Gas pipeline safety monitoring method, system and medium based on regulatory Internet of Things

Abstract

The present invention provides a gas pipeline safety monitoring method, system and medium based on the supervision Internet of Things, and relates to the field of gas pipeline monitoring technology. The method comprises: determining a second vibration sequence based on construction information and a first vibration sequence; determining a suspected leakage point based on feedback information and a second vibration sequence; generating maintenance instructions and parameter adjustment instructions based on the suspected leakage point; sending the maintenance instructions to the corresponding smart device and / or the corresponding maintenance personnel terminal, and sending the parameter adjustment instructions to the target pipeline monitoring equipment. The system comprises a citizen user platform, a smart gas government safety supervision management platform, a smart gas government safety supervision object platform and a smart gas equipment object platform. The method can also be run after being read by a computer instruction stored in a computer-readable storage medium. The present invention can accurately monitor the working status of the pipeline monitoring equipment and improve the safety of the use of the gas pipeline.

Description

Technical Field

[0001] The present invention relates to the field of gas pipeline monitoring technology, and in particular to a gas pipeline safety monitoring method, system and medium based on a regulatory Internet of Things. Background Art

[0002] Gas pipeline monitoring is a necessary step to ensure gas safety. Gas index data is collected through pipeline monitoring equipment, and an alarm is issued when the index data exceeds the preset threshold, so that timely maintenance can be carried out when the gas pipeline is abnormal. However, when the pipeline monitoring equipment fails, it may cause false alarms and other phenomena, resulting in unnecessary manual inspection costs.

[0003] To solve the above problems, CN109239265B proposes a monitoring equipment fault detection method, which can effectively determine the faulty monitoring equipment by analyzing the change pattern of the monitoring data of the monitoring equipment to determine whether there is abnormal data, and then distinguish whether the monitoring equipment has failed. However, the abnormal data may be caused by accidental factors (for example, environmental factors, human activity interference, etc.), not the monitoring equipment itself. This results in the method of judging whether the monitoring equipment is faulty based on the monitoring data is not highly adaptable, and sometimes manual troubleshooting is still required.

[0004] Therefore, a gas pipeline safety monitoring method, system and medium based on the regulatory Internet of Things are provided, which are helpful to accurately monitor the working status of the pipeline monitoring equipment, promptly discover gas pipelines that may have faults, and thus improve the safety of gas pipeline use. Summary of the invention

[0005] In order to accurately monitor the working status of pipeline monitoring equipment and improve the safety of gas pipeline use, this specification provides a gas pipeline safety monitoring method, system and medium based on the regulatory Internet of Things.

[0006] The invention content includes a gas pipeline safety monitoring method based on a regulatory Internet of Things, which is executed based on a smart gas company management platform of a smart gas Internet of Things system, including: obtaining a first vibration sequence based on vibration data uploaded by multiple pipeline monitoring devices collected by a smart gas equipment object platform, and the multiple pipeline monitoring devices are deployed in different pipeline areas; based on a smart gas government safety supervision and management platform, obtaining construction information corresponding to each pipeline area, and determining a second vibration sequence based on the construction information and the first vibration sequence; based on the smart gas government safety supervision and management platform, receiving feedback information from a citizen user platform; based on the feedback information and the second vibration sequence, determining a suspected leakage point; based on the suspected leakage point, generating a maintenance instruction and a parameter adjustment instruction, the maintenance instruction is configured to mobilize smart devices and / or maintenance personnel to maintain the suspected leakage point, and the parameter adjustment instruction is configured to adjust the monitoring parameters of the target pipeline monitoring device; and sending the maintenance instruction to the corresponding smart device and / or the corresponding maintenance personnel terminal through the smart gas equipment object platform, and sending the parameter adjustment instruction to the target pipeline monitoring device through the smart gas equipment object platform.

[0007] The invention content includes a gas pipeline safety monitoring system based on the supervision Internet of Things, the smart gas Internet of Things system includes a citizen user platform, a smart gas government safety supervision service platform, a smart gas government safety supervision management platform, a smart gas government safety supervision sensor network platform, a smart gas government safety supervision object platform, a smart gas gas company sensor network platform and a smart gas equipment object platform, the smart gas government safety supervision object platform includes a smart gas gas company management platform; the smart gas gas company management platform is configured to: based on the vibration data uploaded by multiple pipeline monitoring devices collected by the smart gas equipment object platform, obtain a first vibration sequence, the multiple pipeline monitoring devices are deployed in different pipeline areas; based on the smart gas government safety supervision management platform, obtain the construction information corresponding to each pipeline area, based on the construction The invention relates to a method for generating a smart gas government safety supervision and management platform, wherein the smart gas government safety supervision and management platform comprises the following steps: determining a second vibration sequence based on the worker information and the first vibration sequence; receiving feedback information from the citizen user platform based on the smart gas government safety supervision and management platform; determining a suspected leakage point based on the feedback information and the second vibration sequence; generating a maintenance instruction and a parameter adjustment instruction based on the suspected leakage point, wherein the maintenance instruction is configured to mobilize smart devices and / or maintenance personnel to maintain the suspected leakage point, and the parameter adjustment instruction is configured to adjust the monitoring parameters of a target pipeline monitoring device, wherein the target pipeline detection device is a pipeline monitoring device deployed in the gas pipeline; and sending the maintenance instruction to the corresponding smart device and / or the corresponding maintenance personnel terminal through the smart gas device object platform, and sending the parameter adjustment instruction to the target pipeline monitoring device through the smart gas device object platform.

[0008] The invention content includes a computer-readable storage medium, which stores computer instructions. When the computer reads the computer instructions in the storage medium, the computer executes the above-mentioned gas pipeline safety monitoring method based on the regulatory Internet of Things.

[0009] The beneficial effects brought about by the above invention include but are not limited to: (1) The suspected leakage point is determined by feedback information and the second vibration sequence, and maintenance instructions and parameter adjustment instructions are generated based on the suspected leakage point, so that the working status of the pipeline monitoring equipment can be accurately monitored and adjusted while the gas pipeline is maintained in a timely manner, which helps to reduce unnecessary manual inspections while ensuring the safety of gas pipeline operation; (2) Based on the gas usage characteristics and the suspected leakage point, the first area, the second area and the third area are determined, and the adjustment amount of the target pipeline monitoring equipment in each area is determined in combination with the system data load, which helps to prioritize the maintenance of areas with higher abnormal risks. While protecting the pipeline area, it avoids excessive system computing load and improves the intelligence of equipment monitoring and pipeline maintenance; (3) The fourth vibration sequence is determined by the denoising model, and the self-learning ability of machine learning can be used to find patterns from a large amount of data, quickly and accurately determine the fourth vibration sequence, which is helpful for the subsequent determination of suspected leakage points; (4) The probability of missed fault detection is determined by the scheduling model, and the first adjustment amount, second adjustment amount and third adjustment amount in the parameter adjustment instruction are determined in combination with the probability of missed fault detection, which helps to reduce the probability of missed suspected leakage points after adjusting the target pipeline monitoring equipment according to the first adjustment amount, second adjustment amount and third adjustment amount. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] This specification will be further described in the form of exemplary embodiments, which will be described in detail by the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein:

[0011] Figure 1 It is a platform schematic diagram of a gas pipeline safety system based on the supervision Internet of Things according to some embodiments of this specification;

[0012] Figure 2 is an exemplary flow chart of a gas pipeline safety monitoring method based on a supervisory Internet of Things according to some embodiments of this specification;

[0013] Figure 3 is an exemplary schematic diagram of determining a suspected leakage point according to some embodiments of this specification;

[0014] Figure 4 is an exemplary schematic diagram of a denoising model according to some embodiments of this specification;

[0015] Figure 5 is an exemplary schematic diagram of determining parameter adjustment instructions according to some embodiments of this specification. DETAILED DESCRIPTION

[0016] In order to more clearly illustrate the technical solutions of the embodiments of this specification, the following is a brief introduction to the drawings required for the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of this specification. For ordinary technicians in this field, this specification can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.

