Safety supervision based intelligent gas filling station maintenance method and internet of things system

Abstract

The application provides a kind of based on safe supervision's wisdom gas filling station maintenance method and internet of things system, it is related to gas management field.The method comprises: obtaining the historical gas filling data of gas filling station in preset period;Determine the estimated use feature based on historical gas filling data;Obtain historical operation data;Determine the historical operation feature based on historical operation data;Determine the operation and maintenance parameters based on the estimated use feature and the historical operation feature, and generate maintenance instructions;Obtain the number of reference vehicles;In response to the number of reference vehicles being greater than the reference threshold, generate control instructions.The internet of things system includes government safety supervision service platform, government safety supervision management platform, government safety supervision sensing network platform, government safety supervision object platform, gas company sensing network platform and gas equipment object platform.The application can reasonably maintain gas filling equipment.

Description

TECHNICAL FIELD

[0001] The present specification relates to the field of gas management, in particular to a smart gas filling station maintenance method and Internet of Things system based on safety supervision. BACKGROUND

[0002] The gas filling equipment of the gas filling station needs daily maintenance in addition to maintenance when it fails to reduce risks. Therefore, how to determine the daily maintenance means of different gas filling equipment and auxiliary operation equipment of the gas filling station is extremely important to reduce risks while trying not to affect the daily operation of the gas filling station.

[0003] Traditional maintenance often relies on manual experience and fixed maintenance plans, lacks intelligent prediction of future use and equipment state of the gas filling equipment, and lacks the ability to dynamically adjust the maintenance strategy according to real-time data.

[0004] Therefore, it is necessary to provide a smart gas filling station maintenance method and Internet of Things system based on safety supervision. SUMMARY

[0005] In order to reasonably maintain the gas filling equipment, ensure the stable operation of the gas filling equipment, and reduce the impact of maintenance on the daily operation of the gas filling station, the present specification provides a smart gas filling station maintenance method and Internet of Things system based on safety supervision.

[0006] The invention includes a smart gas filling station maintenance method based on safety supervision, which is executed by a filling station maintenance Internet of Things system, the Internet of Things system comprising a government safety supervision service platform, a government safety supervision management platform, a government safety supervision sensing network platform, a government safety supervision object platform, a gas company sensing network platform, and a gas equipment object platform, the government safety supervision object platform comprising a gas company management platform, the method comprising: the government safety supervision management platform, in response to the current time being a preset time for updating maintenance parameters, and the remaining computing resources of the Internet of Things system at the current time being greater than a computing threshold: obtaining, through the gas equipment object platform, historical gas filling data of the filling station within a preset period; determining, based on the historical gas filling data, an estimated use feature of the filling station in a future period; obtaining, through the gas equipment object platform, historical operation data of a plurality of gas filling devices of the filling station within the preset period; the historical operation data of the plurality of gas filling devices is collected at a first preset frequency, and the first preset frequency of different gas filling devices is different; determining, based on the historical operation data of the plurality of gas filling devices, a historical operation feature of each gas filling device; determining, based on the estimated use feature of the filling station and the historical operation feature of each gas filling device, an operation and maintenance parameter of each gas filling device, and generating a maintenance instruction and sending it to the gas company management platform; the operation and maintenance parameter comprises an operation and maintenance frequency, an operation and maintenance period, and an operation and maintenance item; for each gas filling device, determining a time distance based on the operation and maintenance frequency of the gas filling device, the time distance being the time difference between the current time and the next maintenance period of the gas filling device, and adjusting the first preset frequency corresponding to the gas filling device based on the time distance; obtaining, through the government safety supervision service platform, a reference vehicle quantity at a second preset frequency, the reference vehicle being a vehicle that is driving and whose destination is the filling station; in response to the number of reference vehicles being greater than a reference threshold, generating a regulation and control instruction, and sending the regulation and control instruction to the reference vehicles through the government safety supervision service platform; the regulation and control instruction comprises determining a candidate filling station, the candidate filling station being other filling stations within a preset range of the filling station.

[0007] The invention includes a smart gas filling station maintenance Internet of Things system based on safety supervision, which comprises a government safety supervision service platform, a government safety supervision management platform, a government safety supervision sensing network platform, a government safety supervision object platform, a gas company sensing network platform and a gas equipment object platform, and the government safety supervision object platform comprises a gas company management platform. The Internet of Things system is configured to: the government safety supervision management platform responds to the preset time for updating the maintenance parameters at the current time, and the remaining computing resources of the Internet of Things system at the current time are greater than the computing threshold: through the gas equipment object platform, the historical filling data of the gas filling station in the preset period is obtained; based on the historical filling data, the estimated use characteristics of the gas filling station in the future period are determined; through the gas equipment object platform, the historical operation data of a plurality of gas filling devices of the gas filling station in the preset period are obtained; the historical operation data of the plurality of gas filling devices are collected at a first preset frequency, and the first preset frequencies of different gas filling devices are different; based on the historical operation data of the plurality of gas filling devices, the historical operation characteristics of each gas filling device are determined; based on the estimated use characteristics of the gas filling station and the historical operation characteristics of each gas filling device, the operation and maintenance parameters of each gas filling device are determined, and a maintenance instruction is generated and sent to the gas company management platform; the operation and maintenance parameters include operation and maintenance frequency, operation and maintenance period and operation and maintenance project; for each gas filling device, the time distance is determined based on the operation and maintenance frequency of the gas filling device, the time distance is the time difference between the current time and the next maintenance period of the gas filling device, and the first preset frequency corresponding to the gas filling device is adjusted based on the time distance; through the government safety supervision management platform, the number of reference vehicles is obtained at a second preset frequency, the reference vehicle is a vehicle that is driving and whose destination is the gas filling station; in response to the number of reference vehicles being greater than a reference threshold, a regulation instruction is generated, and the regulation instruction is sent to the reference vehicle through the government safety supervision sensing network platform; the regulation instruction includes determining a candidate gas filling station, and the candidate gas filling station is another gas filling station within the preset range of the gas filling station.

