A reliable monitoring method for intelligent gas pipeline networks and an Internet of Things system

Abstract

An embodiment of this specification provides a reliable monitoring method for an intelligent gas pipeline network. This method is executed based on an intelligent gas safety management platform of an Internet of Things system for reliable monitoring of a gas pipeline network, and includes: obtaining a reliability sequence of the gas pipeline network; the reliability sequence includes the reliability of the gas pipeline network at multiple moments; determining a monitoring plan based on the reliability sequence; wherein, the determination of the reliability of the gas pipeline network at each of the multiple moments includes: obtaining the gas transportation characteristics of the gas pipeline network at the target moment; determining the wall thickness wear degree based on the gas transportation characteristics; and determining the reliability of the gas pipeline network at the target moment based on the wall thickness wear degree.

Description

Technical Field

[0001] This specification relates to the field of gas safety, and particularly to a method for monitoring the reliability of an intelligent gas pipeline network and an Internet of Things system. Background Art

[0002] As the gas transmission and distribution system of a city, the urban gas pipeline network has become one of the important symbols of urban modernization. With the need for urban development, the gas pipeline network continues to extend, and the safety issues in the operation of the gas pipeline network have become increasingly prominent, especially the problem of pipeline damage. Due to long-term wear of the pipe wall, problems such as corrosion and leakage are likely to occur, posing potential safety hazards. The gas pipeline network is generally laid underground, and combined with the complex urban environment, it invisibly increases the difficulty of risk investigation of the gas pipeline network. Once a safety accident occurs, it will cause huge personal and property losses.

[0003] Therefore, it is necessary to provide a method for monitoring the reliability of an intelligent gas pipeline network to ensure the reliable operation of the gas pipeline network. Summary of the Invention

[0004] One or more embodiments of this specification provide a method for monitoring the reliability of an intelligent gas pipeline network. The method is executed based on the intelligent gas safety management platform of the Internet of Things system for monitoring the reliability of the gas pipeline network. The method includes: obtaining a reliability sequence of the gas pipeline network; the reliability sequence includes the reliability of the gas pipeline network at multiple moments; determining a monitoring plan based on the reliability sequence; wherein, the determination of the reliability of the gas pipeline network at each of the multiple moments includes: obtaining the gas transportation characteristics of the gas pipeline network at the target moment; determining the pipe wall wear degree based on the gas transportation characteristics; and determining the reliability of the gas pipeline network at the target moment based on the pipe wall wear degree.

[0005] One or more embodiments of the present specification provide an Internet of Things system for monitoring the reliability of a gas pipeline network. The Internet of Things system includes: a smart gas user platform, a smart gas service platform, a smart gas safety management platform, a smart gas pipeline network equipment sensing network platform, and a smart gas pipeline network equipment object platform. The smart gas pipeline network equipment object platform is used to obtain the gas transportation characteristics of the gas pipeline network at a target time; and transmit the gas transportation characteristics to the smart gas safety management platform through the smart gas pipeline network equipment sensing network platform. The smart gas service platform is used to send the monitoring plan received from the smart gas safety management platform to the smart gas user platform. The smart gas safety management platform is used to: obtain the reliability sequence of the gas pipeline network; the reliability sequence includes the reliability of the gas pipeline network at multiple times; based on the reliability sequence, determine a monitoring plan. Wherein, the determination of the reliability of the gas pipeline network at each of the multiple times includes: obtaining the gas transportation characteristics of the gas pipeline network at a target time; based on the gas transportation characteristics, determining the wall wear degree; based on the wall wear degree, determining the reliability of the gas pipeline network at the target time.

[0006] One or more embodiments of the present specification provide a computer-readable storage medium. The storage medium stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the method for monitoring the reliability of a smart gas pipeline network. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] This specification will be further described by way of exemplary embodiments, and these exemplary embodiments will be described in detail through the drawings. These embodiments are not restrictive. In these embodiments, the same numbers represent the same structures, where:

[0008] Figure 1 is a schematic diagram of an Internet of Things system for monitoring the reliability of a gas pipeline network according to some embodiments of the present specification;

[0009] Figure 2 is an exemplary flowchart of a method for monitoring the reliability of a smart gas pipeline network according to some embodiments of the present specification;

[0010] Figure 3 is an exemplary flowchart of determining the reliability of a gas pipeline network at a target time according to some embodiments of the present specification;

[0011] Figure 4 is a schematic diagram of a wear degree determination model according to some embodiments of the present specification;

[0012] Figure 5 is a schematic diagram of a transportation characteristic prediction model according to some embodiments of the present specification;

[0013] Figure 6 It is an exemplary flowchart for determining the smoothness of reliability shown in some embodiments of this specification. Detailed implementation manners

[0014] To more clearly illustrate the technical solutions of the embodiments of this specification, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some examples or embodiments of this specification. For those of ordinary skill in the art, without creative efforts, this specification can also be applied to other similar scenarios based on these drawings. Unless obvious from the language context or otherwise stated, the same reference numerals in the figures represent the same structure or operation.

[0015] It should be understood that the "system", "device", "unit" and / or "module" used herein is a way to distinguish different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the said words can be replaced by other expressions.

[0016] As shown in this specification and the claims, unless the context clearly indicates an exception, words such as "a", "an", "one" and / or "the" are not specifically singular and may also include plural. Generally speaking, the terms "comprising" and "including" only indicate the inclusion of the clearly identified steps and elements, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0017] Flowcharts are used in this specification to illustrate the operations performed by the systems according to the embodiments of this specification. It should be understood that the operations before or after may not necessarily be executed precisely in sequence. On the contrary, they can be executed in reverse order or simultaneously. At the same time, other operations can also be added to these processes, or one or several operations can be removed from these processes.

[0018] Figure 1 It is a schematic diagram of an Internet of Things system for monitoring the reliability of a gas pipeline network shown in some embodiments of this specification.

[0019] The Internet of Things system is an information processing system that includes some or all of the user platform, service platform, management platform, sensor network platform, and object platform. The user platform is a functional platform for realizing the acquisition of user-perceived information and the generation of control information. The service platform can connect the management platform and the user platform, and plays the functions of sensing information service communication and control information service communication. The management platform can coordinate the connections and collaborations between various functional platforms (such as the user platform and the service platform). The management platform aggregates the information of the Internet of Things operation system and can provide sensing management and control management functions for the Internet of Things operation system. The service platform can connect the management platform and the object platform, and plays the functions of sensing information service communication and control information service communication.

[0020] In some embodiments, the reliable gas pipeline network monitoring Internet of Things system 100 may include a smart gas user platform 110, a smart gas service platform 120, a smart gas safety management platform 130, a smart gas pipeline network equipment sensor network platform 140, and a smart gas pipeline network equipment object platform 150.

