Gas alarm detection method based on intelligent gas and internet of things system

Abstract

The embodiment of the specification provides a gas alarm detection method based on smart gas and an Internet of Things system. The method comprises the following steps: determining self-check parameters, and collecting gas monitoring data through a gas alarm; in response to receiving a cooperative verification request or meeting a cooperative cycle, determining whether the gas alarm has a fault based on the gas monitoring data and gas use data of a user; in response to the gas alarm having a fault, generating a fault data sequence of the gas alarm based on the gas monitoring data; and determining dispatch maintenance parameters of the gas alarm based on the fault data sequence. The Internet of Things system comprises a smart gas user platform, a smart gas service platform, a smart gas safety management platform, a smart gas indoor equipment sensing network platform and a smart gas indoor equipment object platform. The smart gas safety management platform is configured to execute the above-mentioned gas alarm detection method based on smart gas.

Description

Technical Field

[0001] This manual relates to the field of gas equipment testing, and in particular to a gas alarm testing method and Internet of Things system based on smart gas technology. Background Technology

[0002] With the increasing prevalence of natural gas use, the safety hazards posed by gas-related issues (such as gas leaks) are receiving more and more attention, and gas alarms have gradually become common equipment in gas safety monitoring. Gas alarms need to be able to detect low concentrations of flammable gas in the surrounding environment. When a gas leak occurs and the concentration of flammable gas exceeds a critical point, the gas alarm will sound an alarm. Therefore, the proper functioning of a gas alarm is crucial for gas safety. Currently, the proper functioning of a gas alarm is generally determined through pre-shipment testing and periodic manual inspections. However, when a gas alarm malfunctions during use, gas companies or users may not be able to detect the fault in time, leading to potential safety hazards for gas users.

[0003] Therefore, it is hoped that a gas alarm detection method and Internet of Things system based on smart gas technology can be provided to detect gas alarm malfunctions in a timely manner and perform maintenance, thereby improving the performance and reliability of gas alarms, meeting user needs in a timely and sufficient manner, and ensuring user safety. Summary of the Invention

[0004] This specification provides one or more embodiments of a gas alarm detection method based on smart gas technology. The smart gas alarm detection method includes: determining self-test parameters and collecting gas monitoring data through the gas alarm; the self-test parameters include a self-test cycle and a transmission cycle; the gas monitoring data includes at least one of gas concentration data, ambient temperature data, and ambient humidity data; in response to receiving a collaborative verification request or meeting the collaborative cycle, determining whether the gas alarm is faulty based on the gas monitoring data and the user's gas usage data; in response to the gas alarm being faulty, generating a fault data sequence for the gas alarm based on the gas monitoring data; and determining dispatch and maintenance parameters for the gas alarm based on the fault data sequence.

[0005] This specification provides one or more embodiments of a smart gas alarm detection IoT system. The system includes a smart gas user platform, a smart gas service platform, a smart gas safety management platform, a smart gas indoor device sensor network platform, and a smart gas indoor device object platform. The smart gas safety management platform includes a smart gas indoor safety management sub-platform and a smart gas data center. The smart gas indoor device sensor network platform is configured to interact with the smart gas data center and the smart gas indoor device object platform. The smart gas safety management platform is configured to: determine self-test parameters and collect gas monitoring data through the gas alarm. The data includes self-check parameters such as a self-check cycle and a transmission cycle; the gas monitoring data includes at least one of gas concentration data, ambient temperature data, and ambient humidity data; in response to receiving a collaborative verification request or meeting the collaborative cycle, the system determines whether the gas alarm is faulty based on the gas monitoring data and the user's gas usage data; in response to the gas alarm being faulty, the system generates a fault data sequence for the gas alarm based on the gas monitoring data; based on the fault data sequence, the system determines the dispatch and maintenance parameters for the gas alarm; the smart gas service platform is configured to send the dispatch and maintenance parameters to the smart gas user platform.

[0006] This specification provides one or more embodiments of a smart gas alarm detection device, the device including at least one processor and at least one memory; the at least one memory is used to store computer instructions; the at least one processor is used to execute at least a portion of the computer instructions to implement a smart gas alarm detection method.

[0007] This specification provides one or more embodiments of a computer-readable storage medium that stores computer instructions. When a computer reads the computer instructions from the storage medium, the computer executes the smart gas alarm detection method described in the above embodiments.

[0008] Beneficial Effects: Gas alarms perform self-checks based on a self-check cycle and periodically transmit gas monitoring data based on a transmission cycle, which helps to promptly detect potential faults in gas alarms and provides comprehensive gas monitoring data. Upon receiving a collaborative verification request or meeting the collaborative cycle, the intelligent gas safety management platform determines whether a gas alarm is faulty based on gas monitoring data and user gas usage data. It also determines the fault data sequence and dispatch maintenance parameters, allowing for a more comprehensive consideration of factors affecting gas alarm performance, more timely detection of potential problems, and prompt maintenance of the gas alarm. This improves the performance and reliability of gas alarms, ensures safe gas use, and enhances the user experience. Attached Figure Description

[0009] This specification will be further described by way of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not limiting; in these embodiments, the same reference numerals denote the same structures, wherein:

[0010] Figure 1 This is an exemplary platform structure diagram of a smart gas alarm detection Internet of Things system according to some embodiments of this specification;

[0011] Figure 2 This is an exemplary flowchart of a gas alarm detection method based on smart gas, as shown in some embodiments of this specification.

[0012] Figure 3 These are exemplary schematic diagrams of fault detection models shown in some embodiments of this specification; and

[0013] Figure 4 This is an exemplary flowchart illustrating the determination of dispatch maintenance parameters according to some embodiments of this specification. Detailed Implementation

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

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

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

[0017] Figure 1 This is an exemplary platform structure diagram of a smart gas alarm detection IoT system according to some embodiments of this specification. It should be noted that the following embodiments are for illustrative purposes only and do not constitute a limitation thereof.

[0018] like Figure 1 As shown, the smart gas alarm detection IoT system includes a smart gas user platform, a smart gas service platform, a smart gas safety management platform, a smart gas indoor equipment sensor network platform, and a smart gas indoor equipment object platform that interact sequentially.

