A heating equipment fault data processing method and system based on the Internet of Things

Abstract

The present invention relates to the technical field of equipment fault control, and in particular to a method and system for processing heating equipment fault data based on the Internet of Things. The method comprises the following steps: installing temperature sensors, flow sensors and pressure sensors at key parts of the heating equipment and performing real-time monitoring of the equipment operation status to obtain a real-time operation status parameter set of the heating equipment; uploading to a cloud platform using the Internet of Things gateway technology and performing edge delay filtering and time-frequency transformation fluctuation analysis of state parameters, while performing quantitative calculation of signal fault severity scores and equipment fault classification processing to obtain recoverable fault categories and unrecoverable fault categories; when it is determined to be a recoverable fault category, the corresponding recoverable fault maintenance control processing work is performed; when it is determined to be an unrecoverable fault category, a response is made to inform the maintenance personnel to perform the corresponding unrecoverable fault emergency maintenance control processing work. The present invention can improve the fault management and control efficiency of heating equipment.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment failure control, and in particular to a method and system for processing heating equipment failure data based on the Internet of Things. Background Art

[0002] In modern society, more and more heating systems are integrating intelligent sensors and network communication functions to achieve remote monitoring and management. This intelligent heating system can collect equipment operating status, environmental parameters and user demand data in real time, thereby improving heating efficiency and energy saving. It can use data mining and machine learning technology to conduct in-depth analysis of historical fault data and real-time monitoring data to establish a fault pattern recognition model to identify potential fault signs, thereby achieving fault prediction and early warning. This data analysis capability can improve the accuracy and timeliness of fault detection. However, traditional heating equipment fault handling methods mainly rely on manual inspections and regular maintenance. These methods are not only inefficient, but also often lack effective data analysis and fault prediction and recognition capabilities, and cannot fully reflect the fault category status of heating equipment. Summary of the invention

[0003] Based on this, it is necessary for the present invention to provide a heating equipment fault data processing method and system based on the Internet of Things to solve at least one of the above technical problems.

[0004] To achieve the above purpose, a method for processing heating equipment fault data based on the Internet of Things includes the following steps:

[0005] Step S1: by installing temperature sensors, flow sensors and pressure sensors at key parts of the heating equipment, and using the temperature sensors, flow sensors and pressure sensors to monitor the operation status of the heating equipment in real time during the operation process, a real-time operation status parameter set of the heating equipment is obtained, wherein the real-time operation status parameter set of the heating equipment includes the real-time operation temperature of the heating equipment, the real-time operation flow of the heating equipment and the real-time operation pressure of the heating equipment; the real-time operation status parameter set of the heating equipment is uploaded to the cloud platform by using the Internet of Things gateway technology, and the real-time operation status parameter set of the heating equipment is edge-delay filtered by using the cloud platform to obtain a low-delay operation status parameter set of the heating equipment;

[0006] Step S2: performing a state parameter time-frequency transformation fluctuation analysis on the low-latency operating state parameter set of the heating equipment to obtain a time-frequency signal fluctuation frame corresponding to each heating equipment operating state parameter; performing a signal fault severity score quantitative calculation on the time-frequency signal fluctuation frame corresponding to each heating equipment operating state parameter to obtain a time-frequency signal fault severity score corresponding to each heating equipment operating state parameter; performing equipment fault classification processing on the fault category of the heating equipment based on the time-frequency signal fault severity score corresponding to each heating equipment operating state parameter to obtain a recoverable fault category of the heating equipment and an unrecoverable fault category of the heating equipment;

[0007] Step S3: When it is determined that the fault category of the heating equipment is a recoverable fault category of the heating equipment, a recoverable fault maintenance control analysis is performed on the recoverable fault category of the heating equipment using the cloud platform, and a recoverable fault maintenance control measure plan for the heating equipment is generated to perform corresponding recoverable fault maintenance control processing work;

[0008] Step S4: When it is determined that the fault category of the heating equipment is an irrecoverable fault category of the heating equipment, a cloud platform response is used to generate an emergency repair control request for the heating equipment to respond and inform the maintenance personnel to perform corresponding irrecoverable fault emergency repair control processing work.

[0009] Further, step S1 includes the following steps:

[0010] Step S11: Analyze the sensor configuration requirements of key parts of the heating equipment to obtain a sensor configuration requirement report of key parts of the heating equipment, wherein the key parts of the heating equipment include boilers, pipelines and valve areas;

[0011] Step S12: Designing optimal sensor installation positions for temperature sensors, pressure sensors, and flow sensors based on the sensor configuration requirement report for key parts of the heating equipment, so as to generate an implementation plan for sensor installation for key parts of the heating equipment;

[0012] Step S13: installing temperature sensors, flow sensors and pressure sensors at key parts of the heating equipment according to the implementation plan for installing sensors at key parts of the heating equipment, and using the temperature sensor to monitor the equipment operating temperature in real time during the operation of the heating equipment to obtain the real-time operating temperature of the heating equipment; using the flow sensor to monitor the equipment operating flow in real time during the operation of the heating equipment to obtain the real-time operating flow of the heating equipment; using the pressure sensor to monitor the equipment operating pressure in real time during the operation of the heating equipment to obtain the real-time operating pressure of the heating equipment;

[0013] Step S14: merging the real-time operating temperature of the heating equipment, the real-time operating flow rate of the heating equipment, and the real-time operating pressure of the heating equipment as equipment operating status parameters to obtain a real-time operating status parameter set of the heating equipment; uploading the real-time operating status parameter set of the heating equipment to the cloud platform using the Internet of Things gateway technology;

[0014] Step S15: Use the cloud platform to perform edge delay filtering on the real-time operating status parameter set of the heating equipment to obtain a low-latency operating status parameter set of the heating equipment.

[0015] Further, step S15 includes the following steps:

[0016] Step S151: using the cloud platform to monitor the edge transmission duration of each heating equipment operation parameter data point in the real-time operation status parameter set of the heating equipment, and obtaining the edge transmission response duration corresponding to each heating equipment operation parameter data point;

[0017] Step S152: performing transmission reaction speed statistical analysis on the corresponding heating equipment operation parameter data points in the heating equipment real-time operation status parameter set based on the edge transmission response time corresponding to each heating equipment operation parameter data point, and obtaining the edge transmission reaction speed corresponding to each heating equipment operation parameter data point;

[0018] Step S153: Performing network status evaluation and analysis on each heating equipment operation parameter data point in the heating equipment real-time operation status parameter set to obtain network status evaluation parameters corresponding to each heating equipment operation parameter data point, wherein the network status evaluation parameters include network bandwidth value, network delay and data packet loss rate;

[0019] Step S154: Based on the edge transmission reaction speed corresponding to each heating equipment operation parameter data point and the network status evaluation parameter, the edge transmission delay index calculation formula is used to perform edge delay quantitative calculation on the heating equipment operation parameter data point corresponding to the heating equipment real-time operation status parameter set, and obtain the edge transmission operation delay index corresponding to each heating equipment operation parameter data point;

[0020] Step S155: Compare and judge the edge transmission operation delay index corresponding to each heating equipment operation parameter data point according to the preset edge delay threshold. If the edge transmission operation delay index is greater than or equal to the preset edge delay threshold, the corresponding heating equipment operation parameter data point is marked as a high-latency operation parameter data point; if the edge transmission operation delay index is less than the preset edge delay threshold, the corresponding heating equipment operation parameter data point is marked as a low-latency operation parameter data point; the heating equipment operation parameter data points corresponding to the low-latency operation parameter data points in the real-time operation status parameter set of the heating equipment are filtered out and collected to obtain the low-latency operation status parameter set of the heating equipment.

[0021] Furthermore, the edge transmission delay index calculation formula in step S154 is specifically:

[0022] ;

[0023] In the formula, For the The edge transmission operation delay index corresponding to the heating equipment operation parameter data point, is the total number of data points of heating equipment operating parameters, It is the item index parameter of the heating equipment operation parameter data point. For the The edge transmission response speed corresponding to each heating equipment operation parameter data point, is the influence weight coefficient of edge transmission reaction speed, For the The network delay corresponding to each heating equipment operating parameter data point, is the network delay decay rate index, is the impact weight coefficient of network delay, is the time variable parameter, For the Heating equipment operating parameter data points at time The network bandwidth value at For the Heating equipment operating parameter data points at time The data packet loss rate at is the cumulative impact weight coefficient of the network status, Correction factor for edge transport operation latency exponential.

[0024] Further, step S2 includes the following steps:

[0025] Step S21: performing state parameter standardization processing on the low-latency operation state parameter set of the heating equipment to obtain a standardized operation state parameter set of the heating equipment;

[0026] Step S22: performing time-series synchronization processing on the standardized parameter set of the operation status of the heating equipment to obtain the time-series synchronization parameter set of the operation status of the heating equipment;

[0027] Step S23: performing a state parameter time-frequency transformation fluctuation analysis on the heating equipment operation state timing synchronization parameter set to obtain a time-frequency signal fluctuation frame corresponding to each heating equipment operation state parameter, wherein the time-frequency signal fluctuation frame corresponding to each heating equipment operation state parameter includes a time-frequency signal fluctuation frame corresponding to an operation temperature, an operation flow rate, and an operation pressure;

[0028] Step S24: performing quantitative calculation of signal fault severity scores for the time-frequency signal fluctuation frames corresponding to the operating state parameters of each heating device, so as to obtain the time-frequency signal fault severity scores corresponding to the operating state parameters of each heating device, wherein the time-frequency signal fault severity scores corresponding to the operating state parameters of each heating device include the time-frequency signal fault severity scores corresponding to the operating temperature, the operating flow rate and the operating pressure;

[0029] Step S25: Classify the fault category of the heating equipment based on the time-frequency signal fault severity scores corresponding to the operating status parameters of each heating equipment. If the time-frequency signal fault severity scores corresponding to the corresponding operating temperature, operating flow and operating pressure are all within the range of 0-5 points, the fault category of the heating equipment is classified as a recoverable fault category of the heating equipment; if the time-frequency signal fault severity scores corresponding to the corresponding operating temperature, operating flow and operating pressure are within the range of 6 points or above, the fault category of the heating equipment is classified as an unrecoverable fault category of the heating equipment.

[0030] Further, step S23 includes the following steps:

[0031] Step S231: performing a time domain change analysis of the state parameter of the heating equipment operation state timing synchronization parameter set to obtain the time domain change trend data of the operation state parameters of each heating equipment in the time dimension;

[0032] Step S232: Calculate the instantaneous frequency of each heating device operating state parameter at each time domain node on the time dimension of the time domain change trend data to obtain the instantaneous frequency of each heating device operating state parameter at each time domain node;

[0033] Step S233: performing time-frequency signal spectrum transformation on the corresponding time-domain variation trend data based on the time-domain variation instantaneous frequency of each heating equipment operation status parameter at each time-domain node, to obtain the time-frequency variation signal spectrum corresponding to each heating equipment operation status parameter;

[0034] Step S234: performing time-frequency signal fluctuation range identification analysis on the time-frequency variation signal spectrum corresponding to the operating state parameters of each heating device, and obtaining the time range of the time-frequency signal fluctuation corresponding to the operating state parameters of each heating device;

[0035] Step S235: Based on the time range of the time-frequency signal fluctuations corresponding to the operating status parameters of each heating equipment, the corresponding time-frequency change signal spectrum is subjected to signal fluctuation range frame sealing processing to obtain the time-frequency signal fluctuation frames corresponding to the operating status parameters of each heating equipment, wherein the time-frequency signal fluctuation frames corresponding to the operating status parameters of each heating equipment include the time-frequency signal fluctuation frames corresponding to the operating temperature, the operating flow rate and the operating pressure.

[0036] Further, step S232 includes the following steps:

[0037] Performing time domain change smoothing processing on the time domain change trend data of the operating status parameters of each heating device in the time dimension to obtain the real change trend data of the operating status parameters of each heating device in the time dimension;

[0038] The real change trend data of the operating status parameters of each heating device in the time dimension are divided by time domain node marking to obtain the time domain change trend sub-data of the operating status parameters of each heating device at each time domain node;

[0039] Performing statistical analysis on the change amplitude of the time domain change trend sub-data of each heating equipment operating state parameter at each time domain node to obtain the time domain change amplitude of each heating equipment operating state parameter at each time domain node; performing time domain change phase inverse processing on the corresponding time domain change trend sub-data based on the time domain change amplitude of each heating equipment operating state parameter at each time domain node to obtain the time domain signal change phase of each heating equipment operating state parameter at each time domain node;

[0040] The phase difference between adjacent nodes is calculated for the time domain signal change phase of each heating equipment operation status parameter at each time domain node to obtain the time domain change phase difference between each adjacent time domain node of each heating equipment operation status parameter;

[0041] Based on the time domain change phase difference of each heating equipment operating status parameter between each adjacent time domain node, the upper node instantaneous frequency of the corresponding time domain node is calculated to obtain the time domain change instantaneous frequency of each heating equipment operating status parameter at each time domain node.