[0017] It should be understood that the "system", "device", "unit" and / or "module" used herein are a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

[0018] Unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "include" and "comprise" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0019] Flowcharts are used in this specification to illustrate the operations performed by the system according to the embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed precisely in order. Instead, the steps may be processed in reverse order or simultaneously. At the same time, other operations may also be added to these processes, or one or more operations may be removed from these processes.

[0020] In order to ensure the safety of gas pipelines, it is necessary to promptly detect faulty gas pipelines. Pipeline monitoring equipment can monitor gas pipelines and issue early warnings when gas pipelines may fail. Since pipeline monitoring equipment may cause false alarms and other phenomena, manual inspections are required to monitor the working status of pipeline monitoring equipment, which has high labor costs. CN109239265B can accurately determine which pipeline monitoring equipment has faults by analyzing the monitoring data of the monitoring equipment. However, the impact of accidental factors on the monitoring data is not considered, and the working status of the pipeline monitoring equipment cannot be remotely monitored.

[0021] In view of this, some embodiments of the present specification determine suspected leakage points based on the vibration data uploaded by the pipeline monitoring equipment, combined with construction information, feedback information and other data, and generate maintenance instructions and parameter adjustment instructions based on the suspected leakage points, which helps to accurately monitor the working status of the pipeline monitoring equipment and make adjustments, and promptly check for gas pipelines that may fail, thereby reducing unnecessary manual inspections and ensuring the safety of gas pipeline operation.

[0022] Figure 1 It is a platform schematic diagram of a gas pipeline safety monitoring system based on a supervisory Internet of Things as shown in some embodiments of this specification.

[0023] like Figure 1 As shown, the gas pipeline safety monitoring system 100 based on the regulatory Internet of Things may include a citizen user platform 110, a smart gas government safety regulatory service platform 120, a smart gas government safety regulatory management platform 130, a smart gas government safety regulatory sensor network platform 140, a smart gas government safety regulatory object platform 150, a smart gas gas company sensor network platform 160 and a smart gas equipment object platform 170.

[0024] The citizen user platform 110 refers to a platform for interacting with users. Users refer to all citizens who are related to smart gas (e.g., use smart gas). In some embodiments, the citizen user platform 110 can exchange information with users in a two-way manner. For example, users can obtain information or convey requirements through the citizen user platform 110. In some embodiments, the citizen user platform 110 can be configured as a terminal device. For example, the citizen user platform 110 can be a smart phone, a tablet, a laptop, etc., or any combination thereof.

[0025] In some embodiments, the citizen user platform 110 can interact bidirectionally with the smart gas government safety supervision service platform 120. For example, the smart gas government safety supervision service platform 120 can obtain feedback information from the citizen user platform 110.

[0026] The smart gas government safety supervision service platform 120 is a platform for conveying user needs and control information. In some embodiments, the smart gas government safety supervision service platform 120 can interact with the citizen user platform 110 in a two-way manner.

[0027] The smart gas government safety supervision management platform 130 is a platform that coordinates and coordinates the connection and collaboration between various functional platforms, gathers all the information of the Internet of Things, and provides perception management and control management functions for the Internet of Things operation system. The smart gas government safety supervision management platform can be set on at least one distributed server. The distributed server may include a storage device for making the operation of the government supervision comprehensive database. In some embodiments, the smart gas government safety supervision management platform 130 can interact with the smart gas government safety supervision service platform 120 in a two-way manner.

[0028] The smart gas government safety supervision sensor network platform 140 refers to a functional platform for managing the government's sensor communication. In some embodiments, the smart gas government safety supervision sensor network platform 140 can be operated based on a communication network and configured as a communication network or a gateway. In some embodiments, the smart gas government safety supervision sensor network platform 140 can realize the functions of sensing information sensor communication and controlling information sensor communication. In some embodiments, the smart gas government safety supervision sensor network platform 140 can interact with the smart gas government safety supervision management platform 130 in a two-way manner.

[0029] The smart gas government safety supervision object platform 150 refers to an object platform for sensing information generation and controlling information execution.

[0030] In some embodiments, the smart gas government safety supervision object platform 150 includes a smart gas gas company management platform 150-1.

[0031] The smart gas company management platform 150-1 refers to a platform for executing the equipment monitoring method of the smart gas pipeline. In some embodiments, the smart gas company management platform can be set on the gas company server. In some embodiments, the smart gas company management platform 150-1 can be configured as a processor, which can be a single server or a server group, and the server group can be centralized or distributed.

[0032] In some embodiments, the smart gas company management platform 150-1 is configured to: obtain a first vibration sequence based on vibration data uploaded by multiple pipeline monitoring devices collected by the smart gas equipment object platform; obtain construction information corresponding to each pipeline area based on the smart gas government safety supervision and management platform, and determine a second vibration sequence based on the construction information and the first vibration sequence; receive feedback information from the citizen user platform based on the smart gas government safety supervision and management platform; determine suspected leakage points based on the feedback information and the second vibration sequence; generate maintenance instructions and parameter adjustment instructions based on the suspected leakage points; and send maintenance instructions to corresponding smart devices through the smart gas equipment object platform, and / or through the corresponding maintenance personnel terminal, and send parameter adjustment instructions to the target pipeline monitoring equipment through the smart gas equipment object platform.

[0033] In some embodiments, the smart gas company management platform 150-1 is further configured to: obtain a third vibration sequence based on vibration data uploaded by multiple peripheral devices collected by the smart gas equipment object platform; determine a fourth vibration sequence based on the first vibration sequence and the third vibration sequence; determine a first suspicious point based on the feedback information and the second vibration sequence; determine a second suspicious point based on the feedback information and the fourth vibration sequence; determine a suspected leakage point based on the first suspicious point and the second suspicious point.

[0034] In some embodiments, the smart gas company management platform 150-1 is further configured to: perform a first clustering on the first suspicious point to determine multiple first clustering centers; perform a second clustering on the second suspicious point to determine multiple second clustering centers; determine each second clustering center as a suspected leakage point, and determine each first clustering center that meets the preset point conditions as a suspected leakage point.

[0035] In some embodiments, the smart gas company management platform 150-1 is further configured to: determine the fourth vibration sequence through a denoising model based on the first vibration sequence and the third vibration sequence, the input of the denoising model includes the first vibration sequence, the third vibration sequence, the device coordinates and the equipment coordinates, and the denoising model is a machine learning model.

[0036] In some embodiments, the smart gas company management platform 150-1 is further configured to: determine the first area, the second area and the third area based on the gas usage characteristics and the suspected leakage points; determine the maintenance instructions based on the first area; determine the first adjustment amount, the second adjustment amount and the third adjustment amount in the parameter adjustment instruction based on the first area, the second area, the third area and the system data load; send the parameter adjustment instruction to the target pipeline monitoring equipment based on the smart gas equipment object platform, and the parameter adjustment instruction is configured to: adjust the target pipeline monitoring equipment in the first area with the first adjustment amount, adjust the target pipeline monitoring equipment in the second area with the second adjustment amount, and adjust the target pipeline monitoring equipment in the third area with the third adjustment amount.

[0037] In some embodiments, the smart gas company management platform 150-1 is further configured to: generate multiple groups of candidate adjustment amounts based on system data load, each group of candidate adjustment amounts includes corresponding first candidate adjustment amounts, second candidate adjustment amounts and third candidate adjustment amounts; for each group of candidate adjustment amounts, determine the corresponding fault missed probability through a scheduling model, the input of the scheduling model includes the first area, the second area, the third area, the first candidate adjustment amount, the second candidate adjustment amount and the third candidate adjustment amount, and the scheduling model is a machine learning model; based on each group of candidate adjustment amounts and the corresponding fault missed probability, determine the first adjustment amount, the second adjustment amount and the third adjustment amount in the parameter adjustment instruction.

[0038] In some embodiments, the smart gas company management platform 150-1 is further configured to: determine the resonance characteristics based on the second vibration sequence, the third vibration sequence and the fourth vibration sequence; and determine the anti-phase resonance characteristics based on the resonance characteristics.

