A fault prediction system for a wind turbine

Abstract

The present invention relates to the technical field of fault prediction of wind turbines, and discloses a fault prediction system for wind turbines, including a wind turbine environmental data acquisition module, a wind turbine internal data acquisition module, a fault analysis module, and a fault warning scheduling module. The system preliminarily analyzes by collecting and sending electrical data and transmission data, and judges whether to report a fault. If no warning is given, an internal fault factor is output. Then, in combination with the altitude and the number of impacts on the blades of the wind turbine, an environmental fault prediction factor is analyzed and calculated. After obtaining the environmental fault prediction factor, combined with the internal fault factor, a comprehensive fault factor is obtained. Based on the comprehensive fault factor, a secondary fault prediction judgment is carried out, which can provide strong support for the fault warning scheduling module, so as to be able to identify wind turbines with higher fault risks and ensure avoiding safety accidents caused by faults at critical moments.

Description

Technical Field

[0001] The invention relates to the technical field of wind turbine fault prediction, and in particular to a fault prediction system for a wind turbine. Background Art

[0002] As a renewable energy source, wind energy is green and clean, and is currently the focus of research in countries around the world. In recent years, the transformation of my country's energy industry has been accelerating, and my country has become the world's largest and fastest-growing market for wind power generation. However, in the process of wind power generation, wind turbines, as key components of wind power generation, are of paramount importance as to whether they are in normal operation.

[0003] However, due to the complex working environment and long-term operation, wind turbines may face various faults and abnormal conditions. Once a wind turbine fault occurs, it will lead to reduced power generation efficiency and reduced economic benefits of the wind motor. The traditional wind turbine fault prediction method has low prediction accuracy and a high misjudgment rate for faults. Therefore, a method that can accurately predict wind turbine faults in advance is needed to detect abnormal conditions of wind turbines in time and repair them in time. Summary of the invention

[0004] Technical Problems Solved In view of the deficiencies in the prior art, the present invention provides a fault prediction system for a wind turbine generator, which has the advantages of predicting fault problems of the wind turbine generator in advance and making timely dispatches, thereby solving the above-mentioned technical problems.

[0005] Technical Solution To achieve the above-mentioned purpose, the present invention provides the following technical solution: A fault prediction system for a wind turbine generator, comprising a wind turbine generator environment data acquisition module, a wind turbine generator internal data acquisition module, a fault analysis module and a fault warning scheduling module;

[0006] The wind turbine internal data acquisition module includes an electrical data acquisition unit and a transmission data acquisition unit. The electrical data acquisition unit is used to acquire electrical data of the wind turbine during operation and send the electrical data to the fault analysis module. The transmission data acquisition unit is used to acquire transmission data of the wind turbine during operation and send the transmission data to the fault analysis module, wherein the transmission data includes transmission efficiency and noise frequency.

[0007] The fault analysis module includes an initial fault analysis unit, which is used to receive the electrical data and transmission data sent by the internal data acquisition module of the wind turbine for preliminary analysis, and determine whether to perform a fault error report. If a fault error report is performed, the fault early warning scheduling module is directly called to perform a fault early warning scheduling. If no fault error report is performed, the internal fault factor is output and the wind turbine environment data acquisition module is called;

[0008] The wind turbine environment data acquisition module includes a ground environment acquisition unit and a blade damage data acquisition unit. The ground environment acquisition unit is used to acquire the altitude. The blade damage data is used to acquire the number of impacts on the blades of the wind turbine. The wind turbine environment data acquisition module sends the acquired altitude and the number of impacts on the blades of the wind turbine to the fault analysis module.

[0009] The fault analysis module also includes an environmental fault analysis unit, which is used to analyze and calculate the environmental fault prediction factor by combining the altitude and the number of impacts on the blades of the wind turbine. After obtaining the environmental fault prediction factor, the internal fault factor is combined to obtain a comprehensive fault factor, and whether to report a fault error is determined based on the comprehensive fault factor. If a fault error is reported, the fault warning scheduling module is called to perform fault warning scheduling. If no fault error is reported, the process is terminated.

[0010] When the fault warning scheduling module is called, the staff is dispatched to perform maintenance.