[0021] The smart gas user platform 110 may be a platform for interacting with users. The users may be gas users, management personnel, maintenance engineers, etc. For example, the gas users may be ordinary gas users, commercial gas users, industrial gas users, etc. The management personnel may be regulatory users, etc. In some embodiments, the smart gas user platform 110 may be configured as a terminal device. For example, the terminal device may include a mobile device, a tablet computer, etc. or any combination thereof. In some embodiments, the smart gas user platform 110 may be used to receive requests and / or instructions input by users. For example, the smart gas user platform 110 may obtain an instruction for querying the safety information of gas pipeline network equipment through the terminal device. In some embodiments, the smart gas user platform 110 may feedback information to the user through the terminal device. For example, the smart gas user platform 110 may display a warning message (such as the reliability of the gas pipeline network is lower than the threshold) to the user through the terminal device (such as a display). In some embodiments, the smart gas user platform 110 may send the requests and / or instructions input by the user to the smart gas service platform 120 and obtain the corresponding information feedback by the smart gas service platform 120.

[0022] In some embodiments, the intelligent gas user platform 110 may include a gas user sub-platform and a regulatory user sub-platform. The gas user sub-platform corresponds to the intelligent gas usage service sub-platform. For example, the gas user sub-platform may obtain information such as the gas consumption and fees of gas users from the intelligent gas usage service sub-platform and feedback it to the users. Also, for example, the gas user sub-platform may send prompt information, alarm information, etc. regarding gas usage to gas users through terminal devices. The regulatory user sub-platform corresponds to the intelligent supervision service sub-platform. In some embodiments, regulatory users may supervise and manage the safe operation of the entire IoT system through the regulatory user sub-platform to ensure the safe and orderly operation of the IoT system 100 for monitoring the reliability of gas pipelines.

[0023] The intelligent gas service platform 120 may be a platform for communicating users' demands and control information. It connects the intelligent gas user platform 110 and the intelligent gas safety management platform 130. The intelligent gas service platform 120 may obtain data from the intelligent gas safety management platform 130 (such as the intelligent gas data center) and send it to the intelligent gas user platform 110. In some embodiments, the intelligent gas service platform 120 may include processing devices and other components. Among them, the processing device may be a server or a server group.

[0024] In some embodiments, the intelligent gas service platform 120 may include an intelligent gas usage service sub-platform and an intelligent supervision service sub-platform. The intelligent gas usage service sub-platform may be a platform for providing gas usage services to gas users, which corresponds to the gas user sub-platform. For example, the intelligent gas usage service sub-platform may send information such as gas bills, gas usage safety guides, and gas usage anomaly reminders of gas users to the gas user sub-platform, and then feedback it to gas users. The intelligent supervision service sub-platform may be a platform for providing supervision requirements to regulatory users, which corresponds to the regulatory user sub-platform. For example, the intelligent supervision service sub-platform may send information such as the safety management information of gas equipment and the scheduling information of maintenance projects to the regulatory user sub-platform, and regulatory users can conduct inspections, supervision, and guidance.

[0025] The intelligent gas safety management platform 130 may refer to a platform that coordinates and collaborates the connections between various functional platforms, aggregates all the information of the IoT, and provides perception management and control management functions for the IoT operation system. In some embodiments, the intelligent gas safety management platform 130 may include processing devices and other components. Among them, the processing device may be a server or a server group. In some embodiments, the intelligent gas safety management platform 130 may be a remote platform controlled by management personnel, artificial intelligence, or by safety preset rules.

[0026] In some embodiments, the intelligent gas safety management platform 130 may include an intelligent gas pipeline network safety management sub-platform 131 and an intelligent gas data center 132.

[0027] The intelligent gas pipeline network safety management sub-platform 131 may be a platform for analyzing and processing data. In some embodiments, the intelligent gas pipeline network safety management sub-platform 131 may perform two-way interaction with the intelligent gas data center 132. For example, the intelligent gas pipeline network safety management sub-platform 131 may obtain safety management-related data (such as pipeline network safety management data) from the intelligent gas data center 132 for analysis and processing, and send the processing results to the intelligent gas data center 132.

[0028] In some embodiments, the intelligent gas pipeline network safety management sub-platform 131 may include a pipeline network equipment safety monitoring module, a safety emergency management module, a pipeline network risk assessment management module, and a pipeline network geographic information management module. The pipeline network equipment safety monitoring module may be used to process historical safety data and current operating safety data of equipment in the intelligent gas object platform 150. The safety emergency management module may form an emergency treatment plan based on the safety risks of the pipeline network equipment. The pipeline network risk assessment management module may form a pipeline network safety risk assessment according to a preset model, combined with pipeline network basic data and operating data, perform safety risk grading according to the assessment situation, and perform three-dimensional visualization management with different colors combined with the GIS system. The pipeline network geographic information management module may view the geographic information and its own attribute information of pipelines and equipment in real time, providing data support for on-site operations.

[0029] In some embodiments, the intelligent gas data center 132 automatically sends the obtained relevant safety data to the corresponding pipeline network equipment safety monitoring and management module by identifying safety parameter categories (such as gas usage and usage duration); the safety monitoring and management module has preset safety monitoring thresholds, and after exceeding the thresholds, it automatically alarms on the management platform and can choose to automatically push the alarm information to users (such as regulatory users). In some embodiments, the intelligent gas pipeline network safety management sub-platform 131 may further include a pipeline network inspection safety management module, a station inspection safety management module, a pipeline network gas leakage monitoring module, a station gas leakage monitoring module, a station equipment safety monitoring module, a pipeline network simulation management module, etc. It should be noted that the above management modules are not intended to limit the management modules included in the intelligent gas pipeline network safety management sub-platform 131.

[0030] The intelligent gas data center 132 can be used to store and manage all operation information of the Internet of Things system 100 for monitoring the reliability of the gas pipeline network. In some embodiments, the intelligent gas data center 132 can be configured as a storage device (e.g., a database) for storing historical and current gas safety data. For example, the intelligent gas data center 132 can store the safety information of the gas pipeline network, the arrangement records of maintenance personnel, the abnormal information of the gas pipeline network, etc.

[0031] In some embodiments, the intelligent gas safety management platform 130 can interact with the intelligent gas service platform 120 and the intelligent gas pipeline network device sensing network platform 140 respectively through the intelligent gas data center 132. For example, the intelligent gas data center 132 can receive the query instruction of the abnormal information of the gas pipeline network of the maintenance engineering personnel issued by the intelligent gas service platform 120 (e.g., the intelligent supervision service sub-platform), and send the query result to the intelligent gas service platform 120. Also for example, the intelligent gas data center can send an instruction to obtain gas-related data (e.g., gas transportation data) of the gas pipeline network to the intelligent gas pipeline network device sensing network platform 140, and receive the gas transportation data uploaded by the intelligent gas pipeline network device sensing network platform.

