Andrea Giantomassi

Minimal Resource Allocating Networks for Discrete Time Sliding Mode Control of Robotic Manipulators

This paper presents a discrete-time sliding mode control based on neural networks designed for robotic manipulators. Radial basis function neural networks are used to learn about uncertainties affecting the system. The online learning algorithm combines the growing criterion and the pruning strategy of the minimal resource allocating network technique with an adaptive extended Kalman filter to update all the parameters of the networks. A method to improve the run-time performance for the real-time implementation of the learning algorithm has been considered. The analysis of the control stability is given and the controller is evaluated on the ERICC robot arm. Experiments show that the proposed controller produces good trajectory tracking performance and it is robust in the presence of model inaccuracies, disturbances and payload perturbations.

Electric Motor Fault Detection and Diagnosis by Kernel Density Estimation and Kullback–Leibler Divergence Based on Stator Current Measurements

This paper deals with the problem of fault detection and diagnosis of induction motor based on motor current signature analysis. Principal component analysis is used to reduce the three-phase current space to a 2-D space. Kernel density estimation (KDE) is adopted to evaluate the probability density functions of each healthy and faulty motor, which can be used as features in order to identify each fault. Kullback-Leibler divergence is used as an index to identify the dissimilarity between two probability distributions, and it allows automatic fault identification. The aim is also to improve computational performance in order to apply online a monitoring system. KDE is improved by fast Gaussian transform and a points reduction procedure. Since these techniques achieve a remarkable computational cost reduction with respect to the standard KDE, the algorithm can be used online. Experiments are carried out using two alternate current motors: An asynchronous induction machine and a single-phase motor. The faults considered to test the developed algorithm are cracked rotor, out-of-tolerance geometry rotor, and backlash. Tests are carried out at different load and voltage levels to show the proposed method performance.

Multi-scale PCA based fault diagnosis on a paper mill plant

In paper mill plants, the competition for increasing efficiency and reducing costs is a primary purpose. Fault detection and diagnosis can help by minimize the loss of production. In particular for the stock preparation sub-process a signal based fault detection and isolation procedure is developed. Multi-Scale Principal Component Analysis (MSPCA) is used to monitor some critical variables of the stock preparation of a paper mill plant in order to diagnose faults and malfunctions. MSPCA simultaneously extracts both, cross correlation across the sensors (PCA approach) and auto-correlation within a sensor (Wavelet approach). The advantage of MSPCA is validated on considered paper mill plant where several sensors are installed to control and monitor the automation system.

Induction motor fault detection and diagnosis using KDE and Kullback-Leibler divergence

The present paper proposes a novel data-driven Fault Detection and Diagnosis algorithm for induction motors based on Motor Current Signature Analysis. Principal Component Analysis is used to reduce the three-phase currents space in two dimensions. Then, Kernel Density Estimation is adopted to estimate the Probability Density Function of healthy and of each faulty motors, which will give typical patterns that can be used to identify each fault. Kullback-Leibler divergence is used as an index to identify the dissimilarity between two determined probability distributions, that allows the automatic identification of distinct fault types. Several simulations and experimental results are carried out using two benchmarks in order to verify the effectiveness of the proposed methodology: the first is used to prove appropriateness of the method for air gap eccentricity fault diagnosis and the second is used to prove suitability of the method for rotor broken bars and connectors fault diagnosis. Simulations and classification results prove that the proposed Fault Detection and Diagnosis procedure is able to detect and diagnose different induction motor fault types.

Multi-apartment residential microgrid monitoring system based on kernel canonical variate analysis

In the residential energy sector there is a growing interest in smart energy management systems able to monitor, manage and minimize energy consumption. A key factor to curb household energy consumption is the amendment of occupant erroneous behaviors and systems malfunctioning. In this scenario energy efficiency benefits can be either amplified or neutralized by, respectively, good or bad practices carried out by end users. Authors propose a diagnostic system for a residential microgrid application able to detect faults and occupant bad behaviors. In particular a nonlinear monitoring method, based on kernel canonical variate analysis, is developed. To overcome the normality assumption regarding the signals probability distribution, Upper Control Limits are derived from the estimated Probability Density Function through Kernel Density Estimation. The proposed method, applied to a smart residential microgrid, is tested on experimental data acquired from July 2012 to October 2013.

