Wind turbine blades are the most critical components of wind turbines. Full-scale blade fatigue testing is required to verify that the blades possess the strength and service life specified in the design. Unfortunately, the test must be run for a long time period. This problem led the blade testing laboratories to accelerate fatigue testing time. To achieve the objective, this thesis proposes two novel methods called STFT- and WT-based fatigue damage part extracting methods which are based on short-time Fourier transform (STFT) and wavelet transform (WT), respectively. For WT, different wavelet functions which are Morl, Meyr, Dmey, Mexh and DB30 are studied. \n \nAn aerodynamic computer code, HAWTsimulator, based on blade element momentum theory has been developed. This code is used to generate the sets of aerodynamic loads acting along the span of a ‘SERI-8 wind turbine blade’ in the range of wind speed from cut-in to cut-out. SERI-8 blades are installed on 65 kW wind turbines. Each set of aerodynamic loads is applied on the finite element model of the SERI-8 blade in structural software (ANSYS) to generate a plot of von Mises stress at the critical point on the blade versus wind speed. By relating this relationship to the wind speed data, the stress-time history at the critical point on the SERI-8 blade can be generated. It has the same sampling rate and length as the wind speed data. \n \nA concept of applying accumulative power spectral density (AccPSD) distribution with time to identify fatigue damage events contained in the stress-time history has been introduced in this thesis. For STFT, AccPSD is the sum of power spectral density (PSD) of each frequency band at each time interval in the spectrogram. For WT, AccPSD is the sum of PSD of wavelet coefficients of each scale at each time interval in the scalogram. It has been found that the locations of AccPSD spikes imply where the fatigue damage events are. Based on an appropriate AccPSD level called a cutoff level, the fatigue damage events can be identified at time location of the stress-time history. \n \nA fatigue computer code, HAWTfatigue, based on stress-life approach and Miner’s linear cumulative damage rule has been developed. Basically, the code is used for evaluating the fatigue damage and service lifetime of horizontal axis wind turbine blade. In addition, the author has implemented STFT- and WT-based fatigue damage part extracting methods into the code. Fatigue damage parts are extracted from the stress time history and they are concatenated to form the edited stress-time history. The effectiveness of STFT- and WTbased algorithms is performed by comparing the reduction in length and the difference in fatigue damage per repetition of the edited stress-time histories generated by STFT and WT to those of the edited stress-time history generated by an existing method, Time Correlated Fatigue Damage (TCFD) used by commercial software. \n \nThe findings of this research project are as follows: \n \n1. The comparison of the reduction in length of the edited stress-time histories generated by TCFD, STFT and WT indicates that WT with the Mexh wavelet has the maximum reduction of 20.77% in length with respect to the original length, followed by Meyr (20.24%), Dmey (19.70%), Morl (19.66%), DB30 (19.19%), STFT (15.38%), and TCFD (10.18%), respectively. \n \n2. The comparison of the retained fatigue damage per repetition in the edited stress-time histories generated by TCFD, STFT and WT indicates that TCFD has the retained fatigue damage per repetition less than the original fatigue damage per repetition by 0.076%, followed by Mexh (0.068%), DB30 (0.063%), STFT (0.045%), Meyr (0.032%), Dmey (0.014%), and Morl (0.013%), respectively. \n \n3. Both comparison of reduction in length and comparison in the retained fatigue damage per repetition of the edited stress-time histories suggest that WT is the best method for extracting fatigue damage parts from the given stress-time history. It has also been indicated that not only do STFT and WT improve accuracy of fatigue damage per repetition retained in the edited stress-time histories, but also they provide the length of the edited stress-time histories shorter than TCFD does. Thus, STFT and WT are useful methods for performing accelerated fatigue tests. \n \n4. It has been found that STFT is controlled by two main factors which are window size and cutoff level. Also, WT is controlled by three main factors which are wavelet decomposition level, cutoff level and wavelet type. \n \nTo conclude, the edited stress-time history can be used by blade testing laboratories to accelerate fatigue testing time. STFT- and WT-based fatigue damage part extracting methods proposed in this thesis are suggested as alternative methods in accelerating fatigue testing time, especially for the field of wind turbine engineering.
15
