External communication method of power equipment in new energy field based on Wifi

By deploying data acquisition units and wireless transmission communication networks in new energy power equipment, combined with machine learning methods, failure prediction and remote diagnosis of new energy power equipment are realized, problems of equipment data interaction complexity and monitoring difficulty are solved, and the problem of equipment data interaction is improved Monitoring accuracy and safety of power equipment.

CN118945612APending Publication Date: 2024-11-12DATANG TONGLIAO HUOLINHE NEW ENERGY
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411193436.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-28
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

The data interaction volume of new energy power equipment is large and the parameter settings are complex, which makes external processing terminals unable to accurately and timely data collection and monitoring, increasing maintenance costs and security management difficulties.

Method used

Adopt external communication methods for power equipment in the new energy field based on Wifi, including data acquisition unit, communication unit, platform management unit and fault alarm unit, collect data in real time through intelligent sensors, and use wireless transmission communication network WSN and machine learning methods to perform data Preprocessing, fault prediction and remote diagnosis to realize remote control and automated adjustment.

Benefits of technology

Improve data acquisition efficiency and data quality, realize fault prediction and remote diagnosis of new energy power equipment, reduce safety risks and losses, improve the accuracy and reliability of power equipment monitoring, and support intelligent monitoring of power equipment and Safety management.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118945612A_ABST
    Figure CN118945612A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of new energy power equipment, in particular to a Wifi-based external communication method for power equipment in the field of new energy, which comprises a data acquisition unit, a communication unit, a platform management unit, an intelligent control unit and a fault alarm unit. According to the invention, data collection is carried out on the power equipment, the data collected by the data collection unit is transmitted to the platform end and the cloud end by using the wireless transmission communication network WSN, and the wireless transmission communication network WSN has the advantages of high collection efficiency, stable data quality and the like, so that the remote fault diagnosis module can carry out fault diagnosis on the power equipment by using a machine learning method. By means of data preprocessing, data segmentation, long short-term memory network LSTM time sequence analysis, softmax, fault diagnosis result output and early warning and by adopting a time sequence analysis method based on LSTM, more effective equipment operation abnormal state diagnosis is achieved, equipment faults and accidents are effectively prevented, and the accuracy of power equipment monitoring is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of new energy power equipment, and in particular to an external communication method of power equipment in the new energy field based on Wifi. Background Art

[0002] With the world's increasing attention to sustainable development and environmental protection, new energy has become a development trend. Its advantages include low carbon, pollution-free, and sustainability. The development of new energy requires the support of various power equipment, including solar power generation equipment, wind power generation equipment, hydropower generation equipment, energy storage equipment, and charging equipment.

[0003] The Chinese patent CN202455541U discloses an external communication module of power equipment in the new energy field based on Wifi, which has a Wifi communication module inside the power equipment.

[0004] However, there are more and more power equipment in the field of new energy. The amount of data interaction is large and the parameter settings are complex. It is impossible to accurately and quickly interconnect these power equipment in the field of new energy with external processing terminals, resulting in the external processing terminals being unable to accurately and timely collect and monitor data on the new energy power equipment, resulting in high maintenance costs for the new energy power equipment and greater difficulty in safety management.

[0005] In summary, developing a Wifi-based external communication method for power equipment in the new energy field is still a key issue that needs to be urgently solved in the field of new energy power equipment technology. Summary of the invention

[0006] In view of the problems existing in the prior art, the purpose of the present invention is to provide an external communication method for power equipment in the new energy field based on Wifi.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] A Wifi-based external communication method for electric power equipment in the new energy field, comprising a data acquisition unit, a communication unit, a platform management unit, an intelligent control unit and a fault alarm unit;

[0009] The data acquisition unit collects temperature, humidity, current, partial discharge information, equipment status and environmental parameter data in real time by deploying various intelligent sensors on new energy power equipment;