[0042] Further, step S24 includes the following steps:

[0043] Step S241: performing a change amplitude stability evaluation and analysis on the time-frequency signal fluctuation frames corresponding to the operating temperature and the operating flow, and obtaining a time-domain signal change amplitude stability index parameter corresponding to the operating temperature and the operating flow;

[0044] Step S242: performing signal phase shift statistical analysis on the time-frequency signal fluctuation frames corresponding to the operating temperature and the operating flow, and obtaining the time-frequency signal phase shift index parameters corresponding to the operating temperature and the operating flow;

[0045] Step S243: calculating the operating temperature fault severity score for the time-frequency signal fluctuation frame corresponding to the operating temperature based on the time-domain signal variation amplitude stability index parameter and the time-frequency signal phase offset index parameter corresponding to the operating temperature, so as to obtain the time-frequency signal fault severity score corresponding to the operating temperature;

[0046] Step S244: Calculate the operation flow fault severity score for the time-frequency signal fluctuation frame corresponding to the operation flow based on the time-domain signal change amplitude stability index parameter and the time-frequency signal phase offset index parameter corresponding to the operation flow, so as to obtain the time-frequency signal fault severity score corresponding to the operation flow;

[0047] Step S245: Calculate the operating pressure fault severity score for the time-frequency signal fluctuation frame corresponding to the operating pressure to obtain the time-frequency signal fault severity score corresponding to the operating pressure.

[0048] Further, step S245 includes the following steps:

[0049] Perform signal fluctuation frequency and energy distribution analysis on the time-frequency signal fluctuation frame corresponding to the operating pressure to obtain the time-frequency signal fluctuation frequency distribution data and the time-frequency signal fluctuation energy distribution data corresponding to the operating pressure;

[0050] The signal fluctuation rate is calculated for the time-frequency signal fluctuation frequency distribution data corresponding to the operating pressure to obtain the time-frequency signal fluctuation rate corresponding to the operating pressure;

[0051] Based on the time-frequency signal fluctuation energy distribution data corresponding to the operating pressure, the signal energy offset of the corresponding time-frequency signal fluctuation frame is calculated to obtain the time-frequency signal fluctuation energy offset corresponding to the operating pressure;

[0052] The operating pressure fault severity score is calculated for the corresponding time-frequency signal fluctuation frame based on the time-frequency signal fluctuation rate and the time-frequency signal fluctuation energy offset corresponding to the operating pressure to obtain the time-frequency signal fault severity score corresponding to the operating pressure.

[0053] Furthermore, the present invention also provides a heating equipment fault data processing system based on the Internet of Things, which is used to execute the heating equipment fault data processing method based on the Internet of Things as described above. The heating equipment fault data processing system based on the Internet of Things includes:

[0054] The heating equipment status parameter delay filtering module is used to install temperature sensors, flow sensors and pressure sensors at key parts of the heating equipment, and use the temperature sensors, flow sensors and pressure sensors to monitor the equipment operation status in real time during the operation of the heating equipment, so as to obtain a real-time operation status parameter set of the heating equipment, wherein the real-time operation status parameter set of the heating equipment includes the real-time operation temperature of the heating equipment, the real-time operation flow of the heating equipment and the real-time operation pressure of the heating equipment; use the Internet of Things gateway technology to upload the real-time operation status parameter set of the heating equipment to the cloud platform, and use the cloud platform to perform edge delay filtering on the real-time operation status parameter set of the heating equipment, so as to obtain a low-latency operation status parameter set of the heating equipment;

[0055] The heating equipment parameter signal fault classification module is used to perform a state parameter time-frequency transformation fluctuation analysis on the low-latency operating state parameter set of the heating equipment to obtain the time-frequency signal fluctuation frames corresponding to the operating state parameters of each heating equipment; perform a signal fault severity score quantitative calculation on the time-frequency signal fluctuation frames corresponding to the operating state parameters of each heating equipment to obtain the time-frequency signal fault severity score corresponding to the operating state parameters of each heating equipment; perform equipment fault classification processing on the fault categories of the heating equipment based on the time-frequency signal fault severity scores corresponding to the operating state parameters of each heating equipment, thereby obtaining the recoverable fault category of the heating equipment and the unrecoverable fault category of the heating equipment;

[0056] The recoverable fault maintenance control processing module is used to determine that the fault category of the heating equipment is a recoverable fault category of the heating equipment, and then use the cloud platform to perform a recoverable fault maintenance control analysis on the recoverable fault category of the heating equipment, generate a recoverable fault maintenance control measure plan for the heating equipment, and execute the corresponding recoverable fault maintenance control processing work;

[0057] The irrecoverable fault emergency repair control module is used to determine that the fault category of the heating equipment is an irrecoverable fault category of the heating equipment, and then use the cloud platform response to generate an emergency repair control request for the heating equipment to respond and inform the maintenance personnel to perform the corresponding irrecoverable fault emergency repair control processing work.

[0058] Beneficial effects of the present invention:

[0059] 1. The method for processing heating equipment fault data based on the Internet of Things proposed in the present invention has the beneficial effect of installing temperature sensors, flow sensors and pressure sensors at key parts of the heating equipment (including boilers, pipelines and valve areas) and real-time monitoring of the operating temperature, flow and pressure of the heating equipment. It can not only fully understand the operating status of the equipment, but also timely discover potential faults and abnormalities. The real-time data collection after installation will provide intuitive operating conditions for operation and maintenance personnel, so that they can make decisions quickly to deal with emergencies. For example, temperature sensors can help determine the heating efficiency of boilers, flow sensors can reflect the flow status of pipelines, and pressure sensors are the key to ensuring the safety of heating equipment. The effective deployment of these sensors will improve the operating efficiency of the entire heating equipment, reduce energy waste, and also provide data support for the subsequent realization of intelligent fault management. By merging the real-time operating status parameters to form the operating status parameter set of the equipment, this process can not only integrate multiple key data such as temperature, flow and pressure into a unified monitoring indicator, but also provide a basis for subsequent data analysis. The parameter set is uploaded to the cloud platform through the Internet of Things gateway technology, which can realize remote storage and processing of data. In this way, the operation and maintenance personnel can monitor and analyze the operating status of the heating equipment anytime and anywhere. The data processing capability of the cloud platform not only improves the utilization efficiency of data, but also improves the ability of data analysis and fault prediction and identification. At the same time, the edge delay filtering of the real-time operating status parameter set of the heating equipment by using the cloud platform is to improve the efficiency of data transmission and processing. Through advanced edge computing technology, the delay of data in the transmission process can be effectively reduced, thereby realizing real-time monitoring of the equipment status. The generated low-latency operating status parameter set ensures that the operation and maintenance personnel can obtain the latest data and respond in time. This process not only improves the response speed of the heating equipment, but also effectively reduces the complexity of data processing and reduces the interference of redundant information, providing more accurate information support for subsequent data analysis and decision-making. Secondly, by performing time-frequency transformation fluctuation analysis on the low-latency operating status parameter set of the heating equipment, the characteristic changes of the signal in the time and frequency domains can be revealed. This process helps to identify the fluctuation characteristics of key parameters such as operating temperature, flow, and pressure, and provide data support for subsequent fault diagnosis. By analyzing the fluctuation frames of the time-frequency signal, we can more clearly understand the performance of the equipment under different working conditions, identify existing abnormal fault modes or trends, and thus provide early warning of faults.By quantitatively calculating the signal fault severity score of the time-frequency signal fluctuation frames corresponding to the operating status parameters of each heating equipment, a quantitative evaluation standard can be provided for the fault management of the heating equipment. By scoring the time-frequency signal fluctuation frames, the fault severity of different operating status parameters (such as temperature, flow and pressure) can be clearly evaluated. This step converts complex signal features into easy-to-understand scores through quantitative calculation, allowing managers to quickly judge the health status of the equipment. This scoring system can help decision makers effectively distinguish the severity of equipment failures and facilitate the priority treatment of equipment with high potential risks. In addition, by classifying and judging the fault category of the heating equipment based on the time-frequency signal fault severity score corresponding to the operating status parameters of each heating equipment, the fault category can be accurately identified. When the score is in the range of 0-5 points, it indicates that the heating equipment is in a recoverable fault category. This situation usually means that the equipment can resume normal operation after a certain maintenance, which is convenient for rapid intervention and processing. On the contrary, if the score reaches 6 points or above, it means that the equipment has an unrecoverable fault and more stringent maintenance or replacement measures need to be taken. The implementation of this step can help managers make quick decisions, reduce equipment downtime, reduce maintenance costs, and improve the overall reliability and safety of heating equipment. This step can optimize the subsequent fault maintenance process and improve the efficiency of fault maintenance control response by establishing a clear fault classification system, so as to accurately monitor and judge the fault category of heating equipment. Then, when the fault category of the heating equipment is determined to be a recoverable fault category of the heating equipment, the cloud platform is used to perform control analysis of recoverable fault maintenance to generate specific maintenance control measures. The maintenance team can systematically troubleshoot and repair recoverable faults. This systematic maintenance control can not only significantly improve the efficiency of heating equipment maintenance work, but also reduce errors caused by manual judgment. This can cover everything from fault identification, problem diagnosis to specific maintenance operation guidance, forming a complete set of standardized operation procedures. According to these plans, targeted measures are taken to effectively solve equipment failure problems, shorten repair time, and maximize the continuous and stable operation of heating equipment. Finally, when the fault type of the heating equipment is determined to be an irrecoverable fault, an emergency maintenance control request is generated using the cloud platform. The timely response of this process ensures that the impact of the heating equipment failure on users is minimized. In an emergency, maintenance personnel can quickly receive fault alarm information and maintenance requests, thereby immediately launching an emergency response, minimizing the losses caused by equipment failure, and ensuring that they will not be inconvenienced by equipment failure in future use.

[0060] 2. The heating equipment fault data processing system based on the Internet of Things proposed in the present invention is generally composed of a heating equipment state parameter delay filtering module, a heating equipment parameter signal fault classification module, a recoverable fault maintenance control processing module and an irrecoverable fault emergency repair control module. It can implement any heating equipment fault data processing method based on the Internet of Things described in the present invention, and is used to combine the operations between computer programs running on each module to implement the heating equipment fault data processing method based on the Internet of Things. The internal structures of the system cooperate with each other, which can greatly reduce repetitive work and manpower investment, and can quickly and effectively provide a more accurate and efficient heating equipment fault data processing process based on the Internet of Things, thereby simplifying the operating procedures of the heating equipment fault data processing system based on the Internet of Things. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments thereof made with reference to the following drawings:

[0062] Figure 1 It is a schematic diagram of the steps of the method for processing heating equipment fault data based on the Internet of Things of the present invention;

[0063] Figure 2 for Figure 1 Detailed step flow diagram of step S1;

[0064] Figure 3 for Figure 2 Detailed step flow chart of step S15 in FIG. DETAILED DESCRIPTION

[0065] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0066] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0067] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0068] To achieve this, please refer to Figures 1 to 3 The present invention provides a method for processing heating equipment fault data based on the Internet of Things, the method comprising the following steps:

[0069] Step S1: by installing temperature sensors, flow sensors and pressure sensors at key parts of the heating equipment, and using the temperature sensors, flow sensors and pressure sensors to monitor the operation status of the heating equipment in real time during the operation process, a real-time operation status parameter set of the heating equipment is obtained, wherein the real-time operation status parameter set of the heating equipment includes the real-time operation temperature of the heating equipment, the real-time operation flow of the heating equipment and the real-time operation pressure of the heating equipment; the real-time operation status parameter set of the heating equipment is uploaded to the cloud platform by using the Internet of Things gateway technology, and the real-time operation status parameter set of the heating equipment is edge-delay filtered by using the cloud platform to obtain a low-delay operation status parameter set of the heating equipment;

[0070] Step S2: performing a state parameter time-frequency transformation fluctuation analysis on the low-latency operating state parameter set of the heating equipment to obtain a time-frequency signal fluctuation frame corresponding to each heating equipment operating state parameter; performing a signal fault severity score quantitative calculation on the time-frequency signal fluctuation frame corresponding to each heating equipment operating state parameter to obtain a time-frequency signal fault severity score corresponding to each heating equipment operating state parameter; performing equipment fault classification processing on the fault category of the heating equipment based on the time-frequency signal fault severity score corresponding to each heating equipment operating state parameter to obtain a recoverable fault category of the heating equipment and an unrecoverable fault category of the heating equipment;

[0071] Step S3: When it is determined that the fault category of the heating equipment is a recoverable fault category of the heating equipment, a recoverable fault maintenance control analysis is performed on the recoverable fault category of the heating equipment using the cloud platform, and a recoverable fault maintenance control measure plan for the heating equipment is generated to perform corresponding recoverable fault maintenance control processing work;

[0072] Step S4: When it is determined that the fault category of the heating equipment is an irrecoverable fault category of the heating equipment, a cloud platform response is used to generate an emergency repair control request for the heating equipment to respond and inform the maintenance personnel to perform corresponding irrecoverable fault emergency repair control processing work.

