CN107797063A - Running of wind generating set state estimation and method for diagnosing faults based on SCADA - Google Patents

Abstract

The invention discloses a SCADA-based method for evaluating and diagnosing the operating state of a wind turbine, including: based on sample data extracted by the SCADA system, researching the relationship between the operating data of the wind turbine and the operating characteristics of the main components; researching based on a clustering algorithm, Cluster analysis and machine learning methods for predicting the operating status of wind turbines; research on fault diagnosis methods for wind turbines, using decision tree models and association rule theory, combined with statistical characteristics of long-term stable operation of wind turbines, to study fault diagnosis rules. The invention can effectively realize the operation state evaluation and fault diagnosis of the wind turbine.

Description

SCADA-based wind turbine operation status evaluation and fault diagnosis method

technical field

The invention relates to the technical field of analysis methods, in particular to a SCADA-based method for evaluating the operating state of a wind turbine and diagnosing a fault.

Background technique

With the rapid growth of my country's wind power installed capacity, the proportion of total installed capacity is increasing year by year. With the huge development prospects of resources, the construction of large-capacity wind farms is developing from land to offshore, and even to deep sea areas. Compared with land wind turbines, offshore wind turbines will face harsher operating environmental conditions and higher operation and maintenance costs. For example, the 160MW Horns Rev wind farm in Denmark was built and operated in 2002. In the early stage of operation, there were many faults in the safety system, electronic control system, and transformer of the wind turbines. Only during the operation period from 2003 to 2004, 80 On average, each wind turbine is maintained twice a day. Such a high on-site failure maintenance rate is beyond the expectation of the operator Elsam. Therefore, timely, comprehensive and accurate monitoring and evaluation of the operating status of grid-connected wind turbines, effectively avoiding failures and cascading failures, has important practical significance for optimizing the maintenance strategy of wind farms and realizing safe and efficient grid-connection of large-scale wind turbines. .

Based on my country's development and construction of smart grid planning and low-carbon economic strategic goals, how to use various renewable energy sources safely, reliably and on a large scale is one of the current challenges, and wind power is one of the renewable energy sources in my country. One of the most widely developed and utilized power generation methods, large-scale wind turbines with a single unit capacity of megawatts and wind farms of hundreds of megawatts are developing rapidly. With the relative maturity of my country's onshore wind power generation technology and the gradual development of offshore wind energy resources, the construction of large-capacity wind farms is moving from land to offshore and deep sea areas. Compared with land wind turbines, offshore wind turbines will face harsher operating environment, overhaul conditions and higher maintenance costs. --For example, the 160MW Horns Rev wind farm built and operated in Denmark in 2002. In the early stage of operation, there were many faults in the safety system, electronic control system, and transformer of the wind turbine. Only during the operation period from 2003 to 2004, Each of the 80 wind turbines was maintained twice a day on average, which directly resulted in a loss of nearly 40 million euros in 2004. Such a high on-site failure maintenance rate and high maintenance costs were beyond the operator's expectation. Therefore, how to improve the availability of wind turbines (referred to as wind turbines), reduce operation and maintenance costs, and ensure the high reliability of offshore wind turbines has become a key issue that needs to be solved urgently in the development of offshore wind power technology in my country. Important technical and economic indicators pursued by wind turbine manufacturers and wind farm operators. Especially with the rapid increase in the number of installed wind turbines in my country and the development of offshore wind turbines, comprehensive analysis of wind turbine operation status, fault diagnosis, and reliability research are expected to become new growth points for my country's wind power industry.

Contents of the invention

In view of this, the object of the present invention is to propose a SCADA-based method for evaluating the operating state and fault diagnosis of wind turbines, so as to effectively realize the evaluation and fault diagnosis of wind turbines.

Based on the above purpose, a SCADA-based wind turbine operating state evaluation and fault diagnosis method provided by the present invention includes:

Based on the sample data extracted by the SCADA system, the relationship between the wind turbine operating data and the operating characteristics of the main components is studied;

Research on wind turbine operating status prediction methods based on clustering algorithms, cluster analysis and machine learning methods;

To study the fault diagnosis method of wind turbines, the fault diagnosis rules are studied by using the decision tree model and the theory of association rules, combined with the statistical characteristics of the long-term stable operation status of wind turbines.

In some embodiments, the study of the relationship between the wind turbine operating data and the operating characteristics of the main components based on the sample data extracted by the SCADA system includes:

Research on wind turbine operation data cleaning and data preprocessing technology based on big data and data mining technology.