[0008] The above invention has the following beneficial effects: (1) The various functional platforms of the Internet of Things system are coordinated and regularly operated, forming an information operation closed loop, and realizing the informatization and intelligence of real-time detection and daily maintenance of gas filling equipment of the gas filling station; (2) By deploying reference vehicles to other gas filling stations, traffic congestion can be alleviated, the time of gas users can be saved, and the experience of users can be improved; by determining the operation and maintenance parameters of different gas filling devices of the gas filling station in daily maintenance, the efficiency of device operation and maintenance is improved, and the risk of failure is reduced; (3) The prediction model is used to determine the estimated use characteristics, which comprehensively considers the weather, the characteristics of each gas filling station itself and the relationship between the gas filling stations, improves the accuracy of determining the estimated use characteristics, and helps to determine more actual operation and maintenance parameters. BRIEF DESCRIPTION OF DRAWINGS

[0009] The present specification will be further described in the manner of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. The embodiments are not restrictive, and in the embodiments, the same reference numbers denote the same structures, in which:

[0010] Figure 1 is a structural schematic diagram of a smart gas filling station maintenance Internet of Things system based on safety supervision according to some embodiments of the present specification;

[0011] Figure 2 is an exemplary flowchart of a smart gas filling station maintenance method based on safety supervision according to some embodiments of the present specification;

[0012] Figure 3 is an exemplary model diagram of a prediction model according to some embodiments of the present specification;

[0013] Figure 4 is an exemplary model diagram of a failure model according to some embodiments of the present specification. DETAILED DESCRIPTION

[0014] In order to more clearly illustrate the technical solutions of the embodiments of the present specification, the drawings needed to be used in the embodiment description will be briefly introduced below. Obviously, the drawings in the following description are only some examples or embodiments of the present specification, and for those skilled in the art, the present specification can be applied to other similar scenarios without creative labor on the basis of these drawings. Unless the context clearly indicates otherwise or otherwise stated, the same reference numbers in the drawings represent the same structure or operation.

[0015] Unless the context clearly indicates otherwise or otherwise stated, the words "one", "an", "a", and / or "the" do not necessarily refer to the singular, but can also include the plural. Generally speaking, the terms "comprise" and "include" only indicate the inclusion of the steps and elements explicitly identified, and these steps and elements do not constitute an exclusive list, and the method or device can also include other steps or elements.

[0016] Flowcharts are used in the present specification to illustrate the operations performed by the system according to the embodiments of the present specification. It should be understood that the preceding or subsequent operations are not necessarily performed in sequence. On the contrary, each step can be processed in reverse order or simultaneously. At the same time, other operations can also be added to these processes, or one or more steps of operation can be removed from these processes.

[0017] Figure 1 is a structural schematic diagram of a smart gas filling station maintenance Internet of Things system based on safety supervision according to some embodiments of the present specification.

[0018] In some embodiments, as Figure 1As shown, the smart gas station maintenance Internet of Things system based on safety supervision 100 can include a government safety supervision service platform 110, a government safety supervision management platform 120, a government safety supervision sensor network platform 130, a government safety supervision object platform 140, a gas company sensor network platform 150, and a gas equipment object platform 160. The government safety supervision object platform 140 includes a gas company management platform 141.

[0019] The government safety supervision service platform 110 refers to a platform that provides gas supervision services for users.

[0020] The government safety supervision management platform 120 refers to a comprehensive management platform for government management information.

[0021] In some embodiments, the government safety supervision management platform 120 can interact with the government safety supervision service platform 110 and the government safety supervision sensor network platform 130.

[0022] The government safety supervision sensor network platform 130 refers to a platform for comprehensive management of government sensor information. For example, communication base stations, routers, wireless WiFi devices, and the like. In some embodiments, the government safety supervision sensor network platform 130 can interact with the government safety supervision management platform 120 and the government safety supervision object platform 140.

[0023] The government safety supervision object platform 140 refers to a platform for generating and controlling government supervision information. In some embodiments, the government safety supervision object platform 140 includes a gas company management platform 141, which refers to a platform for information management of gas companies.

[0024] In some embodiments, the government safety supervision object platform 140 can interact with the government safety supervision sensor network platform 130 and the gas company sensor network platform 150.

[0025] The gas company sensor network platform 150 refers to a platform for comprehensive management of sensor information of gas companies. In some embodiments, the gas company sensor network platform 150 includes communication base stations, routers, wireless WiFi devices, and the like. In some embodiments, the gas company sensor network platform 150 can interact with the government safety supervision object platform 140 and the gas equipment object platform 160.

[0026] In some embodiments, the gas equipment object platform 160 can be configured to monitor equipment and / or pipe network equipment to obtain operation data of a plurality of gas filling equipment of a gas station. For example, the gas equipment object platform 160 can include cameras, positioning devices, gas compressors, gas pipelines, flow meters, and pressure gauges, and the like.

[0027] In some embodiments, the gas equipment object platform 160 can interact with the government safety supervision object platform 140 through the gas company sensing network platform 150.

[0028] For more information about the functions of the smart gas station maintenance Internet of Things system 100 based on safety supervision, please refer to Figures 2-4 and the related description.

[0029] In some embodiments of the present specification, based on the gas station maintenance Internet of Things system, the coordination between each functional platform, the regular operation, the formation of the information operation closed loop, and the realization of the real-time detection and daily maintenance of the gas station gas equipment information and intelligence.

[0030] Figure 2 is an exemplary flowchart of the smart gas station maintenance method based on safety supervision according to some embodiments of the present specification.

[0031] In some embodiments, the government safety supervision management platform 120 can execute the process 200 as shown in Figure 2 in response to the current time being a preset time for updating the maintenance parameters, and the remaining computing resources of the Internet of Things system being greater than the computing threshold.

[0032] In some embodiments, the government safety supervision management platform 120 can determine a plurality of preset times through a preset update frequency. The preset update frequency can be preset according to experience. For example, if the preset update frequency is 4 times / day, the preset times can be set to 0, 6, 12, and 18 o'clock every day.

[0033] In some embodiments, when the computing resources of the system are sufficient, that is, if the remaining computing resources of the system at the current time are greater than the computing threshold, the government safety supervision management platform 120 can execute the gas station maintenance method as shown in the process 200 to reduce the failure risk of the gas station without affecting the daily operation of the gas station. The computing threshold can be preset according to experience.

[0034] As shown in Figure 2 , the process 200 includes the following steps. In some embodiments, the process 200 can be executed by the government safety supervision management platform 120.

[0035] Step 210, obtaining historical gas station data in a preset time period through a gas equipment object platform. The preset time period can be a period of time in a historical period.

[0036] The refueling data refers to data related to refueling. For example, the refueling data includes a target vehicle, a refueling time of the target vehicle, and a refueling amount. The target vehicle refers to a vehicle that has been refueled at the gas refueling station. The historical refueling data refers to refueling data within a preset time period. In some embodiments, the historical refueling data can be obtained from the gas equipment object platform 160.

[0037] At step 220, based on the historical refueling data, an estimated use feature of the gas refueling station in a future time period is determined.