[0073] In the embodiment of the present invention, please refer to Figure 1 FIG. 1 is a schematic diagram of a step flow chart of a method for processing heating equipment fault data based on the Internet of Things according to the present invention. In this example, the method for processing heating equipment fault data based on the Internet of Things includes the following steps:

[0074] Step S1: by installing temperature sensors, flow sensors and pressure sensors at key parts of the heating equipment, and using the temperature sensors, flow sensors and pressure sensors to monitor the operation status of the heating equipment in real time during the operation process, a real-time operation status parameter set of the heating equipment is obtained, wherein the real-time operation status parameter set of the heating equipment includes the real-time operation temperature of the heating equipment, the real-time operation flow of the heating equipment and the real-time operation pressure of the heating equipment; the real-time operation status parameter set of the heating equipment is uploaded to the cloud platform by using the Internet of Things gateway technology, and the real-time operation status parameter set of the heating equipment is edge-delay filtered by using the cloud platform to obtain a low-delay operation status parameter set of the heating equipment;

[0075] In an embodiment of the present invention, a demand analysis of sensor configuration is performed on the corresponding key parts of the heating equipment (including boilers, pipelines and valve areas) to comprehensively evaluate and identify the specific needs of these key parts for temperature, pressure and flow monitoring. Through an in-depth analysis of the equipment operating conditions, environmental factors and performance requirements, the key monitoring points of the heating equipment, such as the water outlet and return outlet of the boiler and the position of the joints in the pipeline and the opening and closing of the valve, are identified, so that the name, location and required sensor type of each monitoring point are recorded in detail to ensure that the selection and arrangement of sensors in the subsequent implementation process meet the actual needs, and the optimal installation position of the temperature, pressure and flow sensors is designed according to the actual needs, so that the recommended positions of the sensors are marked by using computer-aided design (CAD) software in combination with the on-site layout diagram, so that during the design process, the temperature sensor should be set on both sides of the fluid outlet and inlet, and the pressure sensor should be located at the pipe. The middle section of the pipeline is installed to obtain a uniform pressure value, and the flow sensor should be placed in the horizontal section of the pipeline to ensure accurate measurement of the flow rate. The resulting sensor installation implementation plan will be refined into specific construction drawings. At the same time, the actual installation of sensors will be carried out at key parts of the heating equipment according to the implementation plan, so that the temperature sensor, flow sensor and pressure sensor can be firmly installed in the predetermined position by using electric tools and fixtures. After installation, it is connected to the control system of the equipment through programming to ensure that the sensor can collect data in real time. The temperature sensor will monitor the operating temperature of the heating equipment in real time through technologies such as thermocouples or thermal resistors, so as to obtain the real-time operating temperature of the heating equipment; the flow sensor uses a turbine flowmeter or an electromagnetic flowmeter to monitor the flow of the heating equipment in real time, so as to obtain the real-time operating flow of the heating equipment; and the pressure sensor uses a strain gauge or piezoresistive sensor to monitor the pressure of the heating equipment in real time, so as to obtain the real-time operating pressure of the heating equipment. The real-time operating temperature, real-time operating flow and real-time operating pressure of the heating equipment previously obtained by real-time monitoring are combined to merge the operating status parameters, so as to merge the parameters such as temperature, flow and pressure into a device operating status parameter set, thereby obtaining the real-time operating status parameter set of the heating equipment. The real-time operating status parameter set of the heating equipment is also uploaded to the cloud platform through the Internet of Things gateway using a secure communication protocol (such as MQTT or HTTPs). On the cloud platform, the device operating status parameter set will be marked with a timestamp, and then the edge computing technology is used to filter and calculate the edge delay of the uploaded real-time operating status parameter set of the heating equipment, so as to use the edge computing device to convert the real-time operating status parameter set of the heating equipment into a time series data stream, and through an efficient algorithm (such as Kalman filtering or adaptive filtering), the data stream with high transmission delay is identified and filtered out, and after processing, the operating status parameter set with low transmission delay is retained to ensure the high efficiency of real-time monitoring and control, and finally the low-latency operating status parameter set of the heating equipment is obtained.

[0076] Step S2: performing a state parameter time-frequency transformation fluctuation analysis on the low-latency operating state parameter set of the heating equipment to obtain a time-frequency signal fluctuation frame corresponding to each heating equipment operating state parameter; performing a signal fault severity score quantitative calculation on the time-frequency signal fluctuation frame corresponding to each heating equipment operating state parameter to obtain a time-frequency signal fault severity score corresponding to each heating equipment operating state parameter; performing equipment fault classification processing on the fault category of the heating equipment based on the time-frequency signal fault severity score corresponding to each heating equipment operating state parameter to obtain a recoverable fault category of the heating equipment and an unrecoverable fault category of the heating equipment;

[0077] In an embodiment of the present invention, a Z-score standardization method is used to standardize the low-latency operating status parameter set of the heating equipment obtained after delay filtering, so as to convert the original data into standardized data by calculating the mean and standard deviation of each parameter, so as to eliminate the influence of different dimensions and ranges on subsequent analysis, and a timing synchronization method is used to synchronize the timing of the standardized operating status parameter set of the heating equipment obtained after standardization, so as to align the timestamps by a linear interpolation method. In this process, the time series data of each device is resampled at a uniform time interval, and missing values ​​are filled by interpolation to ensure that the standardized parameters of each device have data at the same time point, thereby forming a timing synchronization parameter set of the operating status of the heating equipment. At the same time, by performing statistical analysis on the fluctuations after time-frequency transformation of the heating equipment operating state timing synchronization parameter set obtained after the previous timing synchronization, the heating equipment operating state timing synchronization parameter set is processed by using the short-time Fourier transform (STFT) or wavelet transform method. Specifically, firstly, an appropriate window length and overlap rate are set, and then the time-frequency signal of the heating equipment operating state parameters in each time period is transformed to obtain the corresponding time-frequency signal, and at the same time, the corresponding signal fluctuation change time frame in the time-frequency signal is analyzed, that is, the corresponding fluctuation frame, wherein each fluctuation frame will contain rich frequency domain information and time information, thereby obtaining the time-frequency signal fluctuation frame corresponding to each heating equipment operating state parameter, including the time-frequency signal fluctuation frame corresponding to the operating temperature, operating flow and operating pressure. Then, after obtaining the time-frequency signal fluctuation frame corresponding to the operating status parameters of each heating equipment, the weighted average method is used to calculate the fault severity score of the corresponding time-frequency change signal in the time-frequency signal fluctuation frame. In the specific implementation, the time-frequency signal fluctuation of each parameter is firstly extracted to calculate indicators such as energy, amplitude and frequency. Then, weights are set for different features, and weighted scores are performed according to the correlation of the actual fault situation. The time-frequency signal fault severity score corresponding to the operating status parameter of each heating equipment is calculated by scoring, where the score range is 0-10 points, and the higher the score, the more serious the fault, thereby obtaining the time-frequency signal fault severity score corresponding to the operating status parameter of each heating equipment.Finally, after obtaining the time-frequency signal fault severity scores corresponding to the operating status parameters of each heating equipment, the fault category is classified and judged to set the scoring standard. That is, when the time-frequency signal fault severity scores corresponding to the operating temperature, operating flow and operating pressure are all in the range of 0-5 points, the fault situation corresponding to the heating equipment is judged as a recoverable fault category; if the score of any parameter reaches 6 points or above, it is classified as an irrecoverable fault category. Through this judgment logic, the fault type of the heating equipment can be identified in time to ensure that appropriate maintenance and handling measures are taken when a fault occurs to minimize equipment downtime and energy consumption, and finally the recoverable fault category and irrecoverable fault category of the heating equipment are obtained.

[0078] Step S3: When it is determined that the fault category of the heating equipment is a recoverable fault category of the heating equipment, a recoverable fault maintenance control analysis is performed on the recoverable fault category of the heating equipment using the cloud platform, and a recoverable fault maintenance control measure plan for the heating equipment is generated to perform corresponding recoverable fault maintenance control processing work;

[0079] In an embodiment of the present invention, if it is determined that the fault category of the heating equipment is a recoverable fault, the cloud platform will be used to control and generate a corresponding maintenance control measure plan based on the corresponding recoverable fault category. This plan includes specific maintenance steps and suggestions, involving replacing specific parts, adjusting operating parameters, or restarting the system, etc., so as to generate accurate maintenance instructions by utilizing data analysis and historical fault cases, combined with fault severity scores. For example, if the temperature sensor is abnormal and the fault score is low, the maintenance plan recommends replacing the sensor or calibrating it. The cloud platform informs the maintenance personnel by push notification, and provides detailed maintenance procedures and a list of required tools through mobile phone applications or other interfaces to ensure that the maintenance work is timely and effective. Finally, the corresponding heating equipment recoverable fault maintenance control measure plan is analyzed and generated to perform the corresponding recoverable fault maintenance control processing work.

[0080] Step S4: When it is determined that the fault category of the heating equipment is an irrecoverable fault category of the heating equipment, a cloud platform response is used to generate an emergency repair control request for the heating equipment to respond and inform the maintenance personnel to perform corresponding irrecoverable fault emergency repair control processing work.

[0081] In an embodiment of the present invention, if it is determined that the fault type of the heating equipment is an irrecoverable fault, the cloud platform immediately responds and generates a corresponding emergency maintenance control request to notify the corresponding heating equipment maintenance team using the Internet of Things gateway technology. This request contains key information such as the fault type, severity, and required response time, and is quickly conveyed to relevant personnel through various means such as text messages and emails. After receiving the notification, the maintenance personnel quickly formulate an emergency maintenance plan based on the fault information and historical data provided by the response generation. For example, immediately stop the operation of the heating equipment to prevent further damage. During this process, the cloud platform provides real-time monitoring functions to track the progress of maintenance, and after the maintenance is completed, requires the maintenance personnel to confirm the fault handling status in order to update the fault record and subsequent data analysis, thereby responding to inform the maintenance personnel to perform the corresponding irrecoverable fault emergency maintenance control processing work.

[0082] Further, step S1 includes the following steps:

[0083] Step S11: Analyze the sensor configuration requirements of key parts of the heating equipment to obtain a sensor configuration requirement report of key parts of the heating equipment, wherein the key parts of the heating equipment include boilers, pipelines and valve areas;

[0084] Step S12: Designing optimal sensor installation positions for temperature sensors, pressure sensors, and flow sensors based on the sensor configuration requirement report for key parts of the heating equipment, so as to generate an implementation plan for sensor installation for key parts of the heating equipment;

[0085] Step S13: installing temperature sensors, flow sensors and pressure sensors at key parts of the heating equipment according to the implementation plan for installing sensors at key parts of the heating equipment, and using the temperature sensor to monitor the equipment operating temperature in real time during the operation of the heating equipment to obtain the real-time operating temperature of the heating equipment; using the flow sensor to monitor the equipment operating flow in real time during the operation of the heating equipment to obtain the real-time operating flow of the heating equipment; using the pressure sensor to monitor the equipment operating pressure in real time during the operation of the heating equipment to obtain the real-time operating pressure of the heating equipment;

[0086] Step S14: merging the real-time operating temperature of the heating equipment, the real-time operating flow rate of the heating equipment, and the real-time operating pressure of the heating equipment as equipment operating status parameters to obtain a real-time operating status parameter set of the heating equipment; uploading the real-time operating status parameter set of the heating equipment to the cloud platform using the Internet of Things gateway technology;

[0087] Step S15: Use the cloud platform to perform edge delay filtering on the real-time operating status parameter set of the heating equipment to obtain a low-latency operating status parameter set of the heating equipment.

