Wind turbine generator bearing fault diagnosis method and system

Abstract

The invention relates to the technical field of wind power, in particular to a wind turbine generator bearing fault diagnosis method and system. According to the invention, on the basis of a multivariate data fusion intelligent early warning algorithm of characteristic value amplification, characteristic value acceleration and dynamic self-learning, a dynamic threshold strategy is adopted to solve the problem of automatic early warning of wind turbine generator difficult faults such as yaw bearing damage and variable pitch bearing damage; a wind turbine generator yaw and variable pitch bearing fault knowledge base based on a characteristic value self-learning algorithm is established, dynamic correction of bearing fault frequency is realized, a wind turbine generator yaw and variable pitch bearing reliability evaluation platform based on fault classification is established, standardized construction is performed on bearing fault types, fault grades and maintenance modes, and the reliability of the bearing is improved. And guiding the wind power plant to perform fan health state evaluation, maintenance plan making and spare part management.

Description

Technical Field

[0001] The present invention relates to the field of wind power technology, and in particular to a method and system for diagnosing bearing faults of a wind turbine set. Background Art

[0002] The yaw and pitch bearings of wind turbines are important components of wind turbines. The yaw and pitch bearings are key components for connecting and rotating the wind turbine nacelle and tower, and the blades and hub. The reliability of their operation directly affects the operating efficiency and safety of the entire wind turbine. Due to factors such as design, manufacturing, materials, installation technology, operation and maintenance, the yaw and pitch bearings are prone to damage to the internal structure of the bearings under the effects of long-term alternating loads, impact torque and insufficient lubrication. Since the replacement of yaw and pitch bearings is difficult and costly, the downtime is long and the failure losses are large. Therefore, it is very necessary to monitor and analyze the internal state of the bearings using online monitoring methods, analyze the development trend of invisible defects in the bearings, predict internal bearing failures in advance, and avoid bearing damage incidents.

[0003] Existing wind turbine condition monitoring methods are only applicable to traditional mechanical transmission structures, and cannot achieve fault warning and diagnosis of large slewing support structures such as yaw and pitch bearings. Fault diagnosis of such bearings is still a technical difficulty in the industry. With the passage of wind turbine service time, the failure and degradation problems of yaw and pitch bearings of wind turbines have become increasingly prominent in recent years. The economic damage caused by this has seriously affected the economic benefits of power generation companies. Summary of the invention

[0004] In view of the above problems, the present invention provides a method and system for diagnosing bearing faults of a wind turbine generator set.

[0005] In a first aspect, the present invention provides a method for diagnosing a bearing fault of a wind turbine generator set, comprising:

[0006] Through the structural characteristics and design parameters of wind turbine yaw and pitch bearings, the characteristic frequencies of various faults are calculated, and a database of fault characteristics of wind turbine yaw and pitch bearings is established;

[0007] Install online monitoring equipment on yaw and pitch bearings to collect vibration data, independent temperature data and soundprint data of yaw and pitch bearings in real time, calculate characteristic values ​​and corresponding increase and increase speed characteristic values, and issue an early warning when the characteristic values ​​and corresponding increase and increase speed characteristic values ​​exceed the corresponding thresholds; match the characteristic values ​​and corresponding increase and increase speed characteristic values ​​with graphic recognition and frequency recognition technology in the fault feature database to diagnose the fault type of yaw and pitch bearing status;

[0008] The wind turbine yaw and pitch bearing faults are graded according to their severity, and different inspection and maintenance methods are adopted for different faults; corresponding inspection and maintenance methods are adopted according to the monitored yaw and pitch bearing status.

[0009] Furthermore, the yaw and pitch bearing failures of wind turbines include: pitting, spalling, and crack failures of the bearing outer ring, pitting, spalling, and crack failures of the bearing inner ring, pitting and spalling failures of the bearing rolling element surface, and bearing retainer fracture failures.

[0010] Furthermore, the characteristic values ​​include: fault time domain, frequency domain, voiceprint and temperature characteristics.

