Wind generating set transmission chain fault online detection system based on AI intelligence

Abstract

The invention relates to the technical field of wind power generation detection, and discloses a wind generating set transmission chain fault on-line detection system based on AI intelligence, which comprises the following steps: summarizing and carding problems generated in the history of a wind generating set, and establishing an AI intelligent fault database according to the problems generated in the history of the wind generating set, in the operation process of the wind generating set, data collection is carried out on the operation state of a transmission chain, the collected data are transmitted to an AI intelligent fault database, and the fault data collected and arranged in the AI intelligent fault database and the collected fault data are compared and analyzed. The data analysis module 5 and the fault diagnosis module 6 can be used for judging and positioning the current operation data, so that the fault type and the fault position of the current operation data can be quickly analyzed, the fault type and the fault position of the operation data can be analyzed, a worker can quickly repair the fault position, and the working efficiency is improved. The power generation efficiency is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of wind power generation detection, and in particular, relates to an AI-based intelligent online detection system for wind power generator transmission chain faults. Background Art

[0002] With the widespread application of wind power generation, the reliability and safety of wind turbines have attracted more and more attention. As one of the core components of wind turbines, the failure of the transmission chain will cause the unit to shut down, affect the power generation efficiency, and may even cause serious safety accidents.

[0003] After a long period of use, wind turbines will have internal faults, and are generally inspected regularly by humans. During the inspection, the entire transmission chain needs to be checked one by one, which will greatly increase the labor intensity of the staff, thereby reducing the overall inspection and maintenance time, thereby reducing the inspection and maintenance efficiency.

[0004] In view of this, the present invention is proposed. Summary of the invention

[0005] In order to solve the problem that the above-mentioned wind turbine generator set may have internal faults after long-term use, it is generally inspected manually on a regular basis. During the inspection, the entire transmission chain needs to be checked one by one, which greatly increases the labor intensity of the staff, thereby reducing the overall inspection and maintenance time, thereby reducing the technical problem of reducing the inspection and maintenance efficiency. The basic concept of the technical solution adopted by the present invention is:

[0006] An AI-based online detection system for wind turbine transmission chain faults, the system method comprising:

[0007] S1: Summarize and sort out the problems that have arisen from the history of wind power generation groups;

[0008] S2: Establish an AI intelligent fault database based on the historical problems of wind turbines;

[0009] S3: Collecting data on the operation status of the transmission chain during the operation of the wind turbine generator set;

[0010] S4: Transmit the collected data to the AI ​​intelligent fault database;

[0011] S5: Compare and analyze the fault data collected and organized internally in the AI ​​intelligent fault database with the collected fault data.

[0012] As a preferred embodiment of the present invention, the following specific steps are included:

[0013] The fault data generated by the wind power generation group in the history are summarized and sorted, and then an AI intelligent fault database is established based on the summarized and sorted fault data; the status of the running transmission chain is collected through various sensors installed on the wind power generation group, and then the collected transmission chain operation status data is transmitted to the AI ​​intelligent fault database, and then the fault data collected in the AI ​​intelligent fault database is compared and analyzed with the data transmitted therein to determine whether there is a fault in the data transmitted this time. When a fault exists, a diagnostic report will be made for the fault data this time, and a fault alarm will be issued for the fault generated this time.

[0014] As a preferred embodiment of the present invention, the following modules are included:

[0015] The sensor module reasonably selects the installation position of the sensor according to the structural characteristics of the transmission chain of the wind turbine generator set to ensure that the operating status data of the transmission chain can be accurately collected.

[0016] The data acquisition module collects and processes the data collected by the sensor in real time, removes noise and interference signals, and improves the accuracy and reliability of the data.

[0017] The data transmission module transmits the collected data to the data analysis module via wired or wireless means. Communication methods such as Ethernet, Wi-Fi, and Bluetooth can be used to ensure the stability and timeliness of data transmission.

[0018] AI intelligent fault database is used to store the data model library of historical faults of wind turbines, which is used to compare and analyze faults with the collected data.

[0019] The data analysis module uses artificial intelligence algorithms to analyze and process the transmitted data and extract fault features. Neural networks, support vector machines, decision trees and other algorithms can be used to select the appropriate algorithm based on the actual situation.