[0010] The communication unit is used to transmit the data collected by the data acquisition unit to the platform end and the cloud through the wireless transmission communication network WSN;

[0011] The platform management unit can perform data preprocessing, data fusion, data cleaning and data analysis on the transmitted data, and then use machine learning methods to process and analyze the data, realize fault prediction and remote diagnosis of new energy power equipment, and transmit the diagnostic information to the intelligent control unit and the fault alarm unit through the communication unit. At the same time, the platform operation and maintenance personnel can view the real-time data of the new energy power equipment, understand the equipment operation status and discover potential problems through the platform-side monitoring system;

[0012] The intelligent control unit is used to realize remote control and automatic regulation of new energy power equipment, automatically adjust the operating state of the new energy power equipment according to the real-time load conditions, and optimize the power output;

[0013] The fault alarm unit is used to set a threshold through the system. When the platform management unit diagnoses that the parameters of the new energy power equipment are abnormal, an alarm message is immediately sent to the platform end through the communication unit.

[0014] The present invention is further configured as follows: the data acquisition unit includes a temperature and humidity monitoring module, a current monitoring module and a sensor module;

[0015] The temperature and humidity monitoring module uses temperature sensors and humidity sensors to intelligently monitor and control the temperature and humidity of the surrounding environment of the new energy power equipment;

[0016] The current monitoring module collects load status information of new energy power equipment through a current transformer;

[0017] The sensor module collects partial discharge information of new energy power equipment through multiple partial discharge detection sensors.

[0018] The present invention is further configured as follows: the platform management unit includes a data preprocessing module, a data processing module, a fault remote diagnosis module, and a data storage module;

[0019] The data preprocessing module eliminates the frequency bands of no concern in the original sampled data signal transmitted by the communication unit through a reasonable band-stop filter, defines the frequency monitoring range, and performs high-order noise reduction;

[0020] The data processing module is used to perform data fusion, data cleaning and data analysis on the pre-processed data to form various sensor data. Various sensor data, basic information of power equipment and historical data are combined to form equipment rating data for power equipment fault judgment.

[0021] The present invention is further configured as follows: the fault remote diagnosis module utilizes a machine learning method, and utilizes data preprocessing, data segmentation, long short-term memory network LSTM timing analysis, softmax, and outputs fault diagnosis results and warnings to process and analyze the equipment rating data, thereby realizing fault prediction and remote diagnosis of new energy power equipment, and transmitting the diagnostic information to the intelligent control unit and the fault alarm unit through a communication unit; the data storage module can integrate and store the data collected by the data acquisition unit, the data preprocessing module, the data processing module, and the fault remote diagnosis module.

[0022] The present invention is further configured as follows: the platform management unit further includes a user management module, a data query module, a remote monitoring module, a device management module and an alarm perception module;

[0023] The user management module is used to manage the user rights of the platform system and provide users with login, registration, and password modification operation permissions;

[0024] The data query module uses data charts to present the data collected by the perception tags to the user in an intuitive and vivid manner, and provides a unified query of historical data, which is convenient for users to view and call.

[0025] The present invention is further configured as follows: the remote monitoring module is used by platform operation and maintenance personnel to view real-time data of new energy power equipment, understand the equipment operation status and discover potential problems through the platform-side monitoring system; the equipment management module is used to record and manage the ledger, maintenance and scrapping information of new energy power equipment; the alarm perception module is used to monitor and perceive the temperature, humidity and posture parameters of new energy power equipment.

