Real-time monitoring method of gas equipment and gas equipment monitoring system

Abstract

The application relates to a real-time monitoring method and system for a gas equipment. In the Flink stream engine, the validity of real-time uploading working condition data according to a preset interval time in a preset time window is judged. If the data is judged as valid working condition data, the data is converted into Flink stream format data according to a conversion rule. Then, corresponding data in the converted valid working condition data is judged by using preset alarm type and fault type index rule judgment models, and alarm type indexes and fault type indexes are correspondingly output. The two indexes and other dimension information of corresponding gas equipment are used to generate equipment abnormality alarm information. Finally, the equipment abnormality alarm information is alarmed in a preset alarm mode, so that real-time monitoring of the gas equipment is realized. By using the method, large-scale working condition data can be efficiently and timely processed, and the correctness of alarm judgment is ensured.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of gas safety, in particular to a real-time monitoring method of a gas equipment and a gas equipment monitoring system. BACKGROUND

[0002] The gas equipment is a very important energy equipment, and the working condition data of the gas equipment has an important influence on the performance and safety of the gas equipment. The conventional gas equipment usually uses sensors to monitor the working condition data of the gas equipment, but the data transmission speed of the sensor is usually slow and is easily disturbed. At the same time, the working condition data of the gas equipment is usually transmitted in the form of flow, resulting in a large amount of data and being difficult to process.

[0003] With the rapid development of the Internet of Things technology at the present stage, the intelligentization, digitization and Internet of Things of the gas equipment have become an important trend in the gas industry, and real-time monitoring and analysis of the working condition data of the gas equipment have become the key to realizing this trend. SUMMARY

[0004] Therefore, it is necessary to provide a real-time monitoring method of a gas equipment and a gas equipment monitoring system which can process large data in real time and accurately alarm and judge.

[0005] A real-time monitoring method of a gas equipment, the method comprising:

[0006] obtaining working condition data, the working condition data being uploaded in real time by the gas equipment at a preset interval time;

[0007] in a Flink stream engine, judging the validity of the working condition data according to a preset time window;

[0008] if the time window is judged as a valid time window, converting the valid working condition data in the time window into Flink stream format data according to a conversion rule;

[0009] respectively using a preset alarm index rule determination model and a fault index rule determination model to judge corresponding indexes in the converted valid working condition data, and correspondingly outputting alarm indexes and fault indexes;

[0010] using a Join operator in the Flink stream engine to associate other dimension information of the corresponding gas equipment, generating equipment abnormal alarm information according to the other dimension information, the alarm indexes and the fault indexes;

[0011] using a preset alarm mode to alarm the equipment abnormal alarm information, so as to realize real-time monitoring of the gas equipment.

[0012] In one embodiment, the operating condition data is obtained by converting the received raw operating condition data by the gas equipment according to the standard model reported by the gas operating condition protocol;

[0013] The operating data includes sensor indicators, alarm status values, fault status indicators, and equipment information of the gas equipment.

[0014] In one embodiment, the interval for the gas equipment to upload operating condition data is calculated based on the equipment status of the gas equipment;

[0015] The equipment status is calculated by considering the location and environmental conditions of the gas equipment, its power consumption and usage status, and its importance.

[0016] In one embodiment, the step of determining the validity of the operational data in the Flink streaming engine according to a preset time window includes:

[0017] If the number of operating condition data received within a preset time window meets the preset number of data entries, then the operating condition data within that time window is determined to be valid operating condition data.

[0018] If the number of received operating condition data within the preset time window does not meet the preset number of data entries, the operating condition data within that time window is determined to be invalid operating condition data and will not be processed.

[0019] The preset number of records is calculated based on the preset time window and the preset interval for uploading operating data corresponding to the gas equipment.

[0020] In one embodiment, the step of using a preset alarm category indicator rule judgment model to judge the corresponding data in the transformed valid operating condition data and outputting alarm category indicators includes:

[0021] Extract multiple alarm data related to alarm indicators from the transformed valid operating condition data;

[0022] Different alarm data are judged using corresponding first and second thresholds. If the alarm data is greater than the first threshold, it is an alarm-type indicator. If the alarm data is less than the first threshold but greater than the second threshold, it is a fuzzy-type indicator. If the alarm indicator is less than the second threshold, it is a normal-type indicator.

[0023] The alarm data includes concentration data, temperature data, humidity data, liquid level data, vibration data, and voltage data from the operating condition information.

[0024] In one embodiment, the first threshold and the second threshold are calculated using the FCM clustering algorithm based on historical data of the corresponding alarm data.