[0019] A smart gas user platform is a platform for interacting with users. In some embodiments, the smart gas user platform can be configured as a terminal device. In some embodiments, the smart gas user platform may include a gas user sub-platform and a regulatory user sub-platform. The gas user sub-platform can be a platform that provides gas users with gas usage-related data and solutions to gas problems. Gas users can be industrial gas users, commercial gas users, general gas users, etc. The regulatory user sub-platform can be a platform for regulatory users to monitor the operation of the entire Internet of Things (IoT) system. Regulatory users can be personnel from safety management departments, etc.

[0020] A smart gas service platform can be a platform used to convey user needs and control information. The smart gas service platform can obtain information from a smart gas safety management platform (e.g., a smart gas data center) and send it to a smart gas user platform. In some embodiments, the smart gas service platform can be configured to send dispatch and maintenance parameters for gas alarms to the smart gas user platform. In some embodiments, the smart gas service platform can include a smart gas consumption service sub-platform and a smart regulatory service sub-platform. The smart gas consumption service sub-platform can be a platform that provides gas consumption services to gas users. The smart regulatory service sub-platform can be a platform that provides regulatory requirements to regulated users.

[0021] A smart gas safety management platform can coordinate and integrate the connections and collaboration between various functional platforms, and aggregate all information from the Internet of Things (IoT), providing sensing and control management functions for the IoT operating system. In some embodiments, the smart gas safety management platform may include a smart gas indoor safety management sub-platform and a smart gas data center. The smart gas indoor safety management sub-platform can be a platform for processing information related to gas alarms, etc. In some embodiments, the smart gas indoor safety management sub-platform may include, but is not limited to, management modules such as intrinsic safety monitoring management, information security monitoring management, functional safety monitoring management, and indoor safety inspection management. The smart gas indoor safety management sub-platform can analyze and process gas alarm-related information through the aforementioned management modules.

[0022] A smart gas data center can be used to store and manage all operational information of a smart gas alarm detection IoT system. In some embodiments, the smart gas data center can be configured as a storage device to store data related to gas alarms, such as gas monitoring data and collaborative verification requests. In some embodiments, the smart gas safety management platform can interact with the smart gas indoor device sensor network platform and the smart gas indoor device object platform through the smart gas data center. For example, the smart gas data center can send self-test parameters to the smart gas indoor device object platform. As another example, the smart gas data center can send a command to the smart gas indoor device sensor network platform to retrieve date data.

[0023] A smart gas indoor equipment sensor network platform can be a functional platform for managing sensor communication. In some embodiments, the smart gas indoor equipment sensor network platform is configured to interact with a smart gas data center and a smart gas indoor equipment object platform. In some embodiments, the smart gas indoor equipment sensor network platform can realize the functions of sensing and communication of perception information and control information. In some embodiments, the smart gas indoor equipment sensor network platform may include modules such as network management, protocol management, command management, and data parsing.

[0024] The smart gas indoor equipment object platform can be a functional platform for generating sensing information and executing control information. For example, the smart gas indoor equipment object platform can monitor and generate operating information of gas equipment. In some embodiments, the smart gas indoor equipment object platform may include a fair metering equipment object sub-platform, a safety monitoring equipment object sub-platform, and a safety valve control equipment object sub-platform. In some embodiments, the smart gas indoor equipment object platform can be configured as gas equipment such as gas alarms, flow meters, pressure gauges, gas meters, gas valve control devices, and gas emergency shut-off valves, wherein gas equipment includes gas stoves, water heaters, etc. The gas alarm includes components such as temperature sensors, humidity sensors, gas concentration sensors, processors, and storage devices. For more details, please refer to [link to relevant documentation]. Figure 2 The relevant description is provided below. For more information on the above, please refer to the following details. Figures 2 to 4 Related descriptions.

[0025] Some embodiments in this specification, based on the smart gas alarm detection IoT system, can form an information operation closed loop between the smart gas indoor equipment object platform and the smart gas user platform, and operate in a coordinated and regular manner under the unified management of the smart gas safety management platform, thereby realizing the informatization and intelligentization of gas alarm detection.

[0026] Figure 2This is an exemplary flowchart illustrating a smart gas alarm detection method according to some embodiments of this specification. Figure 2 As shown, process 200 includes the following steps. In some embodiments, process 200 may be executed by a smart gas safety management platform.

[0027] Step 210: Determine the self-test parameters and collect gas monitoring data through the gas alarm.

[0028] Self-test parameters refer to parameters related to the self-testing of a gas alarm. In some embodiments, self-test parameters include a self-test cycle and a transmission cycle. The self-test cycle refers to the cycle in which the gas alarm performs a self-test. The transmission cycle refers to the cycle in which the gas alarm transmits gas monitoring data to the smart gas data center through the smart gas indoor device sensor network platform. In some embodiments, self-test parameters can be preset by staff.

[0029] In some embodiments, the intelligent gas safety management platform can determine at least one self-test parameter at a preset period and send the self-test parameter to at least one gas alarm. The preset period can be set according to actual needs.

[0030] In some embodiments, the intelligent gas safety management platform can generate inspection feature vectors based on the service life, seasonal data, and gas usage data of the gas alarm; and determine self-inspection parameters through a vector database based on the inspection feature vectors.

[0031] Service life refers to the usage time of a gas alarm, such as 1 year, 2 years, etc. In some embodiments, the smart gas safety management platform can obtain the service life of the gas alarm through the smart gas indoor equipment sensor network platform.

[0032] Seasonal data refers to the season to which the current time belongs. In some embodiments, the intelligent gas safety management platform can automatically acquire seasonal data based on the current time.

[0033] Gas usage data refers to the usage data of gas appliances. For example, gas usage data may include the on-time, continuous usage time, usage volume, and operating power of gas appliances such as gas stoves and water heaters in a user's home. In some embodiments, the smart gas safety management platform can acquire gas usage data from networked gas appliances through a smart gas indoor device sensor network platform. In some embodiments, gas usage data can be represented by user usage characteristics. For example, user usage characteristics may include the frequency and amount of gas used by the user.

[0034] A test feature vector is a vector that characterizes the relevant features of a gas alarm. In some embodiments, the intelligent gas safety management platform can construct a test feature vector based on the gas alarm's service life, seasonal data, and gas usage data. Different elements in the test feature vector can represent the gas alarm's service life, seasonal data, and gas usage data, respectively.