[0026] The present invention is further configured as follows: the fault remote diagnosis module uses a machine learning method to process and analyze the equipment rating data to achieve fault prediction and remote diagnosis of new energy power equipment, including the following steps:

[0027] S1. First, preprocess the data to balance the impact of different dimensions and units between data. Use Z-score to standardize the data and convert its range to between 0 and 1:

[0028]

[0029] Where: a is a dimension in the original sensor data, b is the mean, and c is the standard value;

[0030] S2. Build a machine learning model based on historical information, use LSTM network to diagnose power equipment faults, and use the LSTM network's ability to handle long-term dependencies in remote diagnosis of power equipment. The forget vector d output by the forget gatet It can be expressed as:

[0031] d t =c(E d ·[f t-1 ·a t ]+g d -1);

[0032] Where: E d Represents the weight of the forget gate, g d is the bias, and c is the sigmoid activation function, which can compress the output to between 0 and 1, indicating how much information each cell state unit should forget;

[0033] S3, input gate update decision: The input gate is responsible for deciding how new information is updated to the cell state. It calculates an activation vector i t and a candidate cell state h t , the formula is as follows:

[0034]

[0035] Where: i t indicates which new information should be incorporated into the cell state at the current moment, and h t Specific values ​​for this new information are provided;

[0036] S4: Update the cell state. Based on the decision of the forget gate and the input gate, the cell state will be updated to the new state H. t , the process is expressed as:

[0037] H t =d t ×H t-1 +i t ×h t ;

[0038] Where: The new cell state H t Integrate important information from the past and relevant information from the present, i.e., information selected by the forget gate and injected through the input gate;

[0039] S5, the output gate forms the final prediction result of the power transmission and transformation equipment. After the cell state is updated, the output gate will determine the hidden state J at the next time point t , the hidden state contains the current input information and is also the basis for future predictions.

[0040] The present invention is further configured as follows: in step S5, the hidden state J t The expression is as follows:

[0041]

[0042] Where: k t Represents the output vector, which determines the final output J through the activation of the tanh function and its own adjustment t The content of , that is, the hidden state containing the current input information.

[0043] Beneficial Effects

[0044] Compared with the known public technology, the technical solution provided by the present invention has the following advantages:

[0045] Beneficial effects:

[0046] (1) In the present invention, the wireless transmission communication network WSN is used to transmit the data collected by the data acquisition unit to the platform and the cloud. The wireless transmission communication network WSN senses the equipment operation status in real time through wireless sensor nodes, and can wirelessly transmit the data to the monitoring center. Compared with the traditional manual data collection method, the wireless transmission communication network WSN has the advantages of high collection efficiency and stable data quality. The platform management unit uses the collected data to perform accurate remote fault diagnosis, realize fault prediction and remote diagnosis of new energy power equipment, and facilitate platform operation and maintenance personnel to view the real-time data of new energy power equipment, understand the equipment operation status and discover potential problems through the platform monitoring system. By collecting data on power equipment and monitoring the operation status of power equipment in real time, the occurrence of equipment failures and accidents can be effectively prevented, the accuracy and reliability of power equipment monitoring can be improved, safety risks and losses can be reduced, and intelligent monitoring and safety management of the operation status of power equipment can be realized, providing important technical support for ensuring reliable power supply of power equipment.

[0047] (2) In the present invention, the fault remote diagnosis module uses machine learning methods, and utilizes data preprocessing, data segmentation, long short-term memory network LSTM time series analysis, softmax, and output of fault diagnosis results and warnings to process and analyze the equipment rating data, thereby realizing fault prediction and remote diagnosis of new energy power equipment. The LSTM-based time series analysis method can effectively extract long-term dependent information from the data and realize more effective diagnosis of abnormal equipment operation status. By integrating the algorithm into the system, the status monitoring and diagnosis of power equipment can be effectively realized. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 A system diagram of an external communication method for power equipment in the new energy field based on Wifi;

[0049] Figure 2 The present invention is a flow chart of a fault remote diagnosis module of an external communication method of electric power equipment in the new energy field based on Wifi.

[0050] In the figure: 1. Data acquisition unit; 2. Communication unit; 3. Platform management unit; 4. Intelligent control unit; 5. Fault alarm unit; 11. Temperature and humidity monitoring module; 12. Current monitoring module; 13. Sensor module; 31. Data preprocessing module; 32. Data processing module; 33. Fault remote diagnosis module; 34. Data storage module; 35. User management module; 36. Data query module; 37. Remote monitoring module; 38. Equipment management module; 39. Alarm perception module. DETAILED DESCRIPTION

[0051] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below. 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 ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0052] The present invention will be further described below in conjunction with the embodiments.