[0011] Furthermore, a database of wind turbine yaw and pitch bearing fault characteristics is established, including:

[0012] Collect the design parameters of yaw and pitch bearings, and calculate the fault characteristic frequencies of the outer ring, inner ring, rolling element, and cage of the bearings;

[0013] According to the fault characteristic frequency and the correlation of the fault characteristic values ​​of the yaw and pitch bearings, the fault spectrum characteristics are calculated and stored in the database.

[0014] Furthermore, the wind turbine yaw and pitch bearing faults are graded according to severity, including:

[0015] Faults are divided into minor faults, moderate faults, and severe faults, and are marked in blue, yellow, and red respectively.

[0016] Furthermore, different inspection and maintenance methods are adopted for different faults, including:

[0017] Different operation and maintenance methods are adopted for different faults. For minor faults, the machine can be continued to be used with increased attention; for medium faults, the machine can be continued to be used after repair and maintenance; for serious faults, the machine should be shut down and replaced.

[0018] In a second aspect, the present invention provides a wind turbine bearing fault diagnosis system, comprising: a database unit, a diagnosis unit and a fault response unit;

[0019] The database unit is used to calculate the characteristic frequencies of various faults through the structural characteristics and design parameters of the yaw and pitch bearings of the wind turbine, and to establish a fault characteristic database of the yaw and pitch bearings of the wind turbine;

[0020] The diagnostic unit is used to install online monitoring equipment on the yaw and pitch bearings, collect the vibration data, independent temperature data and soundprint data of the yaw and pitch bearings in real time, calculate the characteristic value and the corresponding increase and increase speed characteristic value, and issue an early warning when the characteristic value and the corresponding increase and increase speed characteristic value exceed the corresponding threshold value; the characteristic value and the corresponding increase and increase speed characteristic value are matched by the graphic recognition and frequency recognition technology in the fault feature database to realize the diagnosis of the yaw and pitch bearing status fault type;

[0021] The fault response unit is used to classify the yaw and pitch bearing faults of the wind turbine according to the severity, and adopt different inspection and maintenance methods for different faults; corresponding inspection and maintenance methods are adopted according to the monitored yaw and pitch bearing status.

[0022] The present invention has at least the following beneficial effects:

[0023] In view of the particularity and importance of the operation modes of the yaw bearings and pitch bearings of wind turbines, the present invention has developed a fault diagnosis system based on the deep integration of multiple diagnostic technologies such as vibration signals, temperature signals, and soundprint signals to ensure the accuracy of fault diagnosis results.

[0024] The present invention realizes real-time fault warning through characteristic value trend "increase" and "speed increase" algorithms combined with multiple fault diagnosis models, evaluates and displays component health status in real time, and regularly generates monitoring equipment fault condition reports;

[0025] The present invention provides theoretical guidance for the operation, maintenance and spare parts management of the unit under fault conditions by intelligently matching the characteristic values ​​and diagnosis results with the bearing fault knowledge base and reliability evaluation system.

[0026] Other features and advantages of the present invention will be described in the following description, and partly become obvious from the description, or be understood by implementing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures pointed out in the description and the drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0028] Figure 1 This is a flow chart of the diagnostic method according to an embodiment of the present invention;

[0029] Figure 2 This is a schematic diagram of the structure of a diagnostic system according to an embodiment of the present invention;

[0030] Figure 3 It is a schematic diagram of the principle of the diagnostic method;

[0031] Figure 4 A schematic diagram for establishing a knowledge base of fault characteristics;

[0032] Figure 5 This is a schematic diagram of fault judgment rating. DETAILED DESCRIPTION

[0033] 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 in conjunction with the drawings in the embodiments of the present invention. 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.

[0034] Existing wind turbine condition monitoring methods are only applicable to traditional mechanical transmission structures, and cannot achieve fault warning and diagnosis of large slewing support structures such as yaw and pitch bearings. Fault diagnosis of such bearings is still a technical difficulty in the industry. With the passage of wind turbine service time, the failure and degradation problems of yaw and pitch bearings of wind turbines have become increasingly prominent in recent years. The economic damage caused by this has seriously affected the economic benefits of power generation companies.