[0039] In some embodiments, the smart gas company management platform 150 - 1 can interact bidirectionally with the smart gas government safety supervision sensor network platform 140 upward, and can interact bidirectionally with the smart gas company sensor network platform 160 downward.

[0040] The smart gas company sensor network platform 160 refers to a platform for comprehensive management of sensor information of the gas company. In some embodiments, the smart gas company sensor network platform 160 includes a communication base station, a router, and a wireless WIF device. The smart gas company sensor network platform can be set on a gas company communication device.

[0041] The smart gas equipment object platform 170 can be configured as various monitoring devices. For example, the smart gas equipment object platform can include a gas flow meter, a pressure sensor, a temperature sensor, etc. The smart gas equipment object platform can be set on a gas company server.

[0042] In some embodiments, the smart gas equipment object platform 170 can bidirectionally interact with the smart gas company sensor network platform 160. In some embodiments, the smart gas equipment object platform can be communicatively connected with multiple pipeline monitoring devices based on a communication network.

[0043] In some embodiments, the smart gas equipment object platform 170 may include a maintenance personnel terminal. The maintenance personnel terminal is a terminal device corresponding to the maintenance personnel, such as a mobile phone, tablet, computer, etc. used by the maintenance personnel. The maintenance personnel can repair the gas pipeline based on the maintenance instructions received by the maintenance personnel terminal.

[0044] For more information about the above platforms, please refer to Figure 2-Figure 5 and related instructions.

[0045] In some embodiments of the present specification, a gas pipeline safety monitoring system 100 based on a regulatory Internet of Things can form an information operation closed loop among a citizen user platform, a smart gas government safety regulatory service platform, a smart gas government safety regulatory management platform, a smart gas government safety regulatory sensor network platform, a smart gas government safety regulatory object platform, a smart gas company sensor network platform, and a smart gas equipment object platform, and coordinate and operate regularly under the unified management of a smart gas company management platform, thereby realizing the informatization and intelligence of equipment monitoring of smart gas pipelines.

[0046] Figure 2 is an exemplary flow chart of a gas pipeline safety monitoring method based on the supervisory Internet of Things according to some embodiments of this specification. In some embodiments, process 200 can be executed by the smart gas company management platform 150-1 of the gas pipeline safety monitoring system 100 based on the supervisory Internet of Things. Figure 2 As shown, process 200 includes the following steps:

[0047] Step 210: Based on the vibration data uploaded by the multiple pipeline monitoring devices collected by the smart gas equipment object platform, a first vibration sequence is obtained. Figure 1 and its related description.

[0048] Pipeline monitoring equipment refers to equipment used to monitor gas pipelines, such as flow sensors, pressure sensors, vibration sensors, etc. Pipeline monitoring equipment can be installed on the surface of gas pipelines.

[0049] In some embodiments, multiple pipeline monitoring devices are deployed in different pipeline areas.

[0050] In some embodiments, the smart gas company management platform can determine the pipeline area corresponding to the pipeline monitoring device by querying the first preset table. The first preset table may include the correspondence between multiple pipeline monitoring devices and multiple pipeline areas. The smart gas company management platform can establish the first preset table based on the correspondence between the pipeline monitoring device and the pipeline area in the design drawing of the gas pipeline.

[0051] Vibration data refers to data related to the vibration of the gas pipeline. For example, the vibration data may include the amplitude of the gas pipeline, etc. In some embodiments, the smart gas company management platform may interact with the pipeline monitoring device based on the smart gas equipment object platform to obtain the vibration data collected by the pipeline monitoring device and uploaded to the smart gas equipment object platform.

[0052] The first vibration sequence refers to a sequence composed of points of different pipeline monitoring equipment at different times and their corresponding vibration data.

[0053] In some embodiments, the smart gas company management platform can construct a first vibration sequence based on the vibration data uploaded by multiple pipeline monitoring devices at different times. For example, the vibration data uploaded by the pipeline monitoring device obtained by the smart gas company management platform are: the vibration data of points a1 and a2 at time t1 are m11 and m21 respectively; the vibration data of points a1 and a2 at time t2 are m12 and m22 respectively, then the first vibration sequence constructed is ((a1, t1, m11), (a1, t2, m12), (a2, t1, m12), (a2, t2, m22)).

[0054] Step 220, based on the smart gas government safety supervision and management platform, obtain the construction information corresponding to each pipeline area, and determine the second vibration sequence based on the construction information and the first vibration sequence.

[0055] Construction information refers to information about construction conditions that may occur around the pipeline area. For example, construction information may include information related to municipal construction, highway construction, railway construction, and heavy vehicle traffic.

[0056] In some embodiments, the smart gas company management platform can access the government information disclosure website to obtain construction information based on the smart gas government safety supervision management platform.

[0057] In some embodiments, the smart gas company management platform can divide the pipeline area corresponding to the construction information in a variety of ways. For example, the smart gas company management platform can divide the pipeline area based on municipal roads. For another example, the smart gas company management platform can divide the pipeline area according to actual needs (e.g., pipeline density, etc.). Exemplarily, the smart gas company management platform can perform semantic matching or geographic location range matching based on the construction information and municipal roads to divide the pipeline area corresponding to the construction information according to the municipal roads.

[0058] The second vibration sequence refers to a vibration sequence obtained by processing the first vibration sequence and removing vibration data corresponding to the construction period.

[0059] In some embodiments, the smart gas company management platform can determine the second vibration sequence in a variety of ways based on the construction information and the first vibration sequence.

[0060] In some embodiments, the smart gas company management platform can determine the construction period based on the construction information, and determine the second vibration sequence based on the construction period and the first vibration sequence. For example, the smart gas company management platform can remove the vibration data corresponding to the points of the corresponding pipeline monitoring equipment within the construction range during the construction period to obtain the second vibration sequence.

[0061] Exemplarily, the first vibration sequence is ((a1, t1, m11), (a1, t2, m12), (a2, t1, m12), (a2, t2, m22)), municipal construction is carried out at time t2, and point a1 is located within the construction range of the municipal construction, then the second vibration sequence is ((a1, t1, m11), (a2, t1, m12), (a2, t2, m22)).

[0062] The construction period refers to the time period for construction. The smart gas company management platform can perform semantic matching based on the construction information to convert the construction information into information such as construction coordinates, vibration interference degree, construction period, and construction scope.

[0063] Construction coordinates refer to the coordinate locations where construction is carried out.

[0064] The degree of vibration interference refers to the degree of interference with the vibration of the gas pipeline. The degree of vibration interference may include mild interference, moderate interference, and severe interference, etc. The smart gas company management platform can determine the corresponding degree of vibration interference by querying the second preset table based on the construction type corresponding to the construction information. The second preset table may include the correspondence between different construction types and different degrees of vibration interference. The second preset table may be determined manually or by the system based on experience. For example, if the construction type is related to underground construction, the corresponding degree of vibration interference is severe interference; if the construction type is related to surface construction, the corresponding degree of vibration interference is mild interference. Exemplary underground construction types may include repairing underground drainage pipes, etc., and exemplary surface construction types may include maintenance of power equipment, etc.

[0065] In some embodiments, the smart gas company management platform may also determine a second vibration sequence based on the construction period, the vibration interference degree, and the first vibration sequence. For example, the smart gas company management platform may retain vibration data during construction periods with light interference and / or moderate interference, and remove vibration data during construction periods with heavy interference to obtain the second vibration sequence.

[0066] Step 230: Based on the smart gas government safety supervision and management platform, feedback information from the citizen user platform is received. For relevant information about the smart gas government safety supervision and management platform and the citizen user platform, please refer to Figure 1 and its related description.

[0067] Feedback information refers to the relevant feedback information of gas users on the failure of gas pipelines and / or pipeline monitoring equipment. For example, feedback information may be that a pipeline monitoring equipment is damaged, a gas pipeline originally buried leaks, etc.

[0068] In some embodiments, the smart gas company management platform can interact with the citizen user platform based on the smart gas government safety supervision management platform to obtain feedback information uploaded by users to the citizen user platform.