[0025] In one embodiment, the step of using a preset fault category index rule judgment model to judge the corresponding data in the transformed valid operating condition data and outputting fault category indicators includes:

[0026] Extract multiple fault data related to fault category indicators from the transformed effective operating condition data;

[0027] Each of the fault data is classified into two categories. If the fault data is 1, it is a fault-type indicator; if the fault data is 0, it is a normal-type indicator.

[0028] The fault data includes sensor detachment identification data, temperature sensor fault identification data, vibration sensor fault identification data, communication equipment fault identification data, and location equipment fault identification data.

[0029] In one embodiment, the device abnormality alarm information is triggered using a preset alarm method, wherein the preset alarm method includes:

[0030] The device abnormality alarm information is sent to a preset host computer, which includes a mobile communication device and a terminal device.

[0031] Alternatively, an alarm command may be sent to the corresponding alarm device based on the device malfunction alarm information;

[0032] Alternatively, an alarm command or stop command may be sent to the corresponding gas equipment based on the abnormal alarm information, so that the gas equipment can automatically alarm or stop operating according to the alarm command or stop command.

[0033] In one embodiment, within the Flink streaming engine, multiple operational data points received within a preset time window may originate from different gas equipment. Before determining the validity of the operational data:

[0034] Based on the equipment information in each operating condition data, multiple operating condition data are grouped, and each group of operating condition data corresponds to a different gas equipment.

[0035] The validity of each set of operating condition data is assessed separately.

[0036] A gas equipment monitoring system includes multiple gas equipment and a monitoring platform;

[0037] Each of the gas-fired devices sends real-time operating data to the monitoring platform;

[0038] The monitoring platform processes the operating data of each condition according to the real-time monitoring method of the gas equipment described above.

[0039] A real-time monitoring device for gas equipment, the device comprising:

[0040] The operating condition data acquisition module is used to acquire operating condition data, which is uploaded in real time by the gas equipment at preset intervals.

[0041] The data validity judgment module is used in the Flink streaming engine to judge the validity of the working condition data according to a preset time window;

[0042] The effective operating condition data conversion module is used to convert the effective operating condition data in the time serial port into Flink streaming format data according to the conversion rules if it is determined to be a valid time window.

[0043] The alarm and fault indicator judgment module is used to judge the corresponding data in the converted effective operating condition data by using the preset alarm indicator rule judgment model and fault indicator rule judgment model respectively, and output the alarm indicator and fault indicator accordingly.

[0044] The abnormal alarm information generation module is used to associate other dimension information of the corresponding gas equipment with the Join operator in the Flink streaming engine, and generate abnormal alarm information of the equipment based on the other dimension information, alarm indicators and fault indicators.

[0045] The alarm module is used to send out alarms for abnormal equipment information using a preset alarm method, so as to realize real-time monitoring of gas equipment.

[0046] A computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program performing the following steps:

[0047] Acquire operating condition data, which is uploaded in real time by the gas equipment at preset intervals;

[0048] In the Flink streaming engine, the validity of the operating condition data is determined according to a preset time window.

[0049] If it is determined to be a valid time window, the valid operating condition data within the time window is converted into Flink streaming format data according to the conversion rules;

[0050] The corresponding indicators in the transformed valid operating condition data are judged by using the preset alarm-type indicator rule judgment model and the fault-type indicator rule judgment model respectively, and the alarm-type indicators and fault-type indicators are output accordingly.

[0051] The Join operator in the Flink streaming engine is used to associate other dimension information of the corresponding gas equipment, and equipment abnormality alarm information is generated based on the other dimension information, alarm indicators and fault indicators;

[0052] The abnormal alarm information of the equipment is alarmed using a preset alarm method to achieve real-time monitoring of the gas equipment.

[0053] A computer-readable storage medium having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0054] Acquire operating condition data, which is uploaded in real time by the gas equipment at preset intervals;

[0055] In the Flink streaming engine, the validity of the operating condition data is determined according to a preset time window.

[0056] If it is determined to be a valid time window, the valid operating condition data within the time window is converted into Flink streaming format data according to the conversion rules;

[0057] The corresponding indicators in the transformed valid operating condition data are judged by using the preset alarm-type indicator rule judgment model and the fault-type indicator rule judgment model respectively, and the alarm-type indicators and fault-type indicators are output accordingly.

[0058] The Join operator in the Flink streaming engine is used to associate other dimension information of the corresponding gas equipment, and equipment abnormality alarm information is generated based on the other dimension information, alarm indicators and fault indicators;

[0059] The abnormal alarm information of the equipment is alarmed using a preset alarm method to achieve real-time monitoring of the gas equipment.

