accidents in the area to be inspected, inspection parameters that meet the requirements of the area to be inspected can be selected from the perspective of accident prevention, thereby reducing the probability of accidents.

[0196] In some embodiments of this specification, the importance of the area to be inspected is assessed based on surface maintenance planning and traffic planning information to obtain inspection priorities, which can ensure the accuracy of inspection priorities; at the same time, inspection priorities are conducive to resource allocation and finding a more suitable inspection plan for the area to be inspected.

[0197] The basic concepts have been described above. Obviously, for those skilled in the art, the detailed disclosure above is merely illustrative and does not constitute a limitation of this specification. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements, and corrections to this specification. Such modifications, improvements, and corrections are suggested in this specification and therefore remain within the spirit and scope of the exemplary embodiments described herein.

[0198] Furthermore, this specification uses specific terms to describe embodiments thereof. For example, "an embodiment," "one embodiment," and / or "some embodiments" refer to a particular feature, structure, or characteristic associated with at least one embodiment of this specification. Therefore, it should be emphasized and noted that references to "an embodiment," "one embodiment," or "an alternative embodiment" in different locations throughout this specification do not necessarily refer to the same embodiment. Moreover, certain features, structures, or characteristics in one or more embodiments of this specification can be appropriately combined.

[0199] Furthermore, unless expressly stated in the claims, the order of processing elements and sequences, the use of numbers and letters, or other names described in this specification are not intended to limit the order of the processes and methods described herein. Although various examples have been discussed in the foregoing disclosure of some embodiments of the invention that are currently considered useful, it should be understood that such details are for illustrative purposes only, and the appended claims are not limited to the disclosed embodiments; rather, the claims are intended to cover all modifications and equivalent combinations that conform to the spirit and scope of the embodiments described herein. For example, while the system components described above can be implemented using hardware devices, they can also be implemented solely using software solutions, such as installing the described system on existing servers or mobile devices.

[0200] Similarly, it should be noted that, in order to simplify the description disclosed herein and thus aid in the understanding of one or more embodiments of the invention, the foregoing description of embodiments in this specification may sometimes combine multiple features into a single embodiment, drawing, or description thereof. However, this method of disclosure does not imply that the subject matter of this specification requires more features than those mentioned in the claims. In fact, the embodiments contain fewer features than all the features of a single embodiment disclosed above.

[0201] Finally, it should be understood that the embodiments described in this specification are merely illustrative of the principles of the embodiments described herein. Other variations may also fall within the scope of this specification. Therefore, alternative configurations of the embodiments described herein are intended to be illustrative rather than limiting, and should be considered consistent with the teachings of this specification. Accordingly, the embodiments described herein are not limited to those explicitly introduced and described herein.

Claims

1. A smart gas unmanned inspection method based on the Internet of Things, characterized in that, The method is executed by the government safety supervision and management platform of the IoT-based smart gas unmanned inspection system, and the method includes: The gas company obtains regional data of its managed area from the gas company management platform within the government's safety supervision object platform through the government's safety supervision sensor network platform. The regional data includes at least one of ground image information, macro image information, air data, and environmental data. The gas company management platform obtains the regional data from the gas inspection object platform through the gas company sensor network platform. Based on the regional data and the traffic data of the managed area, determine whether to identify the managed area as an area to be inspected, including: Based on the macroscopic image information and the traffic data, the dynamic characteristics of the management area are determined; Based on the ground image information, the environmental data, the air data, and the dynamic characteristics, the risk characteristics of gas pipelines in the management area are determined; Based on the aforementioned risk characteristics and facility information of gas-related facilities, the risk of facility damage is determined; In response to the facility damage risk meeting preset conditions, the management area is identified as the area to be inspected, and the preset conditions are related to a risk threshold. In response to identifying the management area as the area to be inspected, the inspection parameters of the area to be inspected are determined, including: Obtain surface maintenance planning, traffic planning information, management resource data of the area to be inspected, and historical maintenance data of gas pipelines in the area to be inspected from the government safety supervision and management platform. Based on the surface maintenance plan and the traffic planning information, the inspection priority of the area to be inspected is determined; The inspection parameters are determined based on the inspection priority, the management resource data, and the historical maintenance data; the inspection parameters are related to at least one of pipeline monitoring equipment, inspection personnel, and unmanned inspection equipment. The inspection parameters are sent to the government's safety supervision platform to control at least one of the pipeline monitoring equipment, the inspection personnel, and the unmanned inspection equipment to complete the inspection of the area to be inspected.

