Wind turbine generator fault early warning and abnormal parameter inspection method

Abstract

The invention belongs to the technical field of wind turbine generators, and particularly relates to a wind turbine generator fault early warning and abnormal parameter inspection method comprising the following steps: collecting historical operation data of a wind turbine generator, analyzing the data, and establishing a data model; the historical data comprises operation data of a generator, a gear box, a main bearing, a variable pitch system and an electrical system; vibration spectrums of a gearbox and a generator rotating part are monitored through an acceleration sensor to identify whether bearing pitting corrosion, gear tooth breakage mechanical faults and frequency are abnormal or not; an on-line monitoring device is installed in an oil way of the wind turbine generator to monitor the oil state in real time. The temperature of the gearbox and the bearing is detected through the thermal infrared imager, and whether the temperature is abnormal or not is monitored; abnormal sound signals of blade cracks or bearing early damage are captured through an ultrasonic sensor, and the blade is judged.

Description

Technical Field

[0001] The present invention belongs to the technical field of wind turbine generators, and particularly relates to a method for fault early warning and abnormal parameter inspection of wind turbine generators. Background Art

[0002] The penetration rate of wind turbine generators connected to the power system is increasing continuously. It is necessary to improve their fault ride-through ability to meet the requirements of the Grid Safety Operation Criteria "Technical Regulations for Wind Farms Connected to the Power System GB / T 19963-2011" promulgated by the State Grid Corporation of China. As one of the main types of current variable-speed constant-frequency wind power generation technology, the fault ride-through ability of doubly-fed wind turbine generators using doubly-fed induction generators (DFIGs) needs to be improved when the voltage fails at the point of common coupling (PCC).

[0003] Wind turbine generators are a common type of rotating machinery and are crucial for the ventilation of factories, boilers, buildings, etc. To ensure the normal operation of these devices, the fault diagnosis of wind turbine generators becomes particularly important. In actual operation, equipment management personnel usually use the method of "listening, touching, checking, and comparing" to regularly inspect the equipment and collect various data, including vibration parameters, noise parameters, oil temperature, etc. However, traditional inspection methods have certain limitations, especially in the face of equipment complexity and non-intuitive fault characteristics. In view of this, we propose a method for fault early warning and abnormal parameter inspection of wind turbine generators. Summary of the Invention

[0004] The purpose of the present invention is to provide a method for fault early warning and abnormal parameter inspection of wind turbine generators to solve the problems raised in the above background art in view of the above existing technical problems.

[0005] In view of this, the present invention provides a method for fault early warning and abnormal parameter inspection of wind turbine generators, including the following methods:

[0006] Collect the historical operation data of the wind turbine generator, analyze the data, and establish a data model;

[0007] The historical data includes the operation data of the generator, gearbox, main bearing, pitch system, and electrical system;

[0008] Monitor the vibration spectrum of the rotating components of the gearbox and generator through an acceleration sensor to identify mechanical faults such as bearing pitting and gear tooth breakage and whether the frequency is abnormal;

[0009] Install an on-line monitoring device in the oil circuit of the wind turbine generator to monitor the oil condition in real time;

[0010] Detect the temperature of the gearbox and bearing through an infrared thermal imager to monitor whether it is abnormal;

[0011] Capture abnormal sound signals of blade cracks or early bearing damage through ultrasonic sensors to judge the blades;

[0012] Set up a high-definition camera to regularly photograph the blade surface, and use AI image recognition to identify cracks or corrosion;

[0013] Measure the dynamic load and structural strain of the blade through fiber Bragg grating sensors for accurate detection of the blade;

[0014] Set warning thresholds, set static or dynamic thresholds for each component and system parameter detected. When the data detected by each sensor exceeds the set static or dynamic threshold, it is determined that the wind turbine has a fault and an alarm command is issued;

[0015] When an abnormality is detected in the wind turbine, receive the alarm command through the alarm device, and at this time the alarm device issues an alarm.

[0016] Among them, this method truly liberates on-site human resources, increases the application of digital and intelligent technologies and function research and development, uses digital technologies to empower new energy enterprises, and improves the level of value creation. Adopting an open system architecture, each business function is designed in layers, with functional, modular and extensible capabilities, meeting the needs of subsequent application development, business expansion and data opening, and providing support for the construction of the industrial ecosystem.

[0017] In the above technical solution, further, the alarm device includes a buzzer, a warning light, and a wireless remote alarm system.

[0018] Among them, when the alarm device issues an alarm, the buzzer will emit a sound alarm, the warning light will flash to emit an alarm light, and the wireless remote alarm system will send a warning signal.