[0038] The estimated use feature refers to a degree to which the gas refueling station is used in the future time period. In some embodiments, the estimated use feature can reflect how much gas the gas refueling station provides in the future time period. In some embodiments, the estimated use feature can reflect a gas supply pressure of the gas refueling station in the future. In some embodiments, the estimated use feature can include an estimated gas supply feature, which refers to a total amount of gas provided by the gas refueling station in the future time period.

[0039] In some embodiments, the government safety supervision and management platform 120 can intercept a historical time period equal to a length of the future time period, obtain a total amount of gas provided by the gas refueling station in the historical refueling data of the historical time period, and determine the total amount of gas as the estimated gas supply feature, which is used as the estimated use feature. For more information about determining the estimated use feature, see Figure 3 and related descriptions thereof.

[0040] At step 230, historical operation data of a plurality of refueling equipment of the gas refueling station in the preset time period is obtained through the gas equipment object platform.

[0041] The refueling equipment refers to related equipment used for refueling work. For example, gas storage equipment, refueling machines, submerged liquid natural gas pumps, refueling columns, defueling columns, and diffusion pipes.

[0042] The historical operation data refers to data related to historical operation of the refueling equipment. For example, a use frequency of the refueling equipment, a sequence of operation parameters, and the like. In some embodiments, the historical operation data can reflect wear and tear of the refueling equipment caused by historical multiple uses, and can also reflect a future failure probability of the refueling equipment.

[0043] The sequence of operation parameters refers to a sequence composed of data of operation parameters of the refueling equipment. In some embodiments, types of operation parameters that need to be supervised and collected are different for different refueling equipment, and the types of operation parameters that need to be supervised and collected can be preset. At a certain time, data corresponding to a group of preset types of operation parameters of a certain refueling equipment can be collected, and at multiple times, multiple groups of data of a certain refueling equipment can be collected, i.e., a sequence of operation parameters is formed.

[0044] The types of operation parameters of different refueling equipment are described below by way of examples.

[0045] For example, for the gas storage device, the types of the operation parameters can include temperature, pressure, audio data, on-off status, current time, etc. For example, for the gas dispenser, the types of the operation parameters can include temperature, pressure, audio data, on-off status, current time, gas filling speed, etc. For example, for the submersible pump, the types of the operation parameters can include temperature, pressure, audio data, on-off status, current time, vibration data, etc. For example, for the gas filling column, the gas releasing column and the diffuser, the types of the operation parameters can include temperature, audio data, on-off status, current time, etc.

[0046] The temperature, the pressure, the gas filling speed and the vibration data can be acquired by the temperature sensor, the pressure sensor, the speed sensor and the vibration sensor installed on the corresponding gas filling device, respectively. The audio data can be acquired by the audio device installed on the corresponding gas filling device.

[0047] In some embodiments, the historical operation data of the plurality of gas filling devices can be collected at a first preset frequency. The first preset frequency of different gas filling devices can be different. The first preset frequency can be determined according to a preset. For example, the initial first preset frequency can be set as t0.

[0048] In some embodiments, the first preset frequency can be adjusted according to the historical maintenance times of the gas filling device. For example, the more the historical maintenance times of the gas filling device, the higher the first preset frequency is adjusted on the basis of the initial first preset frequency. In some embodiments, the first preset frequency can be adjusted according to the time distance. For example, the shorter the time distance, the higher the first preset frequency is adjusted on the basis of the initial first preset frequency. For more information about the time distance, please refer to the following.

[0049] In step 240, the historical operation characteristics of each gas filling device are determined based on the historical operation data of the plurality of gas filling devices.

[0050] The historical operation characteristics reflect the historical use of the gas filling device. In some embodiments, the historical operation characteristics of different gas filling devices are different. For example, for the gas storage device, the historical operation characteristics can include temperature variation sequence, pressure variation sequence, audio data abnormality degree, etc.

[0051] In some embodiments, the government safety supervision and management platform 120 can determine the historical operation characteristics of each gas filling device based on the historical operation data of the plurality of gas filling devices by statistical analysis, etc. For example, the government safety supervision and management platform 120 can acquire the temperature collected at multiple time points in the historical operation data, calculate the temperature variation rate of each adjacent two time points, and form a temperature variation sequence with the multiple temperature variation rates. The pressure variation sequence can be determined in a similar manner.

[0052] For another example, the government safety supervision management platform 120 can calculate the similarity of the audio data in the historical operation data collected in a preset time period with the standard audio data in an audio database one by one, and take the audio data with a similarity lower than a similarity threshold as suspicious audio data, and then calculate the proportion of the total amount of suspicious audio data in all audio data obtained in the preset time period as the audio data abnormality degree, wherein the audio database is a database pre-stored with a large amount of standard audio data, and the similarity threshold can be determined according to experience.

[0053] In step 250, the operation and maintenance parameters of each gas filling device are determined based on the estimated use characteristics of the gas filling station and the historical operation characteristics of each gas filling device, and a maintenance instruction is generated and sent to the gas company management platform.

[0054] The operation and maintenance parameters refer to data related to the operation and maintenance of the gas filling device. In some embodiments, the operation and maintenance parameters can include operation and maintenance frequency, operation and maintenance time period, and operation and maintenance project. The operation and maintenance frequency refers to the frequency of operation and maintenance work, the operation and maintenance time period refers to the time period of operation and maintenance work, and the operation and maintenance project can include work items required for maintenance.

[0055] In some embodiments, the government safety supervision management platform 120 can determine the operation and maintenance parameters based on vector matching. The government safety supervision management platform 120 can construct a first vector database, which includes a plurality of first reference vectors and their corresponding reference operation and maintenance parameters. Each first reference vector can be constructed based on the historical estimated use characteristics of the gas filling station and the historical operation characteristics of each gas filling device. The reference operation and maintenance parameters can be constructed based on the historical operation and maintenance parameters corresponding to the first reference vector, which are the operation and maintenance parameters when the gas filling station is normally operated.

[0056] The government safety supervision management platform 120 can construct a target feature vector based on the estimated use characteristics of the current gas filling station and the historical operation characteristics of each gas filling device. Based on the target feature vector, a first reference vector with the smallest vector distance is matched in the first vector database, and the historical operation and maintenance parameters corresponding to the first reference vector are determined as the operation and maintenance parameters.

[0057] In some embodiments, for each gas filling device, the government safety supervision management platform 120 can determine a time distance based on the operation and maintenance frequency of the gas filling device, which is the time difference between the current time and the next maintenance time period of the gas filling device. The government safety supervision management platform 120 can adjust the first preset frequency corresponding to the gas filling device based on the time distance. For example, the smaller the time distance, the higher the first preset frequency. That is, the closer the current time is to the maintenance time period, the higher the first preset frequency, which is beneficial for maintenance personnel to master the gas filling device data at the most recent time, facilitating the performance of maintenance work.

