Intelligent gas unmanned inspection method and system based on Internet of Things

Abstract

The invention provides an intelligent gas unmanned inspection method and system based on the Internet of Things, the method is executed by a government safety supervision management platform of the intelligent gas unmanned inspection system based on the Internet of Things, and the method comprises the following steps: obtaining area data of a management area; based on the area data and the traffic data of the management area, whether the management area is determined as a to-be-inspected area is judged; in response to determining the management area as a to-be-inspected area, determining inspection parameters of the to-be-inspected area; the inspection parameters are related to at least one of pipeline monitoring equipment, detection personnel and unmanned inspection equipment; and sending the inspection parameters to a government safety supervision object platform to control at least one of pipeline monitoring equipment, detection personnel and unmanned inspection equipment so as to complete inspection of the to-be-inspected area. Through the above method, polling can be completed in a more targeted and timely manner, so that the polling result is more reliable, and smooth proceeding of subsequent troubleshooting is facilitated.

Description

Technical Field

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

[0002] As a vital component of urban infrastructure, the safe and stable operation of gas pipelines is directly impactful on all aspects of residents' lives and urban development. Regular gas pipeline inspections, along with the timely identification and resolution of potential safety hazards, are key measures to ensure a safe gas supply. Traditional gas pipeline inspections rely primarily on manual labor, making comprehensiveness and accuracy difficult to guarantee. Complex inspection environments significantly increase the difficulty and risk of inspections.

[0003] Therefore, it is hoped to propose a smart gas unmanned inspection method based on the Internet of Things to better complete the inspection of gas pipelines. Summary of the Invention

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

[0005] The invention includes a method for intelligent unmanned gas inspection based on the Internet of Things. The method includes: obtaining regional data of a management area from a gas company management platform in a government safety supervision object platform through 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 obtains the regional data from a gas inspection object platform through the gas company sensor network platform; based on the regional data and traffic data of the management area, determining whether to determine the management area as an area to be inspected; in response to determining the management area as the 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 object platform, further controlling at least one of the pipeline monitoring equipment, the inspection personnel, and the unmanned inspection equipment through the government safety supervision object platform to complete the inspection of the area to be inspected.

[0006] The invention also includes a smart gas unmanned inspection system based on the Internet of Things, including a government safety supervision management platform, a government safety supervision sensor network platform, a government safety supervision object platform, a gas company sensor network platform, and a gas inspection object platform; the gas inspection object platform includes unmanned inspection equipment; the government safety supervision object platform includes a gas company management platform; the government safety supervision management platform is configured to: obtain regional data of the management area from the gas company management platform in the government safety supervision object platform through the government safety supervision sensor network platform, and the regional data includes ground image information, macro image information, air data, etc. and environmental data; wherein, the gas company management platform obtains the area data from the gas inspection object platform through the gas company sensor network platform; based on the area data and the traffic data of the management area, determines whether the management area is determined as the area to be inspected; in response to determining the management area as the area to be inspected, determines the inspection parameters of the area to be inspected; sends the inspection parameters to the government safety supervision object platform, and further controls the pipeline monitoring equipment, the inspection personnel and at least one of the unmanned inspection equipment through the government safety supervision object platform to complete the inspection of the area to be inspected.

[0007] Through the above-mentioned method, inspections can be completed in a more targeted and timely manner, making the inspection results more reliable and conducive to the smooth progress of subsequent troubleshooting; the smart gas unmanned inspection system based on the Internet of Things can form an information operation closed loop between various functional platforms, and coordinate and operate regularly under the unified management of the gas company management platform, realizing the informatization and intelligence of smart gas unmanned inspections. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] This specification will be further described in the form of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not limiting, and in these embodiments, like numbers represent like structures, wherein: 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; Figure 2 This is an exemplary flow chart of an IoT-based smart gas unmanned inspection method according to some embodiments of this specification; Figure 3 is a schematic diagram of determining an area to be inspected according to some embodiments of this specification; Figure 4 This is an exemplary flow chart of determining inspection parameters according to some embodiments of this specification.

[0009] Explanation of the accompanying symbols: 100 - smart gas unmanned inspection system based on the Internet of Things; 110 - government safety supervision 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 - macro 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 - risk of damage to facilities; 3100 - area to be inspected. DETAILED DESCRIPTION

[0010] To more clearly illustrate the technical solutions of the embodiments of this specification, the following briefly describes the drawings required for describing the embodiments. Obviously, the drawings described below are merely examples or embodiments of this specification. Those skilled in the art can apply this specification to other similar scenarios based on these drawings without inventive effort. Unless otherwise apparent from the context or otherwise noted, the same reference numerals in the figures represent the same structure or operation.

[0011] It should be understood that the terms "system," "device," "unit," and / or "module" used herein are a method for distinguishing different components, elements, parts, portions, or assemblies at different levels. However, if other terms can achieve the same purpose, the terms may be replaced by other expressions.

[0012] Flowcharts are used throughout this specification to illustrate the operations performed by systems according to embodiments of this specification. It should be understood that preceding or following operations do not necessarily need to be performed in exact order. Instead, the steps may be processed in reverse order or simultaneously. Furthermore, other operations may be added to these processes, or one or more operations may be removed from these processes.

[0013] 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.

[0014] In some embodiments, as Figure 1 As shown, the IoT-based smart gas unmanned inspection system 100 may include a government safety supervision 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 .

[0015] The government security supervision management platform 110 refers to a comprehensive management platform for the government to process and supervise information.

[0016] In some embodiments, the government safety supervision management platform 110 is configured to execute an IoT-based smart gas unmanned inspection method. For details about this method, please refer to the relevant description later in this specification.

[0017] In some embodiments, the government security supervision management platform 110 can be configured on a processor and / or server used by the government, which can process data and / or information obtained from other platforms, and execute program instructions based on these data, information and / or processing results to perform one or more functions described in this specification.

