Search results for "NEURAL NETWORK"
showing 10 items of 1385 documents
Dynamic Preisach Hysteresis Model for Magnetostrictive Materials for Energy Application
2013
In this paper the magnetostrictive material considered is Terfenol-D. Its hysteresis is modeled by applying the DPM whose identification procedure is performed by using a neural network procedure previously publised [. The neural network used is a multiplayer perceptron trained with the Levenberg-Marquadt training algorithm. This allows to obtain the Preisach distribution function, without any special conditioning of the measured data, owing to the filtering capabilities of the neural network interpolators. The model is able to reconstruct both the magnetization relation and the Field-strain relation. The model is validated through comparison and prediction of data collected from a typical …
Autoencoders and Recurrent Neural Networks Based Algorithm for Prognosis of Bearing Life
2018
Bearings are one of the most critical components in electric motors, gearboxes and wind turbines. Therefore, bearing fault detection and prognosis of remaining useful life are important to prevent productivity losses. In this study, a novel method is proposed for prognosis of bearing life using an autoencoder and recurrent neural networks-based prediction algorithm. Promising results have been obtained from the experimental data. A monotonic upward trend of the produced health indicator is obtained for all test cases, being one of critical indicators of a proper prognosis. The remaining useful life estimation is moderately accurate under a limited data.
CNN based Gearbox Fault Diagnosis and Interpretation of Learning Features
2021
Machine learning based fault diagnosis schemes have been intensively proposed to deal with faults diagnosis of rotating machineries such as gearboxes, bearings, and electric motors. However, most of the machine learning algorithms used in fault diagnosis are pattern recognition tools, which can classify given data into two or more classes. The underlined physical phenomena in fault diagnosis are not directly interpretable in machine learning schemes, thus it is usually called black/gray box models. In this study, convolutional neural networks (CNN) machine learning algorithm is proposed to classify gearbox faults, and the learning features of the CNN filters are visualized to understand the…
Automatic detection of thermal anomalies in induction motors
2021
The paper proposes a methodology based on Artificial Intelligence techniques for the automatic detection of abnormal thermal distributions in electric motors, to rapidly identify pre-faults or fault conditions. The proposed approach, applied to induction motors of different sizes, installed in waterworks plants, is based on the execution of Thermographic Non-Destructive Tests, which allow identifying abnormal operating conditions without interrupting the ordinary working conditions of the system. Thermographic images of induction motors are acquired at the installation site and with perspectives visible to the operator, which are sometimes partially obstructed. These thermographic images ar…
Training Artificial Neural Networks With Improved Particle Swarm Optimization
2020
Particle Swarm Optimization (PSO) is popular for solving complex optimization problems. However, it easily traps in local minima. Authors modify the traditional PSO algorithm by adding an extra step called PSO-Shock. The PSO-Shock algorithm initiates similar to the PSO algorithm. Once it traps in a local minimum, it is detected by counting stall generations. When stall generation accumulates to a prespecified value, particles are perturbed. This helps particles to find better solutions than the current local minimum they found. The behavior of PSO-Shock algorithm is studied using a known: Schwefel's function. With promising performance on the Schwefel's function, PSO-Shock algorithm is util…
An Embedded Fingerprints Classification System based on Weightless Neural Networks
2009
Automatic fingerprint classification provides an important indexing scheme to facilitate efficient matching in large-scale fingerprint databases in Automatic Fingerprint Identification Systems (AFISs). The paper presents a new fast fingerprint classification module implementing on embedded Weightless Neural Network (RAM-based neural network). The proposed WNN architecture uses directional maps to classify fingerprint images in the five NIST classes (Left Loop, Right Loop, Whorl, Arch and Tented Arch) without anyone enhancement phase. Starting from the directional map, the WNN architecture computes the fingerprint classification rate. The proposed architecture is implemented on Celoxica RC20…
The Role of Artificial Intelligence in Social Media Big data Analytics for Disaster Management -Initial Results of a Systematic Literature Review
2018
When any kind of disaster occurs, victims who are directly and indirectly affected by the disaster often post vast amount of data (e.g., images, text, speech, video) using numerous social media platforms. This is because social media has recently become a primary communication channel among people to report either to public or to emergency responders (ERs). ERs, who are from various emergency response organizations (EROs), usually consider to gain awareness of the situation in order to respond to occurred disaster. However, with the occurrence of the disaster, within minutes, the social media platforms are flooded with various kinds of data which become overwhelmed for ERs with big data. Fu…
Emotions in a cognitive architecture for human robot interactions
2004
A robot architecture is proposed in which cognitive models of emotions are modelled in terms of conceptual spaces. The architecture has been implemented in a anthropomorphic robotic hand system. Experimental results are described related to an experimental setup in which the robot system plays Rock Paper Scissor against a human opponent Copyright © 2004, American Association for Artificial Intelligence (www.aaai.org).
Domestic load forecasting using neural network and its use for missing data analysis
2015
Domestic demand prediction is very important for home energy management system and also for peak reduction in power system network. In this work, active and reactive power consumption prediction model is developed and analysed for a typical Southern Norwegian house for hourly power (active and reactive) consumptions and time information as inputs. In the proposed model, a neural network is adopted as a main technique and historical domestic load data of around 2 years are used as input. The available data has some measurement errors and missing segments. Before using the data for training purpose, missing and inaccurate data are considered and then it is used for testing the model. It is ob…
External parameters contribution in domestic load forecasting using neural network
2015
Domestic demand prediction is very important for home energy management system and also for peak reduction in the power system network. In this work, for precise prediction of power demand, external parameters, such as temperature and solar radiation, are considered and included in the prediction model for improving prediction performance. Power prediction models for coming hours' power demand estimation are built using neural network based on hourly power consumptions data with / without ambient temperature data and global solar irradiation (GSI) data respectively. In this work, a typical Southern Norwegian household demand has been considered. As a result, both ambient temperature and GSI…