In some embodiments, the study of the relationship between the wind turbine operating data and the operating characteristics of the main components based on the sample data extracted by the SCADA system includes:

Study the statistical characteristics of different operating parameters such as wind turbine power, speed, pitch, and wind turbine main bearing temperature and vibration.

In some implementations, the method for predicting the operating state of wind turbines based on clustering algorithms, cluster analysis and machine learning methods includes:

Study the SCADA data modeling technology based on mathematical statistics and machine learning methods, and establish an evaluation model for the operation status of main components such as wind turbine gearboxes, generators, and main shafts.

In some implementations, the method for predicting the operating state of wind turbines based on clustering algorithms, cluster analysis and machine learning methods includes:

The modeling method of wind turbine operating state under different data time scales is studied.

In some implementations, the method for predicting the operating state of wind turbines based on clustering algorithms, cluster analysis and machine learning methods includes:

Combining with the statistical characteristics of the stable operation state of wind turbines, fuzzy logic, distance identification and other methods are used to study the fault threshold identification method.

In some embodiments, the machine learning method includes: multiple linear regression, neural network, support vector machine.

In some implementations, the research on the fault diagnosis method of wind turbines adopts the decision tree model and association rule theory, combined with the statistical characteristics of the long-term stable operation state of wind turbines, and the research on fault diagnosis rules includes: analyzing typical fault characteristic parameters of wind turbines, establishing Data mining training/learning sample library.

In some embodiments, the research on the fault diagnosis method of wind turbines adopts the decision tree model and association rule theory, combined with the statistical characteristics of the long-term stable operation state of wind turbines, and the research on fault diagnosis rules includes: research based on decision tree model and association analysis theory Fault judgment and fault classification methods for wind turbines, and establish a fault database and fault judgment rules for wind turbines.

On the other hand, the present invention also provides a gateway device, including a memory, a processor, and a computer program stored on the memory and operable on the processor. When the processor executes the program, any of the above-mentioned described method.

It can be seen from the above that the SCADA-based wind turbine operating state evaluation and fault diagnosis method provided by the present invention can effectively realize the wind turbine operating state evaluation and fault diagnosis.

Description of drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only These are some embodiments of the present invention. Those skilled in the art can also obtain other drawings based on these drawings without creative work.

Fig. 1 is a flow chart of a method for evaluating the operating state and fault diagnosis of a wind turbine based on SCADA according to an embodiment of the present invention.

Detailed ways

In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be described in further detail below in conjunction with specific embodiments and with reference to the accompanying drawings.

The embodiment of the present invention provides a method for evaluating and diagnosing the operating state of a wind turbine based on SCADA. With reference to FIG. 1 , the method includes the following steps:

Step 101, based on the sample data extracted by the SCADA system, research the correlation between the wind turbine operating data and the operating characteristics of the main components.

This step includes: research on wind turbine operating data cleaning and data preprocessing technology based on big data and data mining technology; research on the statistical characteristics of different operating parameters such as wind turbine power, speed, pitch, and wind turbine main bearing temperature and vibration .

Step 102, researching a method for predicting the operating state of wind turbines based on clustering algorithms, cluster analysis and machine learning methods.

This step includes: researching SCADA data modeling technology based on mathematical statistics and machine learning methods, establishing an evaluation model for the operation status of main components such as wind turbine gearboxes, generators, and main shafts; Combined with the statistical characteristics of the wind turbine's stable operating state, fuzzy logic, distance identification and other methods are used to study the fault threshold identification method.

Step 103, study the fault diagnosis method of the wind turbine, adopt the decision tree model and association rule theory, combine the statistical characteristics of the long-term stable operation state of the wind turbine, and study the fault diagnosis rules.

This step includes: analyzing typical fault characteristic parameters of wind turbines, establishing a data mining training/learning sample library; researching wind turbine fault judgment and fault classification methods based on decision tree model and correlation analysis theory, and establishing wind turbine fault database and fault judgment rules.

Those of ordinary skill in the art should understand that: the discussion of any of the above embodiments is exemplary only, and is not intended to imply that the scope of the present disclosure (including claims) is limited to these examples; under the idea of the present invention, the above embodiments or Combinations between technical features in different embodiments are also possible, steps may be carried out in any order, and there are many other variations of the different aspects of the invention as described above, which are not presented in detail for the sake of brevity.

