Blade Structure Fault Diagnosis By Using Fuzzy System Theory

As the lifting and control surface, the helicopter rotor once failure would cause seriousconsequences. If the blade structure had a significant injury, it would results in a helicopter crash.Therefore, it has important theoretical and practical value to research the blade structure faultdiagnosis. With the development of artificial intelligence, computational Intelligence is widely used inthe field of fault diagnosis because of its unique advantages, such as intelligence and parallelism.In this paper, the object of study is composite blades. In order to research the key technology ofdiagnosing the blades’ crack fault, the following works were done.1.On the basis of a comprehensive analysis of the blade crack-related home and abroadresearches, introduce the concept of the blade crack density to divide composite blade crack faultlevel and apply it to the process of establishing the genetic fuzzy system. This parameter is moreaccurate and intuitive than conventional injury express characterized by elastic modulus2.After compare the pros and cons of the current main methods of crack modeling, we completedthe establishment of crack blade model using solid modeling method and the analysis of the changesof the top ten natural frequencies in composite blades with different positions and different crackdensity.3.Because of the complexity and uncertainty of the input and output data in the progress of faultdiagnosis, this article introduced the fuzzy theory into the blade structure fault diagnosis system,combining fuzzy systems toolbox and programming languages to build paddle crack damageidentification fuzzy logic system in the MATLAB environment, added the finite element numericalexample impacted by noise data, and verified the accuracy and stability of the fuzzy logic system bythe success rate of fault damage identification.4.The genetic algorithm is used to reduce the dependence of fuzzy inference system onexpertise.In this study,the GA optimizes the fuzzy logic system preliminarily,what means,optimizedthe rules of fuzzy system rule base one by one, completed automatically generate process of the fuzzyrules combine with genetic algorithms)And simulation examples show that this optimized system hasbetter performance.