[0088] As an embodiment of the present invention, refer to Figure 2 As shown, Figure 1 Detailed step flow diagram of step S1 in FIG. 1 , in this embodiment, step S1 includes the following steps:

[0089] Step S11: Analyze the sensor configuration requirements of key parts of the heating equipment to obtain a sensor configuration requirement report of key parts of the heating equipment, wherein the key parts of the heating equipment include boilers, pipelines and valve areas;

[0090] In an embodiment of the present invention, a sensor configuration requirement analysis is performed on the corresponding key parts of the heating equipment (including boilers, pipelines and valve areas) to comprehensively evaluate and identify the specific requirements of these key parts for temperature, pressure and flow monitoring. Through an in-depth analysis of the equipment operating conditions, environmental factors and performance requirements, the key monitoring points of the heating equipment are identified, such as the water outlet and return outlet of the boiler, the location of the joints in the pipeline and the opening and closing of the valve, so as to record the name, location and required sensor type of each monitoring point in detail, ensure that the selection and arrangement of sensors in the subsequent implementation process meet the actual needs, and finally obtain a sensor configuration requirement report for the key parts of the heating equipment.

[0091] Step S12: Designing optimal sensor installation positions for temperature sensors, pressure sensors, and flow sensors based on the sensor configuration requirement report for key parts of the heating equipment, so as to generate an implementation plan for sensor installation for key parts of the heating equipment;

[0092] In an embodiment of the present invention, the optimal installation positions of temperature, pressure and flow sensors are designed by combining the sensor configuration requirement report of key parts of the heating equipment obtained by previous analysis, so as to mark the recommended positions of the sensors by using computer-aided design (CAD) software and combining with the on-site layout diagram. These positions should ensure that the sensors are in contact with the key parameters of the equipment and take into account the accessibility of the equipment during maintenance. During the design process, the temperature sensor should be set on both sides of the fluid outlet and inlet, the pressure sensor should be located in the middle section of the pipeline to obtain a uniform pressure value, and the flow sensor should be placed in the horizontal section of the pipeline to ensure accurate measurement of the flow. The sensor installation implementation plan thus formed will be refined into specific construction drawings, and finally the design will generate a sensor installation implementation plan for key parts of the heating equipment.

[0093] Step S13: installing temperature sensors, flow sensors and pressure sensors at key parts of the heating equipment according to the implementation plan for installing sensors at key parts of the heating equipment, and using the temperature sensor to monitor the equipment operating temperature in real time during the operation of the heating equipment to obtain the real-time operating temperature of the heating equipment; using the flow sensor to monitor the equipment operating flow in real time during the operation of the heating equipment to obtain the real-time operating flow of the heating equipment; using the pressure sensor to monitor the equipment operating pressure in real time during the operation of the heating equipment to obtain the real-time operating pressure of the heating equipment;

[0094] In an embodiment of the present invention, the actual installation of sensors at key parts of the heating equipment is carried out by using a previously formulated implementation plan for the installation of sensors at key parts of the heating equipment, so that the temperature sensor, flow sensor and pressure sensor are firmly installed at predetermined positions using electric tools and fixing devices. After installation, they are connected to the control system of the equipment through programming to ensure that the sensors can collect data in real time. The temperature sensor will monitor the operating temperature of the heating equipment in real time through technologies such as thermocouples or thermistors, thereby obtaining the real-time operating temperature of the heating equipment; the flow sensor uses a turbine flowmeter or an electromagnetic flowmeter to monitor the flow of the heating equipment in real time, thereby obtaining the real-time operating flow of the heating equipment; and the pressure sensor uses a strain gauge or piezoresistive sensor to monitor the pressure of the heating equipment in real time, and finally obtains the real-time operating pressure of the heating equipment.

[0095] Step S14: merging the real-time operating temperature of the heating equipment, the real-time operating flow rate of the heating equipment, and the real-time operating pressure of the heating equipment as equipment operating status parameters to obtain a real-time operating status parameter set of the heating equipment; uploading the real-time operating status parameter set of the heating equipment to the cloud platform using the Internet of Things gateway technology;

[0096] In an embodiment of the present invention, the real-time operating temperature, real-time operating flow and real-time operating pressure of the heating equipment previously monitored in real time are combined to merge the operating state parameters, so as to merge the temperature, flow and pressure parameters into a set of equipment operating state parameters. This process is implemented by data integration software, and the data of each sensor is transmitted to the Internet of Things gateway through a data bus or a local area network, so as to obtain the real-time operating state parameter set of the heating equipment. At the same time, the real-time operating state parameter set of the heating equipment is uploaded to the cloud platform through the Internet of Things gateway using a secure communication protocol (such as MQTT or HTTPs). On the cloud platform, the equipment operating state parameter set will be marked with a timestamp to facilitate subsequent data analysis and fault diagnosis.

[0097] Step S15: Use the cloud platform to perform edge delay filtering on the real-time operating status parameter set of the heating equipment to obtain a low-latency operating status parameter set of the heating equipment.

[0098] In an embodiment of the present invention, edge computing technology is used through a cloud platform to perform edge delay filtering calculation on the uploaded real-time operating status parameter set of the heating equipment, so as to utilize the edge computing device to convert the real-time operating status parameter set of the heating equipment into a time series data stream, and through an efficient algorithm (such as Kalman filtering or adaptive filtering), identify and filter out data streams with high transmission delays, and after processing, retain the operating status parameter set with low transmission delay, thereby ensuring the high efficiency of real-time monitoring and control, and finally obtaining a low-latency operating status parameter set of the heating equipment.

[0099] Further, step S15 includes the following steps:

[0100] Step S151: using the cloud platform to monitor the edge transmission duration of each heating equipment operation parameter data point in the real-time operation status parameter set of the heating equipment, and obtaining the edge transmission response duration corresponding to each heating equipment operation parameter data point;

[0101] Step S152: performing transmission reaction speed statistical analysis on the corresponding heating equipment operation parameter data points in the heating equipment real-time operation status parameter set based on the edge transmission response time corresponding to each heating equipment operation parameter data point, and obtaining the edge transmission reaction speed corresponding to each heating equipment operation parameter data point;

[0102] Step S153: Performing network status evaluation and analysis on each heating equipment operation parameter data point in the heating equipment real-time operation status parameter set to obtain network status evaluation parameters corresponding to each heating equipment operation parameter data point, wherein the network status evaluation parameters include network bandwidth value, network delay and data packet loss rate;

[0103] Step S154: Based on the edge transmission reaction speed corresponding to each heating equipment operation parameter data point and the network status evaluation parameter, the edge transmission delay index calculation formula is used to perform edge delay quantitative calculation on the heating equipment operation parameter data point corresponding to the heating equipment real-time operation status parameter set, and obtain the edge transmission operation delay index corresponding to each heating equipment operation parameter data point;

[0104] Step S155: Compare and judge the edge transmission operation delay index corresponding to each heating equipment operation parameter data point according to the preset edge delay threshold. If the edge transmission operation delay index is greater than or equal to the preset edge delay threshold, the corresponding heating equipment operation parameter data point is marked as a high-latency operation parameter data point; if the edge transmission operation delay index is less than the preset edge delay threshold, the corresponding heating equipment operation parameter data point is marked as a low-latency operation parameter data point; the heating equipment operation parameter data points corresponding to the low-latency operation parameter data points in the real-time operation status parameter set of the heating equipment are filtered out and collected to obtain the low-latency operation status parameter set of the heating equipment.

[0105] As an embodiment of the present invention, refer to Figure 3 As shown, Figure 2 Detailed step flow diagram of step S15 in FIG. 1 , in this embodiment, step S15 includes the following steps:

[0106] Step S151: using the cloud platform to monitor the edge transmission duration of each heating equipment operation parameter data point in the real-time operation status parameter set of the heating equipment, and obtaining the edge transmission response duration corresponding to each heating equipment operation parameter data point;

[0107] In an embodiment of the present invention, the edge transmission duration of each heating equipment operating parameter data time node in the previously received real-time operating status parameter set of the heating equipment is monitored by utilizing the edge computing node connected to the cloud platform and the edge device, so as to monitor and record the start time and end time of the data transmission at each time node to calculate the edge transmission duration of each data point. This process can use a high-precision timestamp recording mechanism to ensure the accuracy of the transmission duration, and finally obtain the edge transmission response duration corresponding to each heating equipment operating parameter data point.

[0108] Step S152: performing transmission reaction speed statistical analysis on the corresponding heating equipment operation parameter data points in the heating equipment real-time operation status parameter set based on the edge transmission response time corresponding to each heating equipment operation parameter data point, and obtaining the edge transmission reaction speed corresponding to each heating equipment operation parameter data point;

[0109] In an embodiment of the present invention, a statistical analysis tool (such as the Pandas library in Python or R language) is used to perform statistical calculations on the transmission reaction speed of the corresponding heating equipment operation parameter data points in combination with the edge transmission response time corresponding to each heating equipment operation parameter data point obtained by previous monitoring, so as to measure the transmission distance between the edge computing node and the cloud platform, and use the ratio of the transmission distance to the edge transmission response time to evaluate and calculate the transmission reaction speed of each data point, and finally obtain the edge transmission reaction speed corresponding to each heating equipment operation parameter data point.

[0110] Step S153: Performing network status evaluation and analysis on each heating equipment operation parameter data point in the heating equipment real-time operation status parameter set to obtain network status evaluation parameters corresponding to each heating equipment operation parameter data point, wherein the network status evaluation parameters include network bandwidth value, network delay and data packet loss rate;

[0111] In an embodiment of the present invention, a network monitoring tool (such as Wireshark or other network monitoring software) is used to monitor the network transmission environment of each heating equipment operating parameter data point in the real-time operating status parameter set of the heating equipment in real time during the upload process, so as to evaluate and calculate the network status of each heating equipment during operation according to the requirements of parameters such as network bandwidth, delay and data packet loss rate, including network bandwidth value, network delay and data packet loss rate, and finally obtain the network status evaluation parameters corresponding to each heating equipment operating parameter data point.

[0112] Step S154: Based on the edge transmission reaction speed corresponding to each heating equipment operation parameter data point and the network status evaluation parameter, the edge transmission delay index calculation formula is used to perform edge delay quantitative calculation on the heating equipment operation parameter data point corresponding to the heating equipment real-time operation status parameter set, and obtain the edge transmission operation delay index corresponding to each heating equipment operation parameter data point;

[0113] In an embodiment of the present invention, a suitable edge transmission delay index calculation formula is formed by combining the number parameters of the heating equipment operation parameter data points, the edge transmission reaction speed, the influence weight coefficient of the edge transmission reaction speed, the network delay, the influence weight coefficient of the network delay, the network delay attenuation rate index, the time variable parameter, the network bandwidth value, the data packet loss rate, the cumulative influence weight coefficient of the network status and related parameters to perform edge delay quantitative calculation on the corresponding heating equipment operation parameter data points in the real-time operation status parameter set of the heating equipment, so as to quantitatively calculate the corresponding transmission delay index, and finally obtain the edge transmission operation delay index corresponding to each heating equipment operation parameter data point.

[0114] Step S155: Compare and judge the edge transmission operation delay index corresponding to each heating equipment operation parameter data point according to the preset edge delay threshold. If the edge transmission operation delay index is greater than or equal to the preset edge delay threshold, the corresponding heating equipment operation parameter data point is marked as a high-latency operation parameter data point; if the edge transmission operation delay index is less than the preset edge delay threshold, the corresponding heating equipment operation parameter data point is marked as a low-latency operation parameter data point; the heating equipment operation parameter data points corresponding to the low-latency operation parameter data points in the real-time operation status parameter set of the heating equipment are filtered out and collected to obtain the low-latency operation status parameter set of the heating equipment.

[0115] In an embodiment of the present invention, a comparison is made between the edge transmission operation delay index corresponding to the heating equipment operation parameter data point previously obtained by quantitative calculation by using a preset edge delay threshold. If the edge transmission operation delay index is greater than or equal to the preset edge delay threshold, the data point is automatically marked as a high-latency operation parameter data point; otherwise, it is marked as a low-latency operation parameter data point. To ensure the accuracy of the marking, this process should be executed through an automated script to reduce the possibility of errors caused by human intervention. At the same time, all heating equipment operation status parameter data points marked as low-latency are filtered out and collected in a large data set to finally obtain a low-latency operation status parameter set for the heating equipment.