[0058] The maintenance instruction is an instruction for mobilizing the maintenance personnel to go to the gas station for maintenance. For example, the maintenance instruction can include the time period of maintenance, the maintenance item, etc. In some embodiments, the government safety supervision and management platform 120 can generate the maintenance instruction based on the operation and maintenance parameter. For example, the government safety supervision and management platform 120 can determine the time period of maintenance in the maintenance instruction based on the operation and maintenance frequency and the operation and maintenance time period, and take the operation and maintenance item as the maintenance item in the maintenance instruction.

[0059] For more information about determining the operation and maintenance parameter, see Figure 3 and the description thereof.

[0060] In step 260, the government safety supervision service platform is used to acquire the number of reference vehicles at a second preset frequency.

[0061] The reference vehicle refers to a vehicle that is driving and whose destination is the gas station. In some embodiments, the government safety supervision service platform 110 can acquire the number of reference vehicles at a second preset frequency. The second preset frequency can be determined according to manual or experience.

[0062] In step 270, in response to the number of reference vehicles being greater than a reference threshold, a regulation instruction is generated, and the regulation instruction is sent to the reference vehicle through the government safety supervision service platform.

[0063] In some embodiments, the reference threshold can be preset. In some embodiments, the reference threshold can be determined based on the actual vehicle flow within the preset range of the gas station. For example, the relationship between the actual vehicle flow and the reference threshold can be a negative correlation. The preset range refers to a spatial range centered on the gas station, and the specific size can be determined according to manual or preset.

[0064] The regulation instruction is an instruction for regulating the reference vehicle to the remaining gas stations. In some embodiments, the regulation instruction can include determining a candidate gas station, which is another gas station within the preset range of the gas station.

[0065] The larger the actual vehicle flow is, the more likely it is to cause traffic congestion. By setting a smaller reference threshold, more reference vehicles can be allocated to other gas stations, which can help to alleviate traffic congestion and save time for gas users, thereby improving the user experience.

[0066] In some embodiments, the government safety supervision and management platform 120 can predict the probability sequence and the time consumption sequence based on the positions of the other gas stations within the preset range of the gas station, the current position of the reference vehicle, the remaining gas amount of the reference vehicle, the type of the reference vehicle, and select at least one of the other gas stations that meet the preset condition as the candidate gas station.

[0067] The location of the other gas stations refers to the spatial location of the other gas stations. The current location of the reference vehicle refers to the spatial location where the reference vehicle is currently located. The remaining gas amount of the reference vehicle refers to the amount of gas currently remaining in the reference vehicle. The type of the reference vehicle refers to the vehicle type (e.g., a car, a truck, etc.) of the reference vehicle.

[0068] The probability sequence is composed of a plurality of success probabilities. A success probability is the probability of the reference vehicle successfully driving to a certain other gas station, and each of the reference vehicle successfully driving to each of the other gas stations corresponds to a success probability, and the plurality of success probabilities constitute the probability sequence.

[0069] In an example, the government safety supervision and management platform 120 can obtain the current time, the estimated distance from the current location of the reference vehicle to the location of a certain gas station (hereinafter referred to as the optional gas station) in the other gas stations, and the estimated driving time. In some embodiments, the government safety supervision and management platform 120 can communicate with the electronic map software, thereby obtaining the estimated distance and the estimated driving time from the electronic map software.

[0070] The government safety supervision and management platform 120 further determines the unit distance gas consumption based on the type of the reference vehicle through a first preset corresponding relationship, and determines the reference gas consumption to the optional gas station based on the estimated distance and the unit distance gas consumption, for example, reference gas consumption = estimated distance x unit distance gas consumption. The government safety supervision and management platform 120 determines the success probability of the optional gas station based on the second preset corresponding relationship between the success probability and the reference gas consumption and the remaining gas amount of the reference vehicle. Based on the success probability of each of the other gas stations, the probability sequence is obtained.

[0071] The time consumption sequence is composed of a plurality of time consumption sums. Each time consumption sum is the sum of the time consumption of the reference vehicle driving to the optional gas station and completing the gas filling at the optional gas station. Each of the reference vehicle driving to the other gas stations corresponds to a time consumption sum, and the plurality of time consumption sums constitute the time consumption sequence.

[0072] In some embodiments, the government safety supervision and management platform 120 can determine the to-be-added gas amount based on the full gas amount (the amount of gas stored when fully filled, which can be obtained from the vehicle factory data) corresponding to the type of the reference vehicle, for example, to-be-added gas amount = full gas amount - remaining gas amount of the reference vehicle. The gas filling time consumption is related to the to-be-added gas amount and the preset reference gas filling speed, for example, gas filling time consumption = to-be-added gas amount ÷ preset reference gas filling speed. The sum of the estimated driving time of the reference vehicle to the optional gas station and the gas filling time consumption is the time consumption sum, and the time consumption sums of the reference vehicle driving to all optional gas stations constitute the time consumption sequence.

[0073] In some embodiments, the preset conditions may include a success probability higher than a success threshold and a refueling time lower than a time threshold. That is, the government safety supervision management platform 120 selects at least one of the other gas stations with a success probability higher than the success threshold and a refueling time lower than the time threshold as a candidate gas refueling station. The success threshold and time threshold may be determined based on experience.

[0074] In some embodiments of this specification, by deploying reference vehicles to other gas stations, it is helpful to alleviate traffic congestion, save time for gas users, and improve user experience; by determining the operation and maintenance parameters of different gas filling equipment at the gas station during daily maintenance, the efficiency of equipment operation and maintenance is improved and the risk of failure is reduced.

[0075] In some embodiments, the government safety supervision management platform 120 may further divide the future period into multiple future sub-periods, and estimate the estimated usage characteristics of the gas station in each future sub-period through a prediction model.

[0076] The future sub-periods can be divided manually or by other methods.

[0077] Figure 3 is an exemplary model diagram of a prediction model according to some embodiments of this specification.

[0078] A prediction model is a model used to determine the estimated usage characteristics. A prediction model can be a machine learning model, such as a Graph Neural Network (GNN) model.

[0079] In some embodiments, as Figure 3 As shown, the input of the prediction model 330 may include the gas filling map 310 and the future sub-period 320, and the output may include the estimated usage feature 340. Each estimated usage feature output by the prediction model 330 corresponds to each future sub-period.

[0080] The gas filling graph 310 is a graph that can represent the relationship between gas filling stations. The gas filling graph can include nodes and edges. Nodes represent gas filling stations, and edges are used to connect two gas filling stations that can be connected. For example, if a vehicle can pass between the two gas filling stations, the two gas filling stations are considered to be connected. For more information about the estimated usage characteristics, please refer to Figure 2 Description.