In addition, well-known power/ground connections to integrated circuit (IC) chips and other components may or may not be shown in the provided figures, for simplicity of illustration and discussion, and so as not to obscure the present invention. . Furthermore, devices may be shown in block diagram form in order to avoid obscuring the invention, and this also takes into account the fact that details regarding the implementation of these block diagram devices are highly dependent on the platform on which the invention is to be implemented (i.e. , these details should be well within the understanding of those skilled in the art). Where specific details (eg, circuits) have been set forth to describe example embodiments of the invention, it will be apparent to those skilled in the art that other embodiments may be implemented without or with variations from these specific details. Implement the present invention down. Accordingly, these descriptions should be regarded as illustrative rather than restrictive.

Although the invention has been described in conjunction with specific embodiments of the invention, many alternatives, modifications and variations of those embodiments will be apparent to those of ordinary skill in the art from the foregoing description. For example, other memory architectures such as dynamic RAM (DRAM) may use the discussed embodiments.

Embodiments of the present invention are intended to embrace all such alterations, modifications and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent replacements, improvements, etc. within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims (10)

1. A SCADA-based wind turbine operating state evaluation and fault diagnosis method, characterized in that, comprising: Based on the sample data extracted by the SCADA system, the relationship between the wind turbine operating data and the operating characteristics of the main components is studied; Research on wind turbine operating status prediction methods based on clustering algorithms, cluster analysis and machine learning methods; To study the fault diagnosis method of wind turbines, the fault diagnosis rules are studied by using the decision tree model and the theory of association rules, combined with the statistical characteristics of the long-term stable operation status of wind turbines. 2. the wind turbine operating state evaluation and fault diagnosis method based on SCADA according to claim 1, characterized in that, the sample data extracted based on the SCADA system is used to study the relationship between the wind turbine operating data and the main component operating characteristics include: Research on wind turbine operation data cleaning and data preprocessing technology based on big data and data mining technology. 3. the wind turbine operating state evaluation and fault diagnosis method based on SCADA according to claim 1, characterized in that, the sample data extracted based on the SCADA system is used to study the relationship between the wind turbine operating data and the main component operating characteristics include: Study the statistical characteristics of different operating parameters such as wind turbine power, speed, pitch, and wind turbine main bearing temperature and vibration. 4. the SCADA-based wind turbine operating state evaluation and fault diagnosis method according to claim 1, wherein the wind turbine operating state prediction method based on clustering algorithm, cluster analysis and machine learning method includes: Study the SCADA data modeling technology based on mathematical statistics and machine learning methods, and establish an evaluation model for the operation status of main components such as wind turbine gearboxes, generators, and main shafts. 5. the SCADA-based wind turbine operating state assessment and fault diagnosis method according to claim 1, wherein said research is based on clustering algorithm, cluster analysis and machine learning methods for wind turbine operating state prediction methods comprising: The modeling method of wind turbine operating state under different data time scales is studied. 6. the SCADA-based wind turbine operating state evaluation and fault diagnosis method according to claim 1, wherein the wind turbine operating state prediction method based on clustering algorithm, cluster analysis and machine learning method includes: Combining with the statistical characteristics of the stable operation state of wind turbines, fuzzy logic, distance identification and other methods are used to study the fault threshold identification method. 7. The SCADA-based wind turbine operating state evaluation and fault diagnosis method according to claim 1, wherein the machine learning method comprises: multiple linear regression, neural network, support vector machine. 8. The SCADA-based wind turbine operating state evaluation and fault diagnosis method according to claim 1, characterized in that, said research wind turbine fault diagnosis method adopts decision tree model and association rule theory, combined with long-term stable operation of wind turbines Statistical characteristics of the state, the study of fault diagnosis rules includes: analysis of typical fault characteristic parameters of wind turbines, and establishment of data mining training/learning sample library. 9. The SCADA-based wind turbine operating state evaluation and fault diagnosis method according to claim 1, characterized in that, said research wind turbine fault diagnosis method adopts decision tree model and association rule theory, combined with long-term stable operation of wind turbines Statistical characteristics of the state, research on fault diagnosis rules includes: research on wind turbine fault judgment and fault classification methods based on decision tree model and correlation analysis theory, and establishment of wind turbine fault database and fault judgment rules. 10. A gateway device, comprising a memory, a processor, and a computer program stored on the memory and operable on the processor, characterized in that, when the processor executes the program, it realizes any one of claims 1 to 9. method described in the item.