[0035] The vector database may include reference feature vectors and corresponding reference self-test parameters for each gas alarm, constructed based on historical usage years, historical seasonal data, and historical user usage characteristics. The reference self-test parameters may include a reference self-test cycle and a reference transmission cycle. The intelligent gas safety management platform can determine reference feature vectors that meet preset conditions from the vector database based on the verified feature vectors, and then determine the reference self-test parameters corresponding to these preset conditions as the self-test parameters for the gas alarms. The preset conditions refer to the judgment criteria used to determine the reference feature vectors. In some embodiments, the preset conditions may include vector distance less than a distance threshold, minimum vector distance, etc.

[0036] Some embodiments in this specification use a vector database to determine self-test parameters, which can more comprehensively consider the factors affecting the performance of the gas alarm, thereby more accurately determining the self-test parameters of the gas alarm and improving the performance and reliability of the gas alarm.

[0037] In some embodiments, the test feature vector is also correlated with gas concentration fluctuation data.

[0038] Gas concentration fluctuation data refers to data that reflects the degree of change in gas concentration. In some embodiments, gas concentration fluctuation data may include the difference, variance, and change per unit time between current and historical gas concentration data. For further explanation regarding current and historical gas concentration data, please refer to [link to relevant documentation]. Figure 2 The following is a related description.

[0039] In some embodiments, the intelligent gas safety management platform can construct a test feature vector based on the service life, seasonal data, user usage data, and gas concentration fluctuation data of the gas alarm. The vector database may include a reference feature vector for each of multiple gas alarms, constructed based on historical service life, historical seasonal data, historical user usage characteristics, and historical gas concentration fluctuation data, along with corresponding reference self-test parameters (e.g., reference self-test cycle and reference transmission cycle). For information on determining the self-test parameters of gas alarms based on the vector database, please refer to [link to relevant documentation]. Figure 2 The above description.

[0040] In some embodiments of this specification, the larger the gas concentration fluctuation data, the greater the magnitude or the faster the change in gas concentration. The intelligent gas safety management platform can shorten the transmission cycle and self-test cycle, and can better assess the condition of the gas alarm.

[0041] A gas alarm is an instrument that detects and alerts the user about gas levels. In some embodiments, a gas alarm may include components such as a temperature sensor, a humidity sensor, a gas concentration sensor, a processor, and a storage device. The temperature sensor can be used to monitor ambient temperature data. The humidity sensor can be used to monitor ambient humidity data. The gas concentration sensor can be used to monitor gas concentration data. The processor can perform basic data processing. The storage device can store a small amount of data collected by the gas alarm, and is periodically cleared to allow for the storage of new data.

[0042] Gas monitoring data refers to monitoring data of the gas usage environment. In some embodiments, gas monitoring data includes at least one of gas concentration data, ambient temperature data, and ambient humidity data. Gas monitoring data includes data from multiple time points, such as current gas monitoring data and historical gas monitoring data.

[0043] Gas concentration data refers to the gas concentration in the gas usage environment. Gas concentration data can include current gas concentration data and historical gas concentration data. In some embodiments, the gas concentration sensor of a gas alarm can collect gas concentration data. The gas alarm can transmit the collected gas concentration data to the smart gas data center via a smart gas indoor device sensor network platform based on a transmission cycle. For more information on current concentration data and historical gas concentration data, see [link to relevant documentation]. Figure 2 The following text and related content.

[0044] Ambient temperature data refers to the temperature of the environment in which gas is used. In some embodiments, the temperature sensor of the gas alarm can collect ambient temperature data. The gas alarm can transmit the collected ambient temperature data to the smart gas data center through the smart gas indoor device sensor network platform based on a transmission cycle.

[0045] Ambient humidity data refers to the humidity of the environment in which gas is used. In some embodiments, the humidity sensor of the gas alarm can collect ambient humidity data. The gas alarm can transmit the collected ambient humidity data to the smart gas data center through the smart gas indoor device sensor network platform based on a transmission cycle.

[0046] In some embodiments, the smart gas safety management platform can collect gas monitoring data through gas alarms. Historical gas monitoring data can be temporarily stored in the storage device within the gas alarm. In some embodiments, the gas alarm can transmit the gas monitoring data and the historical gas monitoring data stored in the storage device to the smart gas data center of the smart gas safety management platform via a smart gas indoor device sensor network platform, based on a transmission cycle. The smart gas safety management platform can receive the gas monitoring data transmitted by the gas alarm and further process the gas monitoring data.

[0047] Step 220: In response to receiving a collaborative verification request or meeting the collaborative cycle, determine whether the gas alarm is faulty based on gas monitoring data and the user's gas usage data.

[0048] A collaborative verification request refers to the request data sent by the smart gas safety management platform to collaboratively determine whether a gas alarm is malfunctioning. The malfunction types of gas alarms can include component failure, sensor failure, circuit aging failure, etc. In some embodiments, the collaborative verification request can be sent by the gas alarm to the smart gas safety management platform through the smart gas indoor device sensor network platform.

[0049] In some embodiments, the intelligent gas safety management platform can determine the self-test result through a gas alarm, the self-test result being determined based on current gas concentration data and historical gas concentration data; and issue a collaborative verification request and gas monitoring data through the gas alarm, the collaborative verification request and gas monitoring data being issued in response to the self-test result meeting a first preset condition.

[0050] Current gas concentration data refers to the gas concentration data collected by the gas alarm during the current time period.

[0051] Historical gas concentration data refers to the gas concentration data collected by the gas alarm over a period of time in the past.

[0052] The self-test result refers to the result obtained by the gas alarm through self-check. In some embodiments, the self-test result may include normal and abnormal. The processor in the gas alarm can determine the self-test result in various ways and send it to the smart gas safety management platform through the smart gas indoor device sensor network platform. In some embodiments, the processor of the gas alarm can compare the current gas concentration data detected within a preset time period with the historical gas concentration data in the corresponding historical time period. If the difference is greater than the concentration threshold, the self-test result is considered abnormal. The preset time period can be the current time period mentioned above. The historical time period can be a period of time in the past that is distant from the current time period. The concentration threshold refers to the minimum concentration value for judging the self-test result as abnormal, which can be preset by the staff.