[0060] The aforementioned real-time monitoring method and system for gas equipment utilizes the Flink streaming engine to determine the validity of real-time uploaded operating condition data at preset intervals within a preset time window. If the data is deemed valid, it is converted into Flink streaming format data according to conversion rules. Then, preset alarm and fault indicator rule judgment models are used to evaluate the corresponding data in the converted valid operating condition data, outputting alarm and fault indicators accordingly. These two indicators are then linked with other dimensions of the gas equipment using the Join operator in the Flink streaming engine to generate equipment anomaly alarm information. Finally, the equipment anomaly alarm information is triggered using a preset alarm method to achieve real-time monitoring of the gas equipment. This method can efficiently and in real-time process large-scale operating condition data while ensuring the accuracy of alarm judgment. Attached Figure Description

[0061] Figure 1 This is a flowchart illustrating a real-time monitoring method for a gas appliance in one embodiment;

[0062] Figure 2 This is a schematic diagram illustrating the specific processing flow of operational data in the Flink stream computing engine in one embodiment.

[0063] Figure 3 This is a structural block diagram of a real-time monitoring device for a gas appliance in one embodiment;

[0064] Figure 4 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0065] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0066] With the rapid pace of urbanization and the dramatic expansion of cities, natural gas, as the second most vital energy source in cities, has seen a surge in usage. However, in recent years, leaks and equipment instability during gas usage have led to some irreversible consequences. Therefore, real-time monitoring of all gas equipment is essential. The operating data of gas equipment has a significant impact on its performance and safety, and real-time analysis of this reported data enables effective supervision. Traditionally, gas equipment uses sensors to monitor its operating data; however, sensor data transmission speeds are typically slow and susceptible to interference. Furthermore, gas equipment operating data is usually transmitted in streaming form, resulting in massive amounts of data that are difficult to process.

[0067] To address the above problems, in one embodiment, such as Figure 1 As shown, a real-time monitoring method for gas equipment is provided, specifically including:

[0068] Step S100: Obtain operating condition data, which is uploaded in real time by the gas equipment at preset intervals.

[0069] Step S110: In the Flink streaming engine, the validity of the working condition data is determined according to the preset time window.

[0070] Step S120: If it is determined to be a valid time window, convert the valid operating condition data within the time window into Flink streaming format data according to the conversion rules.

[0071] Step S130: Using the preset alarm-type indicator rule judgment model and fault-type indicator rule judgment model respectively, the corresponding indicators in the converted effective working condition data are judged, and alarm-type indicators and fault-type indicators are output accordingly.

[0072] Step S140: Use the Join operator in the Flink streaming engine to associate other dimension information of the corresponding gas equipment, and generate equipment abnormal alarm information based on other dimension information, alarm indicators and fault indicators;

[0073] Step S150: The abnormal alarm information of the equipment is alarmed using a preset alarm method to achieve real-time monitoring of the gas equipment.

[0074] In this embodiment, the Flink streaming engine is used to process the operating condition data reported by the gas equipment to ensure the real-time and efficient data processing. Two indicator rule judgment models are used to judge the corresponding data in the operating condition data to ensure the accuracy of the alarm. In addition, the interval time for reporting operating condition data is determined according to the status of different gas equipment. This can reduce unnecessary alarm judgments and reduce computational memory to improve efficiency.

[0075] In this embodiment, the method is actually implemented in multiple gas equipment and data processing platforms, i.e., monitoring platforms.

[0076] In step S100, the received operating condition data comes from the gas equipment. At the gas equipment end, the raw data received by the sensor equipment is parsed using the operating condition data standard model through a data transmission channel, and then its format is converted to obtain the operating condition data. The operating condition data is then sent to the Kafka message middleware, and the Kafka message middleware sends the cached operating condition data to the monitoring platform at preset intervals.

[0077] Since not all raw data received by gas equipment needs to be reported, only a portion of the data needs to be reported, in this embodiment, a standard operating condition data model is used to filter the raw data, select the data that needs to be reported, and process and arrange it to generate the corresponding operating condition data.

[0078] Specifically, the operating data includes sensor parameters, alarm status values, fault status indicators, and equipment information for the gas equipment. Furthermore, the sensor parameters sent to the monitoring platform include: sensor identifier (si), battery level (bc), reporting cycle (rp), operating mode (wd), heartbeat identifier (hi), and location coordinates (pll). Alarm status values ​​include: concentration value (cv), temperature value (tv), humidity value (hv), liquid level value (lv), vibration value (vv), and voltage value (mv). Fault status indicators include: sensor detachment fault (sf), temperature sensor fault (tf), vibration sensor fault (vf), communication equipment fault (cf), and location equipment fault (pf).