[0032] The intelligent gas pipeline network device sensing network platform 140 can be a functional platform for managing sensing communication. In some embodiments, the intelligent gas pipeline network device sensing network platform 140 can connect the intelligent gas safety management platform 130 and the intelligent gas object platform 150 to realize the functions of sensing communication of perception information and sensing communication of control information.

[0033] In some embodiments, the intelligent gas pipeline network device sensing network platform 140 can be used to realize functions such as network management, protocol management, instruction management, and data parsing.

[0034] The intelligent gas object platform 150 can be a functional platform for generating perception information. For example, the intelligent gas object platform 150 can generate the safe operation information of the gas pipeline network (e.g., the abnormal information of the gas pipeline network), and upload it to the intelligent gas data center 132 through the intelligent gas pipeline network device sensing network platform 140.

[0035] In some embodiments, the intelligent gas object platform 150 can include various gas devices (e.g., gas pipeline network devices) and monitoring devices that can be configured to obtain the operation information of the gas devices. For example, the intelligent gas device object platform 150 can obtain the gas transportation characteristics such as gas flow rate, pressure, and temperature of the gas pipeline network devices in real time through gas flow meters, pressure sensors, temperature sensors, etc., and send them to the intelligent gas data center 132 through the intelligent gas pipeline network device sensing network platform 140.

[0036] Some embodiments of this specification are based on the Internet of Things system 100 for reliable monitoring of gas pipe networks, which can form a closed-loop operation of intelligent gas safety management information among pipe network equipment, gas operators, gas users, and regulatory users, realize the informatization and intelligence of pipe network safety management, and ensure the effective management of gas safety.

[0037] It should be noted that the Internet of Things system 100 for reliable monitoring of gas pipe networks is provided only for illustrative purposes and is not intended to limit the scope of this specification. For those of ordinary skill in the art, various modifications or changes can be made according to the description of this specification. For example, the Internet of Things system 100 for reliable monitoring of gas pipe networks can include one or more other suitable components to achieve similar or different functions. However, the changes and modifications will not deviate from the scope of this specification.

[0038] Figure 2 is an exemplary flowchart of the method for reliable monitoring of intelligent gas pipe networks shown in some embodiments of this specification. As Figure 2 shown, process 200 includes the following steps. In some embodiments, process 200 can be executed by the intelligent gas safety management platform 130.

[0039] S210, obtain the reliability sequence of the gas pipe network; the reliability sequence includes the reliability of the gas pipe network at multiple moments.

[0040] Reliability is used to represent the probability that the gas pipe network can maintain safe operation. Reliability can be presented in the form of a numerical value or a percentage. For example, a reliability of 1 or 100% means that the probability of the gas pipe network maintaining safe operation is the highest, and a reliability of 0.6 or 60% means that the probability of the gas pipe network maintaining safe operation is relatively low. As the operation time of the gas pipe network increases, the reliability of the gas pipe network may decrease.

[0041] In some embodiments, the reliability of the gas pipe network can be determined according to the historical maintenance situation of the gas pipe network or the remaining service life of the pipeline. For example, each time the number of gas leaks in the gas pipe network in the historical maintenance record increases by one, the reliability of the gas pipe network decreases by 0.1; when the remaining service life of the pipeline decreases by 10%, the reliability of the gas pipe network decreases by 0.1. The numerical value of the reliability decrease can be set manually according to the historical usage experience of the gas pipe network.

[0042] In some embodiments, the reliability of the gas pipe network can also be determined according to the gas transportation characteristics. For more information about gas transportation characteristics and determining the reliability of the gas pipe network according to gas transportation characteristics, reference can be made to Figure 3 .

[0043] A reliability sequence is a sequence composed of reliabilities at multiple moments. In some embodiments, the reliability sequence can be presented in vector form, and each vector element can be the reliability corresponding to a fixed moment. For example, the reliability sequence can be expressed as (0.8, 0.78, 0.75, 0.73), representing that the reliability of the gas pipeline network at moment A is 0.8, at moment B is 0.78, at moment C is 0.75, and at moment D is 0.73. Among them, the reliabilities in the reliability sequence are arranged in chronological order, that is, moment A is before moment B, moment B is before moment C, and moment C is before moment D. The interval between different moments can be set artificially, and the intervals can be the same or different. For example, the time interval for maintenance personnel to conduct regular inspections, checks, and maintenance can be used as the interval between the moments corresponding to different reliabilities.

[0044] Figure 3 is an exemplary flowchart for determining the reliability of a gas pipeline network at a target moment according to some embodiments of this specification. As Figure 3 shown, process 300 includes the following steps.

[0045] S310, obtain the gas transportation characteristics of the gas pipeline network at the target moment.

[0046] The target moment can be any moment during the operation of the gas pipeline network. For example, the target moment can be 16:00 every afternoon. The target moment can be set artificially. For example, the moment when the gas consumption peak occurs can be set as the target moment.

[0047] The gas transportation characteristics refer to the information related to gas transportation during the transportation of gas. For example, the gas transportation characteristics can include gas component information, transportation pressure information of the gas pipeline network, gas transmission flow information, gas transmission temperature information, etc.

[0048] In some embodiments, the gas transmission flow information of the gas pipeline network equipment, the transportation pressure information of the gas pipeline network, the gas transmission temperature information and other gas transportation characteristics can be obtained in real time through gas flow meters, pressure sensors, temperature sensors, etc. in the intelligent gas equipment object platform 150. The gas component information refers to the components contained in the gas. For example, it can include methane, ethane, propane, hydrogen sulfide, carbon dioxide, water vapor, solid particles, etc. The gas component information can be detected by sampling at a sampling port.

[0049] S320, determine the degree of pipe wall wear based on the gas transportation characteristics.

[0050] The pipe wall wear degree refers to the degree of wear of the pipes in the gas pipeline network, which is used to reflect the wear condition of the pipes in the gas pipeline network. A value between 0 and 1 can be used to reflect the magnitude of the pipe wall wear degree. The higher the value, the greater the pipe wall wear degree and the more serious the wear condition of the pipes in the gas pipeline network. The pipe wall wear degree can be obtained in various ways. For example, it can be judged based on artificial experience, or the specific value of the pipe wall wear degree can be determined through a pipe wall wear degree table. The pipe wall wear degree table includes historical gas transportation characteristics and the corresponding pipe wall wear degree values. For example, the gas transportation characteristic is 2.5 MPa < transmission pressure ≤ 4.0 MPa, high-pressure transmission for 1 year, and the corresponding pipe wall wear degree value is 0.1; 2.5 MPa < transmission pressure ≤ 4.0 MPa, high-pressure transmission for 2 years, and the corresponding pipe wall wear degree value is 0.15.