[0018] In some embodiments, the government security supervision management platform 110 may exchange data with the government security supervision object platform 130 through the government security supervision sensor network platform 120 .

[0019] The government security supervision sensor network platform 120 refers to a connection platform for realizing 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 a server.

[0020] In some embodiments, the government security supervision sensor network platform 120 can be configured as a communication network or a gateway, etc., which can realize the functions of perception information sensor communication and control information sensor communication.

[0021] The government safety supervision object platform 130 is a platform for generating government supervision information and controlling information execution. In some embodiments, the government safety supervision object platform 130 includes a gas company management platform 131 .

[0022] In some embodiments, the government safety supervision object platform 130 interacts with the government safety supervision sensor network platform 120 upward and interacts with the gas company sensor network platform 140 downward.

[0023] The gas company management platform 131 refers to a comprehensive management platform for gas company information.

[0024] The gas company sensor network platform 140 is a platform for managing 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.

[0025] In some embodiments, the gas company sensor network platform 140 exchanges data with the government safety supervision object platform 130 upward and with the gas inspection object platform 150 downward.

[0026] The gas inspection object platform 150 is a functional platform for the gas company to sense information generation and control information execution. In some embodiments, the gas inspection object platform 150 includes unmanned inspection equipment.

[0027] Unmanned inspection equipment refers to inspection equipment that does not require human operator control. In some embodiments, unmanned inspection equipment may include, but is not limited to, drones, unmanned vehicles, and their onboard environmental monitoring equipment, gas monitoring equipment, sensors, image acquisition equipment, and / or laser point cloud equipment.

[0028] In some embodiments of this specification, the smart gas unmanned inspection system based on the Internet of Things can form an information operation closed loop between various functional platforms, and coordinate and operate regularly under the unified management of the gas company management platform, thereby realizing the informatization and intelligence of smart gas unmanned inspection.

[0029] In some embodiments, when implementing a smart gas unmanned inspection method based on the Internet of Things, the government safety supervision management platform can obtain regional data of the management 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 the traffic data of the management area, determine whether to determine the management area as the area to be inspected; in response to determining the management area as the 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 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.

[0030] Figure 2 This is an exemplary flow chart of an IoT-based smart gas unmanned inspection method according to some embodiments of this specification.

[0031] like Figure 2 As shown, the process 200 includes the following steps: In some embodiments, the process 200 may be executed by the government security supervision management platform 110 .

[0032] Step 210: Acquire the area data of the management area.

[0033] The management area is the area obtained by dividing the area where the gas pipeline network is laid.

[0034] In some embodiments, the government security supervision management platform can be divided according to pre-set standards to obtain multiple management areas. For example, it can be divided according to different management personnel.

[0035] The regional data is data reflecting regional information in the management area. In some embodiments, the regional data includes at least one of ground image information, macro image information, air data, and environmental data.

[0036] Ground image information is image data reflecting the surface information of the management area. For example, ground image information may include data representing surface undulations. In some embodiments, ground image information may be represented by point cloud data and / or images.

[0037] Macro image information is image data that reflects the overall situation of the management area. For example, macro image information may include data that reflects the environment and humanities of the management area.

[0038] Air data is data reflecting air conditions. For example, air data may include but is not limited to gas components and their contents in the air.

[0039] Environmental data is data that reflects environmental conditions. For example, environmental data may include but is not limited to temperature, humidity, etc.

[0040] In some embodiments, ground image information and macro image information can be obtained by image acquisition equipment set in the gas inspection object platform, and air data and environmental data can be obtained by sensors set in the gas inspection object platform, and the above-mentioned data can be transmitted to the gas company management platform through the gas company sensor network platform.

[0041] In some embodiments, the government safety supervision management platform can obtain regional data of the management area from the gas company management platform in the government safety supervision object platform through the government safety supervision sensor network platform. Specifically, the gas company management platform can obtain regional data from the gas inspection object platform through the gas company sensor network platform.

[0042] Step 220 : Based on the area data and the traffic data of the management area, it is determined whether the management area is determined as an area to be inspected.

[0043] Traffic data is data reflecting traffic conditions, for example, traffic data may include but is not limited to road traffic volume.

[0044] In some embodiments, the government safety supervision and management platform can obtain traffic data through external platforms, such as traffic monitoring centers, map service providers, etc.

[0045] The area to be inspected refers to the management area that needs to be inspected.

[0046] In some embodiments, the government safety supervision management platform can determine the gas leakage situation in the management area based on air data, determine the vehicle 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; based on at least one of the gas leakage situation, vehicle flow, surface undulation data, building density, road density, temperature and humidity, determine whether to determine the management area as an area to be inspected.

[0047] Gas leakage status is data that indicates whether a gas leak exists. If the percentage of gas contained in the air within a managed area exceeds a gas content threshold, a gas leak is determined within that area. The gas content threshold can be determined based on prior experience.

[0048] Surface relief data is data that reflects the altitude characteristics of an area and may include the altitude of at least one point within the management area.

[0049] Building density is data that reflects the building footprint, which can be determined based on the percentage of building area in the management area to the total area of ​​the management area.

[0050] Road density is data reflecting the density of road distribution and can be determined based on the road length per unit area in the management area.

[0051] In some embodiments, determining whether to determine the management area as an area to be inspected includes at least one stage of determination.

[0052] For example, the government safety supervision management platform can perform a first-stage judgment based on the gas leakage situation in the management area. If there is a gas leak in the management area, the management area is determined as an area to be inspected. If there is no gas leak, the second-stage judgment is entered.