[0079] Specifically, the standard model for operating condition data can be defined as:

[0080]

[0081] In formula (1), n ​​is the number of devices, the subscript i is any one of the n devices, ES is the sensor index, EW is the alarm status value, and EF is the fault status identifier.

[0082] In one embodiment, the business indicators reported by the gas equipment are as follows: Figure 2 As shown. Field definitions include: Working Mode: 1. Continuous monitoring; 2. Periodic monitoring (low power mode, default). Heartbeat indicator: Internal counter value. Alarm status: 1. Concentration alarm; 2. Temperature alarm; 3. Humidity alarm; 4. Liquid level alarm; 5. Vibration alarm; 6. Position alarm; 7. Low voltage alarm. Fault status: 1. Gas sensor detachment; 2. Temperature sensor malfunction; 3. Vibration sensor malfunction; 4. Communication equipment malfunction; 5. Positioning equipment malfunction, etc.

[0083] Because the gas equipment being monitored varies in age and environment, some equipment requires strict monitoring while others are in good condition and do not require frequent monitoring. Therefore, to address this issue and to more effectively extend the battery life of the equipment, this embodiment uses different reporting intervals for different gas equipment. Determining the reporting interval based on the equipment's condition effectively extends its battery life while also enabling appropriate monitoring of different equipment, thus improving the efficiency of the monitoring platform and ensuring the effectiveness of the monitoring.

[0084] In this embodiment, the interval for the gas equipment to upload operating condition data is calculated based on the equipment status of the gas equipment. The equipment status includes the location and environmental conditions of the gas equipment, the power consumption and power usage status, and the importance status.

[0085] Specifically, the location and environmental conditions of the gas equipment further include the characteristics of its location, the hazards of the environment, temperature and humidity, and the importance of the gas equipment, including the importance of the equipment itself and its degree of aging. The electricity consumption and usage status of the gas equipment specifically refer to the remaining electricity and the rate of electricity loss.

[0086] In this embodiment, the interval for uploading operating data of each gas device is specifically calculated using the following formula:

[0087]

[0088] In formula (2), a, b, c, d, e, f, g, and i are all indicator adjustment weight parameters, which can be adjusted separately according to specific circumstances. n represents the number of gas equipment, and the subscript i is any one of the n equipment. LT represents location characteristics, DL represents hazard, IL represents importance, AL represents aging degree, ES represents environmental severity, TL represents temperature, HL represents humidity, BB represents remaining electricity, and BLR represents electricity loss rate. Among them, LT (location characteristics), DL (hazard), IL (importance), AL (aging degree), and ES (environmental severity) are all given by industry professionals from 0 to 10 according to the corresponding scoring rules.

[0089] In step S110, in order to ensure the real-time nature of the uploaded operating condition data, the Flink streaming engine is used in this embodiment to process the operating condition data in real time. In order to improve the accuracy of subsequent alarm judgment, all operating condition data received within the preset time window is processed.

[0090] Since a monitoring platform needs to monitor multiple gas devices simultaneously, the multiple operating condition data received within the preset time window may come from different gas devices. Before judging the validity of the operating condition data, the multiple operating condition data are first grouped according to the device information in each operating condition data. Each group of operating condition data corresponds to a different gas device, and then the validity of each group of operating condition data is judged separately.

[0091] In this embodiment, within the Flink streaming engine, the validity determination of operational data based on a preset time window includes: if the cumulative number of operational data received within the preset time window meets a preset number of records, then the operational data within that time window is determined to be valid operational data; if the cumulative number of operational data received within the preset time window does not meet the preset number of records, then the operational data within that time window is determined to be invalid operational data and is not processed. The preset number of records is calculated based on the preset time window and the preset interval for uploading operational data corresponding to the gas equipment.

[0092] Specifically, the Flink streaming engine uses the Window operator to perform real-time computation of streaming data. After grouping devices, a sliding window computation method is used, with a window step size 'a' (unit: min), a sliding frequency of 1 min, and window data time difference judgment rules + record number judgment rules to verify the validity of the current time window.

[0093] Furthermore, the validity of the time window is determined using a basic model for judging the validity of the window. The model is expressed as follows:

[0094]

[0095] In formula (3), b represents the window validity duration threshold, c represents the window validity record count threshold, dt represents the window data time difference, dc represents the window data record count, and w o ,w n These represent valid and invalid windows, respectively.