[0035] To this end, the present invention proposes an intelligent diagnosis method and system for yaw and pitch bearing faults of wind turbines. Based on a multi-data fusion intelligent early warning algorithm with eigenvalue increase, eigenvalue growth rate and dynamic self-learning, a dynamic threshold strategy is adopted to solve the problem of automatic early warning of difficult faults of wind turbines such as yaw bearing damage and pitch bearing damage. A knowledge base of yaw and pitch bearing faults of wind turbines based on the eigenvalue self-learning algorithm is established to realize dynamic correction of bearing fault frequency. A reliability evaluation platform of yaw and pitch bearings of wind turbines based on fault classification is established to standardize bearing fault types, fault levels and maintenance methods, and guide wind farms to conduct wind turbine health status assessment, maintenance plan formulation and spare parts management.

[0036] like Figure 1 As shown, the present invention provides a method for diagnosing bearing faults of a wind turbine generator set, comprising:

[0037] S101, calculate the characteristic frequencies of various faults through the structural characteristics and design parameters of the wind turbine yaw and pitch bearings, and establish a fault characteristic database for the wind turbine yaw and pitch bearings;

[0038] S102, installing online monitoring equipment on the yaw and pitch bearings, collecting vibration data, independent temperature data and soundprint data of the yaw and pitch bearings in real time, calculating characteristic values ​​and corresponding increase and increase speed characteristic values, and issuing an early warning when the characteristic values ​​and corresponding increase and increase speed characteristic values ​​exceed the corresponding thresholds; matching the characteristic values ​​and corresponding increase and increase speed characteristic values ​​with the graphic recognition and frequency recognition technology in the fault feature database, to achieve the diagnosis of the fault type of the yaw and pitch bearing status;

[0039] S103, classify the yaw and pitch bearing faults of the wind turbine according to their severity, and adopt different inspection and maintenance methods for different faults; adopt corresponding inspection and maintenance methods according to the monitored yaw and pitch bearing status.

[0040] In specific implementation, the threshold is set based on historical data and expert experience.

[0041] In one embodiment, the yaw and pitch bearing failures of the wind turbine include: pitting, spalling, and crack failures of the bearing outer ring, pitting, spalling, and crack failures of the bearing inner ring, pitting, spalling failures of the bearing rolling element surface, and bearing retainer fracture failures.

[0042] In one embodiment, the characteristic values ​​include: fault time domain, frequency domain, sound print and temperature characteristics.

[0043] In one embodiment, a database of wind turbine yaw and pitch bearing fault characteristics is established, including:

[0044] Collect the design parameters of yaw and pitch bearings, and calculate the fault characteristic frequencies of the outer ring, inner ring, rolling element, and cage of the bearings;

[0045] According to the fault characteristic frequency and the correlation of the fault characteristic values ​​of the yaw and pitch bearings, the fault spectrum characteristics are calculated and stored in the database.

[0046] In one embodiment, the yaw and pitch bearing faults of the wind turbine are graded according to severity, including:

[0047] Faults are divided into minor faults, moderate faults, and severe faults, and are marked in blue, yellow, and red respectively.

[0048] In specific implementation, minor faults include: poor bearing lubrication, pitting of bearing outer ring, wear of bearing outer ring, pitting of bearing inner ring, wear of bearing inner ring, pitting of yaw gear tooth surface, peeling of blade surface, etc. Medium faults include: large peeling of bearing outer ring, large peeling of bearing inner ring, large peeling of bearing rolling element, peeling and cracks of yaw gear tooth surface, etc. Severe faults include broken bearing outer ring, broken bearing inner ring, broken bearing cage, broken yaw gear teeth, ice coating on blades, cracks on blades, aerodynamic imbalance of impeller, etc.

[0049] In one embodiment, different inspection and maintenance methods are adopted for different faults, including:

[0050] Different operation and maintenance methods are adopted for different faults. For minor faults, the machine can be continued to be used with increased attention; for medium faults, the machine can be continued to be used after repair and maintenance; for serious faults, the machine should be shut down and replaced.

