Energy equipment health monitoring method and system based on big data

Abstract

The invention discloses an energy equipment health monitoring method and system based on big data, and relates to the technical field of energy equipment health monitoring, and the method comprises the steps: configuring a sensor to collect data, storing the data in a central database through an industrial Internet of Things, and carrying out the data processing; performing data analysis to identify a trend, and calculating a health index; and performing fault prediction, and implementing maintenance optimization. According to the energy equipment health monitoring method based on big data provided by the invention, the trend is analyzed and identified through data, the long-term state of the equipment can be accurately reflected, the accuracy and consistency of the data are ensured by adopting a standardized communication protocol, reliable data are provided for subsequent analysis, the LSTM combined with an Attention mechanism is adopted, and the energy equipment health monitoring method based on big data can be used for monitoring the energy equipment health. According to the method, data of different time steps are subjected to weighted processing, so that the model can pay more attention to a time period related to a current fault in historical data, the prediction accuracy is greatly improved, and better effects are achieved in the aspects of result accuracy and analysis reliability.

Description

Technical Field

[0001] The present invention relates to the technical field of energy equipment health monitoring, and in particular to an energy equipment health monitoring method and system based on big data. Background Art

[0002] With the rapid development of big data technology and the Industrial Internet of Things (IIoT), the health monitoring of energy equipment has gradually shifted towards data-driven intelligence. By deploying various sensors to collect equipment operation data and combining big data analysis technology, real-time monitoring and maintenance of energy equipment can be achieved. Traditional equipment monitoring methods mainly rely on regular manual inspections and simple threshold alarms. The introduction of big data technology can efficiently process massive multi-dimensional equipment data, extract valuable information, and provide data support for equipment fault detection, performance evaluation, and trend prediction. Using big data analysis models, abnormal conditions and potential problems in the operation of energy equipment can be identified in advance, thus providing a basis for predictive maintenance and intelligent optimization. This technological advancement has greatly improved the management efficiency and operational reliability of energy equipment, and reduced unplanned downtime and operational losses caused by equipment failures.

[0003] Although big data analysis has been initially applied in energy equipment monitoring, existing technologies still have many limitations. First, many existing systems are limited to basic data collection and simple statistical analysis, and lack in-depth exploration of complex correlations between data. Due to the complex equipment operating environment and diverse data characteristics, traditional methods are difficult to accurately capture long-term trends and potential equipment health hazards. In addition, most existing technologies rely on static thresholds or rules for fault warnings, ignoring the dynamic changes in the equipment's operating status, which can easily lead to false alarms or missed alarms, affecting the timeliness and accuracy of equipment maintenance. Secondly, in terms of fault prediction, existing methods usually use linear models or simple regression algorithms, which are difficult to deal with the nonlinear characteristics in the equipment operation data, resulting in poor prediction results. Summary of the invention

[0004] In view of the above-mentioned problems, the present invention is proposed.

[0005] Therefore, the technical problem solved by the present invention is: the existing energy equipment health monitoring methods are insufficient in analyzing the operating status of complex equipment, the fault prediction accuracy is not high, and they cannot dynamically adapt to changes in equipment status, as well as how to achieve more accurate health status assessment and fault prediction through big data analysis.

[0006] To solve the above technical problems, the present invention provides the following technical solutions: a method for monitoring the health of energy equipment based on big data, comprising configuring sensors to collect data, storing the data in a central database through the industrial Internet of Things, and processing the data; performing data analysis to identify trends and calculate health indexes; performing fault prediction and implementing maintenance optimization.

[0007] As a preferred solution of the energy equipment health monitoring method based on big data described in the present invention, wherein: the configuration of sensors to collect data and storing it in a central database through the industrial Internet of Things includes collecting operation data by installing sensors in energy equipment, and the sensors include temperature sensors, pressure sensors, and vibration sensors; the storage in a central database through the industrial Internet of Things and data processing include using a standardized communication protocol Modbus to collect equipment operation data in real time, and transmitting the data to the central database through a wired or wireless industrial Internet of Things IIoT gateway.

[0008] As a preferred solution of the energy equipment health monitoring method based on big data described in the present invention, the data processing includes using statistical methods to detect outliers, detect abnormal points in the data, mark and remove abnormal data; use interpolation to estimate missing values, and fill in the data missing due to sensor failure or communication interruption; normalize the data, re-store the processed data in the central database, and adopt a partition storage strategy to classify and manage the data according to the equipment type.

