Additive manufacturing (AM) has gained increasing attention over the past years due to its fast prototype, easier modification, and possibility for complex internal texture devices when compared to traditional manufacture processing. However, potential internal defects are occurring during AM processes, and it requires real-time inspections to minimize the costs by either aborting the processing or repairing the defect. In order to perform the defects inspection, first the defects database NEU-DET is used for training. Then, a convolution neural network (CNN) is applied to perform defects classification. For real-time purposes, Field Programmable Gate Arrays (FPGAs) are utilized for acceleration. A binarized neural network (BNN) is proposed to best fit the FPGA bit operations. Finally, for the image labeled with defects, the selective search and non-maximum algorithms are implemented to help locate the coordinates of defects. Experiments show that the BNN model on NEU-DET can achieve 97.9% accuracy in identifying whether the image is defective or defect-free. As for the image classification speed, the FPGA-based BNN module can process one image within 0.5 s. The BNN design is modularized and can be duplicated in parallel to fully utilize logic gates and memory resources in FPGAs. It is clear that the proposed FPGA-based BNN can perform real-time defects inspection with high accuracy and it can easily scale up to larger FPGA implementations.

No abstract

Unmanned Aerial Vehicles (UAVs, also known as drones) have become increasingly appealing with various applications and services over the past years. Drone-based remote sensing has shown its unique advantages in collecting ground-truth and real-time data due to their affordable costs and relative ease of operability. This paper presents a 3D placement scheme for multi-drone sensing/monitoring platforms, where a fleet of drones are sent for conducting a mission in a given area. It can range from environmental monitoring of forestry, survivors searching in a disaster zone to exploring remote regions such as deserts and mountains. The proposed drone placing algorithm covers the entire region without dead zones while minimizing the number of cooperating drones deployed. Naturally, drones have limited battery supplies which need to cover mechanical motions, message transmissions and data calculation. Consequently, the drone energy model is explicitly investigated and dynamic adjustments are deployed on drone locations. The proposed drone placement algorithm is 3D landscaping-aware and it takes the line-of-sight into account. The energy model considers inter-communications within drones. The algorithm not only minimizes the overall energy consumption, but also maximizes the whole drone team’s lifetime in situations where no power recharging facilities are available in remote/rural areas. Simulations show the proposed placement scheme has significantly prolonged the lifetime of the drone fleet with the least number of drones deployed under various complex terrains.