[0051] like Figure 2 As shown, the present invention provides a wind turbine bearing fault diagnosis system, including: a database unit 201, a diagnosis unit 202 and a fault response unit 203;

[0052] The database unit 201 is used to calculate various fault characteristic frequencies through the structural characteristics and design parameters of the wind turbine yaw and pitch bearings, and establish a wind turbine yaw and pitch bearing fault characteristic database;

[0053] The diagnostic unit 202 is used to install online monitoring equipment on the yaw and pitch bearings, collect vibration data, independent temperature data and sound print data of the yaw and pitch bearings in real time, calculate the characteristic value and the corresponding increase and increase speed characteristic value, and issue an early warning when the characteristic value and the corresponding increase and increase speed characteristic value exceed the corresponding threshold value; and diagnose the fault type of the yaw and pitch bearing status by matching the characteristic value and the corresponding increase and increase speed characteristic value with the graphic recognition and frequency recognition technology in the fault feature database;

[0054] The fault response unit 203 is used to classify the wind turbine yaw and pitch bearing faults according to the severity, and adopt different inspection and maintenance methods for different faults; and adopt corresponding inspection and maintenance methods according to the monitored yaw and pitch bearing status.

[0055] In order to enable those skilled in the art to better understand the present invention, the principle of the present invention is described as follows in conjunction with the accompanying drawings:

[0056] like Figure 3 As shown in the figure, a knowledge base of yaw and pitch bearing fault characteristics is established

[0057] Through the structural characteristics and design parameters of wind turbine yaw and pitch bearings, the characteristic frequencies of various faults such as bearing fatigue peeling, wear, fracture, and cage damage are calculated, and a database of wind turbine yaw and pitch bearing fault characteristics is established. The specific contents include:

[0058] (1) Collect the design parameters of yaw and pitch bearings, and calculate the fault characteristic frequencies of the outer ring, inner ring, rolling element, and cage of the bearings;

[0059] (2) Establish the correlation between the fault characteristic values ​​of yaw and pitch bearing fatigue peeling, wear, fracture, cage damage, etc.;

[0060] (3) Automatic calculation of fault frequency. Bearing-related design parameters can be manually input to calculate fault characteristic frequency and store it in the database;

[0061] like Figure 4 As shown, yaw and pitch bearing fault diagnosis

[0062] Yaw and pitch bearings are low-speed and heavy-load components. Appropriate online monitoring equipment is installed on the yaw and pitch bearings to monitor the status and diagnose faults of the yaw and pitch bearings. The specific contents are as follows:

[0063] Yaw and pitch bearing fault diagnosis technology, including pitting, spalling, and crack faults of bearing outer rings, pitting, spalling, and crack faults of bearing inner rings, pitting and spalling faults of bearing rolling element surfaces, and bearing cage fracture faults in time domain, frequency domain, temperature, and soundprint characteristics and diagnostic algorithm models;

[0064] Intelligent fault diagnosis technology, through graphic recognition and frequency recognition technologies, can realize online automatic diagnosis of "simple" faults, intelligently match the fault knowledge base and reliability evaluation indicators to determine the fault type and severity, and give corresponding maintenance suggestions. "Difficult" faults that cannot be identified by intelligent algorithms are automatically submitted to the remote data diagnosis center for expert diagnosis;

[0065] Data management enables storage, downloading and export of component historical data, supports multiple data decomposition methods and tools, and realizes all-round comparison of monitoring data.

[0066] like Figure 5 As shown, yaw and pitch bearing fault judgment

[0067] Establish the reliability evaluation method and standard of wind turbine yaw and pitch bearings, propose the evaluation index that can dynamically reflect the reliability level and influencing factors of wind turbine yaw and pitch bearings, and establish the bearing reliability evaluation system. The specific contents include:

[0068] Establish reliability evaluation indicators for wind turbine yaw and pitch bearing faults, define fault severity criteria and identification methods, and classify faults into minor faults, moderate faults, and severe faults, which are identified in blue, yellow, and red respectively;

[0069] Establish evaluation standards for wind turbine yaw and pitch bearing fault types, and define yaw and pitch bearing outer ring, inner ring, rolling element, cage faults based on reliability indicators;

[0070] Establish inspection and repair standards for wind turbine yaw and pitch bearing faults, adopt different operation and maintenance methods for different faults, continue to use with increased attention for minor faults, continue to use after repair and maintenance for medium faults, and shut down and replace the machine for serious faults.