[0051] In some embodiments, the pipe wall wear degree can be determined based on the gas transportation characteristics through a wear degree determination model. In some embodiments, the wear degree determination model can be a machine learning model. For more information about the wear degree determination model, please refer to Figure 4 .

[0052] S330. Determine the reliability of the gas pipeline network at the target time based on the pipe wall wear degree.

[0053] In some embodiments, the reliability of the gas pipeline network at the target time can be determined according to the reliability preset rules. For example, the reliability preset rules can be to determine the reliability of the gas pipeline network at the target time based on the occurrence frequencies of gas leakage or safety accidents corresponding to different historical pipe wall wear degrees. Exemplarily, if the pipe wall wear degree of the gas pipeline network at the target time is 0.5 and the gas leakage frequency when the historical pipe wall wear degree is 0.5 is 0.7, then the reliability of the gas pipeline network at the target time can be determined as 1 - 0.7 = 0.3.

[0054] S220. Determine the monitoring plan based on the reliability sequence.

[0055] The monitoring plan refers to the monitoring measures taken for the gas pipeline network parameters to ensure the safe operation of the gas pipeline network. For example, the monitoring plan can include the frequency of internal pipe cleaning and gas leakage detection, the lubrication frequency of the rotating parts of the equipment installed on the gas pipeline, and the accuracy and precision of the monitoring equipment.

[0056] In some embodiments, after obtaining the reliability sequence of the gas pipeline network, a monitoring plan can be determined according to the trend of the change in reliability over time in the reliability sequence. For example, the sequence of reliabilities corresponding to a certain point in the gas pipeline network at the same intervals of time A, time B, time C, time D, and time E is (0.95, 0.94, 0.93, 0.92, 0.8). If the downward trend of the reliability of the gas pipeline network from time D to time E is obvious, the inspection frequency of this point can be increased to determine whether maintenance is required.

[0057] In some embodiments, the stability of the reliability can be determined based on the reliability sequence; and a monitoring plan can be determined based on the stability of the reliability.

[0058] The stability can reflect the magnitude of the change in reliability per unit time. The greater the change in reliability per unit time, the greater the stability.

[0059] In some embodiments, the stability of the reliability can be determined by comparing the variances of the reliabilities corresponding to multiple moments in multiple reliability sequences. The greater the variance gap between the reliability sequences, the worse the stability of the reliability. In some embodiments, the reliability data in the reliability sequence can also be fitted, and the greater the change in the curve slope, the worse the stability of the reliability.

[0060] In some embodiments, a stability threshold of the reliability can be set. When the stability is lower than the stability threshold, the intelligent gas safety management platform 130 automatically alarms and can automatically push the warning information to gas users through the gas user sub-platform.

[0061] Figure 6 is an exemplary flowchart for determining the stability of the reliability according to some embodiments of this specification. As Figure 6 shown, process 600 includes the following steps. In some embodiments, process 600 can be executed based on the intelligent gas safety management platform 130.

[0062] S610, predict the future reliability at at least one future moment based on the reliability sequence.

[0063] Future reliability refers to the reliability corresponding to a time after the time corresponding to the current reliability sequence. For example, for the reliability sequence 1 (0.9, 0.89, 0.88), the corresponding times of the reliabilities are 2022.02.26, 2022.03.26, 2022.04.26 respectively. The future reliability can be the reliability corresponding to a time after 2022.04.26. The future reliability at a future time can be predicted in various ways. For example, based on the reliabilities in the current reliability sequence, the future reliability can be predicted by curve fitting. In some embodiments, the future reliability can be predicted by a time series model. In some embodiments, the time series model is a machine learning model. The time series model can process the reliabilities in the current reliability sequence and output the future reliability.

[0064] S620, expand the future reliability at at least one future time to the reliability sequence to obtain a new reliability sequence.

[0065] Exemplarily, the reliability sequence obtained based on the reliabilities at three times collected on 2022.04.01, 2022.05.01, and 2022.06.01 is reliability sequence 2, which can be expressed as (0.9, 0.85, 0.8). Taking reliability sequence 2 as the input of the model, based on the time series model, the predicted reliabilities at future times 2022.07.01 and 2022.08.01 are 0.72 and 0.7 respectively. 0.72 and 0.7 can be expanded to reliability sequence 2 to obtain a new reliability sequence 2' (0.9, 0.85, 0.8, 0.72, 0.7). The number of reliabilities expanded into the new sequence is not limited and can be set according to the actual situation.

[0066] S630, determine the smoothness of the reliability based on the new reliability sequence.

[0067] In some embodiments, the smoothness of the reliability can be determined based on the smoothness preset rule and the slope change rate of the reliability curve corresponding to the new reliability sequence. Here, the expanded new reliability sequence in S620 is taken as an example for illustration. The obtained new reliability sequence 2' (0.9, 0.85, 0.8, 0.72, 0.7), the slope of the curve corresponding to the reliability sequence before expansion is (0.9 - 0.8) ÷ 2 = 0.05, and the slope between the reliabilities 0.8 and 0.72 in the new reliability sequence is (0.8 - 0.72) ÷ 1 = 0.08. The slope change rate is (0.08 - 0.05) ÷ 0.05 × 100% = 60%.

[0068] In some embodiments, the smoothness preset rule may be that the rate of change of the slope is greater than a preset smoothness threshold, then it is determined that the smoothness is abnormal. The preset smoothness threshold can be set manually. For example, the preset smoothness threshold can be set to 50%. In some embodiments, different levels of smoothness can be divided according to the range in which the rate of change of the slope of the reliability curve lies. For example, when the rate of change of the slope is between 0 - 30%, it corresponds to level 1 smoothness, indicating that the smoothness of the reliability is good; when the rate of change of the slope is between 30 - 60%, it corresponds to level 2 smoothness, indicating that the smoothness of the reliability may be abnormal; when the rate of change of the slope is above 60%, it corresponds to level 3 smoothness, indicating that the smoothness of the reliability is poor. Exemplarily, if the rate of change of the slope corresponding to the reliability curve of the above-mentioned new reliability sequence 2' is 60%, it indicates that the smoothness of the reliability may be abnormal.

[0069] In some embodiments, warning information can also be sent to gas users in various ways according to the level of smoothness. For example, when the smoothness is level 1, it is automatically pushed to gas users through the gas user sub-platform; when the smoothness is above level 2, warning information is transmitted to gas users in the form of a phone call through means such as the intelligent customer service of the intelligent gas service platform 120 to remind gas users to arrange for repairs.

