Laser-Powder Bed Fusion (L-PBF) of metallic parts is a highly multivariate process. An understanding of powder feedstock properties is critical to ensure part quality. In this paper, a detailed examination of two commercial stainless steel 316L powders produced using the gas atomization process is presented. In particular, the effects of the powder properties (particle size and shape) on the powder rheology were examined. The results presented suggest that the powder properties strongly influence the powder rheology and are important factors in the selection of suitable powder for use in an additive manufacturing (AM) process. Both of the powders exhibited a strong correlation between the particle size and shape parameters and the powder rheology. Optical microscope images of melt pools of parts printed using the powders in an L-PBF machine are presented, which demonstrated further the significance of the powder morphology parameters on resulting part microstructures.

Multiple sensor monitoring of machining was investigated for online cutting tool life assessment through cognitive decision making based on signal processing for feature extraction and pattern recognition. Sensor signals obtained from sensor monitoring of turning operations were processed and analysed. The outcome was a set of extracted signal features correlated with the consumed tool life percentage. The aim of the work is to build an online cognitive system, based on artificial neural networks, able to predict the consumed tool life during turning operations. A preliminary experimental campaign was carried out for the construction of the sensorial knowledge database; the neural network type, architecture and training algorithm

Polishing processes are to date gradually evolving from basically manual operations to automated processes. To achieve more accurate, steadfast and dependable automated polishing processes, sensor monitoring offers as a creditable tool for process and product quality control. In this study, an acoustic emission sensor monitoring system was employed for surface roughness assessment during robot assisted polishing of steel bars. After sensor signal pre-processing, feature extraction procedures were applied to the conditioned acoustic emission signals. The scope was to extract relevant signal features to input to pattern recognition paradigms in order to identify correlations between process generated acoustic emission and polished workpiece surface roughness

Cutting force sensor monitoring and wavelet decomposition signal processing were implemented for feature extraction and pattern recognition of chip form typology during turning of 1045 carbon steel. The wavelet packet transform was applied for the analysis of the detected cutting force signals by representing them in a time-frequency domain and providing for the extraction of wavelet packet statistical features. The latter were used to construct wavelet packet feature vectors, ranked according to the number of overlapping elements related to favourable or unfavourable chip forms that cause noise in the pattern recognition procedure (lower number, lower noise, higher rank). The eight highest ranked wavelet packet feature vectors were selected as inputs to a neural network decision-making system on chip form acceptability. Subsequently, a data refinement procedure was employed to improve the neural network performance in the chip form identification process

On-line residual stress assessment in turning of Inconel 718 was carried out through multiple sensor monitoring based on cutting force, acoustic emission and vibration signals acquisition and analysis. The detected sensor signals were processed by the wavelet packet transform technique to extract statistical features from the packet coefficients for the construction of wavelet feature vectors. The latter were used for sensor fusion pattern recognition through neural network data processing grounded on X-ray diffraction residual stress measurements on the turned part surface. The scope of the sensory data fusion approach was to achieve a robust scheme for multi-sensor monitoring decision making on machined surface integrity in terms of residual stress level acceptability