[0011] As a preferred technical solution of the present invention, the specific expression of the electrical data acquisition unit for collecting electrical data of the wind turbine during operation is as follows: Among them, I represents the current set of the wind turbine during operation, U represents the voltage set of the wind turbine during operation, and DQ represents the electrical data set of the wind turbine during operation. They represent the temperature of the first internal sampling point of the wind turbine during operation, , No. The temperature of the internal sampling points, , No. The temperature of the internal sampling points, The transmission data acquisition unit is used to collect the transmission data of the wind turbine during operation. The specific expression is as follows: in, Represents the transmission data set of the wind turbine during operation. It represents the maximum value of the inverse of the transmission efficiency of the wind turbine during operation within a sampling period. Indicates the maximum value of the noise frequency of the wind turbine during operation within a sampling period. As a preferred technical solution of the present invention, the initial fault analysis unit is used to receive the electrical data and transmission data sent by the internal data acquisition module of the wind turbine for preliminary analysis, and the specific steps of determining whether to report a fault are as follows:

[0012] Step A1: Determine the electrical data set of the wind turbine during operation in the same sampling period and the transmission data set of wind turbines during operation Whether any value in exceeds 37.5% of the corresponding safety setting value, if so, execute step A2, if not, execute step A3;

[0013] Step A2: When a fault is reported, the fault warning scheduling module is directly called to perform fault warning scheduling;

[0014] Step A3: If no fault is reported, the internal fault factor is output and the wind turbine environment data acquisition module is called.

[0015] As a preferred technical solution of the present invention, the specific expression of outputting the internal fault factor in step A3 is as follows:

[0016]

[0017] in, Electrical data set representing a wind turbine in operation The number of elements in , A data set representing the transmission of a wind turbine during operation The number of elements in , Represents the electrical data set and sum the elements in the drive data set, Represents an electrical data set and transmission data sets Any element in Indicates the corresponding The safety setting value of express The absolute value of Indicates the internal fault factor.

[0018] As a preferred technical solution of the present invention, the specific expression used by the ground environment acquisition unit to collect the altitude is as follows:

[0019]

[0020] in, Respectively represent the altitude of the first external sampling point, , No. The altitude of the external sampling points, , No. The altitude of the external sampling points, represents the altitude dataset, .

[0021] As a preferred technical solution of the present invention, the specific steps of using the blade damage data to collect the number of impacts on the blades of the wind turbine are as follows:

[0022] Step B1: obtaining values ​​of vibration sensors arranged at three blades of the wind turbine;

[0023] Step B2: When the value of any one of the vibration sensors exceeds the values ​​of the other two vibration sensors by 15%, the number of impacts on the blades of the wind turbine is Plus one.

[0024] As a preferred technical solution of the present invention, the environmental fault analysis unit is used to analyze and calculate the environmental fault prediction factor by combining the altitude and the number of impacts on the blades of the wind turbine as follows: in, represents a natural constant, Indicates the number of times the wind turbine blades are hit. represents the maximum value in the altitude dataset, It means to sum up the total B altitudes. represents the environmental failure predictor.

[0025] As a preferred technical solution of the present invention, after obtaining the environmental fault prediction factor, the environmental fault analysis unit combines the internal fault factor to obtain the specific expression of the comprehensive fault factor as follows: in, represents the comprehensive failure factor, represents the internal fault factor, represents the environmental failure prediction factor, and Represent two different weight coefficients respectively.

[0026] As a preferred technical solution of the present invention, the specific steps of the environmental fault analysis unit determining whether to report a fault according to the comprehensive fault factor are as follows: When the comprehensive fault threshold is exceeded, an early warning is issued and the fault early warning scheduling module is called. If the set comprehensive fault threshold is not exceeded, no warning will be issued.

[0027] As a preferred technical solution of the present invention, the wind turbine environmental data acquisition module and the wind turbine internal data acquisition module update data once every sampling period when the fault analysis module does not issue an early warning, and the wind turbine environmental data acquisition module and the wind turbine internal data acquisition module do not update data when the fault analysis module issues an early warning.

[0028] Compared with the prior art, the present invention provides a fault prediction system for a wind turbine generator, which has the following beneficial effects:

[0029] The present invention collects and sends electrical data and transmission data for preliminary analysis, and determines whether to issue a fault alarm. If no warning is issued, the internal fault factor is output, and then the environmental fault prediction factor is calculated by combining the altitude and the number of impacts on the blades of the wind turbine. After the environmental fault prediction factor is obtained, the internal fault factor is combined to obtain a comprehensive fault factor. A secondary fault prediction and judgment is performed based on the comprehensive fault factor, which can provide strong support for the fault warning scheduling module, thereby identifying wind turbines with higher fault risks, ensuring that safety accidents caused by faults are avoided at critical moments, and avoiding losses caused by misjudgment. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 It is a schematic diagram of the system framework of the present invention. DETAILED DESCRIPTION

[0031] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only 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.

