Defects are a leading issue for the rejection of parts manufactured through the Directed Energy Deposition (DED) Additive Manufacturing (AM) process. In an attempt to illuminate and advance in situ quality monitoring and control of workpieces, we present an innovative data-driven method that synchronously collects sensing data and AM process parameters with a low sampling rate during the DED process. The proposed data-driven technique determines the important influences that individual printing parameters and sensing features have on prediction at the inter-layer qualification to perform feature selection. Three Machine Learning (ML) algorithms including Random Forest (RF), Support Vector Machine (SVM), and Convolutional Neural Network (CNN) are used. During post-production, a threshold is applied to detect low-density occurrences such as porosity sizes and quantities from CT scans that render individual layers acceptable or unacceptable. This information is fed to the ML models for training. Training/testing are completed offline on samples deemed “high-quality” and “low-quality”, utilizing only features recorded from the build process. CNN results show that the classification of acceptable/unacceptable layers can reach between 90% accuracy while training/testing on a “high-quality” sample and dip to 65% accuracy when trained/tested on “low-quality”/“high-quality” (respectively), indicating over-fitting but showing CNN as a promising inter-layer classifier.

The aye-aye (Daubentonia madagascariensis) is best known for its unique acoustic-based foraging behavior called 'tap-scanning' or 'percussive foraging'. The tap-scanning is a unique behavior allowing aye-aye to locate small cavities beneath tree bark and extract wood-boring larvae from it. The tap-scanning requires the animal auditory system to have exceptional acoustic near-field sensitivity. This paper has experimentally investigated the effects of external pinna in the acoustic sensing and detection capabilities of aye-ayes. To experimentally evaluate the effects of external ear (pinna) of the aye-aye, the tap-scanning process was simulated using a robotic arm. A pinna was 3D printed using a CT scan obtained from a carcass. The pinna's effect on the acoustic near-field has been evaluated in time and frequency domains for simulated tap-scanning with the pinna in upright and cupped positions. The idea comes from the morphological trait of the aye-aye where the animal uses its ears this way. The results suggest that the aye-aye can substantially enhance its acoustic near-field sensitivity through a cupped conformation during tap-scanning. Three phenomena contribute to this substantial enhancement of the acoustic near-field: (i) a considerable increase in the signal-to-noise ratio, (ii) the creation of a focal area and potentially a focal point to increase the spatial resolution, and (iii) an increase in the receiver peak frequency by changing near-field beam pattern for higher frequencies that can result in greater sensitivity due to a smaller wavelength.

This journal paper explores the application of Deep Learning (DL)-based Time-Series Classification (TSC) algorithms in ultrasonic testing for pipeline inspection. The utility of Electromagnetic Acoustic Transducers (EMAT) as a non-contact ultrasonic testing technique for compact robotic platforms is emphasized, prioritizing computational efficiency in defect detection over pinpoint accuracy. To address limited sample availability, the study conducts benchmarking of four methods to enable comparative evaluation of classification times. The core of the DL-based TSC approach involves training DL models using varied proportions (60%, 80%, and 100%) of the available training dataset. This investigation demonstrates the adaptability of DL-enabled anomaly detection with shifting data sizes, showcasing the AI-driven process's robustness in identifying pipeline irregularities. The outcomes underscore the pivotal role of artificial intelligence (AI) in facilitating semi-accurate but swift anomaly detection, thereby streamlining subsequent focused inspections on pipeline areas of concern. By synergistically integrating EMAT technology and DL-driven TSC, this research contributes to enhancing the precision and near real-time inspection capabilities of pipeline assessment. This investigation collectively highlights the potential of DL networks to revolutionize pipeline inspection by rapidly and accurately analyzing ultrasound waveform data.