[0096] In step S120, the Flink data structure transformation model is used in the Flink streaming engine to convert the real-time operational data reported from the Kafka middleware into a Flink streaming data structure, DataStream, by setting data stream transformation rules. These data stream transformation rules include: transformation rules + filtering mechanism + data dictionary mapping.

[0097] Specifically, the basic model for data structure transformation is: Input → Transformation (Transformation + Filtering + Dictionary Mapping) → Output, represented as:

[0098]

[0099] In formula (4), n represents the number of devices, m represents the amount of real-time data, i is any one of the n devices, j is any one of the m data, Input represents Flink input, Transform represents transformation rules, Filter represents filtering mechanism, Dict represents data dictionary mapping, Output represents Flink output, and the arrow represents the direction of data transformation.

[0100] Next, in step S130, a preset alarm category indicator judgment model is used to judge the corresponding data in the converted valid operating condition data, and the output alarm category indicators include: extracting multiple alarm data related to the alarm category indicators from the converted valid operating condition data, and judging different alarm data using corresponding first thresholds and second thresholds. If the alarm data is greater than the first threshold, it is an alarm category indicator; if the alarm data is less than the first threshold but greater than the second threshold, it is a fuzzy category indicator; if multiple alarm indicators are less than the second threshold, it is a normal category indicator. The alarm data includes concentration data, temperature data, humidity data, liquid level data, vibration data, and voltage data from the operating condition information.

[0101] In this embodiment, within the Flink streaming engine, alarm indicators such as concentration (cv), temperature (tv), humidity (hv), liquid level (lv), vibration (vv), and voltage (mv) are extracted from the data transformed based on the Flink data structure. An FCM alarm judgment mechanism combined with a Flink real-time pipeline orchestration mechanism is then established to automatically classify and determine these alarm indicators. The basic model for real-time alarm judgment pipeline orchestration is: Input → Judgment → Output, as shown below:

[0102]

[0103] In formula (5), n represents the number of devices, m represents the amount of real-time data, i is any one of the n devices, j is any one of the m data, FaI represents the Flink alarm category input, FCMT represents the clustering classification judgment rule, FaO represents the Flink alarm identifier output, and the arrow indicates the direction of indicator judgment conversion.

[0104] Specifically, the FCMT alarm category indicator rule judgment model used in the judgment step is expressed as follows:

[0105]

[0106] In formula (6), x represents the alarm data that needs to be judged, FCMT represents the clustering classification judgment rule, and w a ,w v ,w n These represent alarm-type indicators, fuzzy-type indicators, and normal-type indicators, respectively. T1 and T2 represent the first threshold and the second threshold, respectively.

[0107] In this embodiment, the first and second thresholds for each alarm data in the alarm category indicator rule determination model are calculated using the FCM clustering algorithm based on historical samples of the corresponding alarm data. By extracting data related to the alarm data from a large number of historical samples of operating conditions, and then calculating the two thresholds using the following formula for the EMC objective function model:

[0108]

[0109] In formula (7), c represents the number of cluster centers, n represents the number of device samples, i is any one of the n cluster centers, j is any one of the m device samples, and μ ij represents the membership degree of the sample, m represents the weight coefficient, and x represents the alarm category indicator sample.

[0110] In this embodiment, a preset fault category indicator rule judgment model is used to judge the corresponding data in the transformed valid operating condition data, and the output fault category indicator includes: extracting multiple fault data related to the fault category indicator from the transformed valid operating condition data, and performing binary classification judgment on each fault data. If the fault data is 1, then the fault data is a fault category indicator; if the fault data is 0, then the fault data is a normal category indicator. The fault data includes sensor detachment identification data, temperature sensor fault identification data, vibration sensor fault identification data, communication equipment fault identification data, and location device fault identification data.

[0111] Specifically, in the Flink streaming engine, fault category indicators such as sensor detachment fault (sf), temperature sensor fault (tf), vibration sensor fault (vf), communication equipment fault (cf), and location equipment fault (pf) are extracted from the data transformed based on the Flink data structure. A TowClass binary classification mechanism combined with a Flink real-time pipeline orchestration mechanism is then implemented to automatically classify and determine these fault indicators. The basic model for real-time fault determination pipeline orchestration is: Input → Decision → Output, as shown below:

[0112]

[0113] In formula (8), n represents the number of devices, m represents the amount of real-time data, i is any one of the n devices, j is any one of the m data, FfI represents the Flink fault class indicator input, TowClass represents the binary classification judgment rule, FfO represents the Flink fault identifier output, and the arrow indicates the indicator judgment conversion direction.