[0053] Example 1: Please refer to Figure 1 and Figure 2 As shown, a Wifi-based external communication method for power equipment in the field of new energy includes a data acquisition unit 1, a communication unit 2, a platform management unit 3, an intelligent control unit 4 and a fault alarm unit 5;

[0054] The data acquisition unit 1 collects temperature, humidity, current, partial discharge information, equipment status and environmental parameter data in real time by deploying various intelligent sensors on the new energy power equipment. The data acquisition unit 1 includes a temperature and humidity monitoring module 11, a current monitoring module 12 and a sensor module 13; the temperature and humidity monitoring module 11 uses temperature sensors and humidity sensors to intelligently monitor and control the temperature and humidity of the surrounding environment of the new energy power equipment; the current monitoring module 12 collects the load status information of the new energy power equipment through a current transformer; the sensor module 13 collects the partial discharge information of the new energy power equipment through multiple partial discharge detection sensors; the communication unit 2 is used to transmit the data collected by the data acquisition unit 1 to the platform end and the cloud through the wireless transmission communication network WSN;

[0055] The platform management unit 3 can perform data preprocessing, data fusion, data cleaning and data analysis on the transmitted data, and then use machine learning methods to process and analyze the data to realize fault prediction and remote diagnosis of new energy power equipment, and transmit the diagnostic information to the intelligent control unit 4 and the fault alarm unit 5 through the communication unit 2. At the same time, the platform operation and maintenance personnel can view the real-time data of the new energy power equipment through the platform-side monitoring system, understand the equipment operation status and find potential problems. The platform management unit 3 includes a data preprocessing module 31, a data processing module 32, a fault remote diagnosis module 33, and a data storage module 34; the data preprocessing module 31 eliminates the frequency bands of no concern in the original sampling data signal transmitted by the communication unit 2 through a reasonable band-stop filter, defines the frequency monitoring range, and performs high-order noise reduction; the data processing module 32 is used to perform data fusion, data cleaning and data analysis on the preprocessed data to form various sensor data, and the various sensor data, basic information of the power equipment and historical data are combined to form equipment rating data for power equipment fault judgment. , the data storage module 34 can integrate and store the data collected by the data acquisition unit 1, the data preprocessing module 31, the data processing module 32, and the fault remote diagnosis module 33. The platform management unit 3 also includes a user management module 35, a data query module 36, a remote monitoring module 37, an equipment management module 38 and an alarm perception module 39; the user management module 35 is used to manage the user rights of the platform system and provide users with login, registration, and password modification operation permissions; the data query module 36 uses data charts to intuitively and vividly present the data collected by the perception tag to the user, as well as a unified query of historical data, which is convenient for users to view and call. The remote monitoring module 37 is used for platform operation and maintenance personnel to view the real-time data of new energy power equipment through the platform-side monitoring system, understand the equipment operation status and discover potential problems. The equipment management module 38 is used to record and manage the ledger, maintenance, and scrapping information of new energy power equipment. The alarm perception module 39 is used to monitor and perceive the temperature, humidity, and posture parameters of new energy power equipment;

[0056] The intelligent control unit 4 is used to realize remote control and automatic regulation of new energy power equipment, automatically adjust the operating status of the new energy power equipment according to the real-time load conditions, and optimize the power output; the fault alarm unit 5 is used to set the threshold through the system. When the platform management unit 3 diagnoses that the parameters of the new energy power equipment are abnormal, it immediately sends an alarm message to the platform end through the communication unit 2.