[0009] As a preferred solution of the energy equipment health monitoring method based on big data described in the present invention, the data analysis and trend identification includes calculating the trend value of each operating data of the equipment through time series analysis, reflecting the long-term status of the equipment, which is expressed as:

[0010]

[0011] Where T(t) represents the trend value at time t, X(t) is the equipment operation data collected at time t, α is the smoothing factor, which controls the degree of trend smoothing, and k is the high-order filter weight, which is used to capture acceleration changes. Indicates the acceleration change of device data.

[0012] As a preferred solution of the energy equipment health monitoring method based on big data described in the present invention, the calculation of the health index includes analyzing the trend change. When the trend change exceeds the preset change speed limit, the health index analysis is performed on the energy equipment, and the trend value is input into the nonlinear mapping model, which is expressed as:

[0013]

[0014] Among them, xi is the trend value of the equipment data obtained from different sensors after trend analysis, γ i , β i , i To control the amplitude of nonlinear mapping and the degree of regularization, f i (x i ) is the Sigmoid function, Z is the normalization factor, α i is the nonlinear weight; through the adaptive parameter γ i , β i and λ i The system maps the trend value of each sensor to the health index HI in a nonlinear way.

[0015] If the health index HI ≥ 80, the device is considered to be in a healthy state and no fault prediction is required.

[0016] As a preferred solution of the energy equipment health monitoring method based on big data described in the present invention, the fault prediction includes that when the equipment is not in a healthy state, the health system automatically determines it as a potential fault signal of the equipment, starts the LSTM prediction model, evaluates the probability of future failures, and uses the health index HI(t) as input sequence data to pass into the fault prediction model, which is expressed as:

[0017]

[0018] Among them, h t represents the hidden state at time t, HI(t) represents the health index of the device at time t, and W h and b h are weight matrix and bias respectively, which are set according to different energy devices, s t,j is the scoring function in the Attention mechanism, k is the sequence length, and v t,j For t,j The corresponding weight matrix, η·∥W h ∥ 2 It is not a regularization term.

[0019] As a preferred solution of the energy equipment health monitoring method based on big data described in the present invention, the implementation of maintenance optimization includes real-time monitoring of various sensor data and health indexes of the equipment through the industrial Internet of Things platform, and data visualization, displaying the data to operation and maintenance personnel, setting up a multi-level early warning mechanism, issuing warnings to operation and maintenance personnel, and automatically generating an analysis report on the cause of equipment failure based on the historical data of the equipment.

[0020] Another object of the present invention is to provide an energy equipment health monitoring system based on big data, which can calculate the trend value of the equipment in different time periods through time series analysis technology, capture drastic changes in equipment operation, not only identify smooth changes in equipment operation, but also respond sensitively to rapid fluctuations. By identifying potential signs of failure, the early detection capability of equipment failure is enhanced, solving the problem that current energy equipment health monitoring methods cannot accurately assess health status and predict failures.

[0021] As a preferred solution of the energy equipment health monitoring system based on big data described in the present invention, it includes: a data acquisition module, a health assessment module, and a fault prediction module; the data acquisition module is used to configure sensors to collect data, store it in a central database through the industrial Internet of Things, and perform data processing; the health assessment module is used to perform data analysis to identify trends and calculate health indexes; the fault prediction module is used to perform fault prediction and implement maintenance optimization.

[0022] A computer device includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement a step of an energy equipment health monitoring method based on big data.

[0023] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of a method for health monitoring of energy equipment based on big data.

[0024] Beneficial effects of the present invention: The energy equipment health monitoring method based on big data provided by the present invention can accurately reflect the long-term status of the equipment by identifying trends through data analysis, and adopts standardized communication protocols to ensure the accuracy and consistency of the data, providing reliable data for subsequent analysis. By adopting LSTM combined with the Attention mechanism and weighted processing of data at different time steps, the model can pay more attention to the time period in the historical data that is related to the current fault, thereby greatly improving the accuracy of the prediction. The present invention achieves better results in terms of result accuracy and analysis reliability. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0026] Figure 1 An overall flow chart of a big data-based energy equipment health monitoring method provided for the first embodiment of the present invention.

[0027] Figure 2 An overall flow chart of an energy equipment health monitoring system based on big data provided for the third embodiment of the present invention. DETAILED DESCRIPTION

[0028] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0029] Example 1, reference Figure 1 , as an embodiment of the present invention, provides an energy equipment health monitoring method based on big data, comprising:

[0030] S1: Configure sensors to collect data, store it in a central database through the Industrial Internet of Things, and process the data.

[0031] Furthermore, configuring sensors to collect data and storing it in a central database through the Industrial Internet of Things includes collecting operating data by installing sensors in energy equipment. The sensors include temperature sensors, pressure sensors, and vibration sensors.