[0114] Specifically, the TooClass binary classification rule based on a 0-1 threshold is used to divide the indicator data into two categories: faulty and normal. The faulty indicator rule classification model is expressed as follows:

[0115]

[0116] In formula (9), x represents the fault data that needs to be judged, TowClass represents the binary classification judgment rule, and w f ,w nThese represent fault-related indicators and normal-related indicators, respectively, with 0 and 1 set as the dual thresholds for fault and normal categories.

[0117] In step S140, in the above steps, by using the Flink stream computing engine and rule discrimination model, the fault and alarm indicators in the gas operating condition data are judged in real time, and the gas equipment identifiers (alarm identifiers, fault identifiers) with abnormal problems are obtained in a timely manner. At the same time, Flink's Join operator is used to associate other dimension information of the equipment (such as equipment manufacturer information, equipment type information, equipment maintenance information, etc.). Finally, complete abnormal gas equipment information is obtained through Flink's real-time dimension association technology, and equipment abnormal alarm information is generated based on the abnormal gas equipment information, alarm indicators and fault indicators.

[0118] Specifically, the real-time abnormal device dimension correlation model is represented as follows:

[0119]

[0120] In formula (10), n is the number of devices, i is any one of the n devices, EAI is the abnormal device identifier, EMI is the device manufacturer information, ETI is the device type information, and EOI is the device maintenance information.

[0121] Finally, in step S150, the device abnormality alarm information is alarmed using a preset alarm method. The preset alarm method includes: sending the device abnormality alarm information to a preset host computer, which includes a mobile communication device or a terminal device; or sending an alarm command to the corresponding alarm device based on the device abnormality alarm information; or sending an alarm command or a stop command to the corresponding gas device based on the device abnormality alarm information, so that the gas device automatically alarms or stops operating according to the alarm command or stop command.

[0122] Specifically, the Flink stream computing engine is used to obtain information on abnormal gas equipment, and alarm, fault and other early warning monitoring information is pushed to various user terminals in real time, such as: safety personnel's mobile phones, large screen applications in the monitoring room, alarms, gas alarm lights. It can also realize automatic alarm and shutdown operations of gas equipment based on the operating status of the gas equipment.

[0123] In one embodiment, such as Figure 2 The diagram shows the specific processing flow of operational data in the Flink stream computing engine.

[0124] In the aforementioned real-time monitoring method for gas equipment, various operating condition data generated and reported by the gas equipment are uniformly collected onto an IoT platform. Certain rules are set, and this data undergoes preprocessing, including data cleaning, data normalization, and anomaly removal. Then, key indicators such as concentration, temperature, humidity, liquid level, vibration, and voltage are extracted from the operating condition data. The FCM clustering algorithm is used to classify a large number of samples of these indicators, and a classification mechanism is set to obtain thresholds for these indicators. Flink stream computing technology is used to collect and analyze these preprocessed data in real time, comparing the results with the clustering thresholds to achieve real-time alarm monitoring of the gas equipment. Specifically, using Flink for real-time stream computing requires transforming the preprocessed gas equipment operating condition data into a data stream model supported by Flink by setting data structure transformation rules. Using Flink's data stream processing APIs and transformation operators, real-time calculations such as dimensional correlation, aggregation statistics, and indicator filtering are performed on the data stream. Flink's Window operator is used to calculate the time window of the data stream. A sliding window model combined with an alarm threshold determination mechanism is used to determine faults and alarms in the equipment indicators, ultimately obtaining the desired results. This method also needs to consider means of implementing real-time alarm monitoring. Different alarm methods, such as SMS, email, and voice, can be used for different operating condition data. Simultaneously, different alarm strategies and handling methods need to be set according to different alarm levels to ensure timely and effective handling of alarm events. The real-time analysis and alarm monitoring method for gas equipment IoT operating condition data based on Flink stream computing technology can quickly and accurately monitor the operating condition of gas equipment in real time and promptly issue alarms in abnormal situations, improving the safety and intelligence level of gas equipment.

[0125] Furthermore, this method defines a standard model for gas equipment IoT operating condition data, forming a unified gas data IoT transmission specification. Through effective data standard management, it improves the efficiency of data reporting from gas equipment from different manufacturers. A unified IoT gas operating condition data protocol is defined, simplifying the data parsing process at each stage of transmission, improving gas data development efficiency, and reducing project development costs. An index classification model based on the Fuzzy C-means algorithm (FCM) is designed, maximizing the similarity of gas alarm indicators within clusters and minimizing the similarity between clusters, effectively improving the classification accuracy of gas alarm indicators. A real-time fault and alarm determination model based on the Flink streaming engine is established. Through Flink real-time data processing technology, and binary classification and FCM clustering classification rules, rapid fault classification and alarm determination are achieved, improving the safety and intelligence level of gas equipment.