[0019] In the above technical solution, further, the wireless remote alarm system sends alarms to mobile phones and the central control room through wireless signals. The wireless signals include cellular network signals, Wi-Fi, Bluetooth, Zigbee, satellite communication, and radar signals.

[0020] Among them, the wireless remote alarm system is a security protection system that uses wireless communication technology to achieve remote monitoring and alarm. When a fault occurs in the wind turbine, a warning signal is sent through wireless signals.

[0021] In the above technical solution, further, the method for establishing the data model includes: connecting the collected historical operation data to the SCADA system and establishing a normal behavior data model through machine learning.

[0022] Among them, the CADA system is the core tool for the intelligent management of wind turbines. Through data collection, monitoring, control, and analysis, it significantly improves the operation efficiency and safety of wind farms. With the continuous development of technology, the SCADA system will further develop towards intelligence, cloudification, and standardization, providing strong support for the sustainable development of the wind power industry.

[0023] In the above technical solution, further, the SCADA system remotely controls the start / stop, pitch, and yaw of wind turbines, optimizes the power generation efficiency, adjusts the power output according to the grid demand, realizes coordinated operation with the grid, supports the batch control function, and improves the operation and maintenance efficiency.

[0024] Among them, through the SCADA system, various functions of wind turbines can be accurately controlled, improving the working efficiency of wind turbines.

[0025] In the above technical solution, further, a fault data storage system is provided in the SCADA system. When a fault occurs in the wind turbine, the SCADA system will record the fault location of this occurrence at the fault moment, mark the fault location, which is convenient for the historical fault investigation of wind turbines when the next fault occurs.

[0026] Among them, the fault data storage system increases the convenience for later maintenance personnel to repair wind turbines, and is convenient for investigating the fault location of wind turbines through historical fault data.

[0027] In the above technical solution, further, the historical operation data also includes: the maximum coordinate value and the minimum coordinate value of wind speed - power for each wind speed section of the wind turbine blades.

[0028] Among them, by recording the wind speed of each wind speed section of the wind turbine blades, it is convenient to judge whether there are any abnormalities in the blades during operation.

[0029] In the above technical solution, further, the method for judging the abnormality of the wind speed section of the wind turbine blades is as follows:

[0030] Abnormality in the low wind speed section:

[0031] Low power: Possible reasons include blade contamination / icing, yaw system error, control system limitation, or sensor failure;

[0032] High power: It may be a problem with the anemometer calibration or abnormal turbulence;

[0033] Abnormality near the rated wind speed section:

[0034] Large power fluctuation: It may be due to the lag of the pitch system response, improper control system parameters, or high turbulence intensity;

[0035] Unable to reach the rated power: commonly seen in pitch mechanism failures, decreased generator efficiency, or grid power curtailment;

[0036] Abnormalities in the high wind speed section:

[0037] Early cut-out: wind speed measurement error or overly conservative safety settings;

[0038] Delayed cut-out: may pose safety hazards, and the protection system needs to be checked.

[0039] Among them, through the above methods, abnormal phenomena of the wind turbine blades can be quickly judged.

[0040] In the above technical solution, further, the on-line monitoring device includes an on-line particle sensor, an on-line moisture sensor, an on-line viscosity sensor, and an on-line ferromagnetic particle sensor, which can comprehensively master the oil condition of the wind turbine and early warn of the failure risks of key components such as gearboxes and bearings.

[0041] Among them, by setting an on-line moisture sensor, an on-line viscosity sensor, and an on-line ferromagnetic particle sensor, the oil condition of the wind turbine can be accurately monitored. When the oil condition is abnormal, each sensor can accurately make a judgment, facilitating maintenance by the staff.

[0042] The beneficial effects of the present invention are:

[0043] 1. The method for early warning of wind turbine failures and inspection of abnormal parameters improves the company's production and operation level, promotes cost reduction and efficiency increase. It improves the construction of business function modules in all links of new energy, and deepens the regional intensive and integrated management mode. With equipment control operations such as remote monitoring, identification and early warning, and intelligent inspection as the main body, it further improves the maintenance efficiency, enhances the equipment reliability, reduces the operation and maintenance costs, and reduces the failure downtime and power loss; at the same time, it actually reduces the workload of on-site personnel, changes the existing work mode, and improves the work efficiency.

[0044] 2. The method for early warning of wind turbine failures and inspection of abnormal parameters constructs a complete new energy safety control system to achieve safety and reliability. It promotes the deep integration of front-end event analysis, high-definition cameras, etc. with the safety control of new energy power stations, comprehensively perceives and identifies safety hazards of "people, machines, environment, management, and network", and realizes high-precision positioning management from personnel access control to the operation process, as well as the situation awareness of network security, helping to build a new intelligent safety control system of "safety control + network security".