[0032] The data is stored in a central database through the Industrial Internet of Things, and data processing includes using the standardized communication protocol Modbus to collect equipment operation data in real time, and transmitting the data to the central database through a wired or wireless Industrial Internet of Things IIoT gateway.

[0033] When collecting data, the sensor needs to set a reasonable collection frequency. Usually, high-frequency collection is set for key components, such as high-speed equipment or high-load equipment, while the collection frequency can be reduced for relatively stable components. The data of all sensors are synchronized through timestamps to ensure that the data in the central database has a unified time base to support subsequent analysis.

[0034] The data is transferred to a central database, which can be a local high-performance server cluster or a cloud database. In order to improve scalability and fault tolerance, a distributed storage solution is used, such as a NoSQL database or a cloud data warehouse Amazon S.

[0035] In order to ensure the real-time and integrity of data, a redundant data collection and transmission mechanism is adopted. When the main system fails, the backup system automatically takes over to ensure that data will not be lost.

[0036] It should be noted that data processing includes using statistical methods to detect outliers, detect abnormal points in the data, and mark and remove abnormal data.

[0037] Interpolation method is used to estimate missing values ​​and fill in the missing data caused by sensor failure or communication interruption.

[0038] The data is normalized and stored back in the central database. A partition storage strategy is adopted to classify and manage the data according to the device type.

[0039] S2: Perform data analysis to identify trends and calculate health index.

[0040] Furthermore, data analysis to identify trends includes calculating the trend values ​​of various equipment operation data through time series analysis, reflecting the long-term status of the equipment, expressed as:

[0041]

[0042] Where T(t) represents the trend value at time t, X(t) is the equipment operation data collected at time t, α is the smoothing factor, which controls the degree of trend smoothing, and k is the high-order filter weight, which is used to capture acceleration changes. Represents the acceleration change of equipment data. This trend analysis can not only capture smooth changes in equipment operation, but also respond sensitively to rapid fluctuations and identify potential signs of failure. High-order derivative terms enhance sensitivity to drastic changes and can help detect the possibility of equipment failure in advance.

[0043] It should be noted that the calculation of the health index includes analyzing trend changes. When the trend change exceeds the preset change speed limit, the health index analysis of the energy equipment is performed, and the trend value is input into the nonlinear mapping model, which is expressed as:

[0044]

[0045] Among them, x i is the trend value of the equipment data obtained from different sensors after trend analysis, γ i , β i , i To control the amplitude of nonlinear mapping and the degree of regularization, f i (x i ) is the Sigmoid function, Z is the normalization factor, α i is a nonlinear weight. Through the adaptive parameter γ i , β i and λ i Under the control of , the system maps the trend value of each sensor to the health index HI in a nonlinear manner.

[0046] If the health index HI ≥ 80, the device is considered to be in a healthy state and no fault prediction is required.

[0047] S3: Perform fault prediction and implement maintenance optimization.

[0048] Furthermore, fault prediction includes when the device is not in a healthy state, the health system automatically determines it as a potential fault signal of the device, starts the LSTM prediction model, evaluates the probability of future failure, and uses the health index HI(t) as input sequence data to pass it into the fault prediction model, which is expressed as:

[0049]

[0050] Among them, h t represents the hidden state at time t, HI(t) represents the health index of the device at time t, and W h and b h are weight matrix and bias respectively, which are set according to different energy devices, s t,j is the scoring function in the Attention mechanism, k is the sequence length, and v t,j For t,j The corresponding weight matrix, η·∥W h ∥ 2 It is not a regularization term. Compared with the traditional LSTM model, the present invention adds the Attention mechanism, so that the model can focus on the time steps in the historical data that are most relevant to the fault. The application of the Attention mechanism in time series analysis greatly improves the accuracy of fault prediction, especially when processing long sequence data. By automatically assigning attention weights, the system can more effectively mine the key time period information that causes equipment failure. This is an innovation that is difficult to achieve in the prior art. Traditional prediction models are usually unable to dynamically adapt to changes in equipment status, nor can they accurately locate the potential time of fault occurrence.

[0051] In summary, the present invention achieves accurate and real-time energy equipment fault prediction through dynamic health monitoring and fault prediction based on LSTM and Attention mechanism. This method can not only improve the operating efficiency of equipment and reduce unplanned downtime, but also cope with the complex operating environment of different equipment through the adaptive characteristics of deep learning models, which is significantly better than the existing technology.