[0020] The fault diagnosis module diagnoses and locates the transmission chain fault according to the fault features extracted by the data analysis module.

[0021] The alarm module can send out alarm signals for analyzed faults. It can use sound and light alarms, SMS alarms, email alarms, etc. to ensure that fault information can be conveyed to relevant personnel in a timely manner.

[0022] As a preferred embodiment of the present invention, based on the specific process of the above-mentioned sensor module and data acquisition module, the operating data of each position on the transmission chain can be sensed by the sensor module, and then the operating data sensed in the sensor module is collected and summarized by the data acquisition module, and the collected operating data is pre-processed.

[0023] As a preferred embodiment of the present invention, based on the specific process of the above-mentioned data acquisition module, a filtering algorithm will be first used to remove noise interference from the collected operating data, and then the abnormal values ​​in the operating data will be identified and processed, so as to ensure the accuracy of the subsequent identification and comparative analysis of the collected operating data.

[0024] As a preferred embodiment of the present invention, based on the specific process of the above-mentioned data transmission module and the AI ​​intelligent fault database, the pre-processed operation data can be transmitted through the data transmission module through communication methods such as Ethernet, Wi-Fi, Bluetooth, etc., and then the operation data will be transmitted to the AI ​​intelligent fault database, so as to be compared and analyzed with the historical fault data stored therein to determine whether there is a fault in the current operation data.

[0025] As a preferred embodiment of the present invention, based on the specific processes of the above-mentioned data analysis module and fault diagnosis module, the data analysis module can be used to perform specific comparative analysis on the transmitted operation data and the data in the AI ​​intelligent fault database, and at the same time, the fault diagnosis module can be used to diagnose the operation data to determine what kind of fault the operation data is, and then the operation data is located to determine the fault location, so as to facilitate direct maintenance by the staff.

[0026] As a preferred implementation of the present invention, based on the specific process of the above fault diagnosis module:

[0027] First, the transmitted operation data is extracted and stored, and then compared and analyzed with a large amount of historical fault data in the AI ​​intelligent fault database to determine whether there is a fault in the current operation data;

[0028] If a fault occurs, the data from different sensors on the transmission chain will be compared and analyzed with a large amount of historical fault data in the AI ​​intelligent database, and the fault will be located based on the structural characteristics of the transmission chain.

[0029] If the fault does not exist, the system will continue to cycle through steps such as data collection and analysis to achieve the purpose of real-time online monitoring.

[0030] As a preferred embodiment of the present invention, based on the specific process of the above-mentioned alarm module, when it is determined that there is a fault in the current operating data, the alarm module at this time will alarm the staff in various ways to ensure that the staff can know the existence of the fault in the first time and carry out emergency repairs.

[0031] Compared with the prior art, the present invention has the following beneficial effects:

[0032] The present invention first summarizes and sorts out the fault data generated by the wind turbine generator set in history, then establishes an AI intelligent database based on the fault data, then senses and collects data at various positions on the transmission chain through a sensor module, preprocesses the sensing and collected operation data, removes noise and interference signals therein, thereby improving the accuracy of subsequent comparison of the operation data and the reliability of the data, then transmits the preprocessed operation data in a variety of ways through a data transmission module to ensure stability and timeliness during the data transmission process, then compares and analyzes the operation data with a large amount of historical fault data in the AI ​​intelligent fault database, thereby determining whether there is a fault in the current operation data, then the data analysis module and the fault diagnosis module can be used to judge and locate the current operation data, so that the fault type and fault position of the current operation data can be quickly analyzed, and after the fault type and position of the operation data are analyzed, the fault can be alarmed through the alarm module, so that the staff can quickly repair the fault and improve the power generation efficiency, so that the staff does not need to perform maintenance on time, and does not need to perform maintenance on all positions, thereby improving the maintenance efficiency and thus improving the power generation efficiency.