[0032] See also Figure 1 , a fault prediction system for a wind turbine generator, comprising a wind turbine generator environment data acquisition module, a wind turbine generator internal data acquisition module, a fault analysis module and a fault warning scheduling module;

[0033] The internal data acquisition module of the wind turbine generator includes an electrical data acquisition unit and a transmission data acquisition unit. The electrical data acquisition unit is used to collect electrical data of the wind turbine generator during operation and send the electrical data to the fault analysis module. The transmission data acquisition unit is used to collect transmission data of the wind turbine generator during operation and send the transmission data to the fault analysis module, wherein the transmission data includes transmission efficiency and noise frequency.

[0034] The specific expression of the electrical data acquisition unit used to collect the electrical data of the wind turbine during operation is as follows: in, represents the current set of the wind turbine during operation, Represents the voltage set of the wind turbine during operation. Represents the electrical data set of a wind turbine during operation. They represent the temperature of the first internal sampling point of the wind turbine during operation, , No. The temperature of the internal sampling points, , No. The temperature of the internal sampling points, ;

[0035] The specific expression of the transmission data acquisition unit used to collect the transmission data of the wind turbine during operation is as follows:

[0036]

[0037] in, Represents the transmission data set of the wind turbine during operation. It represents the maximum value of the inverse of the transmission efficiency of the wind turbine during operation within a sampling period. Indicates the maximum value of the noise frequency of the wind turbine during operation within a sampling period; the fault analysis module includes an initial fault analysis unit, which is used to receive the electrical data and transmission data sent by the internal data acquisition module of the wind turbine for preliminary analysis, and to determine whether to report a fault error. If a fault error is reported, the fault warning scheduling module is directly called to perform fault warning scheduling. If no fault error is reported, the internal fault factor is output, and the wind turbine environment data acquisition module is called;

[0038] The initial fault analysis unit is used to receive the electrical data and transmission data sent by the internal data acquisition module of the wind turbine for preliminary analysis, and the specific steps of determining whether to report a fault are as follows:

[0039] Step A1: Determine the electrical data set of the wind turbine during operation in the same sampling period and whether any value in the transmission data set of the wind turbine during operation exceeds 37.5% of the corresponding safety setting value. If so, execute step A2; if not, execute step A3;

[0040] Step A2: When a fault is reported, the fault warning scheduling module is directly called to perform fault warning scheduling;

[0041] Step A3: If no fault is reported, the internal fault factor is output and the wind turbine environment data acquisition module is called.

[0042] The specific expression of the internal fault factor output in step A3 is as follows: in, Electrical data set representing a wind turbine in operation The number of elements in , A data set representing the transmission of a wind turbine during operation The number of elements in , Represents the electrical data set and sum the elements in the drive data set, Represents an electrical data set and transmission data sets Any element in Indicates the corresponding The safety setting value of express The absolute value of represents the internal fault factor;

[0043] For the 37.5% of the safety setting value, for the equipment fault warning, it is usually stipulated that the fault warning threshold should be set at 30%~40% of the equipment safety setting value. At the same time, its safety margin covers 56% of the equipment limit value, leaving a maintenance window;

[0044] The wind turbine environment data acquisition module includes a ground environment acquisition unit and a blade damage data acquisition unit. The ground environment acquisition unit is used to collect altitude;

[0045] The specific expression used by the ground environment acquisition unit to collect altitude is as follows:

[0046] in, Respectively represent the altitude of the first external sampling point, , No. The altitude of the external sampling points, , No. The altitude of the external sampling points, represents the altitude dataset, ,The blade damage data is used to collect the number of impacts on the blades of wind turbines;

[0047] The specific steps for blade damage data to collect the number of impacts on the blades of wind turbines are as follows:

[0048] Step B1: obtaining values ​​of vibration sensors arranged at three blades of the wind turbine;

[0049] Step B2: When the value of any one of the vibration sensors exceeds the values ​​of the other two vibration sensors by 15%, the number of impacts on the blades of the wind turbine is plus one;

[0050] When a wind turbine is running in a uniform wind field, the vibration amplitudes of the three blades are usually approximately symmetrically distributed (the difference is generally <10%). If a blade is suddenly hit by an external impact (such as hail or birds), its vibration energy will increase significantly, while the other two blades will still maintain a normal fluctuation range. Basis: Through historical data analysis, it is found that the difference in blade vibration caused by natural wind conditions is usually less than 10%~12%, so choosing 15% here can effectively avoid the difference in blade vibration caused by natural wind conditions;

[0051] The wind turbine environment data acquisition module sends the collected altitude and the number of impacts on the wind turbine blades to the fault analysis module;

