Unmanned aerial vehicles (UAVs) with high-resolution optical and infrared ( IR ) imaging have been introduced in recent years to perform inexpensive and fast inspections in operation and maintenance activities of solar power plants, reducing the labor needed, while lowering the on-site inspection time. Even though UAVs can acquire images extremely quickly, the analysis of those images is still a time-consuming procedure that should be performed by a trained professional. Therefore, a computer vision approach may be used to accelerate image analysis. In this work, a dataset of IR images was created from a 10-MW solar power plant and a comparative analysis between mask R- convolutional neural network (CNN) and U-Net was performed for two experiments. Concerning the defective module segmentation, the mask R-CNN algorithm achieved a mean average precision at intersection over union (IoU) = 0.50 of 0.96, using augmentation data. Regarding the segmentation and classification of failure type, the algorithm reached a value of 0.88 considering the same evaluation metric and data augmentation. When compared to the U-Net in terms of IoU, the mask R-CNN outperformed it with 0.87 and 0.83 for the first and second experiments, respectively.

The focus of this research is on thermal contact resistance between a mold and its insert, specifically inserts made by additive manufacturing (AM). Using a thermal steady-state system and varying contact pressures (0, 50, 75, and 100 bars), we present experimental results of the thermal contact resistance at the contact interface between steel A (1.2344), obtained from an extruded rod, and steel B (1.2709), produced by laser powder bed fusion. Thermal tests were performed for unbonded and bonded configurations. Results showed that increasing the contact pressure allows the system equilibrium to be reached at lower temperatures. Furthermore, thermal tests showed that in the transition zone of the bonded configuration, a well-defined resistance is not formed between the two steel samples as it occurs in the unbonded configuration. For the unbonded configuration, the thermal contact resistance values decrease with increasing applied contact pressure, improving the system’s heat transfer.