[0033] The specific implementation modes of the present invention are further described in detail below in conjunction with the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In the attached picture:

[0035] Figure 1 It is a schematic diagram of the overall process of an online detection system for wind turbine transmission chain faults based on AI intelligence;

[0036] Figure 2 It is a schematic diagram of the convergence processing flow of an AI-based online detection system for wind turbine transmission chain faults;

[0037] Figure 3 Schematic diagram of the data analysis process of an AI-based online detection system for wind turbine transmission chain faults Figure 1 ;

[0038] Figure 4 Schematic diagram of the data analysis process of an AI-based online detection system for wind turbine transmission chain faults Figure 2 ;

[0039] Figure 5 This is a schematic diagram of the identification and alarm module of an AI-based online detection system for wind turbine transmission chain faults.

[0040] In the figure: 1. Sensor module; 2. Data acquisition module; 3. Data transmission module; 4. Fault database; 5. Data analysis module; 6. Fault diagnosis module; 7. Alarm module. DETAILED DESCRIPTION

[0041] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. The following embodiments are used to illustrate the present invention.

[0042] Embodiment 1:

[0043] like Figures 1 to 5 As shown, an AI-based online detection system for wind turbine transmission chain faults includes:

[0044] S1: Summarize and sort out the problems that have arisen from the history of wind power generation groups;

[0045] S2: Establish an AI intelligent fault database based on the historical problems of wind turbines;

[0046] S3: Collecting data on the operation status of the transmission chain during the operation of the wind turbine generator set;

[0047] S4: Transmit the collected data to the AI ​​intelligent fault database;

[0048] S5: Compare and analyze the fault data collected and organized internally in the AI ​​intelligent fault database with the collected fault data.

[0049] Further, the following specific steps are included:

[0050] The fault data generated by the wind power generation group in history are summarized and sorted, and then an AI intelligent fault database 4 is established based on the summarized and sorted fault data; the data of the state of the running transmission chain is collected through various sensors installed on the wind power generation group, and then the collected transmission chain operation state data is transmitted to the AI ​​intelligent fault database 4, and then the fault data collected in the AI ​​intelligent fault database 4 is compared and analyzed with the data transmitted thereto, so as to determine whether there is a fault in the data transmitted this time. When a fault exists, a diagnostic report will be made for the fault data this time, and a fault alarm will be issued for the fault generated this time.

[0051] Furthermore, the following modules are included:

[0052] Sensor module 1, according to the structural characteristics of the transmission chain of the wind turbine generator set, reasonably selects the installation position of the sensor to ensure that the operating status data of the transmission chain can be accurately collected.

[0053] The data acquisition module 2 collects and processes the data collected by the sensor in real time, removes noise and interference signals, and improves the accuracy and reliability of the data.

[0054] Data transmission module 3: The data transmission module transmits the collected data to the data analysis module via wired or wireless means. Communication methods such as Ethernet, Wi-Fi, and Bluetooth can be used to ensure the stability and timeliness of data transmission.

[0055] The AI ​​intelligent fault database 4 is used to store the data model library of the historical faults of wind turbines, and is used to compare and analyze the faults with the collected data.

[0056] The data analysis module 5 uses artificial intelligence algorithms to analyze and process the transmitted data and extract fault features. Neural networks, support vector machines, decision trees and other algorithms can be used, and the appropriate algorithm can be selected according to the actual situation.

[0057] The fault diagnosis module 6 diagnoses and locates the fault of the transmission chain according to the fault characteristics extracted by the data analysis module 5 .

[0058] The alarm module 7 can send out an alarm signal for the analyzed fault. It can use sound and light alarm, SMS alarm, email alarm and other methods to ensure that the fault information can be conveyed to relevant personnel in time.

[0059] Furthermore, based on the specific process of the above-mentioned sensor module 1 and data acquisition module 2, the operating data of each position on the transmission chain can be sensed by the sensor module 1, and then the operating data sensed in the sensor module 1 is collected and summarized by the data acquisition module 2, and the collected operating data is pre-processed.

[0060] Based on the specific process of the above-mentioned data acquisition module 2, the collected operating data will first use a filtering algorithm to remove noise interference, and then the abnormal values ​​in the operating data will be identified and processed, so as to ensure the accuracy of the subsequent identification and comparative analysis of the collected operating data.