[0116] Furthermore, the edge transmission delay index calculation formula in step S154 is specifically:

[0117] ;

[0118] In the formula, For the The edge transmission operation delay index corresponding to the heating equipment operation parameter data point, is the total number of data points of heating equipment operating parameters, It is the item index parameter of the heating equipment operation parameter data point. For the The edge transmission response speed corresponding to each heating equipment operation parameter data point, is the influence weight coefficient of edge transmission reaction speed, For the The network delay corresponding to each heating equipment operating parameter data point, is the network delay decay rate index, is the impact weight coefficient of network delay, is the time variable parameter, For the Heating equipment operating parameter data points at time The network bandwidth value at For the Heating equipment operating parameter data points at time The data packet loss rate at is the cumulative impact weight coefficient of the network status, Correction factor for edge transport operation latency exponential.

[0119] The present invention obtains an edge transmission delay index calculation formula by using a specific mathematical model and verifying that it is used to perform edge delay quantitative calculation on the heating equipment operation parameter data points corresponding to the real-time operation status parameter set of the heating equipment. The edge transmission delay index calculation formula is To represent the edge transmission reaction speed, and to include the edge transmission reaction speed in the calculation through the weight coefficient of the edge transmission reaction speed, the timeliness of data transmission can be dynamically evaluated, which is crucial for timely acquisition of the operating status of the heating equipment, ensuring that equipment failures or abnormal conditions can be quickly detected and processed. When the reaction speed is faster, the equipment can more effectively adjust its working state to cope with environmental changes and improve heating efficiency. The network delay is represented by the network delay, and the impact of network delay is introduced into the calculation. Network delay may be caused by many factors, including network congestion or link failure. Evaluating delay can help identify potential network problems and take corresponding optimization measures. By monitoring and analyzing network delay, the data transmission path can be optimized, the network with the lowest delay can be selected for information transmission, and the overall data transmission efficiency can be improved. Secondly, through the comprehensive evaluation of network bandwidth and data packet loss rate, the comprehensive impact of network conditions can be reflected in the delay index calculation. By introducing bandwidth and packet loss rate, the impact of network environment on edge transmission can be fully evaluated, which helps to automatically adjust the operation strategy of heating equipment when network conditions are poor, such as reducing data transmission frequency or selecting a more reliable transmission mechanism, so as to ensure the stability and reliability of heating equipment. By considering time variables, the changes in network conditions over time can be captured, and performance bottlenecks in a specific time period can be identified. This is especially important for equipment that is monitored for a long time, and can help administrators develop more reasonable maintenance and monitoring plans. In addition, by introducing a correction coefficient, the uncertainty and error in the calculation formula can be compensated, making the calculation of edge transmission delay index more accurate and reliable, which is crucial for providing accurate equipment operation status evaluation, especially in complex and dynamic network environments. Therefore, this calculation formula can provide comprehensive support for real-time monitoring and management of heating equipment by comprehensively considering multiple factors such as response speed, network latency, bandwidth, and data packet loss rate. Through these calculations, the equipment operation strategy can be dynamically adjusted to improve heating efficiency and reliability, and ultimately achieve intelligent management and optimization. In summary, this formula fully considers the first The edge transmission operation delay index corresponding to the heating equipment operation parameter data point , the total number of data points of heating equipment operating parameters , item index parameter of heating equipment operation parameter data point , No. The edge transmission response speed corresponding to the heating equipment operation parameter data point , the influence weight coefficient of edge transmission reaction speed , No. The network delay corresponding to the heating equipment operating parameter data point , network delay decay rate index , the impact weight coefficient of network delay , time variable parameter , No. Heating equipment operating parameter data points at time The network bandwidth value at , No. Heating equipment operating parameter data points at time Data packet loss rate at , network status cumulative impact weight coefficient , correction factor for edge transmission operation delay index , according to The edge transmission operation delay index corresponding to the heating equipment operation parameter data point The correlation between the above parameters constitutes a functional relationship This formula can realize the edge delay quantification calculation process of the heating equipment operation parameter data point corresponding to the real-time operation status parameter set of the heating equipment. At the same time, the correction coefficient of the edge transmission operation delay index is The introduction of can be adjusted according to the error situation in the calculation process, thereby improving the accuracy and applicability of the edge transmission delay index calculation formula.

[0120] Further, step S2 includes the following steps:

[0121] Step S21: performing state parameter standardization processing on the low-latency operation state parameter set of the heating equipment to obtain a standardized operation state parameter set of the heating equipment;

[0122] In an embodiment of the present invention, the low-latency operating status parameter set of the heating equipment obtained after delay filtering is standardized by adopting the Z-score standardization method, so as to convert the original data into standardized data by calculating the mean and standard deviation of each parameter, so as to eliminate the influence of different dimensions and ranges on subsequent analysis. Specifically, for each parameter of the heating equipment, its mean and standard deviation are calculated, and then converted using the formula: standardized parameter = (original parameter-mean) / standard deviation, and finally the standardized parameter set of the operating status of the heating equipment is obtained.

[0123] Step S22: performing time-series synchronization processing on the standardized parameter set of the operation status of the heating equipment to obtain the time-series synchronization parameter set of the operation status of the heating equipment;

[0124] In an embodiment of the present invention, a timing synchronization method is used to perform timing synchronization processing on the standardized parameter set of the operating status of the heating equipment obtained after previous standardization, so as to align the timestamps using a linear interpolation method. In this process, the time series data of each device is resampled at a uniform time interval, and missing values ​​are filled by interpolation to ensure that the standardized parameters of each device have data at the same time point. After the timing synchronization is completed, a timing synchronization parameter set of the operating status of the heating equipment is formed, and finally the timing synchronization parameter set of the operating status of the heating equipment is obtained.

[0125] Step S23: performing a state parameter time-frequency transformation fluctuation analysis on the heating equipment operation state timing synchronization parameter set to obtain a time-frequency signal fluctuation frame corresponding to each heating equipment operation state parameter, wherein the time-frequency signal fluctuation frame corresponding to each heating equipment operation state parameter includes a time-frequency signal fluctuation frame corresponding to an operation temperature, an operation flow rate, and an operation pressure;

[0126] In an embodiment of the present invention, a statistical analysis of the fluctuations after time-frequency transformation is performed on the heating equipment operating status timing synchronization parameter set previously obtained after timing synchronization, so that the heating equipment operating status timing synchronization parameter set is processed by using a short-time Fourier transform (STFT) or wavelet transform method. Specifically, an appropriate window length and overlap rate are first set, and then the time-frequency signal is transformed for the heating equipment operating status parameters in each time period to obtain the corresponding time-frequency signal, and at the same time, the corresponding signal fluctuation change time frame in the time-frequency signal, that is, the corresponding fluctuation frame, is analyzed, wherein each fluctuation frame will contain rich frequency domain information and time information, which is helpful to reveal the fluctuation characteristics of the heating equipment operating status parameters during the operation process, and finally the time-frequency signal fluctuation frames corresponding to the operating status parameters of each heating equipment are obtained, including the time-frequency signal fluctuation frames corresponding to the operating temperature, operating flow and operating pressure.

[0127] Step S24: performing quantitative calculation of signal fault severity scores for the time-frequency signal fluctuation frames corresponding to the operating state parameters of each heating device, so as to obtain the time-frequency signal fault severity scores corresponding to the operating state parameters of each heating device, wherein the time-frequency signal fault severity scores corresponding to the operating state parameters of each heating device include the time-frequency signal fault severity scores corresponding to the operating temperature, the operating flow rate and the operating pressure;

[0128] In an embodiment of the present invention, after obtaining the time-frequency signal fluctuation frame corresponding to the operating status parameters of each heating equipment, the weighted average method is used to calculate the fault severity score of the corresponding time-frequency change signal in the time-frequency signal fluctuation frame. In the specific implementation, the time-frequency signal fluctuation of each parameter is firstly extracted, and indicators such as energy, amplitude and frequency are calculated. Then, weights are set for different features, and weighted scoring is performed according to the correlation of the actual fault situation. The time-frequency signal fault severity score corresponding to the operating status parameter of each heating equipment is obtained by scoring calculation, wherein the scoring range is 0-10 points, and the higher the score, the more serious the fault. Finally, the time-frequency signal fault severity score corresponding to the operating status parameter of each heating equipment is obtained, which includes the time-frequency signal fault severity score corresponding to the operating temperature, operating flow and operating pressure.

[0129] Step S25: Classify the fault category of the heating equipment based on the time-frequency signal fault severity scores corresponding to the operating status parameters of each heating equipment. If the time-frequency signal fault severity scores corresponding to the corresponding operating temperature, operating flow and operating pressure are all within the range of 0-5 points, the fault category of the heating equipment is classified as a recoverable fault category of the heating equipment; if the time-frequency signal fault severity scores corresponding to the corresponding operating temperature, operating flow and operating pressure are within the range of 6 points or above, the fault category of the heating equipment is classified as an unrecoverable fault category of the heating equipment.

[0130] In an embodiment of the present invention, after obtaining the time-frequency signal fault severity scores corresponding to the operating status parameters of each heating equipment, the fault category is classified and judged to set the scoring standard. That is, when the time-frequency signal fault severity scores corresponding to the operating temperature, operating flow and operating pressure are all within the range of 0-5 points, the fault condition corresponding to the heating equipment is judged as a recoverable fault category; if the score of any parameter reaches 6 points or above, it is classified as an unrecoverable fault category. Through this judgment logic, the fault type of the heating equipment can be identified in time to ensure that appropriate maintenance and handling measures are taken when a fault occurs to minimize equipment downtime and energy consumption.

[0131] Further, step S23 includes the following steps:

[0132] Step S231: performing a time domain change analysis of the state parameter of the heating equipment operation state timing synchronization parameter set to obtain the time domain change trend data of the operation state parameters of each heating equipment in the time dimension;

[0133] In an embodiment of the present invention, a time series analysis method is used to perform a statistical analysis on the time domain changes of the state parameters of the heating equipment operating status timing synchronization parameter set obtained after the previous timing synchronization, so as to statistically analyze the change trends of the operating status parameters of each heating equipment in the time dimension. Specifically, the sliding window technology is used to analyze indicators such as the average value, maximum value and minimum value of the parameters in each time period, and the change trends in the corresponding time dimension are analyzed based on the statistical indicators obtained by the analysis, and finally the time domain change trend data of the operating status parameters of each heating equipment in the time dimension are obtained.

[0134] Step S232: Calculate the instantaneous frequency of each heating device operating state parameter at each time domain node on the time dimension of the time domain change trend data to obtain the instantaneous frequency of each heating device operating state parameter at each time domain node;

[0135] In an embodiment of the present invention, after obtaining the time domain change trend data of the operating status parameters of each heating equipment in the time dimension, the corresponding time domain change trend data is analyzed using short-time Fourier transform (STFT) to divide the time domain change trend data of the operating status parameters of each heating equipment into multiple overlapping time periods, and for each time period, its spectrum is calculated, and the instantaneous frequency at the corresponding time point is extracted. In a specific implementation, a fast Fourier transform (FFT) algorithm is used to improve the calculation efficiency, obtain the frequency distribution on each time domain node, and finally obtain the time domain change instantaneous frequency of each heating equipment operating status parameter on each time domain node.

[0136] Step S233: performing time-frequency signal spectrum transformation on the corresponding time-domain variation trend data based on the time-domain variation instantaneous frequency of each heating equipment operation status parameter at each time-domain node, to obtain the time-frequency variation signal spectrum corresponding to each heating equipment operation status parameter;

[0137] In an embodiment of the present invention, the spectrum of the time-frequency signal is transformed by combining the instantaneous frequency of the time-domain changes of each heating equipment operating status parameter at each time domain node obtained by previous statistical calculation to the corresponding time-domain change trend, so as to convert the time domain signal into a time-frequency domain signal by using a wavelet transform method, so as to better capture the change characteristics of the signal in time and frequency. Specifically, the instantaneous frequency of the time-domain changes of each heating equipment operating status parameter at each time domain node is convolved with the corresponding mother wavelet to obtain a spectrum representation in the time-frequency domain, thereby forming a spectrum of the time-frequency change signal corresponding to each heating equipment operating status parameter, and finally obtaining a spectrum of the time-frequency change signal corresponding to each heating equipment operating status parameter.

[0138] Step S234: performing time-frequency signal fluctuation range identification analysis on the time-frequency variation signal spectrum corresponding to the operating state parameters of each heating device, and obtaining the time range of the time-frequency signal fluctuation corresponding to the operating state parameters of each heating device;

[0139] In an embodiment of the present invention, the signal fluctuation range is identified and analyzed by analyzing the time-frequency variation signal spectrum corresponding to the operating status parameters of each heating device obtained after the previous transformation, and the signal fluctuation range is determined by using threshold detection and cluster analysis methods. Specifically, a suitable threshold is set to screen out significant signal fluctuations, and similar fluctuation patterns are classified through a clustering algorithm to identify the time range of the time-frequency signal fluctuations of each heating device, so as to determine whether the heating device is in an abnormal state within the time range of the corresponding time-frequency signal fluctuations, and finally the time range of the time-frequency signal fluctuations corresponding to the operating status parameters of each heating device is obtained.