2. The method according to claim 1, characterized in that, The process of determining the risk characteristics of gas pipelines in the management area based on the ground image information, the environmental data, the air data, and the dynamic characteristics includes: Based on the environmental data and the dynamic characteristics, the estimated dynamic characteristics of the management area within a preset future time period are determined by the first prediction model. Based on the air data and the environmental data, the estimated air data of the management area within the preset future time period is determined by the second prediction model; Based on the ground image information, the estimated dynamic characteristics of the management area, and the estimated air quality data, the risk characteristics of the management area are determined using a third prediction model; and... The first prediction model, the second prediction model, and the third prediction model are machine learning models.

3. The method according to claim 1, characterized in that, The process of determining the inspection parameters based on the inspection priority, the management resource data, and the historical maintenance data includes: Based on candidate inspection parameters, inspection priority, management resource data, and historical maintenance data, the probability of an accident is determined by a probability prediction model, which is a machine learning model. The inspection parameters are determined based on the accident probability.

4. A smart unmanned gas inspection system based on the Internet of Things, characterized in that, This includes the government safety supervision and management platform, the government safety supervision sensor network platform, the government safety supervision object platform, the gas company sensor network platform, and the gas inspection object platform; The gas inspection target platform includes unmanned inspection equipment; the government safety supervision target platform includes a gas company management platform. The government security supervision and management platform is configured as follows: The gas company obtains regional data of its managed area from the gas company management platform within the government's safety supervision object platform through the government's safety supervision sensor network platform. The regional data includes at least one of ground image information, macro image information, air data, and environmental data. The gas company management platform obtains the regional data from the gas inspection object platform through the gas company sensor network platform. Based on the regional data and the traffic data of the managed area, determine whether to identify the managed area as an area to be inspected, including: Based on the macroscopic image information and the traffic data, the dynamic characteristics of the management area are determined; Based on the ground image information, the environmental data, the air data, and the dynamic characteristics, the risk characteristics of gas pipelines in the management area are determined; Based on the aforementioned risk characteristics and facility information of gas-related facilities, the risk of facility damage is determined; In response to the facility damage risk meeting preset conditions, the management area is identified as the area to be inspected, and the preset conditions are related to a risk threshold. In response to identifying the management area as an area to be inspected, the inspection parameters for the area to be inspected are determined, including: Obtain surface maintenance planning, traffic planning information, management resource data of the area to be inspected, and historical maintenance data of gas pipelines in the area to be inspected from the government safety supervision and management platform. Based on the surface maintenance plan and the traffic planning information, the inspection priority of the area to be inspected is determined; The inspection parameters are determined based on the inspection priority, the management resource data, and the historical maintenance data. The inspection parameters are sent to the government's safety supervision platform to control at least one of the pipeline monitoring equipment, inspection personnel, and unmanned inspection equipment to complete the inspection of the area to be inspected.

5. The system according to claim 4, characterized in that, The government security supervision and management platform is further configured as follows: Based on the environmental data and the dynamic characteristics, the estimated dynamic characteristics of the management area within a preset future time period are determined by the first prediction model. Based on the air data and the environmental data, the estimated air data of the management area within the preset future time period is determined by the second prediction model; Based on the ground image information, the estimated dynamic characteristics of the management area, and the estimated air data, the risk characteristics of the management area are determined by a third prediction model. as well as, The first prediction model, the second prediction model, and the third prediction model are machine learning models.

6. The system according to claim 4, characterized in that, The government security supervision and management platform is further configured as follows: Based on candidate inspection parameters, inspection priority, management resource data, and historical maintenance data, the probability of an accident is determined by a probability prediction model, which is a machine learning model. The inspection parameters are determined based on the accident probability.

Images