[0069] Step 240: Determine a suspected leakage point based on the feedback information and the second vibration sequence.

[0070] Suspected leakage points refer to points where gas pipelines may experience leakage, cracks or other faults.

[0071] In some embodiments, the smart gas company management platform can determine the suspected leakage point in a variety of ways based on the feedback information and the second vibration sequence.

[0072] For example, the smart gas company management platform can determine the points of the pipeline monitoring equipment corresponding to the feedback information as the first set; determine the points of the pipeline monitoring equipment corresponding to the abnormal vibration data in the second vibration sequence as the second set; based on the first set and the second set, determine the suspected leakage points through the first preset rule.

[0073] The point of the pipeline monitoring device corresponding to the feedback information may be the point of the pipeline monitoring device involved in the feedback information, and the point of the pipeline monitoring device set in the gas pipeline involved in the feedback information. The smart gas company management platform may determine the vibration data whose amplitude exceeds the amplitude threshold in the vibration data as abnormal vibration data. The amplitude threshold may be preset based on historical experience.

[0074] The first preset rule refers to a pre-set rule for determining a suspected leakage point based on the first set and the second set. An exemplary first preset rule may be: in response to the historical leakage frequency of the gas pipeline network exceeding the first frequency threshold, the intersection of the first set and the second set is determined as a suspected leakage point; in response to the historical leakage frequency of the gas pipeline network being lower than the second frequency threshold, the union of the first set and the second set is determined as a suspected leakage point.

[0075] The historical leakage frequency refers to the frequency of leakage in the gas pipeline network, which can be obtained based on the statistics of historical data. The first frequency threshold and the second frequency threshold can be preset by the system or manually, and the first frequency threshold is higher than the second frequency threshold.

[0076] In some embodiments, the smart gas company management platform can determine the suspected leakage point based on the first suspicious point and the second suspicious point. For more information, see Figure 3 and its related description.

[0077] Step 250: Generate maintenance instructions and parameter adjustment instructions based on the suspected leakage points.

[0078] Maintenance instructions refer to instructions for maintaining suspected leakage points. In some embodiments, the maintenance instructions can be configured to mobilize smart devices and / or maintenance personnel to maintain the suspected leakage points.

[0079] Smart devices refer to smart devices used to maintain suspected leakage points, such as pipeline robots, drones, etc. Smart devices can identify (e.g. take photos, videos, etc.) suspected leakage points and automatically inspect them.

[0080] In some embodiments, the smart gas company management platform can generate maintenance instructions based on the suspected leakage point. For example, when the suspected leakage point is a1, the smart gas company management platform can generate a maintenance instruction: there is a risk of pipeline leakage at point a1, please perform maintenance.

[0081] The parameter adjustment instruction refers to an instruction configured to adjust the monitoring parameters of the target pipeline monitoring device.

[0082] The target pipeline monitoring setting refers to the pipeline monitoring equipment deployed in the gas pipeline network. In some embodiments, the smart gas company management platform can interact with the smart gas government safety supervision management platform to obtain the pipeline monitoring equipment deployed in the gas pipeline network stored in the storage device.

[0083] Monitoring parameters refer to the relevant parameters used by pipeline monitoring equipment to monitor the gas pipeline network, such as monitoring accuracy, monitoring frequency, etc.

[0084] In some embodiments, the smart gas company management platform can generate parameter adjustment instructions based on suspected leakage points. For example, the smart gas company management platform can increase the monitoring accuracy and monitoring frequency of the suspected leakage points by a preset accuracy adjustment amount and a preset frequency adjustment amount; the preset accuracy adjustment amount and the preset frequency adjustment amount can be preset by the system or manually. Exemplarily, when the suspected leakage point is a1, the smart gas company management platform can generate a parameter adjustment instruction: There is a risk of pipeline leakage at point a1, please increase the monitoring accuracy and monitoring frequency of the pipeline monitoring equipment at a1 by the preset accuracy adjustment amount and the preset frequency adjustment amount.

[0085] In some embodiments, the smart gas company management platform can determine the first adjustment amount, the second adjustment amount, and the third adjustment amount in the parameter adjustment instruction based on each group of candidate adjustment amounts and the corresponding fault missed judgment probability. For more information, see Figure 5 and its related description.

[0086] Step 260: Send the maintenance instruction to the corresponding smart device and / or the corresponding maintenance personnel terminal through the smart gas equipment object platform, and send the parameter adjustment instruction to the target pipeline monitoring device through the smart gas equipment object platform. For more information about the smart gas equipment object platform, please refer to Figure 1 and its related description.

[0087] In some embodiments, the smart gas company management platform can interact with the smart gas equipment object platform based on the smart gas company sensor network platform, send maintenance instructions to the corresponding smart devices, and send parameter adjustment instructions to the corresponding target pipeline detection equipment; based on the smart gas company sensor network platform and the smart gas equipment object platform, the smart gas company management platform can interact with the smart gas equipment object platform to send maintenance instructions to the corresponding maintenance personnel terminal in the smart gas equipment object platform. For more information about the smart gas equipment object platform and the maintenance personnel terminal, please refer to Figure 1 and its related description.

[0088] In some embodiments of the present specification, suspected leakage points are determined through feedback information and the second vibration sequence, and maintenance instructions and parameter adjustment instructions are generated based on the suspected leakage points. This can accurately monitor the working status of the pipeline monitoring equipment and make adjustments while timely maintaining the gas pipeline, which helps to ensure the safety of gas pipeline operation while reducing unnecessary manual inspections.

[0089] In some embodiments, the smart gas company management platform can determine the first area, the second area and the third area based on the gas usage characteristics and the suspected leakage points; determine the maintenance instructions based on the first area; determine the first adjustment amount, the second adjustment amount and the third adjustment amount in the parameter adjustment instruction based on the first area, the second area, the third area and the system data load; based on the smart gas equipment object platform, send the parameter adjustment instruction to the target pipeline monitoring equipment.

[0090] Gas usage characteristics refer to characteristics related to gas usage, such as gas usage time period, gas usage duration, unit usage, etc. In some embodiments, the smart gas company management platform can obtain the gas usage characteristics recorded by the smart gas meter of the residents based on the smart gas equipment object platform.

[0091] The first area refers to a pipeline area where there is a higher abnormal risk (eg, pipeline leakage, etc.).

[0092] The second area refers to the pipeline area with a lower risk of abnormality.

[0093] The third area refers to the pipeline area without abnormal risks. For the division of pipeline areas, please refer to Figure 2 Related description in the previous article.

[0094] In some embodiments, the smart gas company management platform can determine the first area, the second area, and the third area in a variety of ways based on gas usage characteristics and suspected leakage points.

[0095] In some embodiments, the smart gas company management platform can determine a point quantity threshold based on gas usage characteristics, and determine the first area, the second area, and the third area based on the point quantity threshold and suspected leakage points.

[0096] The point quantity threshold refers to the threshold condition used to judge the first area based on the number of suspected leakage points. The smart gas company management platform can determine the point quantity threshold based on the gas usage time period of the gas usage characteristics. Exemplarily, the lower the point quantity threshold is when the gas usage time period is in the peak gas usage period; the higher the point quantity threshold is when the gas usage time period is in the trough gas usage period. The smart gas company management platform can determine the peak gas usage period and the trough gas usage period based on statistics of multiple residential smart gas meters.

[0097] In some embodiments, the smart gas company management platform can determine the pipeline area where the number of suspected leakage points exceeds the point number threshold as the first area, determine the pipeline area where the number of suspected leakage points does not exceed the point number threshold and is not 0 as the second area, and determine the pipeline area where the number of suspected leakage points is 0 as the third area.

[0098] In some embodiments, the smart gas company management platform can determine maintenance instructions based on the first area. The smart gas company management platform can determine maintenance instructions based on suspected leakage points in the first area. For example, when the suspected leakage points in the first area are a1 and a2, the smart gas company management platform can generate a maintenance instruction: There is a risk of pipeline leakage at points a1 and a2 in the first area, please give priority to maintenance. The smart gas company management platform can adjust the processing order of multiple maintenance instructions and set the priority of the maintenance instructions containing suspected leakage points in the first area to the highest.