[0140] Step S235: Based on the time range of the time-frequency signal fluctuations corresponding to the operating status parameters of each heating equipment, the corresponding time-frequency change signal spectrum is subjected to signal fluctuation range frame sealing processing to obtain the time-frequency signal fluctuation frames corresponding to the operating status parameters of each heating equipment, wherein the time-frequency signal fluctuation frames corresponding to the operating status parameters of each heating equipment include the time-frequency signal fluctuation frames corresponding to the operating temperature, the operating flow rate and the operating pressure.

[0141] In an embodiment of the present invention, by combining the time range of time-frequency signal fluctuations corresponding to the operating status parameters of each heating equipment obtained through previous identification and analysis, frame sealing processing of the fluctuation range is performed on the corresponding time-frequency change signal spectrum, so as to intercept the signal time change range within the identified fluctuation range and integrate it into a complete time-frequency signal fluctuation frame. By using data processing tools, frame sealing processing is performed on the operating status parameters (such as operating temperature, operating flow, and operating pressure) of each heating equipment, and the signal data within the corresponding time period is packaged into a time frame data. This time frame data will be used for subsequent fault analysis and prediction to ensure that the equipment remains in the best state during operation and minimize the risk of faults. Finally, the time-frequency signal fluctuation frames corresponding to the operating status parameters of each heating equipment are obtained, including the time-frequency signal fluctuation frames corresponding to the operating temperature, operating flow, and operating pressure.

[0142] Further, step S232 includes the following steps:

[0143] Performing time domain change smoothing processing on the time domain change trend data of the operating status parameters of each heating device in the time dimension to obtain the real change trend data of the operating status parameters of each heating device in the time dimension;

[0144] In an embodiment of the present invention, the time domain change trend data of the operating status parameters of each heating device in the time dimension obtained by the previous change analysis are smoothed to collect the operating status data of each heating device within a period of time, and the collected time series data are smoothed by using the moving average method or the exponential smoothing method. The specific implementation of the moving average method is to select a sliding window size (such as 5 minutes), and calculate the average value of the time point and several time points before and after the time point at each time point, so as to eliminate short-term fluctuations and obtain a smoother change trend. The exponential smoothing rule uses a weighted average method to give a greater weight to the most recent observation value, so as to capture the true trend of the equipment status change, so that the smoothed data can more accurately reflect the true change trend of the operating status parameters of the heating equipment, and finally obtain the true change trend data of the operating status parameters of each heating equipment in the time dimension.

[0145] Preferably, the real change trend data of the operating state parameters of each heating device in the time dimension are divided by time domain node marking to obtain the time domain change trend sub-data of the operating state parameters of each heating device at each time domain node;

[0146] In an embodiment of the present invention, by marking and dividing the time domain nodes of the real change trend data of the operating status parameters of each heating device obtained after the previous smoothing process in the time dimension, it is necessary to first set the node division standard, such as according to the time interval (every hour or every two hours) or according to the threshold value of the equipment state change (such as the change amplitude of temperature or pressure), and by writing a corresponding algorithm, traverse the smoothed data, and detect the change point that meets the conditions as the time domain node. For each marked node, the corresponding state data is divided to form time domain change trend sub-data, which contains the time domain change trend of the state parameters of each time domain node in a specific time period, and finally the time domain change trend sub-data of the operating status parameters of each heating device at each time domain node is obtained.

[0147] Preferably, a statistical analysis of the change amplitude of the time domain change trend sub-data of each heating equipment operating state parameter at each time domain node is performed to obtain the time domain change amplitude of each heating equipment operating state parameter at each time domain node; based on the time domain change amplitude of each heating equipment operating state parameter at each time domain node, a time domain change phase inverse solution processing is performed on the corresponding time domain change trend sub-data to obtain the time domain signal change phase of each heating equipment operating state parameter at each time domain node;

[0148] In an embodiment of the present invention, a statistical analysis of the change amplitude of the time domain change trend sub-data of each previously divided operating state parameter of each heating device at each time domain node is performed, and this is achieved by calculating the difference in state parameters between adjacent nodes. Specifically, for each time domain node, the difference between its state parameters (such as temperature and pressure) and those of the previous node is calculated to determine the change amplitude. If temperature is used as an example, the formula is: change amplitude = |current node temperature-previous node temperature|. This process can be achieved by writing a data analysis program to form a change amplitude record for each node, thereby obtaining the time domain change amplitude of each heating device operating state parameter at each time domain node. At the same time, by combining the previously calculated time domain change amplitudes of the operating status parameters of each heating equipment at each time domain node, the corresponding time domain change trend sub-data is inversely solved by the phase inverse trigonometric function to convert the time domain change trend of each time domain node state parameter into a frequency domain change parameter. Then, based on the magnitude of the change amplitude, the phase = arccos (frequency domain change parameter / magnitude of change amplitude) is used to determine the phase of each node. By calculating the frequency and amplitude relationship between the nodes, the time domain signal change phase of each node is obtained, and finally the time domain signal change phase of each heating equipment operating status parameter at each time domain node is obtained.

[0149] Preferably, the phase difference between adjacent nodes is calculated for the time domain signal change phase of each heating equipment operating state parameter at each time domain node to obtain the time domain change phase difference between each adjacent time domain node of each heating equipment operating state parameter;

[0150] In an embodiment of the present invention, the phase difference between adjacent nodes is calculated by combining the time domain signal change phase of each heating equipment operating status parameter at each time domain node obtained by inverse calculation previously at each time domain node, so as to calculate the phase difference by comparing the phase values ​​of adjacent nodes pair by pair, and the formula is: Phase difference = Current node phase - Previous node phase. For each node, all nodes are traversed in a loop and the phase difference is recorded in the corresponding data structure. This process can clearly show the change relationship between each adjacent node, and finally the time domain change phase difference of each heating equipment operating status parameter between each adjacent time domain node is obtained.

[0151] Preferably, the upper node instantaneous frequency calculation is performed on the corresponding time domain nodes based on the time domain change phase difference of each heating equipment operating status parameter between each adjacent time domain node to obtain the time domain change instantaneous frequency of each heating equipment operating status parameter at each time domain node.

[0152] In the embodiment of the present invention, the instantaneous frequency at the upper node is quantified for the corresponding time domain node by combining the time domain change phase difference between each adjacent time domain node obtained by the previous quantitative calculation of each heating equipment operating state parameter, so as to use the phase difference and time interval to calculate the instantaneous frequency at the current upper time domain node by the formula: , and the instantaneous frequency at the beginning time node = , select a suitable time interval (such as 1 minute), traverse each pair of adjacent nodes, calculate their instantaneous frequencies, and finally obtain the instantaneous frequency of the time domain changes of the operating status parameters of each heating equipment at each time domain node.

[0153] Further, step S24 includes the following steps:

[0154] Step S241: performing a change amplitude stability evaluation and analysis on the time-frequency signal fluctuation frames corresponding to the operating temperature and the operating flow, and obtaining a time-domain signal change amplitude stability index parameter corresponding to the operating temperature and the operating flow;

[0155] In an embodiment of the present invention, statistical analysis is performed on the time-frequency signal fluctuation frames corresponding to the operating temperature and the operating flow obtained through the previous analysis to analyze the frequency components of the time domain signals corresponding to the operating temperature and the operating flow and their temporal changes. Subsequently, the change amplitude of each time-frequency signal fluctuation frame is calculated, and the stability of the change amplitude is evaluated through a set threshold. The specific operation includes performing peak detection on the signal, calculating the difference between the maximum and minimum values ​​of each fluctuation frame to obtain a change amplitude index, and applying statistical methods such as standard deviation to evaluate the amplitude stability, thereby generating corresponding stability index parameters, and finally obtaining the time domain signal change amplitude stability index parameters corresponding to the operating temperature and the operating flow.

[0156] Step S242: performing signal phase shift statistical analysis on the time-frequency signal fluctuation frames corresponding to the operating temperature and the operating flow, and obtaining the time-frequency signal phase shift index parameters corresponding to the operating temperature and the operating flow;

[0157] In the embodiment of the present invention, the phase information of the time-frequency signal fluctuation frame corresponding to the acquired operating temperature and flow is extracted, so as to extract the phase information of the time domain signal in the time-frequency signal fluctuation frame by using the phase locked loop (PLL) technology, and the Hilbert transform method is applied to calculate the instantaneous phase. Then, the phase changes of different fluctuation frames are statistically analyzed by the time series analysis method, specifically including calculating the mean and variance of the phase, that is, To evaluate the degree of phase shift, and finally obtain the time-frequency signal phase shift index parameters corresponding to the operating temperature and operating flow.

[0158] Step S243: calculating the operating temperature fault severity score for the time-frequency signal fluctuation frame corresponding to the operating temperature based on the time-domain signal variation amplitude stability index parameter and the time-frequency signal phase offset index parameter corresponding to the operating temperature, so as to obtain the time-frequency signal fault severity score corresponding to the operating temperature;

[0159] In an embodiment of the present invention, a temperature fault severity score is calculated for the time-frequency signal fluctuation frame corresponding to the operating temperature by combining the time-domain signal change amplitude stability index parameter and the time-frequency signal phase shift index parameter corresponding to the operating temperature obtained by previous quantitative calculation, and a weighted scoring method is used to process these two indicators. For example, the weight of the change amplitude stability index is set to 0.7, and the weight of the phase shift index is set to 0.3. A linear weighted calculation is performed to generate a corresponding operating temperature fault severity score. The scoring result can be divided into different fault severity levels according to a preset scoring standard to clarify the equipment health status at the operating temperature, and finally the time-frequency signal fault severity score corresponding to the operating temperature is obtained.

[0160] Step S244: Calculate the operation flow fault severity score for the time-frequency signal fluctuation frame corresponding to the operation flow based on the time-domain signal change amplitude stability index parameter and the time-frequency signal phase offset index parameter corresponding to the operation flow, so as to obtain the time-frequency signal fault severity score corresponding to the operation flow;

[0161] In an embodiment of the present invention, the severity of the flow fault is scored and calculated for the time-frequency signal fluctuation frame corresponding to the operating flow by combining the time-domain signal change amplitude stability index parameter and the time-frequency signal phase shift index parameter corresponding to the operating flow obtained by the previous quantitative calculation, and the two indicators are processed by the weighted scoring method. For example, the weight of the change amplitude stability index is set to 0.65, and the weight of the phase shift index is set to 0.35. Through linear weighted calculation, the fault severity score of the operating flow is generated. The scoring result can be divided into different fault severity levels according to the preset scoring standard, and finally the time-frequency signal fault severity score corresponding to the operating flow is obtained.

[0162] Step S245: Calculate the operating pressure fault severity score for the time-frequency signal fluctuation frame corresponding to the operating pressure to obtain the time-frequency signal fault severity score corresponding to the operating pressure.

[0163] In an embodiment of the present invention, a fast Fourier transform (FFT) algorithm is used to perform spectrum analysis on the time-frequency signal fluctuation frame corresponding to the operating pressure obtained by the previous analysis to extract the frequency components of the operating pressure time-frequency signal, and the distribution amplitude of each frequency component is calculated, and the energy distribution of each frame in the time-frequency signal fluctuation frame corresponding to the operating pressure is obtained at the same time, so as to evaluate the signal energy distribution size in different frequency ranges by using the energy spectral density function (PSD), and a statistical analysis method is also used to perform statistical calculation of the signal volatility on the time-frequency signal fluctuation frequency distribution obtained by the previous extraction, and the calculation process includes calculating the mean of the frequency distribution, and then squaring the difference between each frequency value and the mean to obtain the average value of the square difference, and taking the square root thereof as the volatility, and at the same time, by combining the time-frequency signal fluctuation energy distribution obtained by the previous analysis to the corresponding The energy offset of the time-frequency signal is calculated for the corresponding time-frequency signal fluctuation frame, so as to compare the difference between the energy distribution of the current time-frequency signal and the energy distribution under the historical normal state, and quantify the energy offset using indicators such as the root mean square error (RMSE) or the mean deviation (MD). Then, the fault severity score of the operating pressure is calculated for the corresponding time-frequency signal fluctuation frame by combining the time-frequency signal volatility and the energy offset obtained by the previous statistical calculation. The weighted scoring model is adopted to combine the volatility and the energy offset to determine the degree of influence on the fault score to set the weight of each indicator, for example, the volatility accounts for 70%, the energy offset accounts for 30%, and the volatility and the energy offset are combined for calculation to calculate the weighted score, so as to obtain a comprehensive fault severity score value, and finally obtain the time-frequency signal fault severity score corresponding to the operating pressure.