[0057] In this embodiment, by collecting data on power equipment and monitoring the operating status of power equipment in real time, equipment failures and accidents can be effectively prevented, the accuracy and reliability of power equipment monitoring can be improved, safety risks and losses can be reduced, and intelligent monitoring and safety management of the operating status of power equipment can be realized, providing important technical support for ensuring reliable power supply of power equipment.

[0058] Example 2: Please refer to Figure 1 and Figure 2 As shown, a method for external communication of power equipment in the field of new energy based on Wifi, the remote fault diagnosis module 33 uses machine learning methods, and uses data preprocessing, data segmentation, long short-term memory network LSTM timing analysis, softmax, output fault diagnosis results and warning methods to process and analyze equipment rating data, realize fault prediction and remote diagnosis of new energy power equipment, and transmit the diagnosis information to the intelligent control unit 4 and the fault alarm unit 5 through the communication unit 2;

[0059] The fault remote diagnosis module 33 uses machine learning methods to process and analyze the equipment rating data to achieve fault prediction and remote diagnosis of new energy power equipment, including the following steps:

[0060] S1. First, preprocess the data to balance the impact of different dimensions and units between data. Use Z-score to standardize the data and convert its range to between 0 and 1:

[0061]

[0062] Where: a is a dimension in the original sensor data, b is the mean, and c is the standard value;

[0063] S2. Build a machine learning model based on historical information, use LSTM network to diagnose power equipment faults, and use the LSTM network's ability to handle long-term dependencies in remote diagnosis of power equipment. The forget vector d output by the forget gate t It can be expressed as:

[0064] d t =c(E d ·[f t-1 ·a t ]+g d -1);

[0065] Where: E d Represents the weight of the forget gate, g d is the bias, and c is the sigmoid activation function, which can compress the output to between 0 and 1, indicating how much information each cell state unit should forget;

[0066] S3, input gate update decision: The input gate is responsible for deciding how new information is updated to the cell state. It calculates an activation vector i t and a candidate cell state h t , the formula is as follows:

[0067]

[0068] Where: i t indicates which new information should be incorporated into the cell state at the current moment, and h t Specific values ​​for this new information are provided;

[0069] S4: Update the cell state. Based on the decision of the forget gate and the input gate, the cell state will be updated to the new state H. t , the process is expressed as:

[0070] H t =d t ×H t-1 +i t ×h t ;

[0071] Where: The new cell state H t Integrate important information from the past and relevant information from the present, i.e., information selected by the forget gate and injected through the input gate;

[0072] S5, the output gate forms the final prediction result of the power transmission and transformation equipment. After the cell state is updated, the output gate will determine the hidden state J at the next time point t The hidden state contains the current input information and is also the basis for future predictions. t The expression is as follows:

[0073]

[0074] Where: k t Represents the output vector, which determines the final output J through the activation of the tanh function and its own adjustment t The content of , that is, the hidden state containing the current input information.

[0075] In this embodiment, by adopting the LSTM-based time series analysis method, the long-term dependency information in the data can be effectively extracted to achieve more effective diagnosis of abnormal equipment operation status. By integrating the algorithm into the system, the status monitoring and diagnosis of power equipment can be effectively realized.

[0076] In the present invention, the external communication method of the power equipment in the field of new energy based on Wifi, the data acquisition unit 1 collects temperature, humidity, current, partial discharge information, equipment status and environmental parameter data in real time through various intelligent sensors, and then uses the wireless transmission communication network WSN to transmit the data collected by the data acquisition unit 1 to the platform end and the cloud. The wireless transmission communication network WSN senses the equipment operation status in real time through wireless sensor nodes, and can wirelessly transmit the data to the monitoring center. Compared with the traditional manual data collection method, the wireless transmission communication network WSN has the advantages of high collection efficiency and stable data quality, so that the platform management unit 3 performs data preprocessing, data fusion, data cleaning and data analysis on the transmitted data, and uses the collected data to perform accurate remote fault diagnosis, realizing new energy Fault prediction and remote diagnosis of power equipment, and transmission of diagnostic information to the intelligent control unit 4 and the fault alarm unit 5 through the communication unit 2, so that the platform operation and maintenance personnel can view the real-time data of the new energy power equipment through the platform-side monitoring system, understand the equipment operation status and find potential problems, and then remotely control and automatically adjust the new energy power equipment through the intelligent control unit 4, automatically adjust the operation status of the new energy power equipment according to the real-time load conditions, and optimize the power output; data collection of power equipment and real-time monitoring of the operation status of power equipment can effectively prevent equipment failures and accidents, improve the accuracy and reliability of power equipment monitoring, reduce safety risks and losses, and realize intelligent monitoring and safety management of the operation status of power equipment, which provides important technical support for ensuring the reliable power supply of power equipment;