[0099] The system data load refers to the load of data processing by the smart gas IoT system monitored by the equipment of the smart gas pipeline. In some embodiments, the smart gas company management platform can determine the system data load based on the data currently required to be processed. The more data that needs to be processed, the greater the system data load.

[0100] The first adjustment amount refers to the increase in the monitoring parameter of the target pipeline monitoring device in the first area.

[0101] The second adjustment amount refers to the increase in the monitoring parameter of the target pipeline monitoring device in the second area.

[0102] The third adjustment amount refers to the reduction amount of the monitoring parameter of the target pipeline monitoring device in the third area.

[0103] In some embodiments, the smart gas company management platform can determine the first adjustment amount, the second adjustment amount, and the third adjustment amount in the parameter adjustment instruction in a variety of ways based on the first area, the second area, the third area, and the system data load. For example, the greater the system data load, the greater the third adjustment amount, and the smaller the first adjustment amount and the second adjustment amount.

[0104] In some embodiments, the smart gas company management platform may generate a parameter adjustment instruction based on the first adjustment amount, the second adjustment amount, and the third adjustment amount, and send the parameter adjustment instruction to the target pipeline monitoring device based on the smart gas device object platform. For example, the parameter adjustment instruction generated by the smart gas company management platform may be: adjusting the target pipeline monitoring device in the first area with the first adjustment amount, adjusting the target pipeline monitoring device in the second area with the second adjustment amount, and adjusting the target pipeline monitoring device in the third area with the third adjustment amount.

[0105] In some embodiments of the present specification, the first area, the second area and the third area are determined based on the gas usage characteristics and the suspected leakage points, and the adjustment amount of the target pipeline monitoring equipment in each area is determined in combination with the system data load. This helps to avoid excessive system computing load while giving priority to maintaining pipeline areas with higher abnormal risks, thereby improving the intelligence of equipment monitoring and pipeline maintenance.

[0106] In some embodiments, the peripheral device of the gas pipeline may include a vibration generator, and the vibration sound generator may emit vibration based on the anti-phase resonance feature. In some embodiments, the smart gas company management platform may determine the resonance feature based on the second vibration sequence, the third vibration sequence, and the fourth vibration sequence; and determine the anti-phase resonance feature based on the resonance feature. For relevant descriptions of the peripheral device, the third vibration sequence, and the fourth vibration sequence, please refer to Figure 3 and its related description.

[0107] Resonance characteristics refer to characteristics related to the resonance generated by the gas pipeline, such as the natural frequency and phase of the gas pipeline vibration.

[0108] In some embodiments, the smart gas company management platform can determine the resonance characteristics in a variety of ways based on the second vibration sequence, the third vibration sequence, and the fourth vibration sequence.

[0109] For example, the smart gas company management platform can perform spectrum analysis on the second vibration sequence, the third vibration sequence, and the fourth vibration sequence to obtain resonance characteristics. Exemplary spectrum analysis methods may be data statistics, Fourier transform, and the like.

[0110] The anti-phase resonance feature refers to a related feature used to offset the resonance feature. In some embodiments, the smart gas company management platform can determine the anti-phase resonance feature based on the resonance feature. For example, the smart gas company management platform can determine a feature with the same frequency as the resonance feature but opposite phase as the anti-phase resonance feature.

[0111] In some embodiments of the present specification, the anti-phase resonance feature is determined by the resonance feature, and the vibration generator in the peripheral device can emit vibration based on the anti-phase resonance feature, which effectively offsets the resonance of the gas pipeline, reduces the impact of the resonance of the gas pipeline on the determination of suspected leakage points, and improves the accuracy of determining the suspected leakage points.

[0112] Figure 3 It is an exemplary schematic diagram of determining suspected leakage points according to some embodiments of this specification.

[0113] In some embodiments, the smart gas company management platform can obtain the third vibration sequence 321 based on the vibration data 310 uploaded by multiple peripheral devices collected by the smart gas equipment object platform; determine the fourth vibration sequence 331 based on the first vibration sequence 322 and the third vibration sequence; determine the first suspicious point 350 based on the feedback information 332 and the second vibration sequence 333; determine the second suspicious point 340 based on the feedback information and the fourth vibration sequence; determine the suspected leakage point 360 based on the first suspicious point and the second suspicious point. For relevant instructions on vibration data, first vibration sequence, feedback information, second vibration sequence and suspected leakage point, please refer to Figure 2 and its related description.

[0114] The vibration data uploaded by multiple peripheral devices refers to the vibration data collected by multiple peripheral devices and uploaded to the smart gas equipment object platform. The vibration data collected by the peripheral devices is the vibration data generated by the surrounding environment of the gas pipeline.

[0115] Peripheral devices refer to devices that are installed together with gas pipelines and are used to monitor the vibration of the surrounding environment of gas pipelines. For example, peripheral devices may include vibration sensors, etc. It should be noted that there is a certain distance between the peripheral devices and the gas pipelines. For example, when the gas pipeline is buried, the peripheral devices can be set on the surface; when the gas pipeline is exposed to the open air, the peripheral devices can be set on the surface around the gas pipeline and not in contact with the gas pipeline.

[0116] In some embodiments, the peripheral device may collect vibration data with set collection parameters.

[0117] The acquisition parameters refer to parameters related to the collection of vibration data by the peripheral device. For example, the acquisition parameters may include the time points of opening and / or closing the plurality of peripheral devices, the acquisition frequency, etc.

[0118] In some embodiments, the acquisition parameters may be related to the gas usage characteristics. For more information on the gas usage characteristics, see Figure 2 Relevant description after step 260.

[0119] In some embodiments, the greater the proportion of peak hours in the gas usage time period, the longer the gas usage time, and the greater the usage per unit time, the higher the collection frequency in the corresponding collection parameters.

[0120] In some embodiments of the present specification, collection parameters are determined based on gas usage characteristics, and the collection parameters of peripheral devices can be flexibly controlled in combination with actual gas usage conditions, thereby avoiding unnecessary collection of vibration data by peripheral devices.

[0121] The third vibration sequence refers to a sequence of vibration data generated by the surrounding environment of the gas pipeline received by the location of the peripheral device. In some embodiments, the smart gas company management platform can construct a third vibration sequence from the vibration data uploaded by multiple peripheral devices at different times. The data format and construction method of the third vibration sequence are similar to those of the first vibration sequence, which can be referred to Figure 2 Step 210 is a description of the first vibration sequence.

[0122] The fourth vibration sequence refers to a sequence consisting of vibration data generated by the gas pipeline itself (for example, leakage, etc.). Its data format is similar to the first vibration sequence and can be referred to Figure 2 Description of the first vibration sequence.

[0123] In some embodiments, the smart gas company management platform can determine the fourth vibration sequence in a variety of ways based on the first vibration sequence and the third vibration sequence. For example, the smart gas company management platform can determine the fourth vibration sequence through a preset algorithm based on the first vibration sequence and the third vibration sequence. An exemplary preset algorithm may be Fourier transform, etc. The vibration data collected by the pipeline monitoring equipment in the first vibration sequence is the superposition of the vibration caused by the pipeline itself and the vibration caused by the external environment; the vibration data collected by the peripheral device in the third vibration sequence is the vibration caused by the external environment. Through the pre-planned algorithm, the superposition effect of the vibration caused by the pipeline itself and the vibration caused by the external environment can be separated to obtain the vibration data caused by the pipeline itself in the fourth vibration sequence.

[0124] In some embodiments, the smart gas company management platform can determine the fourth vibration sequence based on the denoising model. For more information, see Figure 4 and its related description.

[0125] The first suspicious point refers to a point that may become a suspected leakage point obtained based on the second vibration sequence.

[0126] The second suspicious point refers to a point that may become a suspected leakage point obtained based on the fourth vibration sequence.

[0127] In some embodiments, the smart gas company management platform can determine the first suspicious point based on the feedback information and the second vibration sequence; determine the second suspicious point based on the feedback information and the third vibration sequence. The first suspicious point and the second suspicious point are determined in a similar manner to the method of determining the suspected leakage point in step 240. Figure 2 Related description in the previous article.