[0081] In some embodiments, the nodes of the gas filling map 310 may correspond to various gas filling stations. One node corresponds to one gas filling station. Figure 3As shown, the gas station A, the gas station A1, the gas station A2, the gas station A3, and the gas station A4 are nodes. The node features of the gas refueling graph can include historical refueling data of the gas station, location of the gas station, gas composition provided by the gas station, scale of the gas station, and weather data of the future time period. The description about the historical refueling data and the location of the gas station can refer to the related description of Figure 2 .

[0082] The gas composition provided by the gas station refers to the composition of the gas, which can be obtained through the gas equipment object platform 160. Different gas compositions can affect the use effect of the gas, and further affect the use speed of the gas. The scale of the gas station refers to the size of the gas station, which can be determined based on the land area and the number of staff. The larger the land area and the more the staff, the larger the scale of the gas station. The location of the gas station and the scale of the gas station can affect the passenger flow, and further affect the number of vehicles in the future time period. The weather data of the future time period is the future weather condition, which can be determined based on weather forecast and input into the government safety supervision and management platform 120. The weather data can affect the travel in the future time period, and further affect the gas supply pressure of the gas station in the future time period.

[0083] In some embodiments, the edges of the gas refueling graph can correspond to the communication relationship between the gas stations. For example, if there is a connection relationship between two gas stations, the two gas stations can be connected. If there is no connection relationship, it means that the two gas stations cannot be connected (for example, the path between the two gas stations is blocked). The description about the connection can refer to the foregoing description. The features of the edge can include the straight-line distance and the driving path between the two gas stations connected by the edge.

[0084] In some embodiments, the prediction model can be trained in the following examples.

[0085] First, a first training data set is obtained, which includes a plurality of first training samples and a first label corresponding to each first training sample. Then, a plurality of iterations are performed. When the iteration end condition is met, the iteration is ended, and a trained prediction model is obtained. At least one iteration includes:

[0086] 1) One or more first training samples are selected from the first training data set, and the one or more first training samples are input into the prediction model to obtain the prediction model output corresponding to the one or more first training samples;

[0087] 2) The value of the loss function is calculated by substituting the prediction model output corresponding to the one or more first training samples and the label of the one or more first training samples into the formula of the pre-defined loss function;

[0088] 3) According to the value of the loss function, the model parameters in the prediction model are updated in various possible ways. For example, the update is based on the gradient descent method.

[0089] In some embodiments, the first training sample can be obtained based on historical data. The first label of the first training sample can be obtained by manual annotation. In some embodiments, the first training sample can be a historical gas filling map constructed based on historical data of a first period, and the first label can be an actual use feature corresponding to the first training sample in the historical data of a second period, for example, the first label is [A1, A2,..., Am, A1, A2,..., Am], which respectively corresponds to the actual use feature of m future sub-periods in the first training sample. The first period is earlier than the second period.

[0090] In some embodiments of the present specification, the estimated use feature is determined by the prediction model, which comprehensively considers the weather, the characteristics of each gas filling station itself and the connection between the gas filling stations, improves the accuracy of determining the estimated use feature, and helps to determine the operation and maintenance parameters that are more in line with the actual situation.

[0091] In some embodiments, the estimated use feature further includes an estimated vehicle flow feature.

[0092] The estimated vehicle flow feature refers to the estimated vehicle flow situation in the future period. In some embodiments, the estimated vehicle flow feature can include the number of vehicle flows of different vehicle types in each future sub-period in the gas filling station. For different types of vehicles, their gas storage capacity is different, and the corresponding number of vehicle flows will affect the gas supply pressure of the gas filling station.

[0093] In some embodiments of the present specification, by considering the influence of the number of different types of vehicles on the gas supply pressure of the gas filling station, the accuracy of determining the estimated use feature can be improved.

[0094] In some embodiments, for each gas filling equipment, the government safety supervision and management platform 120 can also determine the failure probability of the gas filling equipment in the future period based on the historical operation feature, and determine the operation and maintenance parameters based on the failure probability and the estimated use feature.

[0095] The failure probability refers to the probability of failure of the gas filling equipment. In some embodiments, the government safety supervision and management platform 120 can determine the failure probability based on the historical operation feature in various ways. For example, the government safety supervision and management platform 120 can determine the failure probability based on a first preset table. The first preset table is a table for representing the correspondence between the historical operation feature and the failure probability, which can be determined according to experience. For more information about determining the failure probability, see Figure 4 and the description thereof.

[0096] In some embodiments, the government safety supervision and management platform 120 can determine the operation and maintenance parameters in various ways based on the failure probability and the estimated use characteristics. For example, the government safety supervision and management platform 120 can determine the operation and maintenance parameters based on a second preset table. The second preset table is a table for representing the correspondence between the failure probability, the estimated use characteristics, and the operation and maintenance parameters, and can be determined according to experience. For more information about the operation and maintenance parameters, see the following.

[0097] Figure 4 is an exemplary model diagram of a failure model according to some embodiments of the present specification.

[0098] In some embodiments, the failure probability can be determined by a failure model.

[0099] The failure model refers to a model for determining the failure probability. The failure model can be a machine learning model. For example, any one or a combination structure of a deep neural network (DNN), a support vector machine (SVM), etc.

[0100] In some embodiments, as shown in Figure 4 , the input of the failure model 470 can include the historical operation characteristics 410 and the gas composition 420, and the output can include the failure probability 480. The historical operation characteristics 410 refer to the historical operation characteristics of each gas filling device. For more information about the historical operation characteristics, see the related description in Figure 2 . The gas composition 420 refers to the gas composition provided by the smart gas station. For more information about the gas composition, see the related description in Figure 2 . The failure probability 480 refers to the failure probability of each gas filling device in a future period. For more information about the failure probability, see the description above. The failure probability of each gas filling device output by the failure model corresponds to the historical operation characteristics of each gas filling device input by the failure model.

[0101] In some embodiments, the failure model can be obtained by joint training with the prediction model.

[0102] The government safety supervision management platform 120 can obtain a second training data set, the second training data set including a plurality of first training samples and a first label corresponding to each first training sample, and a plurality of second training samples and a second label corresponding to each second training sample, and perform multiple iterations. When the iteration end condition is met, the iteration is ended, and a trained fault model is obtained. At least one iteration includes: selecting one or more first training samples from the second training data set, inputting the one or more first training samples into the prediction model to obtain the prediction model output corresponding to the one or more first training samples; inputting the prediction model output corresponding to the one or more first training samples and the one or more second training samples into the fault model to obtain the corresponding fault model output; according to the prediction model output, the first label corresponding to the one or more first training samples, the fault model output, and the second label corresponding to the one or more second training samples, substitute into the pre-defined joint training loss function, calculate the value of the loss function; according to the value of the loss function, the model parameters in the prediction model and the fault model are updated by various feasible methods. For example, update based on gradient descent method, etc.