[0061] Based on the specific process of the above-mentioned data transmission module 3 and the AI ​​intelligent fault database 4, the pre-processed operation data can be transmitted through the data transmission module 3 via communication methods such as Ethernet, Wi-Fi, Bluetooth, etc., and then the operation data will be transmitted to the AI ​​intelligent fault database 4, so as to be compared and analyzed with the historical fault data stored therein to determine whether there is a fault in the current operation data.

[0062] Based on the specific process of the above-mentioned data analysis module 5 and fault diagnosis module 6, the data analysis module 5 can be used to perform specific comparative analysis on the transmitted operation data and the data in the AI ​​intelligent fault database 4. At the same time, the fault diagnosis module 6 can be used to diagnose the operation data to determine what kind of fault the operation data is. The operation data is then located to determine the fault location, which is convenient for the staff to directly perform maintenance.

[0063] Based on the specific process of the above fault diagnosis module 6:

[0064] First, the transmitted operation data is extracted and stored, and then compared and analyzed with a large amount of historical fault data in the AI ​​intelligent fault database 4 to determine whether there is a fault in the current operation data;

[0065] If a fault occurs, the data from different sensors on the transmission chain will be compared and analyzed with a large amount of historical fault data in the AI ​​intelligent database 4, and the fault will be located based on the structural characteristics of the transmission chain;

[0066] If the fault does not exist, the system will continue to cycle through steps such as data collection and analysis to achieve the purpose of real-time online monitoring.

[0067] Based on the specific process of the alarm module 7, when it is determined that there is a fault in the operating data, the alarm module 7 will give an alarm prompt to the staff in various ways to ensure that the staff can know the fault and carry out emergency repairs in the first time.

[0068] The implementation principle of an AI-based online detection system for wind turbine transmission chain faults in this embodiment is as follows: first, the fault data generated by the wind turbine history is summarized and sorted, and then an AI intelligent database 4 is established based on the fault data. Then, the sensor module 1 is used to sense and collect data at various positions on the transmission chain, and the sensing and collected operating data is preprocessed to remove noise and interference signals from the sensing and collected operating data, thereby improving the accuracy of the subsequent comparison of the operating data and improving the reliability of the data. Then, the preprocessed operating data is transmitted in a variety of ways through the data transmission module 3 to ensure stability during data transmission. The operation data is compared and analyzed with a large amount of historical fault data in the AI ​​intelligent fault database 4 to determine whether there is a fault in the current operation data. The data analysis module 5 and the fault diagnosis module 6 can then be used to judge and locate the operation data, so that the fault type and fault location of the current operation data can be quickly analyzed. After the fault type and location of the operation data are analyzed, the alarm module 7 can be used to perform a fault alarm on the fault, so that the staff can quickly repair the fault and improve the power generation efficiency. In this way, there is no need for the staff to perform maintenance on time or to perform maintenance at all locations, thereby improving the maintenance efficiency and thus improving the power generation efficiency.

Claims

1. An AI-based online detection system for wind turbine transmission chain faults, characterized in that: The system method includes: S1: Summarize and sort out the problems that have arisen from the history of wind power generation groups; S2: Establish an AI intelligent fault database based on the historical problems of wind turbines; S3: Collecting data on the operation status of the transmission chain during the operation of the wind turbine generator set; S4: Transmit the collected data to the AI ​​intelligent fault database; S5: Compare and analyze the fault data collected and organized internally in the AI ​​intelligent fault database with the collected fault data.

2. According to claim 1, an AI-based online detection system for wind turbine transmission chain faults is characterized in that: The following specific steps are included The fault data generated by the wind power generation group in the past are summarized and sorted, and then an AI intelligent fault database (4) is established based on the summarized and sorted fault data; data on the status of the running transmission chain is collected through various sensors installed on the wind power generation group, and then the collected transmission chain operation status data is transmitted to the AI ​​intelligent fault database (4), and then the fault data collected in the AI ​​intelligent fault database (4) is compared and analyzed with the data transmitted thereto, so as to determine whether there is a fault in the data transmitted this time. When a fault exists, a diagnostic report will be made for the fault data this time, and a fault alarm will be issued for the fault generated this time.