[0128] In some embodiments, the smart gas company management platform can determine the suspected leakage point in a variety of ways based on the first suspicious point and the second suspicious point. For example, the smart gas company management platform can determine the union of the first suspicious point and the second suspicious point as the suspected leakage point.

[0129] In some embodiments, the smart gas company management platform can perform a first clustering on the first suspicious point 350 to determine multiple first clustering centers 351; perform a second clustering on the second suspicious point 340 to determine multiple second clustering centers 341; determine each second clustering center as a suspected leakage point, and determine each first clustering center that meets the preset point conditions as a suspected leakage point.

[0130] The first clustering refers to a clustering algorithm that clusters multiple first suspicious points and clusters several first suspicious points in the pipeline area into a first clustering center.

[0131] The first cluster center 351 refers to a center point that can represent a plurality of first suspicious points in the pipeline area. In some embodiments, the smart gas company management platform can perform a first clustering on the first suspicious points to determine the first cluster center. The first clustering can be various feasible clustering algorithms, such as hierarchical clustering, K-means clustering, etc.

[0132] The second clustering refers to a clustering algorithm that clusters multiple second suspicious points and clusters several second suspicious points in the pipeline area into a second clustering center.

[0133] The second cluster center 341 refers to a center point that can represent several second suspicious points in the pipeline area. In some embodiments, the smart gas company management platform can perform a second clustering on the second suspicious points to determine the second cluster center. The second clustering can be various feasible clustering algorithms, such as hierarchical clustering, K-means clustering, etc. The clustering algorithms of the second clustering and the first clustering can be the same or different.

[0134] The preset point condition refers to a preset condition for determining whether the first cluster center is a suspected leakage point. In some embodiments, the preset point condition may be: the distance between the first cluster center and at least one second cluster center is less than a preset distance threshold.

[0135] The preset distance threshold refers to the threshold condition that the distance between the first cluster center and at least one second cluster center needs to meet when the first cluster center is used as a suspected leakage point. The preset distance threshold can be set by the system or manually.

[0136] In some embodiments, the preset distance threshold may be related to the number of second cluster centers.

[0137] In some embodiments, the greater the number of second cluster centers, the smaller the corresponding preset distance threshold.

[0138] The more the number of second cluster centers is, the easier it is for the first cluster center to be close to the second cluster center in terms of random probability. In some embodiments of the present specification, by negatively correlating the preset distance threshold with the number of second cluster centers, the suspected leakage points in the first cluster center can be selected more strictly when the number of second cluster centers is larger, thereby improving the accuracy of determining the suspected leakage points.

[0139] Since the second cluster center is determined based on the fourth vibration sequence, its confidence as a suspected leakage point is higher than that of the first cluster center. In some embodiments of the present specification, by treating each second cluster center as a suspected leakage point and determining each first cluster center that meets the preset point conditions as a suspected leakage point, the accuracy of determining the suspected leakage points can be improved, thereby reducing false alarms of suspected leakage points.

[0140] In some embodiments of the present specification, the suspected leakage point is determined by using the first suspected point and the second suspected point, and the vibration of the surrounding environment of the gas pipeline network and the vibration of the gas pipeline network itself can be considered at the same time, which helps to improve the accuracy of the suspected leakage point.

[0141] Figure 4 is an exemplary schematic diagram of a denoising model according to some embodiments of the present specification.

[0142] In some embodiments, the smart gas company management platform can determine the fourth vibration sequence 331 through the denoising model 420 based on the first vibration sequence 322 and the third vibration sequence 321. For the relevant description of the first vibration sequence, see Figure 2 For the third and fourth vibration sequences, please refer to Figure 3 and its related description.

[0143] The denoising model refers to a model used to determine the fourth vibration sequence. In some embodiments, the denoising model may be a machine learning model, for example, the denoising model may be a neural network model or the like.

[0144] In some embodiments, the input of the denoising model may include the first vibration sequence, the third vibration sequence, the device coordinates 411 , and the equipment coordinates 412 .

[0145] The device coordinates refer to the position coordinates corresponding to the peripheral device points in the third vibration sequence; the equipment coordinates refer to the position coordinates corresponding to the pipeline monitoring equipment points in the first vibration sequence. The smart gas company management platform can interact with the smart gas government safety supervision management platform to obtain the device coordinates and equipment coordinates stored in the storage device.

[0146] In some embodiments, the input of the denoising model may also include device characteristics 413 and apparatus characteristics 414 .

[0147] The device's own characteristics refer to characteristic information of the pipeline monitoring device itself corresponding to the vibration data in the first vibration sequence, for example, the burial depth of the pipeline monitoring device, the soil environment in which the pipeline monitoring device is located, and the like.

[0148] The device's own characteristics refer to characteristic information of the peripheral device itself corresponding to the vibration data in the third vibration sequence, for example, the burial depth of the peripheral device, the soil environment in which the peripheral device is located, and the like.

[0149] The smart gas company management platform can interact with the smart gas government safety supervision management platform to obtain the equipment characteristics and device characteristics stored in the storage device.

[0150] The characteristics of the device and the apparatus affect the degree of vibration attenuation. In some embodiments of this specification, the output fourth vibration sequence can be made more consistent with the actual situation by inputting the characteristics of the device and the apparatus into a denoising model.

[0151] In some embodiments, the smart gas company management platform can obtain a denoising model based on a training sample set. The training sample set may include a first training sample and a first label corresponding to the first training sample. For example, a plurality of first training samples with a first label may be input into the denoising model, a loss function may be constructed through the first label and the output of the initial denoising model, and the parameters of the initial denoising model may be iteratively updated based on the loss function through gradient descent or other methods. When the preset conditions are met, a trained denoising model is obtained. Among them, the preset conditions may be that the loss function converges, the number of iterations reaches a threshold, etc.

[0152] In some embodiments, the first training sample may include a sample first vibration sequence, a sample third vibration sequence, a sample device coordinate, and a sample equipment coordinate. The first training sample may be acquired based on experimental data. For example, vibration may be simulated near a peripheral device, and a sample first vibration sequence may be constructed based on vibration data recorded by a pipeline monitoring device before the simulated vibration, and a sample third vibration sequence may be constructed based on vibration data recorded by the peripheral device during the simulated vibration. The sample device coordinates and the sample equipment coordinates are the coordinates corresponding to the peripheral device and pipeline monitoring device as the experimental object. The peripheral device as the experimental object may include the peripheral device corresponding to the vibration data in the sample third vibration sequence; the pipeline monitoring device as the experimental object may include the pipeline monitoring device corresponding to the vibration data in the sample first vibration sequence. Among them, the number of vibration data in the experimental data may be manually selected to construct the sample first vibration sequence and the sample second vibration sequence.

[0153] The first label is the fourth vibration sequence corresponding to the first training sample. The first label can be determined based on the calculation of the experimental data. For example, the fourth vibration sequence corresponding to the first label can be calculated based on the sample first vibration sequence and the sample third vibration sequence in the experimental data by Fourier transform or the like.

[0154] In some embodiments, when the input of the denoising model includes the device's own characteristics and the device's own characteristics, the first training sample may also include the sample device's own characteristics and the sample device's own characteristics. The smart gas company management platform may determine the corresponding characteristics of the peripheral devices and pipeline monitoring equipment as experimental objects as the sample device's own characteristics and the sample device's own characteristics.

[0155] In some embodiments, the training sample set of the denoising model may include training samples of different categories.

[0156] In some embodiments, the category of the first training sample may be divided based on weather characteristics when the training sample is collected.

[0157] Weather features refer to features related to weather conditions when the training samples are collected, such as sunny days, rainy days, snowfall, lightning, strong winds, etc. Weather features can be recorded manually when the training samples are collected, or can be obtained by visiting weather websites.

[0158] In some embodiments, the proportion of training samples in each category is greater than a preset proportion.