[0077] At the same time, the fault remote diagnosis module 33 uses machine learning methods, and uses data preprocessing, data segmentation, long short-term memory network LSTM timing analysis, softmax, and output fault diagnosis results and warnings to process and analyze the equipment rating data, realize fault prediction and remote diagnosis of new energy power equipment, and transmit the diagnostic information to the intelligent control unit 4 and the fault alarm unit 5 through the communication unit 2; the LSTM-based time series analysis method is used to effectively extract long-term dependent information in the data, and realize more effective diagnosis of abnormal equipment operation status. By integrating the algorithm into the system, the status monitoring and diagnosis of power equipment can be effectively realized.

[0078] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements will not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for external communication of power equipment in the field of new energy based on Wifi, It is characterized in that It comprises a data acquisition unit (1), a communication unit (2), a platform management unit (3), an intelligent control unit (4) and a fault alarm unit (5); The data acquisition unit (1) collects temperature, humidity, current, partial discharge information, equipment status and environmental parameter data in real time by deploying various intelligent sensors on the new energy power equipment; The communication unit (2) is used to transmit the data collected by the data collection unit (1) to the platform end and the cloud via a wireless transmission communication network WSN; The platform management unit (3) can perform data preprocessing, data fusion, data cleaning and data analysis on the transmitted data, and then use machine learning methods to process and analyze the data, so as to realize fault prediction and remote diagnosis of the new energy power equipment, and transmit the diagnosis information to the intelligent control unit (4) and the fault alarm unit (5) through the communication unit (2). At the same time, the platform operation and maintenance personnel can view the real-time data of the new energy power equipment, understand the equipment operation status and discover potential problems through the platform-side monitoring system; The intelligent control unit (4) is used to realize remote control and automatic regulation of new energy power equipment, automatically adjust the operating state of the new energy power equipment according to real-time load conditions, and optimize power output; The fault alarm unit (5) is used to set a threshold value through the system, and when the platform management unit (3) diagnoses that the parameters of the new energy power equipment are abnormal, an alarm message is immediately sent to the platform end through the communication unit (2).

2. According to claim 1, the external communication method of power equipment in the field of new energy based on Wifi, It is characterized in that The data acquisition unit (1) comprises a temperature and humidity monitoring module (11), a current monitoring module (12) and a sensor module (13); The temperature and humidity monitoring module (11) performs intelligent monitoring and control of the temperature and humidity of the environment surrounding the new energy power equipment through a temperature sensor and a humidity sensor; The current monitoring module (12) collects load status information of the new energy power equipment through a current transformer; The sensor module (13) collects partial discharge information of the new energy power equipment through a plurality of partial discharge detection sensors.

3. According to claim 1, the external communication method of power equipment in the field of new energy based on Wifi, It is characterized in that The platform management unit (3) comprises a data preprocessing module (31), a data processing module (32), a fault remote diagnosis module (33), and a data storage module (34); The data preprocessing module (31) eliminates the frequency bands of no concern in the original sampled data signal transmitted by the communication unit (2) through a reasonable band-stop filter, defines the frequency monitoring range, and performs high-order noise reduction; The data processing module (32) is used to perform data fusion, data cleaning and data analysis on the pre-processed data to form various sensor data. The various sensor data, basic information of the power equipment and historical data are combined to form equipment rating data for judging power equipment faults.