[0126] In one embodiment, a gas equipment monitoring system is also provided, including multiple gas devices and a monitoring platform. Each gas device sends real-time operating data to the monitoring platform, such as a big data cloud service platform integrating data acquisition, real-time processing, equipment early warning, and message push. The monitoring platform processes the operating data according to the real-time monitoring methods of the gas devices.

[0127] It should be understood that, although Figure 1 The steps in the flowchart are shown sequentially as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order in which these steps are executed, and they can be performed in other orders. Figure 1 At least some of the steps in the process may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least some of the sub-steps or stages of other steps.

[0128] In one embodiment, such as Figure 3 As shown, a real-time monitoring device for gas equipment is provided, comprising: an operating condition data acquisition module 200, a data validity judgment module 210, a valid operating condition data conversion module 220, an alarm and fault index judgment module 230, an abnormal alarm information generation module 240, and an alarm module 250, wherein:

[0129] The operating condition data acquisition module 200 is used to acquire operating condition data, which is uploaded in real time by the gas equipment at preset intervals.

[0130] The data validity judgment module 210 is used to judge the validity of the working condition data in the Flink streaming engine according to a preset time window.

[0131] The effective operating condition data conversion module 220 is used to convert the effective operating condition data within the time window into Flink streaming format data according to the conversion rules if it is determined to be an effective time window.

[0132] The alarm and fault indicator judgment module 230 is used to judge the corresponding indicators in the converted effective working condition data by using the preset alarm indicator rule judgment model and fault indicator rule judgment model respectively, and output the alarm indicator and fault indicator accordingly.

[0133] The abnormal alarm information generation module 240 is used to associate other dimension information of the corresponding gas equipment with the Join operator in the Flink streaming engine, and generate equipment abnormal alarm information based on the other dimension information, alarm indicators and fault indicators.

[0134] The alarm module 250 is used to send alarms for abnormal equipment alarm information using a preset alarm method, so as to realize real-time monitoring of gas equipment.

[0135] Specific limitations regarding the real-time monitoring device for gas equipment can be found in the limitations of the real-time monitoring method for gas equipment mentioned above, and will not be repeated here. Each module in the aforementioned real-time monitoring device for gas equipment can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0136] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 4 As shown, the computer device includes a processor, memory, network interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The network interface is used to communicate with external terminals via a network connection. When the computer program is executed by the processor, it implements a real-time monitoring method for gas equipment. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device casing, or an external keyboard, touchpad, or mouse.

[0137] Those skilled in the art will understand that Figure 4 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0138] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0139] Acquire operating condition data, which is uploaded in real time by the gas equipment at preset intervals;

[0140] In the Flink streaming engine, the validity of the operating condition data is determined according to a preset time window.

[0141] If it is determined to be a valid time window, the valid operating condition data within the time window is converted into Flink streaming format data according to the conversion rules;

[0142] The corresponding indicators in the transformed valid operating condition data are judged by using the preset alarm-type indicator rule judgment model and the fault-type indicator rule judgment model respectively, and the alarm-type indicators and fault-type indicators are output accordingly.

[0143] The Join operator in the Flink streaming engine is used to associate other dimension information of the corresponding gas equipment, and equipment abnormality alarm information is generated based on the other dimension information, alarm indicators and fault indicators;

[0144] The abnormal alarm information of the equipment is alarmed using a preset alarm method to achieve real-time monitoring of the gas equipment.

[0145] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0146] Acquire operating condition data, which is uploaded in real time by the gas equipment at preset intervals;

[0147] In the Flink streaming engine, the validity of the operating condition data is determined according to a preset time window.

[0148] If it is determined to be a valid time window, the valid operating condition data within the time window is converted into Flink streaming format data according to the conversion rules;

[0149] The corresponding indicators in the transformed valid operating condition data are judged by using the preset alarm-type indicator rule judgment model and the fault-type indicator rule judgment model respectively, and the alarm-type indicators and fault-type indicators are output accordingly.

[0150] The Join operator in the Flink streaming engine is used to associate other dimension information of the corresponding gas equipment, and equipment abnormality alarm information is generated based on the other dimension information, alarm indicators and fault indicators;

[0151] The abnormal alarm information of the equipment is alarmed using a preset alarm method to achieve real-time monitoring of the gas equipment.