3. According to claim 1, the AI-based online detection system for wind turbine transmission chain faults is characterized in that: Includes the following modules: The sensor module (1) reasonably selects the installation position of the sensor according to the structural characteristics of the transmission chain of the wind turbine generator set, so as to ensure that the operation status data of the transmission chain can be accurately collected. The data acquisition module (2) collects and processes the data collected by the sensor in real time, removes noise and interference signals, and improves the accuracy and reliability of the data. The data transmission module (3) transmits the collected data to the data analysis module via wired or wireless means, and can adopt communication means such as Ethernet, Wi-Fi, Bluetooth, etc. to ensure the stability and timeliness of data transmission. The AI ​​intelligent fault database (4) is used to store the data model library of historical faults of wind turbine generator sets, and is used to compare and analyze faults with the collected data. The data analysis module (5) uses artificial intelligence algorithms to analyze and process the transmitted data and extract fault features. Neural network, support vector machine, decision tree and other algorithms can be used, and the appropriate algorithm can be selected according to the actual situation. The fault diagnosis module (6) diagnoses and locates the fault of the transmission chain according to the fault characteristics extracted by the data analysis module (5). The alarm module (7) can send out an alarm signal for the analyzed fault, and can use sound and light alarm, SMS alarm, email alarm and other methods to ensure that the fault information can be conveyed to relevant personnel in a timely manner.

4. According to claim 3, an AI-based online detection system for wind turbine transmission chain faults is characterized in that: Based on the specific process of the sensor module (1) and the data acquisition module (2), the sensor module (1) can sense the operating data of each position on the transmission chain, and then the data acquisition module (2) can collect and summarize the operating data sensed in the sensor module (1), and pre-process the collected operating data.

5. The AI-based online detection system for wind turbine transmission chain faults according to claim 4 is characterized in that: Based on the specific process of the above-mentioned data acquisition module (2), the collected operating data will first be subjected to a filtering algorithm to remove noise interference, and then the abnormal values ​​in the operating data will be identified and processed, thereby ensuring the accuracy of the subsequent identification and comparative analysis of the collected operating data.

6. The AI-based online detection system for wind turbine transmission chain faults according to claim 3 is characterized in that: Based on the specific process of the above-mentioned data transmission module (3) and the AI ​​intelligent fault database (4), the pre-processed operating data can be transmitted through the data transmission module (3) via Ethernet, Wi-Fi, Bluetooth and other communication methods, and then the operating data will be transmitted to the AI ​​intelligent fault database (4), so as to be compared and analyzed with the historical fault data stored therein to determine whether there is a fault in the current operating data.

7. The AI-based online detection system for wind turbine transmission chain faults according to claim 3 is characterized in that: Based on the specific processes of the above-mentioned data analysis module (5) and fault diagnosis module (6), the data analysis module (5) can be used to conduct a specific comparative analysis between the transmitted operation data and the data in the AI ​​intelligent fault database (4). At the same time, the fault diagnosis module (6) can be used to diagnose the operation data to determine what kind of fault the operation data is. The operation data is then located to determine the fault location, which is convenient for the staff to directly carry out maintenance.

8. The AI-based online detection system for wind turbine transmission chain faults according to claim 7 is characterized in that: Based on the above fault diagnosis module (6) specific process: First, the transmitted operation data is extracted and stored, and then compared and analyzed with a large amount of historical fault data in the AI ​​intelligent fault database (4) to determine whether there is a fault in the current operation data; If a fault occurs, the data from different sensors on the transmission chain will be compared and analyzed with a large amount of historical fault data in the AI ​​intelligent database (4), and the fault will be located based on the structural characteristics of the transmission chain; If the fault does not exist, the system will continue to cycle through steps such as data collection and analysis to achieve the purpose of real-time online monitoring.

9. The AI-based online detection system for wind turbine transmission chain faults according to claim 3 is characterized in that: Based on the specific process of the alarm module (7), when it is determined that there is a fault in the current operation data, the alarm module (7) will use a variety of methods to give an alarm prompt to the staff to ensure that the staff can know the existence of the fault in the first time and carry out emergency repairs.

Images