ALBERT

Description: This work presents a new methodology for machine tools anomaly detection via operational data processing. The previous methodology has been field tested on a milling-boring machine in a real production environment. This paper also describes the data acquisition process, as well as the technical architecture needed for data processing. Subsequently, a technique for operational machine data segmentation based on dynamic time warping and hierarchical clustering is introduced. The formerly mentioned data segmentation and analysis technique allows for machine tools anomaly detection thanks to comparison between near real-time machine operational information, coming from strategically positioned sensors and outcomes collected from previous production cycles. Anomaly detection techniques shown in this article could achieve significant production improvements: “zero-defect manufacturing”, boosting factory efficiency, production plans scrap minimization, improvement of product quality, and the enhancement of overall equipment productivity.

Description: Rapid developments in the field of underwater photogrammetry have given scientists the ability to produce accurate 3D models which are now increasingly used in the representation and study of local areas of interest. This paper addresses the lack of systematic analysis of 3D reconstruction and navigation fusion strategies, as well as associated error evaluation of models produced at larger scales in GPS-denied environments using a monocular camera (often in deep sea scenarios). Based on our prior work on automatic scale estimation of SfM-based 3D models using laser scalers, an automatic scale accuracy framework is presented. The confidence level for each of the scale error estimates is independently assessed through the propagation of the uncertainties associated with image features and laser spot detections using a Monte Carlo simulation. The number of iterations used in the simulation was validated through the analysis of the final estimate behavior. To facilitate the detection and uncertainty estimation of even greatly attenuated laser beams, an automatic laser spot detection method was developed, with the main novelty of estimating the uncertainties based on the recovered characteristic shapes of laser spots with radially decreasing intensities. The effects of four different reconstruction strategies resulting from the combinations of Incremental/Global SfM, and the a priori and a posteriori use of navigation data were analyzed using two distinct survey scenarios captured during the SUBSAINTES 2017 cruise (doi: 10.17600/17001000). The study demonstrates that surveys with multiple overlaps of nonsequential images result in a nearly identical solution regardless of the strategy (SfM or navigation fusion), while surveys with weakly connected sequentially acquired images are prone to produce broad-scale deformation (doming effect) when navigation is not included in the optimization. Thus the scenarios with complex survey patterns substantially benefit from using multiobjective BA navigation fusion. The errors in models, produced by the most appropriate strategy, were estimated at around 1 % in the central parts and always inferior to 5 % on the extremities. The effects of combining data from multiple surveys were also evaluated. The introduction of additional vectors in the optimization of multisurvey problems successfully accounted for offset changes present in the underwater USBL-based navigation data, and thus minimize the effect of contradicting navigation priors. Our results also illustrate the importance of collecting a multitude of evaluation data at different locations and moments during the survey.