AN AUTOMATIC INSPECTION SYSTEM FOR DIMENSIONAL AND QUALITY CONTROL OF WIND TURBINE BLADES IN A FACTORY ENVIRONMENT THROUGH COMPUTER VISION
Abstract - The blades are considered the main components in the design of a wind turbine and they have the function of capturing wind energy and later converting it into rotational energy on the axis of the wind turbine. The huge structures that make up the blades make manufacturing and inspection difficult and this leads to the search for innovative methods capable of improving product quality. This work proposes the application of an automatic inspection system for dimensional and quality control of wind turbine blades in a factory environment through Computer Vision. The motivation of this work is related to the need to modernize the measurement and inspection systems of wind blades in a factory environment. The proposed system is applied in the evaluation of images captured during the process of measuring the dry paint thickness of the protective coating of the blades. The thickness measurement is performed right after the blades painting process and inside the factory environment. A database of 151 images is evaluated and their results are presented and discussed. The results are analyzed to evaluate the performance of the system in improving the measurement process, in terms of reliability and accuracy. The main contribution of this work is the development of an automatic image analysis system, able to measure the thickness of dry paint applied to wind blades with an accuracy percentage of 97.35 % when compared to the gold standard and considering an admissible error of up to 5% for the wind blade painting process.
Keywords - Computer Vision, Wind Turbine Blade, Automatic Image Analysis, Dry Paint Thickness.