[0053] In some embodiments, a gas alarm can determine its self-test result using a gas concentration index. The gas concentration index is a quantitative value used to determine an abnormal gas concentration. In some embodiments, the gas concentration index can be a weighted sum of detection time and total detected concentration. The weights for the weighted sum can be determined based on historical experience. Detection time refers to the duration for which gas concentration is detected within a preset time period. Total detected concentration refers to the sum of gas concentrations detected within the preset time period. In some embodiments, the gas concentration index can be determined based on the analysis of current and historical gas concentration data. In some embodiments, the gas alarm can compare the gas concentration index obtained from analyzing current gas concentration data with the gas concentration index obtained from analyzing historical gas concentration data. If the difference is greater than a concentration index threshold, the self-test result is considered abnormal. The concentration index threshold is the minimum concentration index value required to determine an abnormal self-test result, and can be preset by the operator.

[0054] In some embodiments of this specification, monitoring only the total concentration may overlook equipment malfunctions or gas supply problems. By considering both gas concentration and detection time, it is possible to more accurately determine whether there is an abnormality in the gas.

[0055] The first preset condition refers to the condition under which a fault risk is determined. In some embodiments, the first preset condition may be an abnormal self-test result. In some embodiments, the first preset condition may be obtained based on pre-set parameters by staff.

[0056] In some embodiments, in response to a self-test result meeting a first preset condition, the gas alarm sends a collaborative verification request and gas monitoring data to the smart gas safety management platform via the smart gas indoor device sensor network platform. The smart gas safety management platform receives the collaborative verification request and gas monitoring data, and based on the gas monitoring data and the user's gas usage data, determines whether the gas alarm is faulty. For instructions on how to determine whether a gas alarm is faulty, see [link to documentation]. Figure 2 The following or Figure 3 And related content.

[0057] Some embodiments in this specification, by considering the current gas concentration data and historical gas concentration data of the gas alarm, can more accurately determine the self-test results of the gas alarm, which is beneficial for timely detection of risks present in the gas alarm, thereby improving the reliability and accuracy of the gas alarm during use.

[0058] In some embodiments, the intelligent gas safety management platform can determine the self-test result through the gas alarm, the self-test result being determined based on the current gas concentration data and the predicted gas concentration data at the current time point; and issue a collaborative verification request and gas monitoring data through the gas alarm, the collaborative verification request and gas monitoring data being issued in response to the self-test result meeting a first preset condition.

[0059] Predicted gas concentration data refers to the gas concentration data for the current time point predicted from historical data. In some embodiments, the predicted gas concentration data may be determined based on a fault detection model. For further explanation of the fault detection model, see [link to relevant documentation]. Figure 3 And its related descriptions.

[0060] In some embodiments, the gas alarm can compare the current gas concentration data detected within a preset time period with the predicted gas concentration data within the same preset time period. If the difference exceeds a concentration threshold, the self-test result is considered abnormal. In some embodiments, the gas alarm can compare the gas concentration index obtained from analyzing the current gas concentration data with the gas concentration index calculated from the predicted gas concentration data. If the difference exceeds a concentration index threshold, the self-test result is considered abnormal.

[0061] In some embodiments, when the current gas concentration data differs from both historical and predicted gas concentration data, the difference between the current and predicted gas concentration data can be used as the primary reference. Alternatively, the two differences can be weighted and summed before being compared with a comprehensive concentration threshold. The weights for the weighted summation can be determined based on historical experience. The comprehensive concentration threshold refers to the minimum sum of the concentration and concentration index that indicates an abnormal self-inspection result, and can be preset by staff.

[0062] In some embodiments, in response to a self-test result meeting a first preset condition, the gas alarm sends a collaborative verification request and gas monitoring data to the smart gas safety management platform via the smart gas indoor device sensor network platform. The smart gas safety management platform receives the collaborative verification request and gas monitoring data, and based on the gas monitoring data and the user's gas usage data, determines whether the gas alarm is faulty. For instructions on how to determine whether a gas alarm is faulty, see [link to documentation]. Figure 2 The following or Figure 3 And related content.

[0063] Some embodiments in this specification, by considering the current gas concentration data of the gas alarm and the predicted gas concentration data at the current time point, can more accurately determine the self-test results of the gas alarm, which is beneficial for timely detection of risks present in the gas alarm, thereby improving the reliability and accuracy of the gas alarm during use.

[0064] The coordination cycle refers to the period during which the intelligent gas safety management platform collaboratively determines whether a gas alarm is malfunctioning. In some embodiments, the coordination cycle can be obtained based on pre-set parameters by staff.

[0065] In some embodiments described in this specification, even without receiving a collaborative verification request, the intelligent gas safety management platform can still perform fault diagnosis on the gas alarm through a collaborative cycle, providing additional system reliability and stability, helping to ensure the safety of gas use, and providing a better user experience.

[0066] In some embodiments, the intelligent gas safety management platform can update the coordination cycle. For further information on updating the coordination cycle, please refer to [link to relevant documentation]. Figure 3 And related content.

[0067] In some embodiments, the intelligent gas safety management platform can pre-calculate multiple gas data clusters based on cluster analysis of multiple historical gas monitoring data and historical gas usage data from multiple historical users. Each gas data cluster corresponds to at least one attribute, which may include fault status, fault type, etc. Historical gas usage data refers to gas usage data over a past period. For an explanation of historical gas monitoring data and gas usage data, see [link to documentation]. Figure 2 The above and related content. In response to receiving a collaborative verification request or meeting a collaborative cycle, the intelligent gas safety management platform can calculate the first distance between the current gas monitoring data, the user's gas usage data, and each gas data cluster. In some embodiments, the first distance may be the distance between the current gas monitoring data, the user's gas usage data, and the cluster center of each gas data cluster. In some embodiments, the first distance may be the distance between the current gas monitoring data, the user's gas usage data, and each cluster within each gas data cluster. In some embodiments, the first distance may be Euclidean distance, etc. The intelligent gas safety management platform can determine whether the gas alarm is faulty based on the faulty attribute corresponding to the gas data cluster with the smallest first distance.