[0053] Exemplarily, the government safety supervision and management platform can make a second-stage judgment based on the traffic volume, surface undulation data, building density and road density of the management area. The second-stage judgment includes whether the traffic volume in the management area is greater than the traffic threshold, whether the variance of the surface undulation data is greater than the undulation threshold, whether the building density is greater than the building density threshold, whether the road density is greater than the road density threshold, whether the temperature is greater than the temperature threshold and whether the humidity is greater than the humidity threshold. If the situation in the management area meets N or more of the above conditions, the management area is determined as an area to be inspected. Wherein, N is an integer greater than 1 and not greater than 6, which can be determined according to actual needs. The traffic 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.

[0054] In some embodiments, the government safety supervision management platform can also determine the dynamic characteristics of the management area based on macro 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 risk of facility damage based on risk characteristics and facility information of gas ancillary facilities; and determine the management area as an area to be inspected in response to the risk of facility damage meeting preset conditions. For more detailed instructions, please refer to this manual Figure 3 and its related descriptions.

[0055] Step 230 : In response to determining the managed area as the area to be inspected, determining inspection parameters of the area to be inspected.

[0056] The inspection parameters are parameters used to guide the inspection process. In some embodiments, the inspection parameters are related to at least one of pipeline monitoring equipment, inspection personnel, and unmanned inspection equipment.

[0057] In some embodiments, in response to determining that a management area is an area to be inspected, the government security supervision and management platform may determine inspection parameters based on preset rules. The preset rules may include: determining at least one of a second collection parameter for unmanned inspection equipment and a dispatch instruction for inspection personnel when the management area is determined to be an area to be inspected in the first stage; and determining at least one monitoring device to be activated and its monitoring frequency when the management area is determined to be an area to be inspected in the second stage.

[0058] The second acquisition parameter is used to instruct the unmanned inspection equipment to hover over the gas pipeline to acquire air data. This second acquisition parameter may include, but is not limited to, at least one of a path and a hovering time. The path can be determined based on the distribution of gas pipelines in the inspection area, and the hovering time can 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 greater the number of downstream users, the longer the hovering time.

[0059] The dispatch instruction is used to instruct inspection personnel to monitor the gas pipeline. In some embodiments, the government safety supervision and management platform can determine whether there is a gas leak in the management area based on the air data obtained by the unmanned inspection equipment based on the second acquisition parameter. In response to the presence of a gas leak at one or more locations, the government safety supervision and management platform can generate a dispatch instruction based on the coordinates of the leak location and send it to the corresponding terminal of the inspection personnel to arrange for the corresponding inspection personnel to conduct inspections.

[0060] The monitoring devices to be activated refer to pipeline monitoring devices that need to be activated. In some embodiments, the government safety supervision and management platform can determine the monitoring devices to be activated based on the value of N used in the second-stage judgment and the level of the pipeline monitoring devices. For example, the government safety supervision and management platform can activate pipeline monitoring devices in descending order of level. A larger value of N indicates a more stringent second-stage judgment, resulting in a smaller number of pipeline monitoring devices to be activated.

[0061] The level of pipeline monitoring equipment is positively correlated with the importance of the data it captures. Data importance can be determined using a frequent item algorithm based on historical accident-related indicators. For example, if a high number of accidents related to a particular indicator are found in historical incidents, this indicates that the indicator is important.

[0062] Monitoring frequency refers to the frequency of monitoring equipment or gas pipeline data through pipelines. Monitoring frequency is negatively correlated with the number of monitoring devices to be activated.

[0063] In some embodiments, the government safety supervision 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, management resource data of the management area, and historical maintenance data. For more detailed instructions, please refer to this manual Figure 4 and its related descriptions.

[0064] In step 240 , the inspection parameters are sent 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.

[0065] In some embodiments, the government safety supervision 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.

[0066] For example, in response to the management area being determined as an area to be inspected in the first stage, the government safety supervision management platform can send the second collection parameter to the unmanned inspection equipment, control the unmanned inspection equipment to perform hovering monitoring along the gas pipeline according to the second collection parameter; and judge whether there is a gas leak location based on the data obtained by the unmanned inspection equipment. If there is a gas leak location, send a scheduling instruction to the corresponding terminal of the inspection personnel to instruct the inspection personnel to conduct manual inspection.

[0067] If the management area is identified as a pending inspection area during the second phase, the government safety supervision and management platform can send the pending monitoring equipment and monitoring frequency to the pipeline monitoring equipment, thereby controlling the relevant pipeline monitoring equipment to obtain gas pipeline data according to the monitoring frequency. At this point, the government safety supervision and management platform can also send the pending monitoring equipment and monitoring frequency to the corresponding terminal of the inspection personnel to synchronize relevant information.

[0068] In some embodiments of this specification, the government security supervision management platform can determine whether the management area needs inspection through regional data, and can determine appropriate inspection parameters when inspection is required to complete the inspection of the inspection area. It can complete the inspection in a more targeted and timely manner, making the inspection results more reliable and conducive to the smooth progress of subsequent troubleshooting.

[0069] Figure 3 This is a schematic diagram of determining an area to be inspected according to some embodiments of this specification.

[0070] In some embodiments, as Figure 3 As shown, the government safety supervision management platform can determine the dynamic characteristics 330 of the management area based on macro image information 310 and traffic data 320; determine the risk characteristics 370 of the gas pipeline 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 the gas ancillary facilities; in response to the facility damage risk 390 meeting the preset conditions, the management area is determined as the area to be inspected 3100.

[0071] For more information about ground image information, macro image information, air data, environmental data, management areas, and areas to be inspected, see Figure 2 The corresponding description.

[0072] Dynamic characteristics refer to parameters related to measuring surface pressure. They can be used to reflect the impact of construction conditions (scale, noise level), traffic, and pedestrian flow on surface pressure.

[0073] In some embodiments, the government safety supervision and management platform determines dynamic features in a variety of ways based on macro image information and traffic data. For example, the government safety supervision and management platform can determine dynamic features using a preset formula based on the positive correlation between macro image information, traffic data, and dynamic features. For example, the preset formula is shown in the following formula (1): (1) in, Represents dynamic features, represents the building density in the macroscopic image information, represents the road density in the macroscopic image information, represents the average flow rate of the road, 、 、 is the order of magnitude parameter. 、 、 It can be preset based on experience or set by system default.