[0159] The preset proportion refers to the preset proportion of training samples of each category in the training samples. In some embodiments, the preset proportion can be preset by the system or manually. The preset proportions of training samples of different categories can be the same or different.

[0160] In some embodiments, the preset proportions of training samples of different categories can be determined based on the weather characteristics throughout the year. Among the weather characteristics throughout the year, the higher the frequency of occurrence of the weather characteristics, the higher the corresponding preset proportion. The weather characteristics throughout the year can be obtained based on the statistics of the weather characteristics of the past year.

[0161] In some embodiments of the present specification, by training a denoising model with training samples of different categories, the denoising model can be adapted to a variety of weather conditions, thereby ensuring the accuracy of the fourth vibration sequence output under various weather characteristics.

[0162] In some embodiments of the present specification, the fourth vibration sequence is determined by a denoising model, and the self-learning ability of machine learning can be used to find patterns from a large amount of data to quickly and accurately determine the fourth vibration sequence, which is helpful for the subsequent determination of suspected leakage points.

[0163] Figure 5 is an exemplary schematic diagram of determining parameter adjustment instructions according to some embodiments of this specification.

[0164] In some embodiments, the smart gas company management platform can generate multiple groups of candidate adjustment amounts 520 based on the system data load 510, each group of candidate adjustment amounts includes a corresponding first candidate adjustment amount 521, a second candidate adjustment amount 522, and a third candidate adjustment amount 523; for each group of candidate adjustment amounts, the corresponding fault missed detection probability 540 is determined through the scheduling model 530; based on each group of candidate adjustment amounts and the corresponding fault missed detection probability, the first adjustment amount 551, the second adjustment amount 552, and the third adjustment amount 553 in the parameter adjustment instruction 550 are determined. For more information about the system data load, parameter adjustment instructions, the first adjustment amount, the second adjustment amount, and the third adjustment amount, please refer to Figure 2 and Figure 3 Related description.

[0165] The candidate adjustment amount refers to an adjustment amount of a monitoring parameter that is a candidate. In some embodiments, each group of candidate adjustment amounts includes a corresponding first candidate adjustment amount 521 , a second candidate adjustment amount 522 , and a third candidate adjustment amount 523 .

[0166] The first candidate adjustment amount refers to a first adjustment amount that may be used as an adjustment amount of the monitoring parameter of the target pipeline monitoring device in the first area.

[0167] The second candidate adjustment amount refers to a second adjustment amount that may be used as an adjustment amount of the monitoring parameter of the target pipeline monitoring device in the second area.

[0168] The third candidate adjustment amount refers to a third adjustment amount that may be used as an adjustment amount of the monitoring parameter of the target pipeline monitoring device in the third area.

[0169] In some embodiments, the smart gas company management platform can generate multiple groups of candidate adjustment amounts in a variety of ways based on the system data load. For example, the smart gas company management platform can randomly generate a first candidate adjustment amount, a second candidate adjustment amount, and a third candidate adjustment amount among the candidate adjustment amounts within a preset generation condition. The preset generation condition refers to a pre-set condition for generating candidate adjustment amounts based on the system data load. An exemplary preset generation condition may be: the total amount of data corresponding to the first candidate adjustment amount, the second candidate adjustment amount, and the third candidate adjustment amount does not exceed the maximum data processing capacity of the system data load. The maximum data processing capacity refers to the maximum amount of data that the system can process, which can be obtained through the configuration information of the smart gas company management platform.

[0170] The scheduling model refers to a model used to determine the probability of missed fault detection. In some embodiments, the scheduling model can be a machine learning model, such as a deep neural network (DNN).

[0171] In some embodiments, the input of the scheduling model may include a first area 524, a second area 525, a third area 526, a first candidate adjustment amount 521, a second candidate adjustment amount 522, and a third candidate adjustment amount 523; the output may include a fault missed detection probability 540. The first area, the second area, and the third area may be represented in the form of coordinates. For relevant descriptions of the first area, the second area, the third area, and their determination, please refer to Figure 2 Related description in the previous article.

[0172] In some embodiments, the input of the scheduling model may also include the location of the first cluster center 527 and the location of the second cluster center 528. The location of the first cluster center and the location of the second cluster center may be expressed in coordinate form.

[0173] For the determination of the first cluster center, the second cluster center and their locations, please refer to Figure 3 Related description in the previous article.

[0174] In some embodiments of the present specification, the accuracy of the probability of missed fault detection output by the scheduling model can be improved by taking the position of the first cluster center and the position of the second cluster center as inputs of the scheduling model.

[0175] The probability of missed fault detection refers to the probability of missing a suspected leakage point.

[0176] In some embodiments, the scheduling model can be trained based on the second training sample with the second label. The training of the scheduling model is similar to the training of the denoising model, which can be referred to Figure 4 Related description in the previous article.

[0177] In some embodiments, the second training sample may include a sample first region, a sample second region, a sample third region, a sample first adjustment amount, a sample second adjustment amount, and a sample third candidate amount; the second training sample may be acquired based on historical data.

[0178] The second label can be a value of 0 or 1. The second label of 1 represents that after adjustment according to the second training sample, unidentified suspected leakage points appear; the second label of 0 represents that after adjustment according to the second training sample, no unidentified suspected leakage points appear. The second label can be determined based on the fault traceback analysis of the suspected leakage point, and the second label can be manually labeled.

[0179] In some embodiments, when the input of the scheduling model includes the location of the first cluster center and the location of the second cluster center, the second training sample may also include the location of the first cluster center and the location of the second cluster center of the sample. The location of the first cluster center and the location of the second cluster center of the sample may be determined based on historical data.

[0180] In some embodiments, the smart gas company management platform may determine the first adjustment amount, the second adjustment amount, and the third adjustment amount in the parameter adjustment instruction based on each group of candidate adjustment amounts and the corresponding probability of missed fault judgment. The smart gas company management platform may determine the first candidate adjustment amount, the second candidate adjustment amount, and the third candidate adjustment amount corresponding to the candidate adjustment amount with the lowest probability of missed fault judgment as the first adjustment amount, the second adjustment amount, and the third adjustment amount in the parameter adjustment instruction.

[0181] In some embodiments of the present specification, the probability of missed fault detection is determined through a scheduling model, and the first adjustment amount, the second adjustment amount, and the third adjustment amount in the parameter adjustment instruction are determined in combination with the probability of missed fault detection. This helps to reduce the probability of missed leakage points after adjusting the target pipeline monitoring equipment according to the first adjustment amount, the second adjustment amount, and the third adjustment amount.

[0182] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only for example and does not constitute a limitation of this specification. Although not explicitly stated here, those skilled in the art may make various modifications, improvements and corrections to this specification. Such modifications, improvements and corrections are suggested in this specification, so such modifications, improvements and corrections still belong to the spirit and scope of the exemplary embodiments of this specification.

[0183] At the same time, this specification uses specific words to describe the embodiments of this specification. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of this specification. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures or characteristics in one or more embodiments of this specification can be appropriately combined.

[0184] In addition, unless explicitly stated in the claims, the order of the processing elements and sequences described in this specification, the use of alphanumeric characters, or the use of other names are not intended to limit the order of the processes and laminar flow hoods in this specification. Although the above disclosure discusses some of the invention embodiments currently considered useful through various examples, it should be understood that such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the 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 by software solutions, such as installing the described system on an existing server or mobile device.

[0185] Similarly, it should be noted that in order to simplify the description disclosed in this specification and thus help understand one or more embodiments of the invention, in the above description of the embodiments of this specification, multiple features are sometimes combined into one embodiment, figure or description thereof. However, this disclosure method does not mean that the features required by the subject matter of this specification are more than the features mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above.

[0186] In some embodiments, numbers describing the number of components and attributes are used. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise specified, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may change according to the required features of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining the digits. Although the numerical domains and parameters used to confirm the breadth of the range in some embodiments of this specification are approximate values, in specific embodiments, the setting of such numerical values ​​is as accurate as possible within the feasible range.

