A novel small-scale wind-turbine blade failure detection according to monitored-data

Small-scale wind turbines, at times of their operation, will not be able to work properly and these moments are called equipment downtime. To reduce this downtime, periodic maintenance is necessary. However, this periodic maintenance will cause the equipment to be out of service for a period of time. Therefore, it is essential to monitor the conditions and analyze the data of this equipment, to prevent major damage and failure. This paper introduces a method for estimating blade damage in small-scale wind turbines, using real data. According to this method, data filtering is done initially to remove the outlier data. Then these data have been taken to the frequency domain and finally, the failure of small-scale wind turbine blade in whole condition of the apparatus as well as all its blades has been evaluated. By examining the results in different sections and comparing these results with each other, the performance of the proposed procedure has been validated. Also, this procedure is completely based on logic and mathematical analysis and is far from human error. Accordingly, it has high performance accuracy. The results highlight the significant impact of cracks on torsional modes compared to flap-wise bending modes, with torsional failures occurring at higher frequencies. Additionally, strain gauge signals demonstrate superior accuracy in identifying failure modes over accelerometer signals. These findings provide valuable insights into mode-specific impacts and the effectiveness of monitoring techniques for accurate fault detection.