[0103] The joint training loss function can include: weighting and summing a plurality of first sub-loss terms based on a first weight set to obtain a first loss term; weighting and summing a plurality of second sub-loss terms based on a second weight set to obtain a second loss term; multiplying or adding the first loss term and the second loss term as the joint training loss function value.

[0104] For example, the joint training loss function = (a1*first sub-loss term 1 +... + am*first sub-loss term m) * (b1*second sub-loss term 1 +... + bn*second sub-loss term n), where m represents the number of future sub-periods corresponding to the prediction model; n represents the number of gas filling equipment. For example, the joint training loss function = (a1*first sub-loss term 1 +... + am*first sub-loss term m) + (b1*second sub-loss term 1 +... + bn*second sub-loss term n), where m represents the number of future sub-periods corresponding to the prediction model; n represents the number of gas filling equipment.

[0105] If the prediction model output of each future sub-period gas filling station is estimated to be[A10,A20,...,Am0]; the corresponding first label is [A1,A2,...,Am], then each element in [(A1-A10),(A2-A20),...,(Am-Am0)] is a first sub-loss term corresponding to a future sub-period.

[0106] If the failure probability of each gas filling device output by the failure model is [B10, B20,..., Bn0], and the corresponding second label is [B1, B2,..., Bn], then each element in [(B1-B10), (B2-B20),..., (Bn-Bn0)] is a second sub-loss term corresponding to each gas filling device.

[0107] The weight corresponding to the first sub-loss term is determined based on the time distance between the corresponding future sub-period and the current time, for example, the weight corresponding to the first sub-loss term is negatively correlated with the time distance; the weight corresponding to the second sub-loss term is determined based on the importance of the corresponding gas filling device, for example, the weight corresponding to the second sub-loss term is positively correlated with the importance. The importance of the gas filling device refers to the usage frequency of the gas filling device within a preset period.

[0108] Wherein, when the future sub-period is T1-T2 period, the current time is T0, the time distance between the future sub-period and the current time can be T1-T0 or T2-T0.

[0109] In some embodiments, the second training sample can be obtained based on historical data. The second label of the second training sample can be obtained by manual annotation. In some embodiments, the second training sample can be the historical running feature and the historical gas composition of the first period, and the second label can be the actual failure probability of each gas filling device corresponding to the second training sample in the historical data of the second period, for example, the second label is [B1, B2,..., Bn], B1, B2,..., Bn are respectively the actual failure situation of n future sub-periods corresponding to the second training sample (if the gas filling device fails, it is recorded as 1, otherwise as 0). Wherein, the first period is earlier than the second period.

[0110] In some embodiments of the present specification, the failure probability is determined by the failure model, which can improve the reliability and accuracy of determining the failure probability based on massive data.

[0111] In some embodiments, as shown in Figure 4 The input of the failure model further includes at least one of the estimated gas supply feature 430 and the estimated vehicle flow feature 440. The estimated gas supply feature 430 refers to the estimated gas supply feature of the gas filling station in the future period. For the estimated gas supply feature, please refer to the related description of Figure 2 The estimated vehicle flow feature 440 refers to the estimated vehicle flow feature 440 in the future period. For the estimated vehicle flow feature, please refer to the related description of Figure 2 .

[0112] The estimated gas supply feature can reflect the estimated traffic flow of different vehicle types in each future sub-period. For example, for a bus, the amount of gas filling is usually larger than that of a general car, which can make the gas filling device run for a longer time, thereby increasing the failure probability. For another example, when the type of vehicle for gas filling changes constantly, the running time of the gas filling device also changes constantly, thereby increasing the failure probability.

[0113] In some embodiments, the second training sample can further include at least one of an actual gas supply feature of the second period and an actual traffic flow feature of the second period.

[0114] In some embodiments, as shown in FIG. 4, the input of the failure model further includes a spatial layout 450 of the gas filling station and a position layout 460 of the gas filling device. The spatial layout of the gas filling station is the spatial structure of the gas filling station, which can be determined by design drawings of the gas filling station. Figure 4

[0115] The position layout of the gas filling device refers to the positions of the gas filling devices in the gas filling station. A spatial rectangular coordinate system is established with any point in the gas filling station as the origin (for example, the entrance of the gas filling station), and the positions of the gas filling devices are represented by coordinates, thereby obtaining the position layout of the gas filling devices. If the spatial layout of the gas filling station is too compact, or the position layout of the gas filling devices has unreasonable design, the efficiency of vehicle access and gas supply can be affected, thereby affecting the failure probability.

[0116] In some embodiments, the second training sample can further include a spatial layout of a historical gas filling station and a position layout of a historical gas filling device.

[0117] In some embodiments of the present specification, by taking the estimated use feature, the estimated traffic flow feature, the spatial layout of the gas filling station, and the position layout of the gas filling device as the input of the failure model, the use of the gas filling device is fully considered, so that the output of the failure model is more in line with the actual situation, and the rationality and accuracy of determining the failure probability are improved. By jointly training the prediction model and the failure model, the accuracy of model training is improved, and the accuracy of the obtained model is improved.

[0118] In some embodiments, the government safety supervision and management platform 120 can further determine an operation and maintenance parameter based on the failure probability of each gas filling device in the future period and the estimated use feature, in response to the failure probability of the gas filling device being less than the maintenance threshold.

[0119] In some embodiments, the government safety supervision and management platform 120 can generate an emergency instruction for reminding maintenance personnel to immediately maintain the gas filling device, in response to the failure probability of the gas filling device being greater than the maintenance threshold.

[0120] ​The maintenance threshold refers to a value used to determine whether the gas filling equipment needs to be maintained. The maintenance threshold can be preset based on manual experience. In some embodiments, the government safety supervision and management platform 120 can also dynamically determine the maintenance threshold. For example, during peak hours or in adverse weather conditions, the government safety supervision and management platform 120 can automatically lower the maintenance threshold to improve the reliability of the gas filling equipment. More information about the maintenance threshold can be referred to the relevant description later.

[0121] In some embodiments, the maintenance threshold can be determined based on at least one of the estimated supply feature and the estimated traffic feature. For more information about the estimated supply feature and the estimated traffic feature, please refer to the previous description.