[0152] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0153] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0154] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A method for real-time monitoring of gas equipment, characterized in that, The method includes: Acquire operating condition data, which is uploaded in real time by the gas equipment at preset intervals; In the Flink streaming engine, the validity of the operating condition data is determined according to a preset time window. If the operating condition data within the preset time window is valid operating condition data, then the valid operating condition data within the time window is converted into Flink streaming format data according to the conversion rules. The corresponding indicators in the transformed valid operating condition data are judged by using the preset alarm-type indicator rule judgment model and the fault-type indicator rule judgment model respectively, and the alarm-type indicators and fault-type indicators are output accordingly. The Join operator in the Flink streaming engine is used to associate other dimension information of the corresponding gas equipment, and equipment abnormality alarm information is generated based on the other dimension information, alarm indicators and fault indicators; The abnormal alarm information of the equipment is alarmed using a preset alarm method to achieve real-time monitoring of the gas equipment.

2. The real-time monitoring method according to claim 1, characterized in that, The operating condition data is obtained by converting the received raw operating condition data by the gas equipment according to the standard model reported by the gas operating condition protocol; The operating data includes sensor indicators, alarm status values, fault status indicators, and equipment information of the gas equipment.

3. The real-time monitoring method according to claim 2, characterized in that, The interval for the gas equipment to upload operating condition data is calculated based on the equipment status of the gas equipment; The equipment status is calculated by considering the location and environmental conditions of the gas equipment, its power consumption and usage status, and its importance.

4. The real-time monitoring method according to claim 1, characterized in that, The validity determination of the working condition data in the Flink streaming engine based on a preset time window includes: If the number of operating condition data received within a preset time window meets the preset number of data entries, then the operating condition data within that time window is determined to be valid operating condition data. If the number of received operating condition data within the preset time window does not meet the preset number of data entries, the operating condition data within that time window is determined to be invalid operating condition data and will not be processed. The preset number of records is calculated based on the preset time window and the preset interval for uploading operating data corresponding to the gas equipment.

5. The real-time monitoring method according to claim 1, characterized in that, The method of using a preset alarm category indicator rule judgment model to judge the corresponding data in the transformed valid operating condition data and outputting alarm category indicators includes: Extract multiple alarm data related to alarm indicators from the transformed valid operating condition data; Different alarm data are judged using corresponding first and second thresholds. If the alarm data is greater than the first threshold, it is an alarm-type indicator. If the alarm data is less than the first threshold but greater than the second threshold, it is a fuzzy-type indicator. If the alarm data is less than the second threshold, it is a normal-type indicator. The alarm data includes concentration data, temperature data, humidity data, liquid level data, vibration data, and voltage data from the operating condition data.

6. The real-time monitoring method according to claim 5, characterized in that, The first threshold and the second threshold are calculated using the FCM clustering algorithm based on the historical data of the corresponding alarm data.

7. The real-time monitoring method according to claim 1, characterized in that, The method of using a preset fault category index rule judgment model to judge the corresponding data in the transformed effective operating condition data, and outputting fault category indicators, includes: Extract multiple fault data related to fault category indicators from the transformed effective operating condition data; Each of the fault data is classified into two categories. If the fault data is 1, it is a fault-type indicator; if the fault data is 0, it is a normal-type indicator. The fault data includes sensor detachment identification data, temperature sensor fault identification data, vibration sensor fault identification data, communication equipment fault identification data, and location equipment fault identification data.

8. The real-time monitoring method according to claim 1, characterized in that, The device malfunction alarm information is triggered using a preset alarm method, which includes: The device abnormality alarm information is sent to a preset host computer, which includes a mobile communication device and a terminal device. Alternatively, an alarm command may be sent to the corresponding alarm device based on the device malfunction alarm information; Alternatively, an alarm command or stop command may be sent to the corresponding gas equipment based on the abnormal alarm information, so that the gas equipment can automatically alarm or stop operating according to the alarm command or stop command.

9. The real-time monitoring method according to claim 1, characterized in that, In the Flink streaming engine, multiple operational data points received within a preset time window may come from different gas equipment. Before determining the validity of these operational data points: Based on the equipment information in each operating condition data, multiple operating condition data are grouped, and each group of operating condition data corresponds to a different gas equipment. The validity of each set of operating condition data is assessed separately.

10. A gas equipment monitoring system, characterized in that, Includes multiple gas equipment and a monitoring platform; Each of the gas-fired devices sends real-time operating data to the monitoring platform; The monitoring platform processes the operating condition data according to the real-time monitoring method for gas equipment as described in any one of claims 1-9.

Images