[0070] In some embodiments, the smoothness of the reliability in the reliability sequence can be calculated by weighted summing the reliabilities in the reliability sequence. For example, for the reliability sequence (R 1 , R 2 , R 3 , R 4 ), the smoothness S of its reliability is:

[0071] S = R 1 ×W 1 +R 2 ×W 2 +R 3 ×W 3 +R 4 ×W 4

[0072] Wherein, R 1 , R 2 , R 3 , R 4 represent the reliabilities at multiple moments, and W 1 , W 2 , W 3 , W 4 represent the weights corresponding to R 1 , R 2 , R 3 , R 4Respectively corresponding smoothness weights. In some embodiments, the smoothness weight of each reliability is related to the confidence level of the pipe wall wear degree corresponding to the reliability. The higher the confidence level of the pipe wall wear degree of the reliability, the greater the corresponding smoothness weight value. For more information about the confidence level of pipe wall wear, please refer to Figure 4 .

[0073] One or more embodiments of the present specification predict multiple future reliabilities, expand the predicted future reliabilities to the original reliability sequence, calculate the smoothness based on the expanded reliability sequence, and can obtain the operation safety situation of the gas pipeline network in advance through the obtained smoothness information, effectively preventing safety accidents from occurring; by associating the smoothness calculation result with the confidence level of pipe wall wear, the accuracy of the smoothness calculation result can be further ensured.

[0074] In some embodiments, the monitoring plan can be determined based on the smoothness of the reliability. For example, when the smoothness is poor, the intelligent gas safety management platform 130 can send an instruction to increase the acquisition accuracy or monitoring frequency to the intelligent gas object platform 150 through the intelligent gas pipeline network equipment sensing network platform 140 to further ensure the operation safety of the gas pipeline network.

[0075] In one or more embodiments of the present specification, by obtaining the reliability sequence of the gas pipeline network and determining the monitoring plan based on the reliability sequence, the change of the safe operation reliability of the gas pipeline network over time can be understood in a timely manner, potential safety hazards can be identified, key attention can be paid to the points where potential safety hazards may exist, and a more targeted monitoring plan can be determined, effectively ensuring the safe operation of the gas pipeline network.

[0076] Figure 4 It is a schematic diagram of the wear degree determination model shown in some embodiments of the present specification.

[0077] In some embodiments, the wear degree determination model 440 can process the gas transportation characteristics of the gas pipeline network equipment terminal of the intelligent gas object platform to determine the pipe wall wear degree 470 of the point to be measured. In some embodiments, the wear degree determination model 440 can be a machine learning model.

[0078] In some embodiments, the gas pipeline network includes several points to be measured. In some embodiments, the gas transportation characteristics may include the upstream gas transportation characteristics 410 of the upstream point of the point to be measured, the downstream gas transportation characteristics 430 of the downstream point, and the gas component information 420 of the point to be measured. For more information about the gas transportation characteristics, please refer to Figure 2 .

[0079] The point to be measured refers to the point where the gas pipeline needs to be monitored. The points to be measured can be set based on manual experience or historical maintenance data. For example, multiple points to be measured can be set in areas with a high historical leakage frequency, or multiple points to be measured can be set in densely populated areas. The number of points to be measured can be set according to the actual situation.

[0080] The upstream point and the downstream point are other points located upstream and downstream of the current point to be measured during gas transportation. The determination of upstream and downstream is related to the gas transportation direction. For example, the upstream point can be a point on the gas pipeline through which the gas passes before being transported to the current point to be measured, and the downstream point can be a point on the gas pipeline through which the gas passes after being transported to the current point to be measured. Any point located upstream of the current point to be measured can be selected as the upstream point, and any point located downstream of the current point to be measured can be selected as the downstream point. The number of upstream points and downstream points can be one or multiple.

[0081] In some embodiments, the wear degree determination model 440 can be obtained through training. The first training sample can include the upstream gas transportation characteristics of historical sample points, the downstream gas transportation characteristics of historical sample points, and the gas component information of historical sample points. The first label of the first training sample can include the pipe wall wear degree of the sample points. The upstream gas transportation characteristics of the first training sample in history, the downstream gas transportation characteristics of history, and the historical gas component information can be input into the wear degree determination model 440. Based on the pipe wall wear degree output by the wear degree determination model 440 and the first label, a first loss function is constructed, and the parameters of the initial wear degree determination model are iteratively updated based on the loss function until the first preset condition is satisfied, the parameters in the wear degree determination model 440 are determined, and the trained wear degree determination model is obtained. The first preset condition can include but is not limited to the convergence of the first loss function, the training cycle reaching the threshold, etc.

[0082] As Figure 4 shown, the wear degree determination model 440 can include a hidden feature determination layer 441 and a wear degree determination layer 443.

[0083] The hidden feature contains the depth information characteristics of gas transportation and can be represented by a feature vector. The processing process of the hidden feature determination layer is essentially a process of extracting depth information. For example, the hidden feature obtained through the hidden feature determination layer can include the corresponding relationship characteristics between the transportation pressure information of the gas pipeline network, the gas transportation flow information, the gas transportation temperature information, the gas component information, and the pipe wall wear degree, and can also include the corresponding relationship characteristics between the upstream gas transportation characteristics and the downstream gas transportation characteristics.

[0084] The hidden feature determination layer 441 can process the upstream gas transportation feature 410 of the upstream point of the point to be measured, the downstream gas transportation feature 430 of the downstream point, and the gas composition information 420 of the point to be measured to determine the hidden feature 442. For example, the input of the hidden feature determination layer 441 may include the upstream gas transportation feature (such as the gas transmission flow rate of 300 m 3 / h, the water vapor content of 20 mg / m 3 , the solid particle content of 0.5 mg / m 3 , and the gas transportation pressure of 0.2 MPa), the downstream gas transportation feature (such as the gas transmission flow rate of 350 m 3 / h, the water vapor content of 20 mg / m 3 , the solid particle content of 0.5 mg / m 3 , and the gas transportation pressure of 0.25 MPa). The output hidden feature may be (such as 50, 0.05, 20, 0.5, 0.2), representing that the difference in gas transmission flow rate between the upstream and downstream of the point to be measured is 50 m 3 / h, the difference in gas transportation pressure between the upstream and downstream is 0.05 MPa, the water vapor content of the point to be measured is 20 mg / m 3 , the solid particle content is 0.5 mg / m 3 , and the corresponding pipe wall wear degree is 0.2.

[0085] The dimension of the hidden feature refers to the number of features included in the feature vector corresponding to the hidden feature. For example, if the hidden feature contains 3 features, the hidden feature is a 3-dimensional hidden feature. The dimension of the hidden feature often affects the result of the model. For example, if the dimension of the hidden feature is too small, the obtained hidden feature cannot fully represent the relationship between the true gas transportation feature and the wear degree, and the wear degree determination model may be difficult to converge; if the dimension of the hidden feature is too large, a larger amount of training samples is required when training the wear degree determination model, which may cause redundancy in the training process.