[0052] The fault analysis module also includes an environmental fault analysis unit, which is used to analyze and calculate the environmental fault prediction factor by combining the altitude and the number of impacts on the blades of the wind turbine, and after obtaining the environmental fault prediction factor, combine it with the internal fault factor to obtain a comprehensive fault factor;

[0053] The environmental fault analysis unit is used to analyze and calculate the specific expression of the environmental fault prediction factor by combining the altitude and the number of impacts on the blades of the wind turbine as follows: in, represents a natural constant, Indicates the number of times the wind turbine blades are hit. represents the maximum value in the altitude dataset, It means to sum up the total B altitudes. represents the environmental failure predictor;

[0054] After obtaining the environmental fault prediction factor, the environmental fault analysis unit combines the internal fault factor to obtain the specific expression of the comprehensive fault factor as follows:

[0055] in, represents the comprehensive failure factor, represents the internal fault factor, represents the environmental failure prediction factor, and Respectively represent two different weight coefficients;

[0056] Determine whether to report a fault error based on the comprehensive fault factor. If a fault error is reported, call the fault warning scheduling module to perform fault warning scheduling. If no fault error is reported, terminate the process. The specific steps are: When the comprehensive fault threshold is exceeded, an early warning is issued and the fault early warning scheduling module is called. If the set comprehensive fault threshold is not exceeded, no warning will be issued;

[0057] When the fault warning scheduling module is called, it dispatches staff to carry out maintenance. It uses a priority scheduling algorithm to schedule personnel and sets maintenance priorities based on the severity of the fault and the scope of impact. The severity is the first priority and the distance of the staff is the second priority. During scheduling, idle staff are given priority to ensure that key equipment is handled first, which improves the response speed to key fans and reduces potential downtime losses.

[0058] When the fault analysis module does not issue an early warning, the wind turbine environment data acquisition module and the wind turbine internal data acquisition module update data once every sampling cycle. When the fault analysis module issues an early warning, the wind turbine environment data acquisition module and the wind turbine internal data acquisition module do not update data.

[0059] Embodiment: The data of the electrical data acquisition unit recorded in this embodiment is shown in Table 1 below.

[0060] The transmission data acquisition unit is used to collect the transmission data of the wind turbine during operation. , and the corresponding values ​​are At this time, the initial fault analysis unit determines that there is no element that exceeds 37.5% of the corresponding safety setting value. At this time, the calculation ; The number of collisions in this paper , , , , , then we can calculate , and the comprehensive calculation is , at this time the comprehensive failure factor The set comprehensive fault threshold is not exceeded , no warning is given;

[0061] The threshold value in the present invention is set for the convenience of comparison. The threshold value depends on the amount of sample data and the number of bases set by technicians in the field for each group of sample data. As long as it does not affect the proportional relationship between the parameter and the quantized value, it can be determined by technicians in the field based on each sample data and multiple rounds of experiments.

[0062] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A fault prediction system for a wind turbine, characterized in that: It includes a wind turbine environment data acquisition module, a wind turbine internal data acquisition module, a fault analysis module and a fault warning and dispatching module; The wind turbine internal data acquisition module includes an electrical data acquisition unit and a transmission data acquisition unit; The fault analysis module includes an initial fault analysis unit, which is used to receive the electrical data and transmission data sent by the internal data acquisition module of the wind turbine and perform preliminary analysis, and determine whether to perform a fault error report. If a fault error report is performed, the fault early warning scheduling module is directly called to perform a fault early warning scheduling. If no fault error report is performed, the internal fault factor is output and the wind turbine environment data acquisition module is called; The wind turbine environment data acquisition module includes a ground environment acquisition unit and a blade damage data acquisition unit. The wind turbine environment data acquisition module sends the acquired altitude and the number of impacts on the wind turbine blades to the fault analysis module. The fault analysis module also includes an environmental fault analysis unit, which is used to analyze and calculate the environmental fault prediction factor by combining the altitude and the number of impacts on the blades of the wind turbine. After obtaining the environmental fault prediction factor, the internal fault factor is combined to obtain a comprehensive fault factor, and whether to report a fault error is determined based on the comprehensive fault factor. If a fault error is reported, the fault warning scheduling module is called to perform fault warning scheduling. If no fault error is reported, the process is terminated. When the fault warning scheduling module is called, the staff is dispatched to perform maintenance.