[0074] In some embodiments, the government safety supervision management platform can determine dynamic characteristics based on macro image information, traffic data, noise information and vibration information in the management area.

[0075] Noise information refers to information related to noise characteristics in a management area. For example, the noise information may include noise frequencies of multiple noises.

[0076] Vibration information refers to information related to vibration characteristics in the management area. For example, vibration information may include vibration frequencies of multiple vibrations, etc.

[0077] In some embodiments, the dynamic features are positively correlated with macroscopic image information, traffic data, noise information, and vibration information in the management area. The government safety supervision management platform can determine the dynamic features using a preset formula based on the macroscopic image information, traffic data, noise information, and vibration information in the management area. For example, the preset formula is shown in the following formula (2): (2) in, represents the average noise frequency of multiple noises, represents the average vibration frequency of multiple vibrations, 、 is the order of magnitude parameter. 、 It can be preset based on experience or set by system default.

[0078] The resonance caused by sound waves and the energy they carry will affect the condition of the surface, causing the surface to vibrate.

[0079] In some embodiments of this specification, considering the impact of noise and vibration on dynamic characteristics is conducive to more accurate determination of dynamic characteristics, thereby ensuring the accuracy of subsequently determined risk characteristics and other data, and improving the efficiency of determining areas to be inspected.

[0080] Risk characteristics refer to data related to the risk of gas pipelines in the management area. In some embodiments, the risk characteristics include risk type and risk intensity.

[0081] 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, while passive risks refer to risks caused by external pressure, interference, etc.

[0082] Risk intensity is data that characterizes the likelihood of risks existing in gas pipelines.

[0083] In some embodiments, the government safety supervision 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 characteristics.

[0084] For example, the government safety supervision and management platform can determine whether the temperature in the environmental data is greater than the temperature threshold, whether the humidity is greater than the humidity threshold, or whether the dynamic characteristics are greater than the dynamic threshold. If one of the above three conditions is met, the risk type can be judged as a passive risk, otherwise it is an active risk.

[0085] For example, the government safety supervision and management platform can determine the risk intensity based on the judgment results of at least one evaluation item related to ground image information, environmental data, air data, and dynamic characteristics. The evaluation items include: a) judging based on ground image information that the variance of surface undulation is greater than a undulation threshold; b) judging based on environmental data that the temperature is greater than a temperature threshold; c) judging based on environmental data that the humidity is greater than a humidity threshold; d) judging based on air data that the presence of a gas leak in the management area is greater than a flow threshold; e) judging based on traffic data that the average flow rate of roads in the management area is greater than a flow threshold; f) judging based on dynamic characteristics that the dynamic characteristics are greater than a dynamic threshold.

[0086] For example, the government security supervision and management platform can determine the risk intensity through a preset formula based on the initial risk level and the aforementioned judgment results. The preset formula is shown in the following formula (3): (3) in, Indicates the risk intensity, represents the initial risk, Indicates the number of items that meet the judgment in the evaluation items. It can be preset by staff based on experience or set by system default.

[0087] The temperature threshold, humidity threshold, dynamic threshold, fluctuation threshold, and flow threshold are preset critical values ​​for temperature, humidity, dynamic characteristics, fluctuation variance, and average road flow, respectively. These thresholds can be preset by staff based on experience or set by system default.

[0088] In some embodiments, the government security supervision management platform can determine the estimated dynamic characteristics of the management area within a preset future time period through a first prediction model based on environmental data and dynamic characteristics; determine the estimated air data of the management area within a preset future time period through a second prediction model based on air data and environmental data; and determine the risk characteristics of the management area through a third prediction model based on ground image information, estimated dynamic characteristics, and estimated air data.

[0089] The preset future period refers to a preset period of time in the future, for example, the next 0.5 hours, the next 1 hour, etc.

[0090] Estimated dynamic characteristics refer to the relevant parameters that measure surface pressure within a preset future period.

[0091] Estimated air data refers to data related to air characteristics within a preset future period.

[0092] In some embodiments, the first prediction model may be a machine learning model, for example, a neural network (NN) model or other trained machine learning models.

[0093] In some embodiments, the input of the first prediction model includes environmental data and dynamic characteristics, and the output includes estimated dynamic characteristics of the management area within a preset future time period.

[0094] In some embodiments, the first prediction model can be obtained in various ways, for example, by training a large number of first training samples with first labels. A set of first training samples includes sample environmental data and sample dynamic features from a first historical period, and the corresponding first labels include sample dynamic features from a second historical period. The first historical period is earlier than the second historical period.

[0095] For example, the government security supervision and management platform can obtain the historical environmental data and historical dynamic features of the historical management area in the first historical period as the first training sample, and obtain the dynamic features of the historical management area in the second historical period as the first label corresponding to the first training sample.

[0096] The government security supervision and management platform can input a first training sample into an initial first prediction model to obtain an output of the initial first prediction model; construct a first loss function based on the first label and the output of the initial first prediction model; and iteratively update parameters of the initial first prediction model based on the first loss function. Training is completed until an iterative termination condition is met, thereby obtaining a trained first prediction model. The iterative termination condition may include convergence of the first loss function or a threshold number of iterations.

[0097] In some embodiments, the second prediction model may be a machine learning model, for example, a neural network (NN) model or other trained machine learning models.

[0098] In some embodiments, the input of the second prediction model includes air data and environmental data, and the output includes estimated air data of the management area within a preset future period.

[0099] In some embodiments, the second prediction model can be obtained in various ways, for example, by training a large number of second training samples with second labels. A set of second training samples includes sample air data and sample environmental data from a first historical period, and the corresponding second labels include sample air data from a second historical period.