4. The external communication method of power equipment in the field of new energy based on Wifi according to claim 3, It is characterized in that The fault remote diagnosis module (33) uses a machine learning method and utilizes data preprocessing, data segmentation, long short-term memory network (LSTM) time series analysis, softmax, and output of fault diagnosis results and warnings to process and analyze equipment rating data, thereby realizing fault prediction and remote diagnosis of new energy power equipment, and transmitting the diagnosis information to the intelligent control unit (4) and the fault alarm unit (5) through the communication unit (2). The data storage module (34) can integrate and store the data collected by the data acquisition unit (1), the data preprocessing module (31), the data processing module (32), and the fault remote diagnosis module (33).

5. The external communication method of power equipment in the field of new energy based on Wifi according to claim 1, It is characterized in that The platform management unit (3) further comprises a user management module (35), a data query module (36), a remote monitoring module (37), a device management module (38) and an alarm perception module (39); The user management module (35) is used to manage the user rights of the platform system and provide users with login, registration, and password modification operation rights; The data query module (36) uses data charts to present the data collected by the perception tags to the user in an intuitive and vivid manner, and provides a unified query for historical data, making it easy for the user to view and call.

6. The external communication method of power equipment in the field of new energy based on Wifi according to claim 5, It is characterized in that The remote monitoring module (37) is used by platform operation and maintenance personnel to view the real-time data of new energy power equipment, understand the equipment operation status and discover potential problems through the platform-side monitoring system. The equipment management module (38) is used to record and manage the inventory, maintenance and scrapping information of new energy power equipment. The alarm perception module (39) is used to monitor and perceive the temperature, humidity and posture parameters of new energy power equipment.

7. The external communication method of electric power equipment in the field of new energy based on Wifi according to claim 4, It is characterized in that The fault remote diagnosis module (33) uses a machine learning method to process and analyze the equipment rating data to achieve fault prediction and remote diagnosis of new energy power equipment, including the following steps: S1. First, preprocess the data to balance the impact of different dimensions and units between data. Use Z-score to standardize the data and convert its range to between 0 and 1: Where: a is a dimension in the original sensor data, b is the mean, and c is the standard value; S2. Build a machine learning model based on historical information, use LSTM network to diagnose power equipment faults, and use the LSTM network's ability to handle long-term dependencies in remote diagnosis of power equipment. The forget vector d output by the forget gate t It can be expressed as: d t =c(E d ·[f t-1 ·a t ]+g d -1); Where: E d Represents the weight of the forget gate, g d is the bias, and c is the sigmoid activation function, which can compress the output to between 0 and 1, indicating how much information each cell state unit should forget; S3, input gate update decision: The input gate is responsible for deciding how new information is updated to the cell state. It calculates an activation vector i t and a candidate cell state h t , the formula is as follows: Where: i t indicates which new information should be incorporated into the cell state at the current moment, and h t Specific values ​​for this new information are provided; S4: Update the cell state. Based on the decision of the forget gate and the input gate, the cell state will be updated to the new state H. t , the process is expressed as: H t =d t ×H t-1 +i t ×h t ; Where: The new cell state H t Integrate important information from the past and relevant information from the present, i.e., information selected by the forget gate and injected through the input gate; S5, the output gate forms the final prediction result of the power transmission and transformation equipment. After the cell state is updated, the output gate will determine the hidden state J at the next time point t , the hidden state contains the current input information and is also the basis for future predictions.

8. The external communication method of power equipment in the field of new energy based on Wifi according to claim 7, It is characterized in that In step S5, the hidden state J t The expression is as follows: Where: k t Represents the output vector, which determines the final output J through the activation of the tanh function and its own adjustment t The content of , that is, the hidden state containing the current input information.