MSPCA with KDE Thresholding to Support QC in Electrical Motors Production Line

Abstract In this paper a Fault Detection and Isolation (FDI) procedure is applied for the defects detection and analysis of electrical motors at the end of production line in hood factories. The objective consists of developing a fast and robust methodology to detect defective motors and to identify defects for quality analysis on production line. Using a signal based FDI procedure, an end of a line bench system is designed, which is able to analyze the defects of produced motors. Multi-Scale Principal Component Analysis (MSPCA) is used for defect detection and a Kernel Density Estimation (KDE) algorithm is used for fault isolation on the PCA residual contributions. Also a method to choose the WT levels is adopted. MSPCA with KDE thresholding advantage is demonstrated by experimentations on test bench, using vibration measurements. Experiments show that the stochastic method used to compute thresholds on PCA residuals is robust and at the same time accurate.

Fault detection and prognosis methods for a monitoring system of rotating electrical machines

Companies are involved in a high competition for reducing the cost of production in order to maintain their market shares. Since the costs of maintenance contribute a substantial portion of the production costs, companies must budget maintenance effectively. Machine deterioration prognosis can decrease the costs of maintenance by minimizing the loss of production due to machine breakdown and avoiding the overstocking of spare parts. This paper gives a review of some fault detection and prognosis methods to diagnose faults and failure on rotating electrical machines. To develop the monitoring system accelerometers have been used to acquire vibration measurements. Performance are studied on a laboratory-scale experimental system.

RGBD camera monitoring system for Alzheimer's disease assessment using Recurrent Neural Networks with Parametric Bias action recognition

Abstract The present paper proposes a computer vision system to diagnose the stage of illness in patients affected by Alzheimers disease. In the context of Ambient Assisted Living (AAL), the system monitors people in home environment during daily personal care activities. The aim is to evaluate the dementia stage, observing actions listed in the Direct Assessment of Funcional Status (DAFS) index and detecting anomalies during the performance, in order to assign a score explaining if the action is correct or not. In this work brushing teeth and grooming hair by a hairbrush are analysed. The technology consists of the application of a Recurrent Neural Network with Parametric Bias (RNNPB) that is able to learn movements connected with a specific action and recognize human activities by parametric bias that work like mirror neurons. This study has been conducted using Microsoft Kinect to collect data about the actions observed and oversee the user tracking and gesture recognition. Experiments prove that the proposed computer vision system can learn and recognize complex human activities and evaluates DAFS score.

Kernel canonical variate analysis based management system for monitoring and diagnosing smart homes

In the contest of household energy management, a growing interest is addressed to smart system development, able to monitor and manage resources in order to minimize wasting. One of the key factors in curbing energy consumption in the household sector is the amendment of occupant erroneous behaviours and systems malfunctioning, due to the lack of awareness of the final user. Indeed the benefits achievable with energy efficiency could be either amplified or neutralized by, respectively, good or bad practices carried out by the final users. Authors propose a diagnostic system for home energy management application able to detect faults and occupant behaviours. In particular a nonlinear monitoring method, based on Kernel Canonical Variate Analysis, is developed. To remove the assumption of normality, Upper Control Limits are derived from the estimated Probability Density Function through Kernel Density Estimation. The proposed method is applied to smart home temperature sensors to detect anomalies respect to efficient user behaviours and sensors and actuators faults. The method is tested on experimental data acquired in a real apartment.

Hidden Markov Model for Health Estimation and Prognosis of Turbofan Engines

Determining the residual life time of systems is a determinant factor for machinery and environment safety. In this paper the problem of estimate the residual useful life (RUL) of turbo-fan engines is addressed. The adopted approach is especially suitable for situations in which a large amount of data is available offline, by allowing the processing of such data for the determination of RUL. The procedure allows to calculate the RUL through the following steps: features extraction by Artificial Neural Networks (ANN) and determination of remaining life time by-prediction models based on a Hidden Markov Model (HMM). Simulations confirm the effectiveness of the proposed approach and the promising power of Bayesian methods.© 2011 ASME