[0045] 3. The fault warning and abnormal parameter inspection method for this wind turbine truly liberates on-site human resources, increases the application of digital and intelligent technologies and function R & D, empowers new energy enterprises with digital technologies, and improves the level of value creation. It adopts an open system architecture, and each business function is designed in layers, with the capabilities of being functional, modular, and extensible, meeting the needs of subsequent application development, business expansion, and data opening, and providing support for the construction of the industrial ecological system. Brief Description of the Drawings

[0046] Figure 1 is the flowchart of the present invention. Detailed Embodiments

[0047] Next, the technical solutions in the embodiments of the present application will be clearly described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art belong to the scope protected by the present application.

[0048] Embodiment 1:

[0049] Please refer to Figure 1 as shown, this embodiment provides a fault warning and abnormal parameter inspection method for a wind turbine.

[0050] It includes the following methods:

[0051] Collect the historical operation data of the wind turbine, analyze the data, and establish a data model;

[0052] The historical data includes the operation data of the generator, gearbox, main bearing, pitch system, and electrical system;

[0053] Monitor the vibration spectrum of the rotating components of the gearbox and generator through an acceleration sensor to identify mechanical faults such as bearing pitting and gear tooth breakage, and whether the frequency is abnormal;

[0054] Install an on-line monitoring device in the oil circuit of the wind turbine to monitor the oil condition in real time;

[0055] Through an infrared thermal imager: detect the temperature of the gearbox and bearing, and monitor whether it is abnormal;

[0056] Capture abnormal sound signals of blade cracks or early bearing damage through an ultrasonic sensor to judge the blades;

[0057] Set up a high-definition camera to regularly photograph the blade surface, and use AI image recognition to identify cracks or corrosion;

[0058] Measure the dynamic load and structural strain of the blade through a fiber Bragg grating sensor to accurately detect the blade;

[0059] Set warning thresholds, set static or dynamic thresholds for each detected component and system parameter. When the data detected by each sensor exceeds the set static or dynamic threshold, it is determined that the wind turbine has a fault and an alarm command is issued.

[0060] When it is detected that the wind turbine is abnormal, the alarm device receives the alarm command. At this time, the alarm device issues an alarm. This method truly liberates on-site human resources, increases the application of digital and intelligent technologies and the research and development of functions, empowers new energy enterprises with digital technologies, and improves the level of value creation. Adopting an open system architecture, each business function is designed in layers, with functional, modular, and extensible capabilities, meeting the needs of subsequent application development, business expansion, and data opening, and providing support for the construction of the industrial ecological system.

[0061] Embodiment 2:

[0062] This embodiment provides a method for wind turbine fault warning and abnormal parameter inspection. In addition to the technical solutions of the above embodiments, it also has the following technical features.

[0063] In this embodiment, the alarm device includes a buzzer, a warning light, and a wireless remote alarm system. When the alarm device issues an alarm, the buzzer will emit a sound alarm, the warning light will flash and emit an alarm light, and the wireless remote alarm system will send a warning signal.

[0064] Embodiment 3:

[0065] This embodiment provides a method for wind turbine fault warning and abnormal parameter inspection. In addition to the technical solutions of the above embodiments, it also has the following technical features.

[0066] In this embodiment, the wireless remote alarm system sends an alarm to a mobile phone and a central control room through a wireless signal. The wireless signal includes a cellular network signal, Wi-Fi, Bluetooth, Zigbee, satellite communication, and radar signal. The wireless remote alarm system is a security protection system that uses wireless communication technology to achieve remote monitoring and alarm. When the wind turbine has a fault, a warning signal is sent through the wireless signal.

[0067] Embodiment 4:

[0068] This embodiment provides a method for wind turbine fault warning and abnormal parameter inspection. In addition to the technical solutions of the above embodiments, it also has the following technical features.

[0069] In this embodiment, the method for establishing a data model includes: connecting the collected historical operation data to the SCADA system, and establishing a normal behavior data model through machine learning. The CADA system is the core tool for the intelligent management of wind turbines. Through data collection, monitoring, control, and analysis, it significantly improves the operation efficiency and safety of wind farms. With the continuous development of technology, the SCADA system will further develop towards intelligence, cloudification, and standardization, providing strong support for the sustainable development of the wind power industry.

[0070] Embodiment 5:

[0071] This embodiment provides a method for fault warning and abnormal parameter inspection of wind turbines. In addition to including the technical solutions of the above embodiments, it also has the following technical features.

