Delamination in Wind Turbine Blades (WTB) is a common structural problem that can generate large costs. Delamination is the separation of layers of a composite material, which produces points of stress concentration. These points suffer greater traction and compression forces in working conditions, and they can trigger cracks, and partial or total breakage of the blade. Early detection of delamination is crucial for the prevention of breakages and downtime. The main novelty presented in this paper has been to apply an approach for detecting and diagnosing the delamination WTB. The approach is based on signal processing of guided waves, and multiclass pattern recognition using machine learning. Delamination was induced in the WTB to check the accuracy of the approach. The signal is denoised by wavelet transform. The autoregressive Yule–Walker model is employed for feature extraction, and Akaike’s information criterion method for feature selection. The classifiers are quadratic discriminant analysis, k-nearest neighbors, decision trees, and neural network multilayer perceptron. The confusion matrix is employed to evaluate the classification, especially the receiver operating characteristic analysis by: recall, specificity, precision, and F-score.

There is a significant rising in development of new concentrated solar plants due to global energy demands. Concentrated solar plant requires to improve the operational and maintainability in this industry. This article presents a new approach to identify defects in the solar receiver tubes and welds employing a simple electromagnetic acoustic transducer. The absorber tubes in normal working conditions must withstand high temperatures, which can cause the tubes to deteriorate in areas such as welding, or it can cause hot spots due to defects or corrosion. A proper predictive maintenance program for the absorber pipes is required to detect defects in the tubes at an early stage, reducing corrective maintenance costs and increasing the reliability, availability, and safety of the concentrated solar plant. This article presents a novel approach based on signal processing and pattern recognition for predictive maintenance employing electromagnetic acoustic transducers. Hilbert transform is used to obtain the envelope of the signal that is smoothed by wavelet transform. It reduces the probability of detecting false-positive alarms. The algorithm uses the distance of the sensors from the edges to perform a self-identification of signal events. The events are located using two possible ways of ultrasound propagation, forward and reverse, and the time of flight of each echo. The algorithm correlates the theoretical events with events found experimentally. These echoes could come from different paths due to the electromagnetic acoustic transducer that generates forward and reverse shear waves. The main novelty in this approach is that the detection and location of the defect is determined considering two echoes that come from the same defect, but they arrive at the sensor flowing by different paths. The results are obtained with a double validation by matching the echoes that meet certain conditions. It increases the accuracy of the inspection and reduces false alarms. The approach has been tested and validated in an experimental platform that simulates the concentrated solar plants.