[0164] Further, step S245 includes the following steps:

[0165] Perform signal fluctuation frequency and energy distribution analysis on the time-frequency signal fluctuation frame corresponding to the operating pressure to obtain the time-frequency signal fluctuation frequency distribution data and the time-frequency signal fluctuation energy distribution data corresponding to the operating pressure;

[0166] In an embodiment of the present invention, a fast Fourier transform (FFT) algorithm is used to perform spectrum analysis on the time-frequency signal fluctuation frame corresponding to the operating pressure obtained by the previous analysis to extract the frequency components of the operating pressure time-frequency signal, and the distribution amplitude of each frequency component is calculated, and the energy distribution of each frame in the time-frequency signal fluctuation frame corresponding to the operating pressure is obtained at the same time, so as to use the energy spectral density function (PSD) to evaluate the signal energy distribution size in different frequency ranges, and finally obtain the time-frequency signal fluctuation frequency distribution data and the time-frequency signal fluctuation energy distribution data corresponding to the operating pressure.

[0167] Preferably, the signal fluctuation rate is calculated for the time-frequency signal fluctuation frequency distribution data corresponding to the operating pressure to obtain the time-frequency signal fluctuation rate corresponding to the operating pressure;

[0168] In an embodiment of the present invention, a statistical analysis method is used to perform statistical calculation of the signal volatility on the time-frequency signal fluctuation frequency distribution data corresponding to the operating pressure previously extracted. The calculation process includes calculating the mean of the frequency distribution, and then squaring the difference between each frequency value and the mean to obtain the average value of the square difference, and taking the square root of the difference is the volatility. This volatility value indicates the stability of the operating pressure time-frequency signal within a certain period of time, and finally the time-frequency signal volatility corresponding to the operating pressure is obtained.

[0169] Preferably, based on the time-frequency signal fluctuation energy distribution data corresponding to the operating pressure, the signal energy offset calculation is performed on the corresponding time-frequency signal fluctuation frame to obtain the time-frequency signal fluctuation energy offset corresponding to the operating pressure;

[0170] In an embodiment of the present invention, the time-frequency signal energy offset calculation is performed on the corresponding time-frequency signal fluctuation frame by combining the time-frequency signal fluctuation energy distribution data corresponding to the operating pressure obtained by previous analysis, so as to determine the energy offset by comparing the energy distribution of the current time-frequency signal with the energy distribution under the historical normal state. In specific implementation, a baseline model of energy distribution is first established, and the difference between the baseline model and the current time-frequency signal energy distribution is calculated. The degree of energy offset is quantified using indicators such as the root mean square error (RMSE) or the mean deviation (MD), and finally the time-frequency signal fluctuation energy offset corresponding to the operating pressure is obtained.

[0171] Preferably, the operating pressure fault severity score is calculated for the corresponding time-frequency signal fluctuation frame based on the time-frequency signal fluctuation rate and the time-frequency signal fluctuation energy offset corresponding to the operating pressure to obtain the time-frequency signal fault severity score corresponding to the operating pressure.

[0172] In an embodiment of the present invention, the fault severity score of the operating pressure is calculated for the corresponding time-frequency signal fluctuation frame by combining the time-frequency signal fluctuation rate and the time-frequency signal fluctuation energy offset corresponding to the operating pressure obtained by previous statistical calculations, and a weighted scoring model is adopted to combine the volatility and the energy offset to determine the degree of influence on the fault score to set the weight of each indicator, for example, the volatility accounts for 70%, the energy offset accounts for 30%, and the volatility and the energy offset are calculated to calculate the weighted score, thereby obtaining a comprehensive fault severity score value, and finally obtaining the time-frequency signal fault severity score corresponding to the operating pressure.

[0173] Furthermore, the present invention also provides a heating equipment fault data processing system based on the Internet of Things, which is used to execute the heating equipment fault data processing method based on the Internet of Things as described above. The heating equipment fault data processing system based on the Internet of Things includes:

[0174] The heating equipment status parameter delay filtering module is used to install temperature sensors, flow sensors and pressure sensors at key parts of the heating equipment, and use the temperature sensors, flow sensors and pressure sensors to monitor the equipment operation status in real time during the operation of the heating equipment, so as to obtain a real-time operation status parameter set of the heating equipment, wherein the real-time operation status parameter set of the heating equipment includes the real-time operation temperature of the heating equipment, the real-time operation flow of the heating equipment and the real-time operation pressure of the heating equipment; use the Internet of Things gateway technology to upload the real-time operation status parameter set of the heating equipment to the cloud platform, and use the cloud platform to perform edge delay filtering on the real-time operation status parameter set of the heating equipment, so as to obtain a low-latency operation status parameter set of the heating equipment;

[0175] The heating equipment parameter signal fault classification module is used to perform a state parameter time-frequency transformation fluctuation analysis on the low-latency operating state parameter set of the heating equipment to obtain the time-frequency signal fluctuation frames corresponding to the operating state parameters of each heating equipment; perform a signal fault severity score quantitative calculation on the time-frequency signal fluctuation frames corresponding to the operating state parameters of each heating equipment to obtain the time-frequency signal fault severity score corresponding to the operating state parameters of each heating equipment; perform equipment fault classification processing on the fault categories of the heating equipment based on the time-frequency signal fault severity scores corresponding to the operating state parameters of each heating equipment, thereby obtaining the recoverable fault category of the heating equipment and the unrecoverable fault category of the heating equipment;

[0176] The recoverable fault maintenance control processing module is used to determine that the fault category of the heating equipment is a recoverable fault category of the heating equipment, and then use the cloud platform to perform a recoverable fault maintenance control analysis on the recoverable fault category of the heating equipment, generate a recoverable fault maintenance control measure plan for the heating equipment, and execute the corresponding recoverable fault maintenance control processing work;

[0177] The irrecoverable fault emergency repair control module is used to determine that the fault category of the heating equipment is an irrecoverable fault category of the heating equipment, and then use the cloud platform response to generate an emergency repair control request for the heating equipment to respond and inform the maintenance personnel to perform the corresponding irrecoverable fault emergency repair control processing work.

[0178] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A method for processing heating equipment fault data based on the Internet of Things, characterized in that: The following steps are involved: Step S1: by installing temperature sensors, flow sensors and pressure sensors at key parts of the heating equipment, and using the temperature sensors, flow sensors and pressure sensors to monitor the operation status of the heating equipment in real time during the operation process, a real-time operation status parameter set of the heating equipment is obtained, wherein the real-time operation status parameter set of the heating equipment includes the real-time operation temperature of the heating equipment, the real-time operation flow of the heating equipment and the real-time operation pressure of the heating equipment; the real-time operation status parameter set of the heating equipment is uploaded to the cloud platform by using the Internet of Things gateway technology, and the real-time operation status parameter set of the heating equipment is edge-delay filtered by using the cloud platform to obtain a low-delay operation status parameter set of the heating equipment; wherein step S1 includes the following steps: Step S11: Analyze the sensor configuration requirements of key parts of the heating equipment to obtain a sensor configuration requirement report of key parts of the heating equipment, wherein the key parts of the heating equipment include boilers, pipelines and valve areas; Step S12: Designing optimal sensor installation positions for temperature sensors, pressure sensors, and flow sensors based on the sensor configuration requirement report for key parts of the heating equipment, so as to generate an implementation plan for sensor installation for key parts of the heating equipment; Step S13: installing temperature sensors, flow sensors and pressure sensors at key parts of the heating equipment according to the implementation plan for installing sensors at key parts of the heating equipment, and using the temperature sensor to monitor the equipment operating temperature in real time during the operation of the heating equipment to obtain the real-time operating temperature of the heating equipment; using the flow sensor to monitor the equipment operating flow in real time during the operation of the heating equipment to obtain the real-time operating flow of the heating equipment; using the pressure sensor to monitor the equipment operating pressure in real time during the operation of the heating equipment to obtain the real-time operating pressure of the heating equipment; Step S14: merging the real-time operating temperature of the heating equipment, the real-time operating flow rate of the heating equipment, and the real-time operating pressure of the heating equipment as equipment operating status parameters to obtain a real-time operating status parameter set of the heating equipment; uploading the real-time operating status parameter set of the heating equipment to the cloud platform using the Internet of Things gateway technology; Step S15: Utilize the cloud platform to perform edge delay filtering on the real-time operating status parameter set of the heating equipment to obtain a low-delay operating status parameter set of the heating equipment; wherein step S15 includes the following steps: Step S151: using the cloud platform to monitor the edge transmission duration of each heating equipment operation parameter data point in the real-time operation status parameter set of the heating equipment, and obtaining the edge transmission response duration corresponding to each heating equipment operation parameter data point; Step S152: performing transmission reaction speed statistical analysis on the corresponding heating equipment operation parameter data points in the heating equipment real-time operation status parameter set based on the edge transmission response time corresponding to each heating equipment operation parameter data point, and obtaining the edge transmission reaction speed corresponding to each heating equipment operation parameter data point; Step S153: Performing network status evaluation and analysis on each heating equipment operation parameter data point in the heating equipment real-time operation status parameter set to obtain network status evaluation parameters corresponding to each heating equipment operation parameter data point, wherein the network status evaluation parameters include network bandwidth value, network delay and data packet loss rate; Step S154: Based on the edge transmission reaction speed corresponding to each heating equipment operation parameter data point and the network status evaluation parameter, the edge transmission delay index calculation formula is used to perform edge delay quantitative calculation on the heating equipment operation parameter data point corresponding to the heating equipment real-time operation status parameter set, and obtain the edge transmission operation delay index corresponding to each heating equipment operation parameter data point; wherein, the edge transmission delay index calculation formula is specifically as follows: ； In the formula, For the The edge transmission operation delay index corresponding to the heating equipment operation parameter data point, is the total number of data points of heating equipment operating parameters, It is the item index parameter of the heating equipment operation parameter data point. For the The edge transmission response speed corresponding to each heating equipment operation parameter data point, is the influence weight coefficient of edge transmission reaction speed, For the The network delay corresponding to each heating equipment operating parameter data point, is the network delay decay rate index, is the impact weight coefficient of network delay, is the time variable parameter, For the Heating equipment operating parameter data points at time The network bandwidth value at For the Heating equipment operating parameter data points at time The data packet loss rate at is the cumulative impact weight coefficient of the network status, Correction factor for edge transport operational delay index; Step S155: comparing and judging the edge transmission operation delay index corresponding to each heating equipment operation parameter data point according to the preset edge delay threshold, if the edge transmission operation delay index is greater than or equal to the preset edge delay threshold, marking the corresponding heating equipment operation parameter data point as a high-delay operation parameter data point; if the edge transmission operation delay index is less than the preset edge delay threshold, marking the corresponding heating equipment operation parameter data point as a low-delay operation parameter data point; filtering and selecting the heating equipment operation parameter data points corresponding to the low-delay operation parameter data points in the real-time operation status parameter set of the heating equipment, and collecting them to obtain a low-delay operation status parameter set of the heating equipment; Step S2: performing a state parameter time-frequency transformation fluctuation analysis on the low-latency operating state parameter set of the heating equipment to obtain a time-frequency signal fluctuation frame corresponding to each heating equipment operating state parameter; performing a signal fault severity score quantitative calculation on the time-frequency signal fluctuation frame corresponding to each heating equipment operating state parameter to obtain a time-frequency signal fault severity score corresponding to each heating equipment operating state parameter; performing equipment fault classification processing on the fault category of the heating equipment based on the time-frequency signal fault severity score corresponding to each heating equipment operating state parameter to obtain a recoverable fault category of the heating equipment and an unrecoverable fault category of the heating equipment; Step S3: When it is determined that the fault category of the heating equipment is a recoverable fault category of the heating equipment, a recoverable fault maintenance control analysis is performed on the recoverable fault category of the heating equipment using the cloud platform, and a recoverable fault maintenance control measure plan for the heating equipment is generated to perform corresponding recoverable fault maintenance control processing work; Step S4: When it is determined that the fault category of the heating equipment is an irrecoverable fault category of the heating equipment, a cloud platform response is used to generate an emergency repair control request for the heating equipment to respond and inform the maintenance personnel to perform corresponding irrecoverable fault emergency repair control processing work.