[0086] Therefore, the dimension of the hidden feature can be preset manually. For example, according to the historical training results of the model, the dimension of the hidden feature is preset to 4 dimensions. In some embodiments, the hidden feature can be dynamically adjusted based on the training effect of the model. In some embodiments, the initial dimension of the hidden feature can be determined based on the number of model training samples. For example, when the number of model training samples is small, the initial dimension of the hidden feature can be increased to obtain more model training samples; when the number of model training samples is large, the initial dimension of the hidden feature can be restricted to avoid redundancy in the training process. The restriction on the dimension of the hidden feature can be flexibly changed according to the number of model samples to avoid the adverse effects caused by too large or too small dimensions of the hidden feature on the training effect of the model. For more content about model training, please refer to the following text.

[0087] One or more embodiments of the present specification determine the dimension of the latent feature based on the number of model training samples, and the dimension of the latent feature can also be dynamically adjusted based on the model training effect, which can avoid poor model training effects caused by inappropriate latent feature dimensions.

[0088] In some embodiments, the wear degree determination layer 443 is configured to determine the pipe wall wear degree 470 based on the latent feature 442. In some embodiments, the latent feature 442 output by the latent feature determination layer 441 can be used as the input of the wear degree determination layer 443, and the wear degree determination layer 443 can process the latent feature 442 and output the pipe wall wear degree 470. For example, the wear degree determination layer 443 processes a 3-dimensional latent feature and outputs a pipe wall wear degree of 0.2.

[0089] The wear degree determination model 440 can be obtained by training the latent feature determination layer 441 and the wear degree determination layer 443. The second training sample may include the upstream gas transportation characteristics of the historical sample points, the downstream gas transportation characteristics of the historical sample points, and the gas composition information of the historical sample points. The second label of the second training sample may include the pipe wall wear degree of the sample points. The upstream gas transportation characteristics, downstream gas transportation characteristics, and historical gas composition information of the second training sample can be input into the latent feature determination layer 441, the output of the latent feature determination layer 441 can be input into the wear degree determination layer 443, a second loss function can be constructed based on the output of the wear degree determination layer 443 and the second label, and the parameters of the initial latent feature determination layer and the initial wear degree determination layer can be iteratively updated based on the second loss function until the second preset condition is met, and the parameters in the latent feature determination layer 441 and the wear degree determination layer 443 are determined to obtain a trained wear degree determination model. The second preset condition may include but is not limited to the convergence of the second loss function, the training cycle reaching a threshold, etc.

[0090] One or more embodiments of the present specification determine the pipe wall wear degree of the point to be measured through the wear degree determination model based on the upstream gas transportation characteristics, downstream gas transportation characteristics, and gas composition information of the point to be measured, which can make the predicted pipe wall wear degree more accurate, so as to be able to timely discover problems such as corrosion and leakage in the gas pipeline network and reduce potential safety hazards.

[0091] In some embodiments, the input of the wear degree determination model may further include the distance 450 between the point to be measured and the upstream point, and the distance 460 between the point to be measured and the downstream point. For example, the wear degree determination model 440 processes the upstream gas transportation characteristics such as (gas transportation flow rate 300 m 3 / h, water vapor content 20 mg / m 3 , solid particle content 0.5 mg / m 3 , gas transportation pressure 0.2 MPa), downstream gas transportation characteristics such as (gas transportation flow rate 350 m 3 / h, water vapor content 20 mg / m 3 , solid particle content 0.5 mg / m 3 , the gas transportation pressure is 0.25 MPa), and the distance between the point to be measured and the upstream point (such as 50 m), the distance between the point to be measured and the downstream point (such as 100 m) are processed, and the pipe wall wear degree (such as 0.25) is output.

[0092] In some embodiments, the second training sample may further include the distance between the point to be measured of the historical sample point and the upstream point, and the distance between the point to be measured of the historical sample point and the downstream point.

[0093] In some embodiments, the output of the wear degree determination model 440 may further include the pipe wall wear degree confidence 480.

[0094] The wear degree confidence is the credibility of the predicted value of the pipe wall wear degree output by the wear degree determination model. For example, the higher the consistency between the pipe wall wear degree output by the wear degree confidence and the pipe wall sample label, the higher the wear degree confidence.

[0095] When predicting the pipe wall wear degree through the wear degree determination model in one or more embodiments of this specification, in addition to the gas transportation characteristics, the distances between the upstream point and the downstream point are also considered, making the pipe wall wear degree output by the wear degree determination model closer to the actual situation; through the wear degree confidence output by the wear degree determination model, it is judged whether the pipe wall wear degree predicted by the wear degree determination model is accurate, the quality of the wear degree determination model is evaluated based on the wear degree confidence, and the prediction result of the wear degree determination model is made closer to the true value through continuous training according to the evaluation result, so as to achieve more accurate model prediction.

[0096] In some embodiments, the downstream gas transportation characteristics 430 may be determined based on the upstream gas transportation characteristics 410 through a transportation characteristics prediction model. The transportation characteristics prediction model may be a machine learning model.

[0097] Figure 5 is a schematic diagram of the transportation characteristics prediction model shown in some embodiments of this specification. In some embodiments, the transportation characteristics prediction model 500 is used to determine the downstream gas transportation characteristics 430 based on the hidden characteristics 442 output by the hidden characteristics determination layer 441 of the wear degree determination model 440 and the upstream gas transportation characteristics 410. In some embodiments, the hidden characteristics 442 output by the hidden characteristics determination layer 441 and the upstream gas characteristics 410 may be used as the input of the transportation characteristics prediction model 500, and the transportation characteristics prediction model 500 may process the hidden characteristics 442 and the upstream gas characteristics 410 and output the downstream gas transportation characteristics 430. For example, the transportation characteristics prediction model 500 takes the upstream gas transportation characteristics such as (gas transmission flow rate 300 m 3 / h, water vapor content 20 mg / m3 , the solid particle content is 0.5 mg / m 3 , the gas transportation pressure is 0.2 MPa), and the hidden feature 442 is processed to output the upstream gas transportation features such as (gas transportation flow rate 350 m 3 / h, the water vapor content is 20 mg / m 3 , the solid particle content is 0.5 mg / m 3 , the gas transportation pressure is 0.25 MPa).