[0122] In some embodiments, the maintenance threshold can be negatively correlated with the estimated supply feature. For example, when the estimated use feature is large, indicating that the supply amount in the future period is large, the government safety supervision and management platform 120 can lower the maintenance threshold to reduce the operation risk of the gas filling equipment and avoid service interruption.

[0123] In some embodiments, the maintenance threshold is negatively correlated with the estimated traffic feature. For example, when the estimated traffic feature is large, indicating that the traffic volume in the future period is large, the government safety supervision and management platform 120 can lower the maintenance threshold to reduce the operation risk of the gas filling equipment and avoid service interruption.

[0124] Based on the dynamic adjustment of the maintenance threshold based on the estimated use feature and the estimated traffic feature, the maintenance strategy can be flexibly adjusted according to the real-time status of the gas filling station, avoiding service interruption due to gas filling equipment failure, and thus improving the experience of gas users.

[0125] In some embodiments, the government safety supervision and management platform 120 can cluster the to-be-clustered vectors in the clustering database based on the failure probability in the future period as the clustering index, obtain a plurality of cluster families, and the cluster family in which the failure probability of the gas filling equipment in the future period is located is the target cluster family; for each gas filling equipment, based on the historical estimated use features and historical operation and maintenance parameters corresponding to the plurality of first type cluster vectors in the target cluster family in which the gas filling equipment is located, determine the operation and maintenance parameters of the gas filling equipment.

[0126] The clustering database refers to a database used to store historical data. In some embodiments, the clustering database can store historical maintenance data, such as historical operation and maintenance frequency, historical operation and maintenance period, and historical operation and maintenance projects, etc. In some embodiments, the historical data stored in the clustering database can be used for clustering analysis. In some embodiments, the clustering database can also store relevant data involved in the clustering process, such as a plurality of to-be-clustered vectors, a plurality of cluster families, and a target cluster family, etc.

[0127] In some embodiments, the government safety supervision management platform 120 can build a clustering database. For example, the government safety supervision management platform 120 can store the historical gas filling equipment type, the historical probability of failure of the gas filling equipment in a future period, the historical estimated use feature, and the historical operation and maintenance parameter into the clustering database.

[0128] In some embodiments, the clustering database includes a to-be-clustered vector.

[0129] The to-be-clustered vector refers to a vector used for clustering analysis in the clustering database. In some embodiments, the to-be-clustered vector can include a first type of clustering vector and a second type of clustering vector.

[0130] In some embodiments, the government safety supervision management platform 120 can build a first type of clustering vector based on the historical gas filling equipment type, the historical actual failure probability of the gas filling equipment in a corresponding future period, the historical estimated use feature, and the historical operation and maintenance parameter. For the description of the gas filling equipment type, the failure probability, the estimated use feature, and the operation and maintenance parameter, please refer to the foregoing description.

[0131] In some embodiments, the government safety supervision management platform 120 can build a second type of clustering vector based on the gas filling equipment type, the failure probability of the gas filling equipment in a future period, and the estimated use feature. For the description of the gas filling equipment type, the failure probability, and the estimated use feature, please refer to the foregoing description.

[0132] A clustering family is a result obtained by grouping the to-be-clustered vectors through a clustering algorithm, and each clustering family contains a group of similar to-be-clustered vectors (for example, the first type of clustering vector and the second type of clustering vector). The target clustering family refers to a clustering family containing the second type of clustering vector. In some embodiments, the clustering family in which the failure probability of the gas filling equipment in a future period is located is the target clustering family.

[0133] In some embodiments, the government safety supervision management platform 120 can perform clustering analysis on the first type of clustering vector and the second type of clustering vector through a clustering algorithm (for example, a K-means clustering algorithm). For example, the government safety supervision management platform can perform clustering on the first type of clustering vector and the second type of clustering vector through the K-means clustering algorithm, taking the failure probability of the gas filling equipment in a current future period as a constraint, to obtain a plurality of target clustering families.

[0134] In some embodiments, the operation and maintenance parameters include operation and maintenance periods, operation and maintenance projects, and operation and maintenance frequencies. In some embodiments, the government security supervision and management platform 120 may use the historical operation and maintenance period with the largest number of occurrences in the historical operation and maintenance parameters of multiple first-category cluster vectors in the target cluster family as the current operation and maintenance period. In some embodiments, the government security supervision and management platform 120 may use the union of the historical operation and maintenance projects in the historical operation and maintenance parameters as the current operation and maintenance project. In some embodiments, the government security supervision and management platform 120 may weightedly sum the historical operation and maintenance frequencies in the historical operation and maintenance parameters of the first-category cluster vectors, and use the weighted sum result as the current operation and maintenance frequency.

[0135] In some embodiments, the weight of the weighted summation can be determined based on the historical estimated usage characteristics corresponding to the first-category clustering vector. For example, the weight can be negatively correlated with the historical estimated usage characteristics corresponding to the first-category clustering vector. A larger historical estimated usage characteristic, i.e., a larger estimated gas supply characteristic and estimated traffic flow characteristic, indicates a higher gas supply volume and higher traffic flow in the future, which in turn indicates increased use of the gas filling equipment. In this case, more frequent maintenance should be performed, i.e., the frequency of operation and maintenance should be reduced.

[0136] Based on historical data, the failure probability in the future period is used as the clustering indicator to cluster the vectors to be clustered in the clustering database, which can improve the accuracy and effectiveness of determining operation and maintenance parameters.

[0137] One or more embodiments of this specification also provide a computer-readable storage medium, which stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes any of the methods in the above embodiments.

[0138] 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.

[0139] Each patent, patent application, patent application publication, and other materials, such as articles, books, specifications, publications, and documents, cited in this specification is hereby incorporated by reference in its entirety. This includes application history documents that are inconsistent with or conflict with the content of this specification, as well as documents (currently or subsequently attached to this specification) that limit the broadest scope of the claims of this specification. It should be noted that if the descriptions, definitions, and / or terminology used in the accompanying materials are inconsistent or conflicting with the content of this specification, the descriptions, definitions, and / or terminology used in this specification will control.

[0140] Finally, it should be understood that the embodiments described herein are only given by way of example. Other variations might fall within the scope of the present description. Accordingly, the present embodiments are not limited to the examples described herein. Instead, other alternative configurations can be used and still fall within the scope of the present description. For example, the present embodiments can be used in other applications than the ones described herein.