[0052] It should be noted that the implementation of maintenance optimization includes real-time monitoring of various sensor data and health indexes of equipment through the industrial Internet of Things platform, data visualization, displaying the data to operation and maintenance personnel, setting up a multi-level early warning mechanism, issuing warnings to operation and maintenance personnel, and automatically generating analysis reports on the causes of equipment failures based on the historical data of the equipment.

[0053] In order to facilitate operation and maintenance personnel to monitor equipment, the industrial Internet of Things platform provides a graphical visualization interface to convert real-time data into readable charts, dashboards or other interactive visualization tools. The specific design includes:

[0054] Trend analysis charts: By displaying the historical and real-time trends of various sensor data through time series charts, operation and maintenance personnel can easily identify the changing patterns during equipment operation. This includes historical curves of key data such as equipment temperature, vibration frequency, pressure fluctuations, etc., so as to understand the long-term operation status of the equipment.

[0055] Health Index Dashboard: The health index can be displayed in the form of a dashboard. The health status is divided into different color ranges, such as green for healthy status, yellow for maintenance required, and red for predicted failure. The intuitive display method can help operation and maintenance personnel quickly understand the current operating status of the equipment.

[0056] Abnormal data annotation: When data fluctuates abnormally, the system can mark the abnormal points in the form of charts to remind operation and maintenance personnel to focus on monitoring or further analysis. This visual abnormal annotation can better help operation and maintenance personnel find potential problems and reduce the complexity of data analysis.

[0057] When a device triggers an early warning, the system will not only issue an alarm, but also automatically generate a fault cause analysis report for the device. The report is based on in-depth analysis of historical data, and automatically mines the cause of the device failure through big data analysis and machine learning models such as decision trees. The specific process includes:

[0058] The system will first extract the historical operation data of the equipment, compare it with the current abnormal data, and analyze whether there is a similar operation mode. It will identify whether the equipment has experienced similar problems before and provide corresponding treatment experience.

[0059] The system can identify possible failure modes of equipment, such as whether an abnormal temperature rise is associated with a sharp fluctuation in vibration frequency, thereby determining whether there is a problem such as mechanical component wear or motor overload.

[0060] While generating the fault analysis report, the system will automatically generate maintenance recommendations based on historical data and current equipment status. This includes when to replace parts, whether immediate downtime is required, and future maintenance cycle adjustments. This feature can help operation and maintenance personnel develop more targeted maintenance plans to avoid sudden equipment failures.

[0061] Example 2 An embodiment of the present invention provides an energy equipment health monitoring method based on big data. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0062] First, in order to verify the effectiveness and innovation of the energy equipment health monitoring method based on big data, this experiment was conducted on an industrial wind turbine. The operating status of the generator was monitored in real time through the Industrial Internet of Things (IIoT) platform, and the data collection included key parameters such as the temperature, pressure, and vibration of the equipment. The collection frequency of each sensor was set according to the importance of the component, and all data was transmitted to the central database through the IIoT gateway using the Modbus communication protocol to ensure the real-time and accuracy of the data. The specific experimental data are shown in Table 1.

[0063] Table 1 Experimental data comparison table

[0064]

[0065] First, the health index decreases with the gradual increase of temperature, pressure and vibration frequency. From the table, it can be found that the health index gradually decreases from 85 to 65, indicating that the operation status of the equipment is gradually deteriorating. Compared with the prior art that relies on fixed time period inspection, the present invention can dynamically adjust the health status through real-time data analysis and timely reflect the health changes of the equipment.

[0066] The fault prediction probability in the table also gradually increases, which shows how the introduction of LSTM and Attention mechanism improves the accuracy of prediction. As the equipment operating parameters deteriorate, the system can dynamically identify the key historical time steps related to the fault (such as the sudden acceleration of the vibration frequency at 10:45 and 11:00), and issue an emergency warning when the health index drops to 70, predicting the probability of possible future failures. Traditional fault prediction models are usually unable to flexibly respond to these nonlinear changes, and the present invention effectively overcomes this problem by combining time series analysis with Attention mechanism, so that the system can adaptively adjust the parameters of the prediction model to cope with the complex operating environment of the equipment.

[0067] In addition, maintenance recommendations gradually evolve from "normal" to "maintenance required" and "urgent inspection". By combining with the fault prediction module, the system can not only detect potential problems of the equipment, but also provide specific maintenance recommendations to operation and maintenance personnel. This maintenance optimization strategy based on big data analysis can greatly reduce the probability of sudden equipment failures and unplanned downtime, significantly improving the operating efficiency of the equipment.

[0068] Example 3, reference Figure 2 , as an embodiment of the present invention, provides an energy equipment health monitoring system based on big data, including a data acquisition module, a health assessment module, and a fault prediction module.