[0098] In some embodiments, the transportation feature prediction model 500 can be obtained through training. The third training sample can include the upstream gas transportation features of historical sample points and the hidden features of historical sample points. Among them, the hidden features of historical sample points can be obtained based on the output of the hidden feature determination layer in the wear degree determination model. The third label of the third training sample can include the actual downstream gas transportation features. The historical upstream gas transportation features and historical hidden features of the third training sample can be input into the transportation feature prediction model 500, and a third loss function is constructed based on the downstream gas transportation features output by the transportation feature prediction model 500 and the third label. The parameters of the initial transportation feature prediction model are iteratively updated based on the third loss function until the third preset condition is satisfied, and the parameters in the transportation feature prediction model 500 are determined to obtain the trained transportation feature prediction model. The third preset condition can include but is not limited to the convergence of the third loss function, the training cycle reaching the threshold, etc.

[0099] In some embodiments, the wear degree determination model 440 can be obtained based on joint training with the transportation feature prediction model 500. The fourth training sample includes the upstream gas transportation features of historical sample points, the downstream gas transportation features of historical sample points, the gas component information of historical sample points, and the hidden features of historical sample points. The fourth label of the fourth training sample can include the pipe wall wear degree and the true value of the downstream gas features.

[0100] In some embodiments, the pipe wall wear degree output by the wear degree determination model can be directly used as the fourth training label of the fourth training sample.

[0101] During joint training, the historical upstream gas transportation characteristics, historical downstream gas transportation characteristics, and historical gas composition information of the fourth training sample can be input into the hidden feature determination layer 441 of the wear degree determination model 440. The output of the hidden feature determination layer 441 is input into the wear degree determination layer 443. Based on the output of the wear degree determination layer 443 and the pipe wall wear degree in the fourth label, the first loss term of the fourth loss function is constructed. The historical upstream gas transportation characteristics and historical hidden features are input into the transportation feature prediction model 500. Based on the downstream gas transportation characteristics output by the transportation feature prediction model 500 and the true value of the downstream gas characteristics in the fourth label, the second loss term of the fourth loss function is constructed. Then, based on the fourth loss function, the parameters of the initial hidden feature determination layer, the initial wear degree determination layer, and the initial transportation feature prediction model are iteratively updated until the fourth preset condition is met. The parameters in the hidden feature determination layer 441, the wear degree determination layer 443, and the transportation feature prediction model 500 are determined, and the trained wear degree determination model and transportation feature prediction model are obtained. The fourth preset condition can include, but is not limited to, the convergence of the fourth loss function, the training cycle reaching a threshold, etc.

[0102] In some embodiments, when the short-term reliability smoothness is low, it may be that the training effect is poor, which affects the pipe wall wear degree output by the wear degree determination model, and the confidence level of the pipe wall wear degree is not high. At this time, the weights of the first loss term and the second loss term of the fourth loss function can be adjusted. For example, the weight of the loss term corresponding to the gas transportation characteristics can be increased. The weight adjustment method of the first loss term or the second loss term can be preset based on historical training results. In some embodiments, the weight adjustment amplitude is related to the reliability smoothness. For example, the lower the reliability smoothness, the greater the adjustment amplitude. Exemplarily, the fourth loss function is:

[0103] LOSS=l 1 ×W a +l 2 ×W b

[0104] where l 1 and l 2 are the error losses of the first loss term and the second loss term respectively; W a and W b are reference weights. Correspondingly, when the decline amplitude of the reliability smoothness determined according to the predicted pipe wall wear degree exceeds the smoothness error threshold (e.g., 10%) within a short period (e.g., within 1 hour), then according to historical training experience, the reference weight W b of the second loss term is adjusted accordingly. For example, for every 10% that the decline amplitude of the reliability smoothness exceeds the smoothness error threshold, W b is increased by 10%.

[0105] In one or more embodiments of the present specification, a wear degree determination model is obtained through joint training. After adding a transportation feature prediction model, the training can be effectively improved, making the model prediction results more accurate. By adjusting the first loss term and the second loss term, the abnormality of smoothness caused by poor model training can be corrected, and the misjudgment of smoothness abnormality can be reduced.

[0106] In some embodiments, the input of the transportation feature prediction model 500 and the hidden feature determination layer 441 may further include the distance 450 between the point to be measured and the upstream point, and the distance 460 between the point to be measured and the downstream point. The above distances can be determined according to the actual scale with reference to the pipeline laying diagram of the pipeline network simulation module of the intelligent gas pipeline network safety management sub-platform. For example, the transportation feature prediction model 500 processes the upstream gas transportation pressure of 0.2 MPa, the hidden feature 442, the distance between the point to be measured and the upstream point of 50 m, and the distance between the point to be measured and the downstream point of 100 m, and outputs a downstream gas transportation pressure of 0.25 MPa. In some embodiments, the fourth training sample may further include the distance between the point to be measured and the upstream point of the historical sample point, and the distance between the point to be measured and the downstream point of the historical sample point.

[0107] In one or more embodiments of the present specification, when determining the hidden feature and the downstream gas transportation feature, the distances between the point to be measured and the upstream point and the downstream point are further considered, which can make the information corresponding to the hidden feature and the downstream gas transportation feature more real and comprehensive, so that the model prediction results are more accurate and reliable.

[0108] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only an example and does not constitute a limitation to the present specification. Although not explicitly stated here, those skilled in the art may make various modifications, improvements, and corrections to the present specification. Such modifications, improvements, and corrections are proposed in the present specification, so such modifications, improvements, and corrections still belong to the spirit and scope of the exemplary embodiments of the present specification.

[0109] Meanwhile, the present specification uses specific terms to describe the embodiments of the present specification. Such as "one embodiment", "an embodiment", and / or "some embodiments" mean a certain feature, structure, or characteristic related to at least one embodiment of the present specification. Therefore, it should be emphasized and noted that the "an embodiment" or "one embodiment" or "an alternative embodiment" mentioned twice or more at different positions in the present specification does not necessarily refer to the same embodiment. In addition, certain features, structures, or characteristics in one or more embodiments of the present specification can be combined appropriately.

[0110] In addition, unless explicitly stated in the claims, the order of the processing elements and sequences, the use of numerical and alphabetical characters, or the use of other names described in this specification are not used to limit the order of the processes and methods in this specification. Although some currently useful embodiments of the invention are discussed through various examples in the above disclosure, it should be understood that such details are for illustrative purposes only. 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 conform to the essence 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 through software solutions, such as installing the described system on existing servers or mobile devices.

[0111] Similarly, it should be noted that, in order to simplify the presentation of the disclosure in this specification and thus help the understanding of one or more embodiments of the invention, in the previous description of the embodiments of this specification, sometimes multiple features are merged into one embodiment, drawing, or description thereof. However, this disclosure method does not mean that the features required by the subject matter of this specification are more than those mentioned in the claims. In fact, the features of the embodiments are fewer than all the features of the individual embodiments disclosed above.