[0072] In this embodiment, the SCADA system remotely controls the start / stop, pitch, and yaw of wind turbines, optimizes the power generation efficiency, adjusts the power output according to the grid demand, realizes coordinated operation with the grid, supports the batch control function, improves the operation and maintenance efficiency, and can accurately control various functions of wind turbines through the SCADA system, improving the working efficiency of wind turbines.

[0073] Embodiment 6:

[0074] This embodiment provides a method for fault warning and abnormal parameter inspection of wind turbines. In addition to including the technical solutions of the above embodiments, it also has the following technical features.

[0075] In this embodiment, a fault data storage system is provided in the SCADA system. When a fault occurs in the wind turbine, the SCADA system records the location of the fault at the moment of the fault and marks the fault location, which is convenient for the historical fault investigation of the wind turbine when the next fault occurs. The fault data storage system improves the convenience of the later maintenance personnel for the inspection and repair of the wind turbine and facilitates the investigation of the fault location of the wind turbine through the historical fault data.

[0076] Embodiment 7:

[0077] This embodiment provides a method for fault warning and abnormal parameter inspection of wind turbines. In addition to including the technical solutions of the above embodiments, it also has the following technical features.

[0078] In this embodiment, the historical operation data further includes: the maximum coordinate value and the minimum coordinate value of wind speed - power for each wind speed section of the wind turbine blades. By recording the wind speed of each wind speed section of the wind turbine blades, it is convenient to judge whether there are abnormalities when the blades are working.

[0079] In this embodiment, the method for judging the abnormality of the wind speed section of the wind turbine blades is as follows:

[0080] Abnormality in low wind speed section:

[0081] Low power: Possible causes include blade contamination / icing, yaw system error, control system limitation or sensor failure;

[0082] High power: It may be due to anemometer calibration problem or abnormal turbulence;

[0083] Abnormality near rated wind speed section:

[0084] Large power fluctuation: It may be due to the lag of pitch system response, improper control system parameters or high turbulence intensity;

[0085] Unable to reach rated power: Commonly seen in pitch mechanism failure, generator efficiency decline or grid power curtailment;

[0086] Abnormality in high wind speed section:

[0087] Early cut-out: Wind speed measurement error or overly conservative safety settings;

[0088] Delayed cut-out: It may pose a safety hazard. It is necessary to check the protection system. Through the above methods, the abnormal phenomena of the wind turbine blades can be quickly judged.

[0089] Embodiment 7:

[0090] This embodiment provides a method for fault early warning and abnormal parameter inspection of a wind turbine. In addition to including the technical solutions of the above embodiments, it also has the following technical features.

[0091] In this embodiment, the on-line monitoring device includes an on-line particle sensor, an on-line moisture sensor, an on-line viscosity sensor, and an on-line ferromagnetic particle sensor, which can comprehensively master the oil fluid state of the wind turbine, early warn of the fault risks of key components such as the gearbox and bearings. By setting the on-line moisture sensor, on-line viscosity sensor, and on-line ferromagnetic particle sensor, the oil fluid state of the wind turbine can be accurately monitored. When the oil fluid state is abnormal, each sensor can accurately make a judgment, which is convenient for the staff to repair it.

[0092] When in use: This method improves the company's production and operation level, promotes cost reduction and efficiency increase. It improves the construction of business function modules in each link of new energy, and deepens the regional intensive and integrated management mode. Taking equipment control operations such as remote monitoring, identification and early warning, and intelligent inspection as the main body, it further improves the maintenance efficiency, enhances the equipment reliability, reduces the operation and maintenance cost, reduces the fault downtime and power loss; at the same time, it actually reduces the workload of on-site personnel, changes the existing working mode, and improves the work efficiency.

[0093] This method constructs and improves a new energy safety control system to achieve safety and reliability. It promotes the deep integration of front-end event analysis, high-definition cameras, etc. with the safety control of new energy power stations, comprehensively senses and identifies safety hazards in "people, machines, environment, management, and network", and realizes a new type of intelligent safety control system of "safety control + network security" from personnel access control to high-precision positioning management during the operation process and the situation awareness of network security.

[0094] This method truly liberates on-site human resources, increases the application of digital and intelligent technologies and function R & D, empowers new energy enterprises with digital technologies, and improves the level of value creation. By adopting an open system architecture, each business function is designed in layers, with the capabilities of being functionalized, modularized, and extensible, meeting the needs of subsequent application development, business expansion, and data opening, and providing support for the construction of the industrial ecological system.

