1,721,035 research outputs found
Experimental variability of track to ground conductance measurements
No full textTo fulfil IEC 62128-2 (EN 50122-2) standard stray current requirements, the new or revamped DC electrified transportation systems shall achieve very good levels of track to ground insulation. This insulation shall be witnessed, usually in construction phases, by means of accurate measurement. Some measurement techniques are suggested by IEC 62128-2 standard but literature leaks about considerations about their measurement uncertainty. The paper purpose is to fill this gap and analyse the variability of track to ground conductance measurements
Computationally Light Algorithms for Tactile Sensing Signals Elaboration and Classification
No full textTactile sensing systems require embedded processing to extract structured information in many application domains as prosthetics and robotics. In this regard, this paper proposes computationally light strategies to pre-process the sensor signals and extract features, feeding single layer feed-forward neural networks (SLFNNs) that proved good generalization performance keeping low the computational cost. We validate our proposal by integrating a tactile sensing system on a Baxter robot to collect and classify data from three objects of different stiffness. We compare different features extraction techniques and five SLFNNs to show the trade-off between generalization accuracy and computational cost of the whole processing unit. The results show that the processing unit that extracts the mean and standard deviation features from signals and adopts a fully connected neural network (FCNN) with 50 neurons and ReLu activation function achieves a high accuracy (94.4%) in the 3-class classification problem with a low computational cost, leading to the deployment on a resource-constrained device
A Novel Tactile Sensing System for Robotic Tactile Perception of Object Properties
No full textTactile sensing has become crucial in robotic applications such as
teleoperation, as it gives information about the object properties that cannot be
perceived by other senses. In fact, it is essential that robots are equipped with
advanced touch sensing in order to be aware of their surroundings and give a
feedback to an operator. Such sensing system are made of sensors and an elaboration unit that acquires tactile signals and process the data, retrieving information such as texture, hardness, and shape. In this paper, we propose a novel
tactile sensing system made of flexible, high sensitive and high spatial resolution piezoelectric polyvinylidene fluoride‐trifluoroethylene P(VDF-TrFE) sensors, and a low power and low cost Interface Electronics (IE) that can acquire
data from 32 channels simultaneously with a sampling frequency of
2kSamples/s. We validate the system acquiring data from three different objects
to classify their hardness using an artificial neural networks of one hidden layer
with approximately 89% accuracy. The signal processing and the classifier will
be hosted by the IE in the next future
Balance of distribution of some transition metals between the (M',M")B and (M',M")2B phases
No full text
Distribution of chromiun and nickel between the phases present in the borided layer of alloy steels
No full text- …