[0112] In some embodiments, numbers are used to describe the components and the quantity of attributes. It should be understood that such numbers used for the description of the embodiments are modified by the modifiers "about", "approximate", or "substantially" in some examples. Unless otherwise stated, "about", "approximate", or "substantially" indicate that the said numbers allow a variation of ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, and such approximate values may change according to the characteristics required by individual embodiments. In some embodiments, the numerical parameters should consider the specified significant digits and adopt the method of retaining the general number of digits. Although the numerical ranges and parameters used in some embodiments of this specification to confirm the breadth of their scope are approximate values, in specific embodiments, the setting of such numerical values is as precise as possible within the feasible range.

[0113] For each patent, patent application, patent application publication, and other materials cited in this specification, such as articles, books, specifications, publications, documents, etc., their entire contents are hereby incorporated into this specification by reference. Except for the application history documents that are inconsistent with or conflict with the content of this specification, and also except for the documents that limit the broadest scope of the claims of this specification (currently or subsequently appended to this specification). It should be noted that if there are inconsistencies or conflicts between the descriptions, definitions, and / or the use of terms in the supplementary materials of this specification and the content described in this specification, the descriptions, definitions, and / or the use of terms in this specification shall prevail.

[0114] Finally, it should be understood that the embodiments described in this specification are only used 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 regarded as consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly presented and described in this specification.

Claims

1. A method for monitoring the reliability of an intelligent gas pipeline network, characterized in that, the method is executed based on an intelligent gas safety management platform of an Internet of Things system for monitoring the reliability of a gas pipeline network, and the method includes: Obtaining a reliability sequence of the gas pipeline network; the reliability sequence includes the reliability of the gas pipeline network at multiple moments; Determining a monitoring plan based on the reliability sequence; wherein, the determination of the reliability of the gas pipeline network at each of the multiple moments includes: Obtaining the gas transportation characteristics of the gas pipeline network at the target moment; Determining the pipe wall wear degree based on the gas transportation characteristics; wherein, the determination of the pipe wall wear degree based on the gas transportation characteristics includes: determining the pipe wall wear degree of the to-be-detected point based on the gas transportation characteristics through a wear degree determination model; the wear degree determination model is a machine learning model; the gas pipeline network includes one or more of the to-be-detected points; the gas transportation characteristics include the upstream gas transportation characteristics of the upstream point of the to-be-detected point, the downstream gas transportation characteristics of the downstream point, and the gas component information of the to-be-detected point; the wear degree determination model includes a hidden feature determination layer and a wear degree determination layer, and the wear degree determination model and the transportation feature prediction model are obtained synchronously through joint training. The transportation feature prediction model is used to determine the downstream gas transportation characteristics based on the upstream gas transportation characteristics and the hidden features, and the transportation feature prediction model is a machine learning model; the hidden feature is a feature vector containing the deep information characteristics of gas transportation, and the hidden feature is obtained based on the hidden feature determination layer; the hidden feature includes the relationship characteristics corresponding to the transportation pressure information, gas transmission flow information, gas transmission temperature information of the gas pipeline network, and the relationship between the gas component information and the pipe wall wear degree, as well as the relationship characteristics between the upstream gas transportation characteristics and the downstream gas transportation characteristics; Determining the reliability of the gas pipeline network at the target moment based on the pipe wall wear degree.

2. According to the method of claim 1, the Internet of Things system for monitoring the reliability of a gas pipeline network further includes: An intelligent gas user platform, an intelligent gas service platform, an intelligent gas pipeline network equipment sensing network platform, and an intelligent gas pipeline network equipment object platform; The intelligent gas pipeline network equipment object platform is used to obtain the gas transportation characteristics of the gas pipeline network at the target moment; And transmit the gas transportation characteristics to the intelligent gas safety management platform through the intelligent gas pipeline network equipment sensing network platform; The method further includes: The intelligent gas service platform sends the monitoring plan received from the intelligent gas safety management platform to the intelligent gas user platform.

3. According to the method of claim 1, characterized in that, the determination of the monitoring plan based on the reliability sequence includes: Determining the smoothness of the reliability based on the reliability sequence; Determining the monitoring plan based on the smoothness of the reliability.

4. An Internet of Things system for monitoring the reliability of a gas pipeline network, characterized in that, The Internet of Things system includes: a smart gas user platform, a smart gas service platform, a smart gas safety management platform, a smart gas pipeline network equipment sensing network platform, and a smart gas pipeline network equipment object platform; The smart gas pipeline network equipment object platform is used to obtain the gas transportation characteristics of the gas pipeline network at a target moment; and transmit the gas transportation characteristics to the smart gas safety management platform through the smart gas pipeline network equipment sensing network platform; The smart gas service platform is used to send the monitoring plan received from the smart gas safety management platform to the smart gas user platform; The smart gas safety management platform is used for: Obtaining the reliability sequence of the gas pipeline network; the reliability sequence includes the reliability of the gas pipeline network at multiple moments; Determining a monitoring plan based on the reliability sequence; Wherein, the determination of the reliability of the gas pipeline network at each of the multiple moments includes: Obtaining the gas transportation characteristics of the gas pipeline network at a target moment; Determining the pipe wall wear degree based on the gas transportation characteristics; wherein, the determination of the pipe wall wear degree based on the gas transportation characteristics includes: determining the pipe wall wear degree of a to-be-detected point based on the gas transportation characteristics through a wear degree determination model; the wear degree determination model is a machine learning model; the gas pipeline network includes one or more of the to-be-detected points; the gas transportation characteristics include the upstream gas transportation characteristics of the upstream point of the to-be-detected point, the downstream gas transportation characteristics of the downstream point, and the gas component information of the to-be-detected point; the wear degree determination model includes a hidden feature determination layer and a wear degree determination layer, and the wear degree determination model and the transportation feature prediction model are obtained synchronously through joint training. The transportation feature prediction model is used to determine the downstream gas transportation characteristics based on the upstream gas transportation characteristics and the hidden features, and the transportation feature prediction model is a machine learning model; the hidden feature is a feature vector containing the depth information features of gas transportation, and the hidden feature is obtained based on the hidden feature determination layer; the hidden feature includes the corresponding relationship features between the transportation pressure information, gas transportation flow information, gas transportation temperature information of the gas pipeline network and the pipe wall wear degree, and the corresponding relationship features between the upstream gas transportation characteristics and the downstream gas transportation characteristics; Determining the reliability of the gas pipeline network at the target moment based on the pipe wall wear degree.

5. The system according to claim 4, wherein, The smart gas safety management platform is further used for: Determining the smoothness of the reliability based on the reliability sequence; Determining the monitoring plan based on the smoothness of the reliability.

6. A computer-readable storage medium, wherein, The storage medium stores computer instructions, and when a computer reads the computer instructions, the computer executes the method according to claim 1.

Images