[0068] In some embodiments, the smart gas safety management platform can determine whether a gas alarm is faulty based on a fault detection model. For further explanation of the fault detection model, see [link to relevant documentation]. Figure 3 And its related descriptions.

[0069] Step 230: In response to a malfunction in the gas alarm, generate a fault data sequence for the gas alarm based on the gas monitoring data.

[0070] A fault data sequence refers to a sequence of data related to a malfunctioning gas alarm. In some embodiments, the fault data sequence includes the fault type of the gas alarm and the fault confidence level of that fault type. The fault confidence level refers to the degree of certainty that the gas alarm has experienced that particular fault type. For an explanation of fault types, see [link to documentation]. Figure 2 The superior position and related content.

[0071] In some embodiments, in response to receiving a collaborative verification request or meeting a collaborative cycle, the intelligent gas safety management platform can calculate the current gas monitoring data and a second distance for each gas data cluster. In some embodiments, the second distance can be calculated using Euclidean distance. The intelligent gas safety management platform can determine the fault type and fault confidence level based on the fault type data of each gas data cluster and the corresponding second distance. For example, the intelligent gas safety management platform can identify at least one fault type with a second distance less than a distance threshold as the fault type in the fault data sequence, pre-record and save a first preset table of correspondences between different second distances and different fault confidence levels, and determine the fault confidence level of at least one fault type based on the second distance through table lookup or other methods, thereby determining the fault data sequence.

[0072] In some embodiments, the fault data sequence can be determined based on a fault parameter determination model. For further explanation of the fault parameter determination model, see [link to relevant documentation]. Figure 4 And its related descriptions.

[0073] Step 240: Based on the fault data sequence, determine the dispatch and maintenance parameters for the gas alarm.

[0074] Maintenance dispatch parameters refer to relevant parameters regarding the maintenance of gas alarms. In some embodiments, maintenance dispatch parameters may include parameters such as the dispatched personnel, the dispatch time, and the maintenance tools used.

[0075] Different dispatched personnel can be associated with various types of information. For example, personnel information may include their ID number, repair experience, and the types of faults they are skilled at repairing. Dispatch time can be the time difference between the start time of the repair and the current time. Repair tools may include gas pipes, screwdrivers, new gas alarms, etc.

[0076] In some embodiments, the intelligent gas safety management platform can pre-record and save a second preset table showing the correspondence between different fault types and different dispatch maintenance parameters. The intelligent gas safety management platform can determine the dispatch maintenance parameters by querying the second preset table based on the fault type corresponding to a fault confidence level greater than a fault confidence threshold in the fault data sequence.

[0077] In some embodiments, the intelligent gas safety management platform can determine dispatch and maintenance parameters based on the fault data sequence output by the fault parameter determination model. For further explanation of the fault parameter determination model, see [link to relevant documentation]. Figure 4 And related content.

[0078] In some embodiments described in this specification, the gas alarm performs self-checks based on a self-check cycle and periodically transmits gas monitoring data based on a transmission cycle. This facilitates the timely detection of potential faults in the gas alarm and provides comprehensive gas monitoring data. Upon receiving a collaborative verification request or meeting the collaborative cycle, the intelligent gas safety management platform determines whether a fault exists in the gas alarm based on the gas monitoring data and the user's gas usage data. It also determines the fault data sequence and dispatch maintenance parameters. This allows for a more comprehensive consideration of factors affecting the gas alarm's performance, more timely detection of potential problems, and prompt repairs, improving the gas alarm's performance and reliability, ensuring gas safety, and enhancing the user experience.

[0079] It should be noted that the above description of the process is for illustrative purposes only and does not limit the scope of this specification. Those skilled in the art can make various modifications and changes to the process under the guidance of this specification. However, these modifications and changes remain within the scope of this specification.

[0080] Figure 3 This is an exemplary schematic diagram of a fault inspection model shown in some embodiments of this specification.

[0081] In some embodiments, the intelligent gas safety management platform can determine the failure probability 331 of the gas alarm based on gas monitoring data 311, gas usage data 313, and user room parameters 312, using a fault detection model 320. The intelligent gas safety management platform can then determine whether the gas alarm is faulty based on the failure probability 331.

[0082] Gas monitoring data 311 includes at least one of gas concentration data, ambient temperature data, and ambient humidity data. Gas monitoring data 311 includes data from multiple time points, such as current gas monitoring data and historical gas monitoring data. For further information on gas monitoring data and gas usage data, please refer to [link to relevant documentation]. Figure 2 And its related descriptions.

[0083] User room parameter 312 refers to relevant parameters of the room where gas is used. For example, user room parameter 312 may include data such as the size of the room. In some embodiments, the installer can measure and obtain user room parameter 312 when installing the gas alarm. In some embodiments, the installer can upload user room parameter 312 through the smart gas user platform, which is then transmitted through the smart gas service platform and pre-stored in the smart gas data center of the smart gas safety management platform.

[0084] The failure probability of 331 refers to the probability that the gas alarm may fail.

[0085] In some embodiments, the fault detection model 320 can be a machine learning model with a custom structure as described below. The fault detection model 320 can also be a machine learning model with other structures, such as a Neural Networks (NN) model.

[0086] In some embodiments, the input 310 of the fault detection model 320 may include gas monitoring data 311, gas usage data 313, and user room parameters 312, and the output may include fault probability 331.

[0087] In some embodiments, the fault detection model can be trained based on first training samples with a first label. Multiple first training samples with the first label can be input into the initial fault detection model. A loss function is constructed using the first label and the results of the initial fault detection model. The parameters of the initial fault detection model are iteratively updated based on the loss function. Model training is complete when the loss function of the initial fault detection model meets preset conditions, resulting in a trained fault detection model. These preset conditions may include loss function convergence, reaching a threshold number of iterations, etc. In some embodiments, each group of training samples may include sample monitoring data, sample gas usage data, and sample user room parameters. The first label of each group of training samples can indicate whether the gas alarm corresponding to the sample is actually faulty. For example, a first label of 0 indicates that the gas alarm is not faulty, and a first label of 1 indicates that the gas alarm is faulty. In some embodiments, the first training samples and the first label can be obtained based on historical data.

[0088] In some embodiments, the smart gas safety management platform determines that the gas alarm is faulty when the fault probability is greater than the fault threshold; otherwise, it determines that it is not faulty.

