Deep learning with mixup augmentation for improved pore detection during additive manufacturing.

In additive manufacturing (AM), process defects such as keyhole pores are difficult to anticipate, affecting the quality and integrity of the AM-produced materials. Hence, considerable efforts have aimed to predict these process defects by training machine learning (ML) models using passive measurements such as acoustic emissions. This work considered a dataset in which keyhole pores of a laser powder bed fusion (LPBF) experiment were identified using X-ray radiography and then registered both in space and time to acoustic measurements recorded during the LPBF experiment. Due to AM's intrinsic process controls, where a pore-forming event is relatively rare, the acoustic datasets collected during monitoring include more non-pores than pores. In other words, the dataset for ML model development is imbalanced. Moreover, this imbalanced and sparse data phenomenon remains ubiquitous across many AM monitoring schemes since training data is nontrivial to collect. Hence, we propose a machine learning approach to improve this dataset imbalance and enhance the prediction accuracy of pore-labeled data. Specifically, we investigate how data augmentation helps predict pores and non-pores better. This imbalance is improved using recent advances in data augmentation called Mixup, a weak-supervised learning method. Convolutional neural networks (CNNs) are trained on original and augmented datasets, and an appreciable increase in performance is reported when testing on five different experimental trials. When ML models are trained on original and augmented datasets, they achieve an accuracy of 95% and 99% on test datasets, respectively. We also provide information on how dataset size affects model performance. Lastly, we investigate the optimal Mixup parameters for augmentation in the context of CNN performance.

Spectral energy scattering and targeted energy transfer in phononic lattices with local vibroimpact nonlinearities.

We propose a method for manipulating wave propagation in phononic lattices by employing local vibroimpact (VI) nonlinearities to scatter energy across the underlying linear band structure of the lattice, and transfer energy from lower to higher optical bands. First, a one-dimensional, two-band phononic lattice with embedded VI unit cells is computationally studied to demonstrate that energy is scattered in the wave number domain, and this nonlinear scattering mechanism depends on the energy of the propagating wave. Next, a four-band lattice is studied with a similar technique to demonstrate the concept of nonresonant interband targeted energy transfer (IBTET) and to establish analogous scaling relations with respect to energy. Both phononic lattices are shown to exhibit a maximum energy transfer at moderate input energies, followed by a power-law decay of relative energy transfer either to the wave number domain or between bands on input energy. Last, the nonlinear normal modes (NNMs) of a reduced order model (ROM) of a VI unit cell are computed with the method of numerical continuation to provide a physical interpretation of the IBTET scaling with respect to energy. We show that the slope of the ROM's frequency-energy evolution for 1:1 resonance matches well with IBTET scaling in the full lattice. Moreover, the phase-space trajectories of the NNM solutions elucidate how the power-law scaling is related to the nonlinear dynamics of the VI unit cell.

Low-cost double pendulum for high-quality data collection with open-source video tracking and analysis.

The double pendulum is a system that manifests fascinating non-linear behavior. This made it a popular tool in academic settings for illustrating the intricate response of a seemingly simple physical apparatus, or to validate tools for studying nonlinear phenomena. In addition, the double pendulum is also widely used in several modeling applications including robotics and human locomotion analysis. However, surprisingly, there is a lack of a thoroughly documented hardware that enables designing, building, and reliably tracking and collecting data from a double pendulum. This paper provides comprehensive documentation of a research quality bench top double pendulum. The contributions of our work include (1) providing detailed CAD drawings, part lists, and assembly instructions for building a low friction double pendulum. (2) A new tracking algorithm written in Python for tracking the position of both links of the double pendulum. This algorithm measures the angles of the links by examining each frame, and computes uncertainties in the measured angles by following several trackers on each link. Additionally, our tracking algorithm bypasses the data transmission difficulties caused by instrumenting the bottom link with physical sensors. (3) A derivation of the equations of motion of the actual physical system. (4) A description of the process (with provided Python code) for extracting the model parameters-e.g., damping-with error bounds from physical measurements.