[0100] The process of obtaining the second training sample and the second label is similar to the process of obtaining the first training sample and the first label. The training process of the second prediction model is similar to the training process of the first prediction model. Please refer to the relevant description above.

[0101] In some embodiments, the input of the first prediction model also includes surface maintenance planning and traffic planning information of the management area; the input of the second prediction model also includes pipeline monitoring parameters of the pipeline monitoring equipment in the management area.

[0102] Surface maintenance planning refers to information related to changes to the surface within a management area. For example, it may be necessary to address a sinkhole or other situation requiring surface maintenance or repairs within a management area.

[0103] Traffic planning information refers to information related to the regulation of roads within the management area. For example, a road in the management area needs to be temporarily closed for maintenance, or other situations require traffic control.

[0104] Pipeline monitoring parameters refer to the type of pipeline information that needs to be acquired through monitoring. In some embodiments, pipeline monitoring parameters can be determined based on the type of pipeline monitoring device. For example, when the pipeline monitoring device is a temperature sensor, the pipeline monitoring parameter is temperature; when the pipeline monitoring device is a humidity sensor, the pipeline monitoring parameter is humidity.

[0105] In some embodiments, when the input of the first prediction model also includes surface maintenance planning and traffic planning information of the management area, the first training sample also includes sample surface maintenance planning and sample traffic planning information; when the input of the second prediction model also includes pipeline monitoring parameters of pipeline monitoring equipment in the management area, the second training sample also includes sample pipeline monitoring parameters.

[0106] In some embodiments of the present specification, the input of the first prediction model takes into account some municipal construction information, such as surface maintenance planning and traffic planning information, and can take into account the pressure changes of the underground gas pipeline caused by macro changes; the input of the second prediction model takes into account the pipeline monitoring parameters, which can provide more data to rely on when estimating whether a gas leak will occur in the future, making the final result more accurate.

[0107] In some embodiments, the third prediction model may be a machine learning model, for example, a neural network (NN) model or other trained machine learning models.

[0108] In some embodiments, the input of the third prediction model includes ground image information, estimated dynamic characteristics, and estimated air data, and the output includes risk characteristics of the management area.

[0109] 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 second historical period, and the corresponding third labels include sample risk features from a third historical period. The second historical period is earlier than the third historical period.

[0110] For example, the government safety supervision and management platform can obtain historical ground image information, historical dynamic characteristics, 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.

[0111] The government safety supervision and management platform can count accidents that occurred within the historical management area during the third period, determine the historical accident type based on the type of accident, and use the ratio of the time from the accident occurrence to the current time to a preset time threshold as the historical risk intensity to determine the historical risk characteristics. The preset time threshold can be represented by the average time interval between the occurrence of such accidents in historical data. If no accidents occurred during the third period, the third label is marked as 0.

[0112] The training process of the third prediction model is similar to that of the first prediction model, and reference may be made to the relevant description above.

[0113] In some embodiments of this specification, the uncertainty of the risk characteristics themselves is taken into account, and future risk situations are estimated through machine learning models, so that early regulation can be carried out, and preventive measures can be given in advance for possible risks to reduce losses.

[0114] Gas ancillary facilities refer to various auxiliary equipment and structures related to the transmission, distribution, and use of gas. For example, gas ancillary facilities include pressure regulating equipment and metering devices.

[0115] Facility information is related information that characterizes the characteristics / attributes of a gas auxiliary facility. For example, facility information may include but is not limited to the type of gas auxiliary facility, the geographical coordinates of the gas auxiliary facility, etc.

[0116] Facility damage risk is data that characterizes the possibility of gas ancillary facilities being damaged.

[0117] In some embodiments, the government safety supervision and management platform may determine the facility damage risk in various ways based on risk characteristics and facility information of gas ancillary facilities. For example, if the risk type is active risk, the government safety supervision and management platform may determine the risk intensity as the facility damage risk; if the risk type is passive risk, the government safety supervision and management platform may determine the facility damage risk based on the correlation between the facility damage risk and the risk intensity.

[0118] For example, the government safety supervision and management platform can determine the facility damage risk through a preset formula based on the positive correlation between risk intensity and facility damage risk. The preset formula is shown in the following formula (4): (4)

[0119] in, Indicates the risk of damage to facilities, Indicates the risk intensity, Represents the risk factor. The range is between 0-1, Can be preset by staff based on experience, or, It can be expressed as the ratio of the number of data showing failures of gas auxiliary facilities in passive risks to the total number of times passive risks occur in historical data.

[0120] In some embodiments, the government safety supervision and management platform can determine the risk of facility damage based on risk characteristics and facility key values ​​of gas ancillary facilities.

[0121] The facility criticality is data that characterizes the criticality of the gas auxiliary facility. The higher the facility criticality, the higher the criticality of the gas auxiliary facility. In some embodiments, the facility criticality is positively correlated with the number of downstream branches and the timeliness of maintenance of the gas auxiliary facility.

[0122] The number of downstream branches refers to the number of pipelines branching out from the current gas auxiliary facilities to the end users or other gas pipelines.

[0123] Maintenance timeliness is a metric that indicates the promptness of repairs to gas ancillary facilities. It is negatively correlated with the average time from fault discovery to repair completion.

[0124] In some embodiments, if the risk type is active risk, the government safety supervision management platform can determine the risk intensity as the risk of facility damage; if the risk type is passive risk, the risk of facility damage is positively correlated with the facility key value and risk intensity.

[0125] In some embodiments of this specification, when the risk type is passive risk, the facility key values ​​of the gas ancillary facilities also need to be considered. The more important the facility, the higher the risk of damage to the corresponding facility should be, so that it can receive higher attention, so that the subsequent inspection area can be determined more accurately, and when inspecting the inspection area, damage can be discovered in time for subsequent processing.

[0126] The preset condition refers to a preset condition for determining whether a management area is an area to be inspected. In some embodiments, the preset condition is related to a risk threshold. The preset condition can be that the risk of damage to facilities in the management area is greater than the risk threshold.