[0071] The present invention realizes intelligent early warning of characteristic value increase, characteristic value speed increase, and dynamic self-learning. The intelligent fault diagnosis model trained by machine learning and classification model realizes yaw and pitch bearing fault judgment. The present invention establishes a knowledge base of wind turbine yaw and pitch bearing faults and formulates reliability evaluation standards for wind turbine yaw and pitch bearings.

[0072] Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent substitutions for some of the technical features therein; and these modifications or substitutions do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A wind turbine bearing fault diagnosis method, It is characterized in that include: Through the structural characteristics and design parameters of wind turbine yaw and pitch bearings, the characteristic frequencies of various faults are calculated, and a database of fault characteristics of wind turbine yaw and pitch bearings is established; Install online monitoring equipment on yaw and pitch bearings to collect vibration data, independent temperature data and soundprint data of yaw and pitch bearings in real time, calculate characteristic values ​​and corresponding increase and increase speed characteristic values, and issue an early warning when the characteristic values ​​and corresponding increase and increase speed characteristic values ​​exceed the corresponding thresholds; match the characteristic values ​​and corresponding increase and increase speed characteristic values ​​with graphic recognition and frequency recognition technology in the fault feature database to diagnose the fault type of yaw and pitch bearing status; The wind turbine yaw and pitch bearing faults are graded according to their severity, and different inspection and maintenance methods are adopted for different faults; corresponding inspection and maintenance methods are adopted according to the monitored yaw and pitch bearing status.

2. A wind turbine bearing fault diagnosis method according to claim 1, It is characterized in that Wind turbine yaw and pitch bearing failures include: pitting, spalling, and crack failures on the bearing outer ring, pitting, spalling, and crack failures on the bearing inner ring, pitting and spalling failures on the bearing rolling element surface, and bearing retainer fracture failures.

3. A wind turbine bearing fault diagnosis method according to claim 1, It is characterized in that Characteristic values ​​include: fault time domain, frequency domain, soundprint and temperature characteristics.

4. A wind turbine bearing fault diagnosis method according to claim 1, It is characterized in that Establish a database of wind turbine yaw and pitch bearing fault characteristics, including: Collect the design parameters of yaw and pitch bearings, and calculate the fault characteristic frequencies of the outer ring, inner ring, rolling element, and cage of the bearings; According to the fault characteristic frequency and the correlation of the fault characteristic values ​​of the yaw and pitch bearings, the fault spectrum characteristics are calculated and stored in the database.

5. A wind turbine bearing fault diagnosis method according to claim 1, It is characterized in that The wind turbine yaw and pitch bearing faults are graded according to severity, including: Faults are divided into minor faults, moderate faults, and severe faults, and are marked in blue, yellow, and red respectively.

6. A wind turbine bearing fault diagnosis method according to claim 5, It is characterized in that Different inspection and maintenance methods are adopted for different faults, including: Different operation and maintenance methods are adopted for different faults. For minor faults, the machine can be continued to be used with increased attention; for medium faults, the machine can be continued to be used after repair and maintenance; for serious faults, the machine should be shut down and replaced.

7. A wind turbine bearing fault diagnosis system, It is characterized in that include: Database unit, diagnostic unit and fault response unit; The database unit is used to calculate the characteristic frequencies of various faults through the structural characteristics and design parameters of the yaw and pitch bearings of the wind turbine, and to establish a fault characteristic database of the yaw and pitch bearings of the wind turbine; The diagnostic unit is used to install online monitoring equipment on the yaw and pitch bearings, collect the vibration data, independent temperature data and soundprint data of the yaw and pitch bearings in real time, calculate the characteristic value and the corresponding increase and increase speed characteristic value, and issue an early warning when the characteristic value and the corresponding increase and increase speed characteristic value exceed the corresponding threshold value; the characteristic value and the corresponding increase and increase speed characteristic value are matched with the graphic recognition and frequency recognition technology in the fault feature database to realize the diagnosis of the yaw and pitch bearing status fault type; The fault response unit is used to classify the yaw and pitch bearing faults of the wind turbine according to their severity, and adopt different inspection and maintenance methods for different faults; corresponding inspection and maintenance methods are adopted according to the monitored yaw and pitch bearing status.

Images