2. The method for processing heating equipment fault data based on the Internet of Things according to claim 1 is characterized in that: Step S2 includes the following steps: Step S21: performing state parameter standardization processing on the low-latency operation state parameter set of the heating equipment to obtain a standardized operation state parameter set of the heating equipment; Step S22: performing time-series synchronization processing on the standardized parameter set of the operation status of the heating equipment to obtain the time-series synchronization parameter set of the operation status of the heating equipment; Step S23: performing a state parameter time-frequency transformation fluctuation analysis on the heating equipment operation state timing synchronization parameter set to obtain a time-frequency signal fluctuation frame corresponding to each heating equipment operation state parameter, wherein the time-frequency signal fluctuation frame corresponding to each heating equipment operation state parameter includes a time-frequency signal fluctuation frame corresponding to an operation temperature, an operation flow rate, and an operation pressure; Step S24: performing quantitative calculation of signal fault severity scores for the time-frequency signal fluctuation frames corresponding to the operating state parameters of each heating device, so as to obtain the time-frequency signal fault severity scores corresponding to the operating state parameters of each heating device, wherein the time-frequency signal fault severity scores corresponding to the operating state parameters of each heating device include the time-frequency signal fault severity scores corresponding to the operating temperature, the operating flow rate and the operating pressure; Step S25: Classify the fault category of the heating equipment based on the time-frequency signal fault severity scores corresponding to the operating status parameters of each heating equipment. If the time-frequency signal fault severity scores corresponding to the corresponding operating temperature, operating flow and operating pressure are all within the range of 0-5 points, the fault category of the heating equipment is classified as a recoverable fault category of the heating equipment; if the time-frequency signal fault severity scores corresponding to the corresponding operating temperature, operating flow and operating pressure are within the range of 6 points or above, the fault category of the heating equipment is classified as an unrecoverable fault category of the heating equipment.

3. The method for processing heating equipment fault data based on the Internet of Things according to claim 2 is characterized in that: Step S23 includes the following steps: Step S231: performing a time domain change analysis of the state parameter of the heating equipment operation state timing synchronization parameter set to obtain the time domain change trend data of the operation state parameters of each heating equipment in the time dimension; Step S232: Calculate the instantaneous frequency of each heating device operating state parameter at each time domain node on the time dimension of the time domain change trend data to obtain the instantaneous frequency of each heating device operating state parameter at each time domain node; Step S233: performing time-frequency signal spectrum transformation on the corresponding time-domain variation trend data based on the time-domain variation instantaneous frequency of each heating equipment operation status parameter at each time-domain node, to obtain the time-frequency variation signal spectrum corresponding to each heating equipment operation status parameter; Step S234: performing time-frequency signal fluctuation range identification analysis on the time-frequency variation signal spectrum corresponding to the operating state parameters of each heating device, and obtaining the time range of the time-frequency signal fluctuation corresponding to the operating state parameters of each heating device; Step S235: Based on the time range of the time-frequency signal fluctuations corresponding to the operating status parameters of each heating equipment, the corresponding time-frequency change signal spectrum is subjected to signal fluctuation range frame sealing processing to obtain the time-frequency signal fluctuation frames corresponding to the operating status parameters of each heating equipment, wherein the time-frequency signal fluctuation frames corresponding to the operating status parameters of each heating equipment include the time-frequency signal fluctuation frames corresponding to the operating temperature, the operating flow rate and the operating pressure.

4. The method for processing heating equipment fault data based on the Internet of Things according to claim 3 is characterized in that: Step S232 includes the following steps: Performing time domain change smoothing processing on the time domain change trend data of the operating status parameters of each heating device in the time dimension to obtain the real change trend data of the operating status parameters of each heating device in the time dimension; The real change trend data of the operating status parameters of each heating device in the time dimension are divided by time domain node marking to obtain the time domain change trend sub-data of the operating status parameters of each heating device at each time domain node; Performing statistical analysis on the change amplitude of the time domain change trend sub-data of each heating equipment operating state parameter at each time domain node to obtain the time domain change amplitude of each heating equipment operating state parameter at each time domain node; performing time domain change phase inverse processing on the corresponding time domain change trend sub-data based on the time domain change amplitude of each heating equipment operating state parameter at each time domain node to obtain the time domain signal change phase of each heating equipment operating state parameter at each time domain node; The phase difference between adjacent nodes is calculated for the time domain signal change phase of each heating equipment operation status parameter at each time domain node to obtain the time domain change phase difference between each adjacent time domain node of each heating equipment operation status parameter; Based on the time domain change phase difference of each heating equipment operating status parameter between each adjacent time domain node, the upper node instantaneous frequency of the corresponding time domain node is calculated to obtain the time domain change instantaneous frequency of each heating equipment operating status parameter at each time domain node.

5. The method for processing heating equipment fault data based on the Internet of Things according to claim 2 is characterized in that: Step S24 includes the following steps: Step S241: performing a change amplitude stability evaluation and analysis on the time-frequency signal fluctuation frames corresponding to the operating temperature and the operating flow, and obtaining a time-domain signal change amplitude stability index parameter corresponding to the operating temperature and the operating flow; Step S242: performing signal phase shift statistical analysis on the time-frequency signal fluctuation frames corresponding to the operating temperature and the operating flow, and obtaining the time-frequency signal phase shift index parameters corresponding to the operating temperature and the operating flow; Step S243: calculating the operating temperature fault severity score for the time-frequency signal fluctuation frame corresponding to the operating temperature based on the time-domain signal variation amplitude stability index parameter and the time-frequency signal phase offset index parameter corresponding to the operating temperature, so as to obtain the time-frequency signal fault severity score corresponding to the operating temperature; Step S244: Calculate the operation flow fault severity score for the time-frequency signal fluctuation frame corresponding to the operation flow based on the time-domain signal change amplitude stability index parameter and the time-frequency signal phase offset index parameter corresponding to the operation flow, so as to obtain the time-frequency signal fault severity score corresponding to the operation flow; Step S245: Calculate the operating pressure fault severity score for the time-frequency signal fluctuation frame corresponding to the operating pressure to obtain the time-frequency signal fault severity score corresponding to the operating pressure.

6. The method for processing heating equipment fault data based on the Internet of Things according to claim 5 is characterized in that: Step S245 includes the following steps: Perform signal fluctuation frequency and energy distribution analysis on the time-frequency signal fluctuation frame corresponding to the operating pressure to obtain the time-frequency signal fluctuation frequency distribution data and the time-frequency signal fluctuation energy distribution data corresponding to the operating pressure; The signal fluctuation rate is calculated for the time-frequency signal fluctuation frequency distribution data corresponding to the operating pressure to obtain the time-frequency signal fluctuation rate corresponding to the operating pressure; Based on the time-frequency signal fluctuation energy distribution data corresponding to the operating pressure, the signal energy offset of the corresponding time-frequency signal fluctuation frame is calculated to obtain the time-frequency signal fluctuation energy offset corresponding to the operating pressure; Based on the time-frequency signal fluctuation rate corresponding to the operating pressure and the time-frequency signal fluctuation energy offset, the operating pressure fault severity score of the corresponding time-frequency signal fluctuation frame is calculated to obtain the time-frequency signal fault severity score corresponding to the operating pressure.

7. A heating equipment fault data processing system based on the Internet of Things, characterized in that: Used to execute the heating equipment fault data processing method based on the Internet of Things as claimed in claim 1, the heating equipment fault data processing system based on the Internet of Things includes: The heating equipment status parameter delay filtering module is used to analyze the sensor configuration requirements of the key parts of the heating equipment and obtain the sensor configuration requirements report of the key parts of the heating equipment, wherein the key parts of the heating equipment include boilers, pipelines and valve areas; based on the sensor configuration requirements report of the key parts of the heating equipment, the optimal sensor installation positions of the temperature sensors, pressure sensors and flow sensors are designed to generate the sensor installation implementation plan for the key parts of the heating equipment; according to the sensor installation implementation plan for the key parts of the heating equipment, the temperature sensors, flow sensors and pressure sensors are installed at the key parts of the heating equipment, and the temperature sensors are used to monitor the equipment operation temperature in real time during the operation of the heating equipment to obtain the real-time operation temperature of the heating equipment; the flow sensors are used to monitor the equipment operation flow in real time during the operation of the heating equipment to obtain the real-time operation flow of the heating equipment; the pressure sensors are used to monitor the equipment operation pressure in real time during the operation of the heating equipment to obtain the real-time operation pressure of the heating equipment; the real-time operation temperature of the heating equipment, the real-time operation flow of the heating equipment and the real-time operation pressure of the heating equipment are merged to obtain the real-time operation status parameter set of the heating equipment; the real-time operation status parameter set of the heating equipment is merged by using the Internet of Things gateway technology Upload to the cloud platform; use the cloud platform to monitor the edge transmission duration of each heating equipment operation parameter data point in the real-time operation status parameter set of the heating equipment, and obtain the edge transmission response duration corresponding to each heating equipment operation parameter data point; based on the edge transmission response duration corresponding to each heating equipment operation parameter data point, perform transmission reaction speed statistics analysis on the corresponding heating equipment operation parameter data point in the real-time operation status parameter set of the heating equipment, and obtain the edge transmission reaction speed corresponding to each heating equipment operation parameter data point; perform network status evaluation analysis on each heating equipment operation parameter data point in the real-time operation status parameter set of the heating equipment, and obtain the network status evaluation parameters corresponding to each heating equipment operation parameter data point, wherein the network status evaluation parameters include network bandwidth value, network delay and data packet loss rate; based on the edge transmission reaction speed and network status evaluation parameters corresponding to each heating equipment operation parameter data point, use the edge transmission delay index calculation formula to perform edge delay quantitative calculation on the corresponding heating equipment operation parameter data point in the real-time operation status parameter set of the heating equipment, and obtain the edge transmission operation delay index corresponding to each heating equipment operation parameter data point; wherein the edge transmission delay index calculation formula is specifically as follows: ； In the formula, For the The edge transmission operation delay index corresponding to the heating equipment operation parameter data point, is the total number of data points of heating equipment operating parameters, It is the item index parameter of the heating equipment operation parameter data point. For the The edge transmission response speed corresponding to each heating equipment operation parameter data point, is the influence weight coefficient of edge transmission reaction speed, For the The network delay corresponding to each heating equipment operating parameter data point, is the network delay decay rate index, is the impact weight coefficient of network delay, is the time variable parameter, For the Heating equipment operating parameter data points at time The network bandwidth value at For the Heating equipment operating parameter data points at time The data packet loss rate at is the cumulative impact weight coefficient of the network status, is a correction coefficient for the edge transmission operation delay index; the edge transmission operation delay index corresponding to each heating equipment operation parameter data point is compared and judged according to the preset edge delay threshold; if the edge transmission operation delay index is greater than or equal to the preset edge delay threshold, the corresponding heating equipment operation parameter data point is marked as a high-latency operation parameter data point; if the edge transmission operation delay index is less than the preset edge delay threshold, the corresponding heating equipment operation parameter data point is marked as a low-latency operation parameter data point; the heating equipment operation parameter data points corresponding to the low-latency operation parameter data points in the real-time operation status parameter set of the heating equipment are filtered out and collected to obtain a low-latency operation status parameter set of the heating equipment; The heating equipment parameter signal fault classification module is used to perform a state parameter time-frequency transformation fluctuation analysis on the low-latency operating state parameter set of the heating equipment to obtain the time-frequency signal fluctuation frames corresponding to the operating state parameters of each heating equipment; perform a signal fault severity score quantitative calculation on the time-frequency signal fluctuation frames corresponding to the operating state parameters of each heating equipment to obtain the time-frequency signal fault severity score corresponding to the operating state parameters of each heating equipment; perform equipment fault classification processing on the fault categories of the heating equipment based on the time-frequency signal fault severity scores corresponding to the operating state parameters of each heating equipment, thereby obtaining the recoverable fault category of the heating equipment and the unrecoverable fault category of the heating equipment; The recoverable fault maintenance control processing module is used to determine that the fault category of the heating equipment is a recoverable fault category of the heating equipment, and then use the cloud platform to perform a recoverable fault maintenance control analysis on the recoverable fault category of the heating equipment, generate a recoverable fault maintenance control measure plan for the heating equipment, and execute the corresponding recoverable fault maintenance control processing work; The irrecoverable fault emergency repair control module is used to determine that the fault category of the heating equipment is an irrecoverable fault category of the heating equipment, and then use the cloud platform response to generate an emergency repair control request for the heating equipment to respond and inform the maintenance personnel to perform the corresponding irrecoverable fault emergency repair control processing work.

Images