[0127] The risk threshold refers to the preset maximum value of the risk of facility damage.

[0128] In some embodiments, the risk threshold is associated with gas delivery data for a managed area.

[0129] Gas transmission data refers to data related to gas pipelines in a management area. In some embodiments, the gas transmission data includes pipeline levels, end-user types, and the like.

[0130] The pipeline grade is determined by the number of end users connected to the pipeline. The greater the number of end users, the higher the pipeline grade.

[0131] The end-user type refers to a type of user that uses gas, etc. For example, the end-user type includes commercial users, government users, individual users, etc.

[0132] In some embodiments, the risk threshold is related to the gas transmission data of the management area. For example, the risk threshold is positively correlated with the pipeline level. In another example, the risk threshold corresponding to commercial users and government users is higher than the risk threshold for individual users.

[0133] In some embodiments of this specification, the higher the pipeline level, the more important the pipeline is, and the risks need to be strictly controlled. Furthermore, considering the type of end user, the corresponding risks of commercial users and government users with a larger impact need to be strictly controlled compared with individual users. Strict risk control is conducive to timely response to changes in the pipeline and reducing losses.

[0134] In some embodiments, the government safety supervision management platform may 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 determined as an area to be inspected.

[0135] In some embodiments of this specification, by calculating the dynamic characteristics and risk characteristics of the management area, the accuracy of the determined facility damage risk can be improved, and then the area to be inspected can be determined, which is conducive to dispatching staff to repair the risky areas and investigate the risks caused by facility failures, which can reduce the waste of resources on investigating other failures that are not caused by facilities.

[0136] Figure 4 This is an exemplary flow chart of determining inspection parameters according to some embodiments of this specification.

[0137] In some embodiments, in response to determining a management area as an area to be inspected, inspection parameters of 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 a government safety supervision management platform; determining the inspection priority of the area to be inspected based on the surface maintenance planning and traffic planning information; and determining inspection parameters based on the inspection priority, management resource data, and historical maintenance data.

[0138] In some embodiments, as Figure 4 As shown, the process 400 includes the following steps: The process 400 may be executed by a government security supervision management platform.

[0139] Step 410: 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 management platform.

[0140] Management resource data refers to data related to resource characteristics in the area to be inspected. For example, management resource data may include the number of maintenance personnel, the number of backup resources, etc. The number of backup resources includes the number of backup facilities that are gas auxiliary facilities.

[0141] 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 through the network, and store them in the government safety supervision and management platform for use when needed.

[0142] Historical maintenance data refers to data related to maintenance performed on gas pipelines in the inspection area in the past. For example, historical maintenance data may include the time of maintenance and the type of accident that occurred.

[0143] The accident type refers to the type of gas pipeline failure. For example, the accident types include gas pipeline breakage and valve damage.

[0144] In some embodiments, after a gas pipeline failure occurs, the maintenance data generated by the maintenance will be uploaded to the government safety supervision and management platform for storage so that it can be obtained from the government safety supervision and management platform when needed.

[0145] Step 420: Determine the inspection priority of the area to be inspected based on the surface maintenance plan and traffic planning information.

[0146] Information on surface maintenance planning and traffic planning can be found at Figure 3 The corresponding description.

[0147] Inspection priority is a hierarchical standard used to guide the order and resource allocation of inspections for multiple inspection areas. Inspection priority is related to the importance of the inspection area. The more important the inspection area, the higher the inspection priority.

[0148] In some embodiments, the government safety supervision and management platform can determine the inspection priority of the area to be inspected in various ways based on the surface maintenance plan and traffic planning information. For example, the government safety supervision and management platform can determine whether the area to be inspected is included in both the surface maintenance plan and the traffic planning information. If so, the inspection priority is the highest; if only in the surface maintenance plan, the inspection priority is second; if only in the traffic planning information, the inspection priority is third; if neither is included, the inspection priority is the lowest.

[0149] In some embodiments, the inspection priority is also related to the facility key value of the gas auxiliary facilities in the area to be inspected. For more information about gas auxiliary facilities and facility key values, please refer to Figure 3 The corresponding description.

[0150] In some embodiments, the inspection priority is positively correlated with the facility key value of the gas auxiliary facilities in the area to be inspected.

[0151] In some embodiments of this specification, the importance of gas ancillary facilities is taken into consideration when setting inspection priorities, which can increase the priority of areas where more critical pipelines are located, so that resources can be effectively allocated.

[0152] Step 430: Determine inspection parameters based on inspection priority, management resource data, and historical maintenance data.

[0153] In some embodiments, the government safety supervision management platform can determine inspection parameters based on inspection priorities, management resource data, and historical maintenance data.

[0154] For example, for an area to be inspected with a higher inspection priority, if there are fewer management resources, the inspection parameters include using unmanned inspection equipment for inspection; if there are more management resources, the inspection parameters include dispatching inspection personnel for inspection; for an area to be inspected with a lower inspection priority, if there are fewer management resources, the inspection parameters include using unmanned inspection equipment for inspection; if there are more management resources, the inspection parameters include using pipeline monitoring equipment for inspection.

[0155] In some embodiments, the government safety supervision management platform can determine the accident probability through a probability prediction model based on candidate inspection parameters, inspection priorities, management resource data, and historical maintenance data; and determine inspection parameters based on the accident probability.

[0156] The candidate inspection parameters refer to parameters that are candidates for inspection parameters.

[0157] In some embodiments, the government security supervision and management platform can obtain candidate inspection parameters based on historical inspection parameters. For example, the government security supervision and management platform can count the number of times each historical inspection parameter appears in historical data and select a preset number of historical inspection parameters with the largest number of occurrences as candidate inspection parameters. The value of the preset number is determined based on actual needs.

[0158] Accident probability refers to the probability of an accident occurring in the area to be inspected.