[0069] The data acquisition module is used to configure sensors to collect data, store it in a central database through the industrial Internet of Things, and process the data. The health assessment module is used to analyze data to identify trends and calculate health indexes. The fault prediction module is used to predict faults and implement maintenance optimization.

[0070] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0071] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0072] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering, or processing in another suitable manner as necessary, and then stored in a computer memory.

[0073] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc. It should be noted that the above embodiments are only used to illustrate the technical solution of the present invention and are not limited. Although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention, which should be included in the scope of the claims of the present invention.

[0074] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for monitoring the health of energy equipment based on big data, characterized in that: include: Configure sensors to collect data, store it in a central database through the Industrial Internet of Things, and process the data; Conduct data analysis to identify trends and calculate health indices; Predict failures and optimize maintenance.

2. The method for monitoring the health of energy equipment based on big data according to claim 1, characterized in that: The configuring of sensors to collect data and storing the data in a central database through the industrial Internet of Things includes collecting operating data by installing sensors in energy equipment, the sensors including temperature sensors, pressure sensors, and vibration sensors; The storage in a central database through the Industrial Internet of Things and the data processing include using the standardized communication protocol Modbus to collect equipment operation data in real time, and transmitting the data to the central database through a wired or wireless Industrial Internet of Things IIoT gateway.

3. The method for monitoring the health of energy equipment based on big data according to claim 2, characterized in that: The data processing includes using statistical methods to detect outliers, detect abnormal points in the data, and mark and remove abnormal data; Interpolation is used to estimate missing values ​​and fill in missing data caused by sensor failure or communication interruption; The data is normalized and stored back in the central database. A partition storage strategy is adopted to classify and manage the data according to the device type.

4. The method for monitoring the health of energy equipment based on big data according to claim 3, characterized in that: The data analysis and trend identification includes calculating the trend value of each operation data of the equipment through time series analysis, reflecting the long-term status of the equipment, which is expressed as: Where T(t) represents the trend value at time t, X(t) is the equipment operation data collected at time t, α is the smoothing factor, which controls the degree of trend smoothing, and k is the high-order filter weight, which is used to capture acceleration changes. Indicates the acceleration change of device data.

5. The method for monitoring the health of energy equipment based on big data according to claim 4, characterized in that: The calculation of the health index includes analyzing the trend change. When the trend change exceeds the preset change speed limit, the health index analysis is performed on the energy equipment, and the trend value is input into the nonlinear mapping model, which is expressed as: Among them, x i is the trend value of the equipment data obtained from different sensors after trend analysis, γ i , β i , i To control the amplitude of nonlinear mapping and the degree of regularization, f i (x i ) is the Sigmoid function, Z is the normalization factor, α i is the nonlinear weight; through the adaptive parameter γ i , β i and λ i The system maps the trend value of each sensor to the health index HI in a nonlinear way. If the health index HI ≥ 80, the device is considered to be in a healthy state and no fault prediction is required.

6. The method for monitoring the health of energy equipment based on big data according to claim 5, characterized in that: The fault prediction includes that when the device is not in a healthy state, the health system automatically determines it as a potential fault signal of the device, starts the LSTM prediction model, evaluates the probability of future faults, and uses the health index HI(t) as input sequence data to pass into the fault prediction model, which is expressed as: Among them, h t represents the hidden state at time t, HI(t) represents the health index of the device at time t, and W h and b h are weight matrix and bias respectively, which are set according to different energy devices, s t,j is the scoring function in the Attention mechanism, k is the sequence length, and v t,j For t,j The corresponding weight matrix, η·∥W h ∥ 2 It is not a regularization term.

7. The method for monitoring the health of energy equipment based on big data according to claim 6, characterized in that: The implementation of maintenance optimization includes real-time monitoring of various sensor data and health indexes of equipment through the industrial Internet of Things platform, and data visualization, displaying the data to operation and maintenance personnel, setting up a multi-level early warning mechanism to issue warnings to operation and maintenance personnel, and automatically generating an analysis report on the cause of equipment failure based on the historical data of the equipment.

8. A system using the energy equipment health monitoring method based on big data as claimed in any one of claims 1 to 7, characterized in that: Including data acquisition module, health assessment module, and fault prediction module; The data acquisition module is used to configure sensors to collect data, store it in a central database through the industrial Internet of Things, and perform data processing; The health assessment module is used to perform data analysis to identify trends and calculate health indexes; The fault prediction module is used to perform fault prediction and implement maintenance optimization.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the energy equipment health monitoring method based on big data described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the energy equipment health monitoring method based on big data described in any one of claims 1 to 7 are implemented.

Images