|
Carrasco, M., Alvarez, F., Velazquez, R., Concha, J., & Perez-Cotapos, F. (2019). Brush-Holder Integrated Load Sensor Prototype for SAG Grinding Mill Motor. Electronics, 8(11), 14 pp.
Abstract: One of the most widely used electro-mechanical systems in large-scale mining is the electric motor. This device is employed in practically every phase of production. For this reason, it needs to be inspected regularly to maintain maximum operability, thus avoiding unplanned stoppages. In order to identify potential faults, regular check-ups are performed to measure the internal parameters of the components, especially the brushes and brush-holders. Both components must be properly aligned and calibrated to avoid electric arcs to the internal insulation of the motor. Although there is an increasing effort to improve inspection tasks, most inspection procedures are manual, leading to unnecessary costs in inspection time, errors in data entry, and, in extreme cases, measurement errors. This research presents the design, development, and assessment of an integrated measurement prototype for measuring spring tension and other key parameters in brush-holders used in electric motors. It aims to provide the mining industry with a new, fully automatic inspection system that will facilitate maintenance and checking. Our development research was carried out specifically on the brush system of a SAG grinding mill motor. These machines commonly use SIEMENS motors; however, the instrument can be easily adapted to any motor by simply changing the physical dimensions of the prototype.
|
|
|
Carrasco, M., Mery, D., Concha, A., Velazquez, R., De Fazio, R., & Visconti, P. (2021). An Efficient Point-Matching Method Based on Multiple Geometrical Hypotheses. Electronics, 10(3), 246.
Abstract: Point matching in multiple images is an open problem in computer vision because of the numerous geometric transformations and photometric conditions that a pixel or point might exhibit in the set of images. Over the last two decades, different techniques have been proposed to address this problem. The most relevant are those that explore the analysis of invariant features. Nonetheless, their main limitation is that invariant analysis all alone cannot reduce false alarms. This paper introduces an efficient point-matching method for two and three views, based on the combined use of two techniques: (1) the correspondence analysis extracted from the similarity of invariant features and (2) the integration of multiple partial solutions obtained from 2D and 3D geometry. The main strength and novelty of this method is the determination of the point-to-point geometric correspondence through the intersection of multiple geometrical hypotheses weighted by the maximum likelihood estimation sample consensus (MLESAC) algorithm. The proposal not only extends the methods based on invariant descriptors but also generalizes the correspondence problem to a perspective projection model in multiple views. The developed method has been evaluated on three types of image sequences: outdoor, indoor, and industrial. Our developed strategy discards most of the wrong matches and achieves remarkable F-scores of 97%, 87%, and 97% for the outdoor, indoor, and industrial sequences, respectively.
|
|
|
Rozas Andaur, J. M., Ruz, G. A., & Goycoolea, M. (2021). Predicting Out-of-Stock Using Machine Learning: An Application in a Retail Packaged Foods Manufacturing Company. Electronics, 10(22), 2787.
Abstract: For decades, Out-of-Stock (OOS) events have been a problem for retailers and manufacturers. In grocery retailing, an OOS event is used to characterize the condition in which customers do not find a certain commodity while attempting to buy it. This paper focuses on addressing this problem from a manufacturer’s perspective, conducting a case study in a retail packaged foods manufacturing company located in Latin America. We developed two machine learning based systems to detect OOS events automatically. The first is based on a single Random Forest classifier with balanced data, and the second is an ensemble of six different classification algorithms. We used transactional data from the manufacturer information system and physical audits. The novelty of this work is our use of new predictor variables of OOS events. The system was successfully implemented and tested in a retail packaged foods manufacturer company. By incorporating the new predictive variables in our Random Forest and Ensemble classifier, we were able to improve their system’s predictive power. In particular, the Random Forest classifier presented the best performance in a real-world setting, achieving a detection precision of 72% and identifying 68% of the total OOS events. Finally, the incorporation of our new predictor variables allowed us to improve the performance of the Random Forest by 0.24 points in the F-measure.
|
|