[0089] In some embodiments described in this specification, the intelligent gas safety management platform processes gas monitoring data and gas usage data through a fault detection model. It can utilize the self-learning capability of machine learning models to find patterns in a large amount of gas monitoring data and gas usage data, obtain the correlation between fault probability and gas monitoring data and gas usage data, improve the accuracy and efficiency of determining fault probability, and avoid losses caused by gas alarm malfunctions.

[0090] In some embodiments, the fault detection model 320 may include a decision layer 330 and a prediction layer 340. In some embodiments, the decision layer 330 and the prediction layer 340 may be Deep Neural Networks (DNNs).

[0091] In some embodiments, the intelligent gas safety management platform can determine the fault probability 331 through the judgment layer 330 based on gas monitoring data 311, gas usage data 313, and user room parameters 312; in response to the gas alarm not being faulty, it can determine the predicted gas concentration data 341 of the gas alarm at a future time point through the prediction layer 340 based on the fault probability 331, gas monitoring data 311, gas usage data 313, user room parameters 312, and date data 314.

[0092] In some embodiments, the inputs to the judgment layer 330 may include gas monitoring data 311, gas usage data 313, and user room parameters 312, and the output may be a fault probability 331.

[0093] In some embodiments, the decision layer can be trained based on second training samples with a second label. In some embodiments, each set of training samples may include sample gas monitoring data, sample gas usage data, and sample user room parameters. The second label for each set of training samples can be whether the corresponding gas alarm is faulty. For example, a first label of 0 indicates that the gas alarm is not faulty, and a first label of 1 indicates that the gas alarm is faulty. In some embodiments, the second training samples and the second label can be obtained based on historical data. The training process of the decision layer is similar to the training process of a fault detection model; see [link to relevant documentation] for details. Figure 3 The above is related content.

[0094] In some embodiments, in response to a second preset condition being met by the fault probability 331, the intelligent gas safety management platform may update the coordination period based on the fault probability 331. For further explanation of the coordination period, see [link to relevant documentation]. Figure 2 And its related content.

[0095] The second preset condition refers to the condition for determining whether to update the coordination cycle. In some embodiments, the second preset condition can be that the failure probability 331 is greater than the suspicion threshold but less than the failure threshold. The suspicion threshold is the minimum failure probability that requires updating the coordination cycle, and can be determined based on historical experience. In some embodiments, the second preset condition can be preset in advance based on historical experience.

[0096] In some embodiments, the initial coordination period is preset, and the length of the updated coordination period can be negatively correlated with the fault probability 331. For example, when the alarm fault probability is greater than the suspicion threshold but less than the fault threshold, the coordination period should be shortened, and the greater the fault probability, the more the corresponding coordination period should be shortened, and the shorter the updated coordination period.

[0097] Some embodiments in this specification update the coordination cycle based on the failure probability of the gas alarm, which can improve the accuracy of the determined coordination cycle, make the monitoring of the gas alarm more effective, improve the reliability of the gas alarm during use, and reduce the possibility of accidents.

[0098] In some embodiments, the inputs to the prediction layer 340 may include fault probability 331, gas monitoring data 311, gas usage data 313, user room parameters 312, and date data 314, etc. The output of the prediction layer 340 may be predicted gas concentration data 341 for a future time point.

[0099] In some embodiments, the extent to which the prediction layer 340 uses current gas concentration data from gas monitoring data during prediction can be positively correlated with the confidence level. For further explanation of current gas concentration data, see [link to relevant documentation]. Figure 2 And related descriptions. Trust level refers to the degree of confidence the prediction layer has in the current gas concentration data. In some embodiments, trust level is negatively correlated with the failure probability. For example, if there are currently 15 historical gas concentration data points and 5 current gas concentration data points, and the judgment layer determines a low failure probability, i.e., a high degree of confidence in the current gas concentration data, the prediction layer can use 10 historical gas concentration data points and 5 current gas concentration data points to predict the predicted gas concentration data for future time points. If the failure probability is high but not greater than the suspicion threshold, the prediction layer can use 13 historical gas concentration data points and 2 randomly selected current gas concentration data points to predict the predicted gas concentration data for future time points.

[0100] Date data 314 refers to data related to the current time. For example, date data 314 may include seasonal data for the current season and the specific date of the current time. In some embodiments, the smart gas safety management platform can obtain date data 314 from the network through the smart gas indoor device sensor network platform. Gas consumption may vary in different seasons and on different dates, thus predicting different gas concentration data.

[0101] Predicted gas concentration data for future time points refers to the gas concentration data corresponding to the predicted future time points. Predicted gas concentration data may include gas concentration data for multiple future time points. For more information on predicted gas concentration data, please see [link to documentation]. Figure 2 And its related descriptions.

[0102] In some embodiments, the prediction layer can be trained based on third training samples with a third label. In some embodiments, each set of training samples in the third training set may include sample fault probabilities, sample gas monitoring data, sample gas usage data, sample user room parameters, and sample date data from a historical first time period. The third label for each set of training samples can be the actual gas concentration data from a historical third time period. The historical first time period is earlier than the historical third time period. In some embodiments, the third training samples can be obtained based on historical data, and the third label can be obtained by labeling the actual gas concentration data from the historical third time period. The training process of the prediction layer is similar to that of the fault detection layer, which can be found in [reference needed]. Figure 3 The above is a related explanation.

[0103] In some embodiments, the intelligent gas safety management platform can transmit the predicted gas concentration data 341 from the prediction layer to the gas alarm on the intelligent gas indoor device object platform via the intelligent gas indoor device sensor network platform. This allows the gas alarm to determine its self-check result based on the current gas concentration data and the predicted gas concentration data at the current time, and then determine whether to issue a collaborative verification request and gas monitoring data. For more details, please refer to [link to relevant documentation]. Figure 2 And related explanations.

[0104] In some embodiments described in this specification, the intelligent gas safety management platform divides the fault detection model into a judgment layer and a prediction layer to process gas monitoring data and gas usage data. It can utilize the self-learning capability of machine learning models to find patterns from a large amount of gas monitoring data and gas usage data, and more comprehensively consider the factors affecting the performance of gas alarms. This improves the accuracy and efficiency of determining fault probability and predicting gas concentration data, and helps to promptly identify potential problems and take corresponding preventive and corrective measures.