Claims

1. A smart gas filling station maintenance method based on safety supervision, characterized in that: The method is performed by a smart gas filling station maintenance Internet of Things system, which includes a government safety supervision service platform, 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 equipment object platform. The government safety supervision object platform includes a gas company management platform. The method includes: The government security supervision management platform responds that the current moment is a preset moment for updating maintenance parameters, and the remaining computing resources of the Internet of Things system at the current moment are greater than a computing threshold: Obtain historical gas filling data of the gas filling station within a preset time period through the gas equipment object platform; Determining estimated usage characteristics of the gas station in a future period based on the historical gas filling data; Obtaining, through the gas equipment object platform, historical operating data of a plurality of gas filling appliances at the gas filling station within the preset period; the historical operating data of the plurality of gas filling appliances are collected at a first preset frequency, the first preset frequency being different for different gas filling appliances; Determining a historical operating characteristic of each of the gas filling devices based on the historical operating data of the plurality of gas filling devices; Based on the estimated usage characteristics of the gas station and the historical operating characteristics of each gas filling device, the operation and maintenance parameters of each gas filling device are determined, and a maintenance instruction is generated and sent to the gas company management platform; the operation and maintenance parameters include the operation and maintenance frequency, the operation and maintenance period, and the operation and maintenance items; for each gas filling device, a time distance is determined based on the operation and maintenance frequency of the gas filling device, the time distance being the time difference between the current time and the next maintenance period of the gas filling device, and the first preset frequency corresponding to the gas filling device is adjusted based on the time distance; Obtaining, through the government safety supervision service platform, a number of reference vehicles at a second preset frequency; the reference vehicles are vehicles that are traveling and whose destination is the gas station; In response to the number of the reference vehicles being greater than a reference threshold, a control instruction is generated and sent to the reference vehicles through the government safety supervision service platform; the control instruction includes determining candidate gas stations, and the candidate gas stations are other gas stations within a preset range of the gas stations.

2. The method according to claim 1, wherein The determining, based on the historical gas filling data, the estimated usage characteristics of the gas filling station in a future period includes: The future period is divided into a plurality of future sub-periods, and the estimated usage characteristics of the gas station in each of the future sub-periods are estimated through a prediction model; the prediction model is a machine learning model.

3. The method according to claim 1, wherein The determining of the operation and maintenance parameters of each of the gas filling equipment based on the estimated usage characteristics of the gas filling station and the historical operation characteristics of each of the gas filling equipment includes: For each of the gas filling devices, determining a failure probability of the gas filling device in the future time period based on the historical operating characteristics; The operation and maintenance parameters are determined based on the failure probability and the estimated usage characteristics.

4. The method according to claim 3, wherein The method further includes: in response to the failure probability of the gas filling device not exceeding a maintenance threshold, determining the operation and maintenance parameter based on the failure probability of each gas filling device in the future time period and the estimated usage characteristics.

5. The method according to claim 4, wherein The method further comprises: Clustering the vectors to be clustered in the clustering database using the failure probability in the future time period as a clustering index to obtain a plurality of cluster groups, wherein the cluster group in which the failure probability of the gas filling equipment in the future time period belongs is a target cluster group; For each of the gas filling devices, the operation and maintenance parameters of the gas filling device are determined based on historical estimated usage characteristics and historical operation and maintenance parameters corresponding to a plurality of first-category cluster vectors in the target cluster group where the gas filling device is located.

6. A smart gas filling station maintenance Internet of Things system based on safety supervision, characterized in that: The Internet of Things system includes a government safety supervision service platform, 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 equipment object platform. The government safety supervision object platform includes a gas company management platform. The Internet of Things system is configured as follows: The government security supervision management platform responds that the current moment is a preset moment for updating maintenance parameters, and the remaining computing resources of the Internet of Things system at the current moment are greater than a computing threshold: Obtaining historical gas filling data of the gas filling station within a preset time period through the gas equipment object platform; Determining estimated usage characteristics of the gas station in a future period based on the historical gas filling data; Obtaining, through the gas equipment object platform, historical operating data of a plurality of gas filling appliances at the gas filling station within the preset period; the historical operating data of the plurality of gas filling appliances are collected at a first preset frequency, the first preset frequency being different for different gas filling appliances; Determining a historical operating characteristic of each of the gas filling devices based on the historical operating data of the plurality of gas filling devices; Determine the operation and maintenance parameters of each gas filling device based on the estimated usage characteristics of the gas filling station and the historical operation characteristics of each gas filling device, and generate a maintenance instruction and send it to the gas company management platform; The operation and maintenance parameters include an operation and maintenance frequency, an operation and maintenance period, and an operation and maintenance item; for each of the gas filling equipment, a time distance is determined based on the operation and maintenance frequency of the gas filling equipment, the time distance being the time difference between the current moment and the next maintenance period of the gas filling equipment, and the first preset frequency corresponding to the gas filling equipment is adjusted based on the time distance; Obtaining, through the government safety supervision service platform, a number of reference vehicles at a second preset frequency, the reference vehicles being vehicles that are traveling and whose destination is the gas station; In response to the number of the reference vehicles being greater than a reference threshold, generating a control instruction, and sending the control instruction to the reference vehicles via the government safety supervision service platform; The control instruction includes determining candidate gas filling stations, and the candidate gas filling stations are other gas filling stations within a preset range of the gas filling stations.

7. The Internet of Things system according to claim 6, wherein: The determining, based on the historical gas filling data, the estimated usage characteristics of the gas filling station in a future period includes: The future period is divided into a plurality of future sub-periods, and the estimated usage characteristics of the gas station in each of the future sub-periods are estimated through a prediction model; the prediction model is a machine learning model.

8. The Internet of Things system according to claim 6, wherein: The determining of the operation and maintenance parameters of each of the gas filling equipment based on the estimated usage characteristics of the gas filling station and the historical operation characteristics of each of the gas filling equipment includes: For each of the gas filling devices, determining a failure probability of the gas filling device in the future time period based on the historical operating characteristics; The operation and maintenance parameters are determined based on the failure probability and the estimated usage characteristics.

9. The Internet of Things system according to claim 8, wherein: The Internet of Things system is further configured to: in response to the failure probability of the gas filling equipment not exceeding a maintenance threshold, determine the operation and maintenance parameters based on the failure probability of each gas filling equipment in the future time period and the estimated usage characteristics.

10. The Internet of Things system according to claim 9, wherein: The Internet of Things system is further configured to: Clustering the vectors to be clustered in the clustering database using the failure probability in the future time period as a clustering index to obtain a plurality of cluster groups, wherein the cluster group in which the failure probability of the gas filling equipment in the current future time period belongs is a target cluster group; For each of the gas filling devices, the operation and maintenance parameters of the gas filling device are determined based on historical estimated usage characteristics and historical operation and maintenance parameters corresponding to a plurality of first-category cluster vectors in the target cluster group where the gas filling device is located.

Images