[0159] A probabilistic prediction model refers to a model used to determine accident probability. In some embodiments, the probabilistic prediction model is a machine learning model, such as a neural network (NN) model or other trained machine learning model.

[0160] In some embodiments, the input of the probability prediction model includes candidate inspection parameters of the area to be inspected, inspection priority, management resource data, and historical maintenance data, and the output includes accident probability.

[0161] In some embodiments, the probability prediction model can be trained to obtain an initial probability 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 of 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 sample accident probabilities corresponding to the sample areas to be inspected.

[0162] 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 in historical data as the fourth training sample, and use the probability of subsequent actual accidents as the fourth label corresponding to the fourth training sample.

[0163] The probability of an actual subsequent accident refers to the probability of an accident occurring within the execution time of the historical inspection parameter. Execution time refers to the time required to complete an inspection using the inspection parameter. In some embodiments, the government safety supervision and management platform can count the frequency of subsequent accidents that actually occurred within the execution time of a historical inspection parameter in the historical data, calculate the ratio of this frequency to the execution time, normalize this ratio, and determine the resulting result as the probability of an actual subsequent accident. Normalization refers to the process of converting the ratio of frequency to execution time into a value between 0 and 1.

[0164] The training process of the probability prediction model is similar to that of the first prediction model, and can be found in the corresponding description above.

[0165] In some embodiments, the government security supervision management platform can split the sample data set 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, the validation set, and the test set to obtain a probability prediction model.

[0166] The preset ratio refers to the pre-set ratio of the training set, validation set, and test set. For example, the preset ratio may be 8:1:1 for the number of samples in the training set, validation set, and test set.

[0167] In some embodiments, the preset ratio may be pre-set by the government security supervision management platform based on default settings or prior experience.

[0168] In some embodiments, the government security supervision management platform can split the sample data set based on a preset ratio to obtain a training set, a validation set, and a test set.

[0169] The splitting method may include sampling statistics, which may include but is not limited to random sampling, stratified sampling, etc. In some embodiments, the gas company management platform may also split the sample data set in other ways.

[0170] In some embodiments, the training set is a dataset used to adjust the model's learning parameters during model training. Learning parameters include weights, biases, and other parameters. The validation set is a dataset used to adjust the model's hyperparameters during model training. Hyperparameters include the number of network layers, number of network nodes, number of iterations, and learning rate. The test set is a dataset used to evaluate the performance of the final model.

[0171] There is no data overlap between the training set, validation set, and test set obtained by splitting, that is, there is no duplicate data between any two of the training set, validation set, and test set.

[0172] In some embodiments, the government security supervision management platform can train the initial probability prediction model based on the training set, the validation set and the test set to obtain an estimation model.

[0173] The training process includes multiple stages of training. Among them, 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, and updating the parameters of the initial probability prediction model through multiple rounds of iterations based on the loss function; in the aforementioned training process, based on a pre-set verification frequency, the trained initial probability prediction model is verified through the verification set, and the initial learning rate or the learning rate during the training process of the initial probability prediction model after this round of training is adjusted based on the verification result; when the preset condition is triggered, the obtained estimation model is tested through the test set to evaluate the performance of the obtained estimation model; multiple stages of training are performed, and the estimation model with the best performance is used as the trained estimation model.

[0174] There are many strategies that can be used to adjust the learning rate, such as one or more of the following methods: learning rate decay strategy, learning rate warm-up, cyclic learning rate, and adaptive learning rate adjustment algorithm.

[0175] The preset conditions may include one or more of the number of iterations reaching a threshold, the loss function converging, and the value of the loss function being less than a preset threshold.

[0176] The above process of using the training set, validation set and test set to train the model is only an example. Other processes familiar to those skilled in the art can also be used when training the model based on the training set, validation set and test set.

[0177] In some embodiments, the sample data set can be randomly divided into multiple groups of sample data, and one group 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 security supervision management platform can train the initial probability prediction model based on multiple groups of divided sample data.

[0178] In some embodiments, the learning rate corresponding to a set of sample data is related to the number of sample maintenance data in the set of sample data. The larger the number of sample maintenance data, the larger the learning rate corresponding to the set of sample data. The large number of sample maintenance data refers to a large number of maintenance records in the set of sample data.

[0179] In some embodiments of the present specification, training based on a training set, a validation set, and a test set can obtain a more appropriate probability prediction model, which is beneficial to improving the robustness of the probability prediction model and preventing the probability prediction model from 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 probability prediction model in making predictions can be improved.

[0180] In some embodiments, the input of the probability prediction model also includes pipeline monitoring parameters of the pipeline monitoring equipment in the area to be inspected.

[0181] For more information on pipeline monitoring parameters, see Figure 3 The corresponding description.

[0182] When the input of the probability prediction model also includes pipeline monitoring parameters, the sample data set also includes sample pipeline monitoring parameters.

[0183] In some embodiments of this specification, the input of the probability prediction model also considers pipeline monitoring parameters. Its essence is to consider the specific conditions of the pipeline and be able to fit the actual conditions of the pipeline. By considering the loss of the pipeline caused by the gas inside the pipeline, the determined accident probability is more comprehensive and accurate.

[0184] In some embodiments of this specification, by evaluating the accident probability of 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 accident probability.

[0185] In some embodiments of this specification, the importance of the inspection area is evaluated based on surface maintenance planning and traffic planning information to obtain inspection priorities, which can ensure the accuracy of the inspection priorities; at the same time, the inspection priorities are conducive to resource allocation and finding an inspection plan that is more suitable for the area to be inspected.

[0186] While the basic concepts have been described above, it will be apparent to those skilled in the art that the detailed disclosure is merely illustrative and does not limit this specification. Although not explicitly stated herein, various modifications, improvements, and revisions to this specification may be made by those skilled in the art. Such modifications, improvements, and revisions are suggested in this specification and remain within the spirit and scope of the exemplary embodiments of this specification.