[0105] In some embodiments, the intelligent gas safety management platform can predict gas concentration data 341 for future time points through the prediction layer 340 according to a preset prediction period. The fault probability 331 in the input of the prediction layer 340 can be the fault probability 331 output by the judgment layer most recently at the current time point.

[0106] The preset prediction period refers to the period at which the prediction layer performs predictions. In some embodiments, the preset prediction period can be obtained based on settings pre-configured by staff.

[0107] In some embodiments described in this specification, the intelligent gas safety management platform can not only predict the predicted gas concentration data for future time points when a collaborative verification request is made, but also predict the predicted gas concentration data for future time points at regular intervals (according to a preset prediction cycle) and send it to the gas alarm for self-checking, which can improve the reliability of the gas alarm and ensure the safety of gas use.

[0108] Figure 4 This is an exemplary flowchart illustrating the determination of dispatch maintenance parameters according to some embodiments of this specification. Figure 4 As shown, process 400 includes the following steps. In some embodiments, process 400 may be executed by a smart gas safety management platform.

[0109] Step 410: Based on gas monitoring data, gas usage data, and historical maintenance data, determine the fault data sequence through the fault parameter determination model.

[0110] In some embodiments, the fault parameter determination model can be a machine learning model, such as a Deep Neural Networks (DNN) model, a Convolutional Neural Networks (CNN) model, or any combination thereof.

[0111] In some embodiments, the input to the fault parameter determination model may include gas monitoring data, gas usage data, and historical maintenance data, and the output may be a fault data sequence.

[0112] For more information on gas monitoring data, gas usage data, and fault data sequences, please see [link to relevant documentation]. Figure 2 And its related descriptions.

[0113] Historical maintenance data refers to data related to the inspection and maintenance of gas alarms over a historical period. For example, historical maintenance data may include the number of inspections and maintenance performed on the gas alarms, the time of inspection, and the specific details of the inspections and maintenance. In some embodiments, the smart gas safety management platform can obtain historical maintenance data from the storage devices of the gas alarms on the smart gas indoor equipment object platform through the smart gas indoor equipment sensor network platform.

[0114] In some embodiments, the fault parameter determination model can be trained based on a fourth training sample with a fourth label. In some embodiments, each set of training samples may include sample gas monitoring data, sample gas usage data, and sample historical maintenance data. The fourth label corresponding to each set of training samples can be at least one actual fault type. A value of 1 corresponds to an actual fault type, and a value of 0 corresponds to a fault type that does not actually exist. In some embodiments, the fourth training samples and the fourth label can be obtained based on historical data. The training process of the fault parameter determination model is similar to that of the fault inspection model; see [link to relevant documentation] for details. Figure 3 And its related descriptions.

[0115] Step 420: Determine the estimated fault type based on the fault data sequence.

[0116] The fault data sequence includes the fault type of the gas alarm and the fault confidence level for each fault type. For more information on the fault data sequence, see [link to relevant documentation]. Figure 2 And related content.

[0117] The estimated fault type refers to the type of fault that the gas alarm is expected to have.

[0118] In some embodiments, the intelligent gas safety management platform can determine the fault type corresponding to a fault confidence level greater than the fault confidence level threshold as the estimated fault type.

[0119] Step 430: Determine the dispatch maintenance parameters based on the estimated fault type.

[0120] In some embodiments, the intelligent gas safety management platform can determine dispatching parameters (such as dispatching time and dispatching personnel) based on the estimated fault type and a second preset table, through methods such as table lookup. For further explanation of the second preset table and dispatching parameters, please refer to [link to relevant documentation]. Figure 2 And related content.

[0121] In some embodiments, the intelligent gas safety management platform can search the dispatch personnel database based on the estimated fault type and select dispatch personnel skilled in estimating fault types as the dispatch personnel in the dispatch maintenance parameters. The maintenance personnel database can store relevant information for different dispatch personnel. For more information on maintenance personnel, please refer to [link to relevant documentation]. Figure 2 And related descriptions. The intelligent gas safety management platform can, based on the predicted fault type, remind maintenance personnel of the necessary repair tools through control commands, or, if it determines that the gas alarm cannot be repaired, to bring a new one for replacement.

[0122] In some embodiments, the dispatch maintenance scheme is also related to user usage characteristics. For further explanation of user usage characteristics, see [link to relevant documentation]. Figure 2 And related content. For example, user usage characteristics indicate that the more frequently a user uses gas and the greater their gas consumption, the shorter the dispatch time in the corresponding dispatch and maintenance plan.

[0123] In some embodiments described in this specification, the intelligent gas safety management platform determines fault data sequences based on a fault parameter determination model, and then determines the estimated fault type and dispatch maintenance parameters. By analyzing and learning from a large amount of historical data, the platform can more accurately determine fault data sequences, thereby improving the accuracy of the determined estimated fault type and dispatch maintenance parameters. This facilitates more timely scheduling of gas alarm maintenance work and improves the reliability of gas alarms.

[0124] This specification provides a smart gas alarm detection device according to some embodiments. The device includes at least one processor and at least one memory. The at least one memory is used to store computer instructions. The at least one processor is used to execute at least a portion of the computer instructions to implement the smart gas alarm detection method according to any one of the embodiments of this specification.

[0125] Some embodiments of this specification provide a computer-readable storage medium for storing computer instructions. When a computer reads the computer instructions from the storage medium, the computer can execute a gas alarm detection method based on smart gas.

[0126] The basic concepts have been described above. Obviously, for those skilled in the art, the detailed disclosure above is merely illustrative and does not constitute a limitation of this specification. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements, and corrections to this specification. Such modifications, improvements, and corrections are suggested in this specification and therefore remain within the spirit and scope of the exemplary embodiments described herein.

[0127] Furthermore, unless expressly stated in the claims, the order of processing elements and sequences, the use of numbers and letters, or other names described in this specification are not intended to limit the order of the processes and methods described herein. Although various examples have been discussed in the foregoing disclosure of some embodiments of the invention that are currently considered useful, it should be understood that such details are for illustrative purposes only, and the appended claims are not limited to the disclosed embodiments; rather, the claims are intended to cover all modifications and equivalent combinations that conform to the spirit and scope of the embodiments described herein. For example, while the system components described above can be implemented using hardware devices, they can also be implemented solely using software solutions, such as installing the described system on existing servers or mobile devices.