[0187] Each patent, patent application, patent application publication, and other materials, such as articles, books, specifications, publications, documents, etc., cited in this specification is hereby incorporated by reference in its entirety. Except for application history documents that are inconsistent with or conflicting with the contents of this specification, documents that limit the broadest scope of the claims of this specification (currently or later attached to this specification) are also excluded. It should be noted that if the descriptions, definitions, and / or use of terms in the materials attached to this specification are inconsistent or conflicting with the contents described in this specification, the descriptions, definitions, and / or use of terms in this specification shall prevail.

[0188] 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, as an example and not a limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. A gas pipeline safety monitoring method based on the supervision Internet of Things, characterized in that: The method is executed by a smart gas company management platform of a gas pipeline safety monitoring system based on the supervision Internet of Things, and includes: Acquire a first vibration sequence based on vibration data uploaded by multiple pipeline monitoring devices collected by the smart gas equipment object platform, wherein the multiple pipeline monitoring devices are deployed in different pipeline areas; Based on the smart gas government safety supervision and management platform, obtain the construction information corresponding to each pipeline area; Determine a construction period based on the construction information, process the first vibration sequence based on the construction period, and determine a second vibration sequence after removing the vibration data corresponding to the construction period; Based on the smart gas government safety supervision and management platform, feedback information is received from the citizen user platform, wherein the feedback information refers to information about the failure of the gas pipeline and / or the pipeline monitoring equipment; Determining a suspected leakage point based on the feedback information and the second vibration sequence includes: Acquire a third vibration sequence based on vibration data uploaded by multiple peripheral devices collected by the smart gas equipment object platform; Based on the first vibration sequence and the third vibration sequence, determining a fourth vibration sequence by using a denoising model, wherein an input of the denoising model includes the first vibration sequence, the third vibration sequence, a device coordinate, and a equipment coordinate, and the denoising model is a machine learning model; Determine a first suspicious point based on the feedback information and the second vibration sequence, where the first suspicious point refers to a point that may become the suspected leakage point obtained based on the second vibration sequence; Determine a second suspicious point based on the feedback information and the fourth vibration sequence, where the second suspicious point refers to a point that may become the suspected leakage point obtained based on the fourth vibration sequence; Determine the union of the first suspicious point and the second suspicious point as the suspected leakage point; Based on the gas usage characteristics and the suspected leakage point, determine the first area, the second area and the third area, the first area refers to the pipeline area with a higher abnormal risk, the second area refers to the pipeline area with a lower abnormal risk, and the third area refers to the pipeline area without abnormal risk; Determine a maintenance instruction based on the suspected leakage point in the first area, wherein the maintenance instruction is configured to mobilize smart devices and / or maintenance personnel to perform maintenance on the suspected leakage point; Determining a first adjustment amount, a second adjustment amount, and a third adjustment amount in a parameter adjustment instruction based on the first area, the second area, the third area, and a system data load, wherein the parameter adjustment instruction is configured to adjust a monitoring parameter of a target pipeline monitoring device, including: Based on the system data load, generating a plurality of groups of candidate adjustment amounts, each group of candidate adjustment amounts including a corresponding first candidate adjustment amount, a second candidate adjustment amount, and a third candidate adjustment amount; For each group of candidate adjustment amounts, determining a corresponding fault missed detection probability through a scheduling model, wherein an input of the scheduling model includes the first area, the second area, the third area, the first candidate adjustment amount, the second candidate adjustment amount, and the third candidate adjustment amount, and the scheduling model is a machine learning model; Determine the first adjustment amount, the second adjustment amount, and the third adjustment amount in the parameter adjustment instruction based on each group of candidate adjustment amounts and the corresponding fault missed detection probability; and The maintenance instruction is sent to the corresponding smart device and / or the corresponding maintenance personnel terminal through the smart gas equipment object platform, and the parameter adjustment instruction is sent to the target pipeline monitoring device through the smart gas equipment object platform, and the parameter adjustment instruction is configured to: adjust the target pipeline monitoring device in the first area with the first adjustment amount, adjust the target pipeline monitoring device in the second area with the second adjustment amount, and adjust the target pipeline monitoring device in the third area with the third adjustment amount.

2. A gas pipeline safety monitoring system based on the Internet of Things, characterized in that: The smart gas Internet of Things system includes a citizen user platform, a smart gas government safety supervision service platform, a smart gas government safety supervision management platform, a smart gas government safety supervision sensor network platform, a smart gas government safety supervision object platform, a smart gas gas company sensor network platform and a smart gas equipment object platform. The smart gas government safety supervision object platform includes a smart gas gas company management platform. The smart gas company management platform is configured as follows: Acquire a first vibration sequence based on vibration data uploaded by multiple pipeline monitoring devices collected by the smart gas equipment object platform, wherein the multiple pipeline monitoring devices are deployed in different pipeline areas; Based on the smart gas government safety supervision and management platform, obtain the construction information corresponding to each pipeline area; Determine a construction period based on the construction information, process the first vibration sequence based on the construction period, and determine a second vibration sequence after removing the vibration data corresponding to the construction period; Based on the smart gas government safety supervision and management platform, feedback information is received from the citizen user platform, wherein the feedback information refers to information about the failure of the gas pipeline and / or the pipeline monitoring equipment; Determining a suspected leakage point based on the feedback information and the second vibration sequence includes: Acquire a third vibration sequence based on vibration data uploaded by multiple peripheral devices collected by the smart gas equipment object platform; Based on the first vibration sequence and the third vibration sequence, determining a fourth vibration sequence by using a denoising model, wherein an input of the denoising model includes the first vibration sequence, the third vibration sequence, a device coordinate, and a equipment coordinate, and the denoising model is a machine learning model; Determine a first suspicious point based on the feedback information and the second vibration sequence, where the first suspicious point refers to a point that may become the suspected leakage point obtained based on the second vibration sequence; Determine a second suspicious point based on the feedback information and the fourth vibration sequence, where the second suspicious point refers to a point that may become the suspected leakage point obtained based on the fourth vibration sequence; Determine the union of the first suspicious point and the second suspicious point as the suspected leakage point; Based on the gas usage characteristics and the suspected leakage point, determine the first area, the second area and the third area, the first area refers to the pipeline area with a higher abnormal risk, the second area refers to the pipeline area with a lower abnormal risk, and the third area refers to the pipeline area without abnormal risk; Determine a maintenance instruction based on the suspected leakage point in the first area, wherein the maintenance instruction is configured to mobilize smart devices and / or maintenance personnel to perform maintenance on the suspected leakage point; Determining a first adjustment amount, a second adjustment amount, and a third adjustment amount in a parameter adjustment instruction based on the first area, the second area, the third area, and a system data load, wherein the parameter adjustment instruction is configured to adjust a monitoring parameter of a target pipeline monitoring device, including: Based on the system data load, generating a plurality of groups of candidate adjustment amounts, each group of candidate adjustment amounts including a corresponding first candidate adjustment amount, a second candidate adjustment amount, and a third candidate adjustment amount; For each group of candidate adjustment amounts, determining a corresponding fault missed detection probability through a scheduling model, wherein an input of the scheduling model includes the first area, the second area, the third area, the first candidate adjustment amount, the second candidate adjustment amount, and the third candidate adjustment amount, and the scheduling model is a machine learning model; Determine the first adjustment amount, the second adjustment amount, and the third adjustment amount in the parameter adjustment instruction based on each group of candidate adjustment amounts and the corresponding fault missed detection probability; and The maintenance instruction is sent to the corresponding smart device and / or the corresponding maintenance personnel terminal through the smart gas equipment object platform, and the parameter adjustment instruction is sent to the target pipeline monitoring device through the smart gas equipment object platform, and the parameter adjustment instruction is configured to: adjust the target pipeline monitoring device in the first area with the first adjustment amount, adjust the target pipeline monitoring device in the second area with the second adjustment amount, and adjust the target pipeline monitoring device in the third area with the third adjustment amount.

3. A computer-readable storage medium, characterized in that: The storage medium stores computer instructions. When the computer reads the computer instructions in the storage medium, the computer executes the gas pipeline safety monitoring method based on the supervisory Internet of Things as described in claim 1.

Images