2. A fault prediction system for a wind turbine according to claim 1, characterized in that: The electrical data acquisition unit is used to collect electrical data of the wind turbine during operation, and send the electrical data to the fault analysis module. The transmission data acquisition unit is used to collect transmission data of the wind turbine during operation, and send the transmission data to the fault analysis module, wherein the transmission data includes transmission efficiency and noise frequency. The electrical data acquisition unit is used to collect the electrical data of the wind turbine during operation, specifically: the current set I of the wind turbine during operation, the voltage set U of the wind turbine during operation, and the temperature of 1 to A internal sampling points of the wind turbine during operation, where A represents the total number of internal sampling points. The transmission data acquisition unit is used to collect transmission data of the wind turbine during operation, specifically including: the maximum value max{ZL} of the inverse of the transmission efficiency of the wind turbine during operation within a sampling period and the maximum value max{ZYPL} of the noise frequency of the wind turbine during operation within a sampling period.

3. A fault prediction system for a wind turbine according to claim 2, characterized in that: The initial fault analysis unit is used to receive the electrical data and transmission data sent by the internal data acquisition module of the wind turbine for preliminary analysis, and the specific steps of determining whether to report a fault are as follows: Step A1: Determine whether any value in the electrical data set DQ of the wind turbine during operation and the transmission data set CD of the wind turbine during operation in the same sampling period exceeds 37.5% of the corresponding safety setting value, if so, execute step A2, if not, execute step A3; Step A2: When a fault is reported, the fault warning scheduling module is directly called to perform fault warning scheduling; Step A3: If no fault is reported, the internal fault factor is output and the wind turbine environment data acquisition module is called.

4. A fault prediction system for a wind turbine according to claim 3, characterized in that: The specific expression of the internal fault factor output in step A3 is as follows: Among them, crad{DQ} represents the number of elements in the electrical data set DQ of the wind turbine during operation, and crad{CD} represents the number of elements in the transmission data set CD of the wind turbine during operation. It means to sum the elements in the electrical data set DQ and the transmission data set CD, x means any element in the electrical data set DQ and the transmission data set CD, x0 means the safety setting value corresponding to x, |x-x0| means the absolute value of x-x0, and NBGZ means the internal fault factor.

5. A fault prediction system for a wind turbine according to claim 4, characterized in that: The specific expression used by the ground environment acquisition unit to collect the altitude is as follows: CJ=[GD1,…,GD b ,…,GD B ] Among them, GD1,…,GD b ,…,GD B They respectively represent the altitude of the 1st external sampling point, …, the altitude of the bth external sampling point, …, the altitude of the Bth external sampling point. CJ represents the altitude dataset, b∈[1,B].

6. A fault prediction system for a wind turbine according to claim 5, characterized in that: The blade damage data is used to collect the number of impacts on the blades of the wind turbine, and the specific steps are as follows: Step B1: obtaining values ​​of vibration sensors arranged at three blades of the wind turbine; Step B2: When the value of any one of the vibration sensors exceeds the values ​​of the other two vibration sensors by 15%, the number of impacts ZJ received by the blades of the wind turbine generator is increased by one.

7. A fault prediction system for a wind turbine according to claim 6, characterized in that: The environmental fault analysis unit is used to analyze and calculate the environmental fault prediction factor by combining the altitude and the number of impacts on the blades of the wind turbine as follows: Where, e represents a natural constant, ZJ represents the number of times the blades of the wind turbine are hit, and max{CJ} represents the maximum value in the altitude data set. represents the sum of B altitudes, and HJGZ represents the environmental failure prediction factor.

8. A fault prediction system for a wind turbine according to claim 7, characterized in that: After obtaining the environmental fault prediction factor, the environmental fault analysis unit combines the internal fault factor to obtain the specific expression of the comprehensive fault factor as follows: ZHGZ=α*HJGZ+β*NBGZ Among them, ZHGZ represents the comprehensive failure factor, NBGZ represents the internal failure factor, HJGZ represents the environmental failure prediction factor, and α and β represent two different weight coefficients respectively.

9. A fault prediction system for a wind turbine according to claim 8, characterized in that: The specific steps of the environmental fault analysis unit determining whether to report a fault based on the comprehensive fault factor are as follows: if the comprehensive fault factor ZHGZ exceeds the set comprehensive fault threshold, an early warning is issued and the fault early warning scheduling module is called; if the comprehensive fault factor ZHGZ does not exceed the set comprehensive fault threshold, no early warning is issued.

10. A fault prediction system for a wind turbine according to claim 9, characterized in that: The wind turbine environment data acquisition module and the wind turbine internal data acquisition module update data once every sampling period when the fault analysis module does not issue an early warning. The wind turbine environment data acquisition module and the wind turbine internal data acquisition module do not update data when the fault analysis module issues an early warning.

Images