[0128] Similarly, it should be noted that, in order to simplify the description disclosed herein and thus aid in the understanding of one or more embodiments of the invention, the foregoing description of embodiments in this specification may sometimes combine multiple features into a single embodiment, drawing, or description thereof. However, this method of disclosure does not imply that the subject matter of this specification requires more features than those mentioned in the claims. In fact, the embodiments contain fewer features than all the features of a single embodiment disclosed above.

[0129] In some embodiments, numbers describing the quantity of components and attributes are used. It should be understood that such numbers used in the description of embodiments are modified in some examples with the terms "approximately," "approximately," or "generally." Unless otherwise stated, "approximately," "approximately," or "generally" indicates 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 be changed depending on the characteristics required by individual embodiments. In some embodiments, numerical parameters should take into account specified significant digits and employ a general method of digit reservation. Although the numerical ranges and parameters used to confirm their breadth of range in some embodiments of this specification are approximate values, in specific embodiments, such values ​​are set as precisely as feasible.

[0130] Finally, it should be understood that the embodiments described in this specification are merely illustrative of the principles of the embodiments described herein. Other variations may also fall within the scope of this specification. Therefore, alternative configurations of the embodiments described herein are intended to be illustrative rather than limiting, and should be considered consistent with the teachings of this specification. Accordingly, the embodiments described herein are not limited to those explicitly introduced and described herein.

Claims

1. A gas alarm detection method based on smart gas technology, characterized in that, The method includes: Determine self-test parameters and collect gas monitoring data through a gas alarm. The self-test parameters include a self-test cycle and a transmission cycle. The gas monitoring data includes at least one of gas concentration data, ambient temperature data, and ambient humidity data. Based on the gas concentration data and at least one of historical gas concentration data and predicted gas concentration data, the self-test result is determined by the gas alarm. In response to the self-test result meeting the first preset condition, a collaborative verification request and the gas monitoring data are sent through the gas alarm. In response to receiving the collaborative verification request, or in response to not receiving the collaborative verification request and meeting the collaborative cycle, the failure probability of the gas alarm is determined by a fault detection model based on the gas monitoring data, the user's gas usage data, and the user's room parameters. The fault detection model is a machine learning model. In response to the failure probability satisfying a second preset condition, the coordination period is updated based on the failure probability. The second preset condition is that the failure probability is greater than a suspicion threshold and less than a failure threshold. The duration of the updated coordination period is negatively correlated with the failure probability. Based on the aforementioned failure probability, it is determined whether the gas alarm is faulty; When the gas alarm malfunctions, based on the gas monitoring data, the gas usage data, and historical maintenance data, the fault data sequence of the gas alarm is determined by a fault parameter determination model, which is a machine learning model. Based on the fault data sequence, the estimated fault type is determined, wherein the fault data sequence includes the fault type of the gas alarm and the fault confidence level of the fault type; Based on the estimated fault type, the dispatch and maintenance parameters for the gas alarm are determined, including the dispatch personnel and the dispatch time.

2. The method according to claim 1, characterized in that, The determination of the self-test parameters includes: Based on the service life and seasonal data of the gas alarm and the gas usage data, a verification feature vector is generated. Based on the aforementioned test feature vector, the self-test parameters are determined using a vector database.

3. A smart gas alarm detection IoT system, characterized in that, The system includes a smart gas user platform, a smart gas service platform, a smart gas safety management platform, a smart gas indoor equipment sensor network platform, and a smart gas indoor equipment object platform that interact sequentially. The intelligent gas safety management platform includes an intelligent gas indoor safety management sub-platform and an intelligent gas data center; The smart gas indoor equipment sensor network platform is configured to interact with the smart gas data center and the smart gas indoor equipment object platform. The intelligent gas safety management platform is configured as follows: Determine self-test parameters and collect gas monitoring data through a gas alarm. The self-test parameters include a self-test cycle and a transmission cycle. The gas monitoring data includes at least one of gas concentration data, ambient temperature data, and ambient humidity data. Based on the gas concentration data and at least one of historical gas concentration data and predicted gas concentration data, the self-test result is determined by the gas alarm. In response to the self-test result meeting the first preset condition, a collaborative verification request and the gas monitoring data are sent through the gas alarm. In response to receiving the collaborative verification request, or in response to not receiving the collaborative verification request and meeting the collaborative cycle, the failure probability of the gas alarm is determined by a fault detection model based on the gas monitoring data, the user's gas usage data, and the user's room parameters. The fault detection model is a machine learning model. In response to the failure probability satisfying a second preset condition, the coordination period is updated based on the failure probability. The second preset condition is that the failure probability is greater than a suspicion threshold and less than a failure threshold. The duration of the updated coordination period is negatively correlated with the failure probability. Based on the aforementioned failure probability, it is determined whether the gas alarm is faulty; When the gas alarm malfunctions, based on the gas monitoring data, the gas usage data, and historical maintenance data, the fault data sequence of the gas alarm is determined by a fault parameter determination model, which is a machine learning model. Based on the fault data sequence, the estimated fault type is determined, wherein the fault data sequence includes the fault type of the gas alarm and the fault confidence level of the fault type; Based on the estimated fault type, the dispatch and maintenance parameters for the gas alarm are determined, including the dispatch personnel and the dispatch time. The smart gas service platform is configured to send the dispatch and maintenance parameters to the smart gas user platform.

4. The system according to claim 3, characterized in that, The intelligent gas safety management platform is further configured as follows: Based on the service life and seasonal data of the gas alarm and the gas usage data, a verification feature vector is generated. Based on the aforementioned test feature vector, the self-test parameters are determined using a vector database.

5. A gas alarm detection device based on intelligent gas technology, characterized in that, The device includes at least one processor and at least one memory; The at least one memory is used to store computer instructions; The at least one processor is configured to execute at least a portion of the computer instructions to implement the method as described in any one of claims 1 to 2.

6. A computer-readable storage medium, characterized in that, The storage medium stores computer instructions. When the computer reads the computer instructions from the storage medium, the computer executes the method as described in any one of claims 1 to 2.

Images