[0187] This specification also uses specific terms to describe the embodiments of this specification. For example, "one embodiment," "an embodiment," and / or "some embodiments" refer to a feature, structure, or characteristic associated with at least one embodiment of this specification. Therefore, it should be emphasized and noted that references to "one embodiment," "an embodiment," or "an alternative embodiment" two or more times in different locations in this specification do not necessarily refer to the same embodiment. Furthermore, certain features, structures, or characteristics of one or more embodiments of this specification may be appropriately combined.

[0188] In addition, unless expressly stated in the claims, the order of the processing elements and sequences, the use of alphanumeric characters, or the use of other names described in this specification are not intended to limit the order of the processes and methods of this specification. Although the above disclosure discusses some of the invention embodiments currently considered useful through various examples, it should be understood that such details are for illustrative purposes only, and the appended claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the spirit and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0189] Similarly, it should be noted that, in order to simplify the presentation of this specification and thus facilitate understanding of one or more embodiments of the invention, the foregoing descriptions of the embodiments of this specification sometimes combine multiple features into a single embodiment, figure, or description thereof. However, this disclosure method does not imply that the subject matter of this specification requires more features than those recited in the claims. In fact, an embodiment may have fewer features than all of the features of a single disclosed embodiment.

[0190] Finally, it should be understood that the embodiments described in this specification are intended only to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, by way of example and not limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly described and illustrated in this specification.

Claims

1. A smart gas unmanned inspection method based on the Internet of Things, characterized in that: The method is executed by a government safety supervision and management platform of a smart gas unmanned inspection system based on the Internet of Things, and the method includes: Obtaining regional data of a management area from a gas company management platform in a government safety supervision object platform via a government safety supervision sensor network platform, wherein the regional data includes at least one of ground image information, macroscopic image information, air data, and environmental data; wherein the gas company management platform obtains the regional data from a gas inspection object platform via the gas company sensor network platform; Based on the area data and the traffic data of the management area, determining whether to determine the management area as an area to be inspected; In response to determining the management area as the area to be inspected, determining inspection parameters of the area to be inspected; 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 a government safety supervision object 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 determining, based on the area data and the traffic data of the management area, whether to determine the management area as an area to be inspected includes: determining dynamic characteristics of the management area based on the macro image information and the traffic data; determining risk characteristics of the gas pipeline in the management area based on the ground image information, the environmental data, the air data, and the dynamic characteristics; Determining the risk of facility damage based on the risk characteristics and facility information of the gas ancillary facilities; In response to the facility damage risk meeting a preset condition, the management area is determined as the area to be inspected, where the preset condition is related to a risk threshold.

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

4. The method according to claim 1, wherein In response to determining the management area as the area to be inspected, determining inspection parameters of the area to be inspected includes: 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 management platform; Determining the inspection priority of the area to be inspected based on the surface maintenance plan and the traffic planning information; The inspection parameters are determined based on the inspection priority, the management resource data, and the historical maintenance data.

5. The method according to claim 4, characterized in that The determining of the inspection parameters based on the inspection priority, the management resource data, and the historical maintenance data includes: Determining the accident probability through a probability prediction model based on the candidate inspection parameters, the inspection priority, the management resource data, and the historical maintenance data, wherein the probability prediction model is a machine learning model; The inspection parameters are determined based on the accident probability.

6. A smart gas unmanned inspection system based on the Internet of Things, characterized by: Including government safety supervision management platform, government safety supervision sensor network platform, government safety supervision object platform, gas company sensor network platform and gas inspection object platform; The gas inspection object platform includes unmanned inspection equipment; the government safety supervision object platform includes the gas company management platform; The government security supervision and management platform is configured to: Obtaining regional data of a management area from a gas company management platform in a government safety supervision object platform via a government safety supervision sensor network platform, wherein the regional data includes at least one of ground image information, macroscopic image information, air data, and environmental data; wherein the gas company management platform obtains the regional data from a gas inspection object platform via the gas company sensor network platform; Based on the area data and the traffic data of the management area, determining whether to determine the management area as an area to be inspected; In response to determining the management area as an area to be inspected, determining inspection parameters of the area to be inspected; The inspection parameters are sent to a government safety supervision object 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.

7. The system according to claim 6, characterized in that The government security supervision and management platform is further configured to: determining dynamic characteristics of the management area based on the macro image information and the traffic data; determining risk characteristics of the gas pipeline in the management area based on the ground image information, the environmental data, the air data, and the dynamic characteristics; Determining the risk of facility damage based on the risk characteristics and facility information of the gas ancillary facilities; In response to the facility damage risk meeting a preset condition, the management area is determined as the area to be inspected, where the preset condition is related to a risk threshold.

8. The system according to claim 7, characterized in that The government security supervision and management platform is further configured to: Based on the environmental data and the dynamic characteristics, determining, by a first prediction model, estimated dynamic characteristics of the management area within a preset future period; Determining, based on the air data and the environmental data, estimated air data of the management area within the preset future period using a second prediction model; determining the risk characteristics of the management area by a third prediction model based on the ground image information, the estimated dynamic characteristics of the management area, and the estimated air data; as well as, The first prediction model, the second prediction model and the third prediction model are machine learning models.

9. The system according to claim 6, wherein: The government security supervision and management platform is further configured to: 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 management platform; Determining the inspection priority of the area to be inspected based on the surface maintenance plan and the traffic planning information; The inspection parameters are determined based on the inspection priority, the management resource data, and the historical maintenance data.

10. The system according to claim 9, characterized in that The government security supervision and management platform is further configured to: Determining the accident probability through a probability prediction model based on the candidate inspection parameters, the inspection priority, the management resource data, and the historical maintenance data, wherein the probability prediction model is a machine learning model; The inspection parameters are determined based on the accident probability.

Images