[0095] The embodiments of the present application have been described above in conjunction with the accompanying drawings. Without conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application is not limited to the above specific implementation manners. The above specific implementation manners are merely illustrative rather than restrictive. Under the inspiration of the present application, those of ordinary skill in the art can also make many forms without departing from the purpose of the present application and the scope protected by the claims, and all of them belong to the protection scope of the present application.

Claims

1. A method for fault early warning and abnormal parameter inspection of a wind turbine unit, characterized in that, Including the following methods: Collect historical operation data of the wind turbine, analyze the data, and establish a data model; The historical data includes the operation data of the generator, gearbox, main bearing, pitch system, and electrical system; Monitor the vibration spectrum of the rotating components of the gearbox and generator through acceleration sensors to identify mechanical faults such as bearing pitting and gear tooth breakage, and check whether the frequency is abnormal; Install an on-line monitoring device in the oil circuit of the wind turbine to monitor the oil condition in real time; Through an infrared thermal imager: detect the temperature of the gearbox and bearings, and monitor whether it is abnormal; Through ultrasonic sensors, capture abnormal sound signals of blade cracks or early bearing damage, and judge the blades; Set up a high-definition camera to regularly photograph the blade surface, and use AI image recognition to detect cracks or corrosion; Measure the dynamic load and structural strain of the blade through fiber Bragg grating sensors to accurately detect the blade; Set warning thresholds, set static or dynamic thresholds for the parameters of each detected component and system. When the data detected by each sensor exceeds the set static or dynamic threshold, it is determined that the wind turbine has a fault, and an alarm command is issued; When it is detected that the wind turbine is abnormal, receive the alarm command through the alarm device, and at this time the alarm device issues an alarm.

2. The method for fault early warning and abnormal parameter inspection of a wind turbine unit according to claim 1, characterized in that, The alarm device includes a buzzer, a warning light, and a wireless remote alarm system.

3. The method for fault early warning and abnormal parameter inspection of a wind turbine unit according to claim 2, characterized in that, The wireless remote alarm system sends alarms to mobile phones and the central control room through wireless signals. The wireless signals include cellular network signals, Wi-Fi, Bluetooth, Zigbee, satellite communication, and radar signals.

4. A method for fault early warning and abnormal parameter inspection of a wind turbine unit according to claim 1, characterized in that, The method for establishing the data model includes: connecting the collected historical operation data to the SCADA system, and establishing a normal behavior data model through machine learning.

5. A method for fault early warning and abnormal parameter inspection of a wind turbine unit according to claim 4, characterized in that, The SCADA system remotely controls the start / stop, pitching, and yawing of the wind turbine, optimizes the power generation efficiency, adjusts the power output according to the grid demand, realizes coordinated operation with the grid, supports batch control functions, and improves the operation and maintenance efficiency.

6. The method for fault early warning and abnormal parameter inspection of a wind turbine set according to claim 5, characterized in that There is a fault data storage system in the SCADA system. When a fault occurs in the wind turbine, the SCADA system will record the fault location at this time, mark the fault location, which is convenient for troubleshooting the historical faults of the wind turbine when the next fault occurs.

7. A method for fault early warning and abnormal parameter inspection of a wind turbine unit according to claim 1, characterized in that, The historical operation data also includes: the maximum coordinate values of wind speed-power and the minimum coordinate values of wind speed-power for each wind speed section of the wind turbine blade.

8. A method for fault early warning and abnormal parameter inspection of a wind turbine unit according to claim 1, characterized in that, The method for judging the abnormality of the wind speed section of the wind turbine blade is as follows: Abnormality in the low wind speed section: Low power: Possible reasons include blade contamination / icing, yaw system error, control system limitation, or sensor failure; High power: It may be due to anemometer calibration problems or abnormal turbulence; Abnormality near the rated wind speed section: Large power fluctuations: May be due to pitch system response lag, improper control system parameters, or high turbulence intensity; Unable to reach the rated power: Commonly seen in pitch mechanism failures, generator efficiency decline, or grid power curtailment; Abnormality in the high wind speed section: Early cut-out: Wind speed measurement error or overly conservative safety settings; Delayed cut-out: May pose a safety hazard, and the protection system needs to be checked.

9. A method for fault early warning and abnormal parameter inspection of a wind turbine unit according to claim 1, characterized in that, The online monitoring device includes an online particle sensor, an online moisture sensor, an online viscosity sensor, and an online ferromagnetic particle sensor, which can comprehensively grasp the oil fluid state of the wind turbine and early warn of the failure risks of key components such as the gearbox and bearings.

Images