Search

Fault detection in induction motors operated by inverters is an actual industrial need. Most line-fed machines are being replaced by inverter-fed drives, due to their improved speed regulation, and fast dynamic response, despite the insertion of undesired harmonics. Under this particular operating condition, most of the detection techniques so far developed are unable to distinguish induction motor faults. This paper presents a detection methodology based on the combined use of two techniques: Complete Ensemble Empirical Mode Decomposition and the Multiple Signal Classification. The proposed methodology is applied to an inverter-fed induction motor during a start-up followed by a steady-state regime, where it is verified its capability to identify a single broken rotor bar, mixed eccentricity in the form of motor-load misalignment, and the combination of both faults. From the experimental results, the proposed methodology is proven to be sensitive enough to detect the fault evolution in the time-frequency plane of single and combined faults under different operating regimes (start-up and steady-state) in inverter-fed induction motor.

Over the course of the last two decades, continuous advances in the stereo vision field have been documented. In this paper we present an analysis of the efficiency for the stereo vision algorithm of the Census Transform algorithm. In addition to the conventional correlation method based on Hamming distance minimization, we use two similarity measures: the Tanimoto and the Dixon-Koehler distances. Then, we compare its performance in terms of accuracy and hardware resources needed for implementation. These comparisons are performed by introducing a generalized model for each hardware architecture, scalable depending on design parameters such as Census Transform window size and maximum disparity range.

In order to optimize the movements of a robot, every object found in the work environment must not just be identified, but located in reference to the robot itself. Usually, object segmentation from an image is achieved using color segmentation. This segmentation can be achieved by processing the R, G and B chromatic components. However, this method has the disadvantage of been very sensitive to the changes on lighting. Converting the RGB image to the CIE-Lab color space avoids the lack of sensitivity by increasing the accuracy of the color segmentation. Unfortunately, if multiple objects of the same color are presented in the scene, is not possible to identify one of these objects using only this color space. Therefore, we need to consider an additional data source, in this case the depth, in order to discriminate objects that are not in the same plane as the object of interest. In this paper, we introduce an algorithm to detect objects, essentially on indoor environments, using CIE-Lab and depth segmentation techniques. We process the color and depth images provided by the Kinect sensor for proposing a visual strategy with real-time performance