Performance Analysis And Health Status Evaluation Of Wind Turbines Based On SCADA Data

Wind power has been paid more and more attention to its technical and economic advantages in the new energy fie ld.However,the high cost of operation and maintenance has seriously restricted the development of wind power industry.The large scale and complex structure of wind turbine make the performance evaluation of the wind turbine become very important,and it is also the key to ensure long-term stable operation and safe power generation.Power equipment has experienced from the init ial failure repair,preventive maintenance,to today's predictive maintenance process.Accurate and reliable equip ment health assessment is the prerequis ite and key to imple ment this kind of maintenance system.Carrying out health status assessment of wind turbines,making prejudgment about the health trend of the unit according to the results of the assessment,adjusting and arranging the maintenance operation properly,which are of great significance to improve the safety and reliability of the wind turbine operation and reduce the cost of operation and maintenance.So this article mainly carry on the research from two aspects,performance analysis and health state evaluation of wind turbine,carried out the following work.1)The performance of the wind turbine has a direct impact on the safety production and economic benefit of the wind farm.The output power is one of the most important and representative performance indexes of the wind turbine.The wind power curve is the most direct expression of its electricity-generating capacity.With the output power and wind speed as the data source,the characteristic value of cloud model is used to study the fluctuation characteristics of output power,which is beneficial to learning the production status of the wind turbine.Based on the data sieving of the wind speed and power data collected by wind turbine SC ADA system,a scatter plot is drawn to describe the wind speed and power in the normal working state of the wind turbine,and the actual wind power curve of wind turbine is established by method of bins.The overall power cloud of different units can be obtained through the statistical analysis of the output power of different wind speed ranges and the construction of the cloud model of output power at different wind speeds using the reverse cloud generator.The output power size,the fluctuation range and the degree of dispersion are analyzed through comparing the characteristic value of the power cloud.At the same time,the correlation coefficients of wind speed and power are calculated to reflect and evaluate the sensitivity of the wind turbine response.The application of cloud model allows the evaluation of unit state to develop from a qualitative one to a quantitative one,from a macro comprehensive assessment to the precise assessment based on different wind speed range segments.In this way,it improves the accuracy of wind turbine performance analysis and comprehensiveness.2)As a result of the poor and variable operating environment of wind turbine,and the complex fault mechanisms,the health status assessment has obvious characteristics of fuzziness and randomness.At present,the determination of membership function in fuzziness evaluation is subjective and does not consider the randomness.To solve this problem,this paper presents a method of health status assessment of wind turbine based on combination weighting and cloud model.Based on establishment of health state evaluation index system and healt h status classification of wind turbine,the weight of each index is determined with the combination weighting method,while the membership degree of each state grade is determined with the membership cloud model.The comprehensive evaluation of the health status of the wind turbine is carried out by using the method of stratified evaluation.Finally,an applied example is used to prove the effectiveness and reliability of the algorithm.