Search results for "Fault detection"
showing 10 items of 77 documents
A Geometrical Simple Approach for Power Silicon Devices Fault Detection and Fault-Tolerant Operation of a Voltage Source Inverter
2012
Fault-tolerant converters have been widely investigated for years and nowadays an extensive technical literature on this field exists. This paper presents a novel fault detection algorithm based on a simple geometrical approach. In the algorithm analysis both the case of faults in single device and the lose of an entire inverter leg have been considered. False positive detections are avoided by considering a proper number of current samples. The proposed fault detection algorithm is characterized by simplicity, low computational and implementation effort with a consequent enough fast execution, easy control integration with the possibility to use it both in hardware in the loop systems and …
Food Tray Sealing Fault Detection in Multi-Spectral Images Using Data Fusion and Deep Learning Techniques
2021
A correct food tray sealing is required to preserve food properties and safety for consumers. Traditional food packaging inspections are made by human operators to detect seal defects. Recent advances in the field of food inspection have been related to the use of hyperspectral imaging technology and automated vision-based inspection systems. A deep learning-based approach for food tray sealing fault detection using hyperspectral images is described. Several pixel-based image fusion methods are proposed to obtain 2D images from the 3D hyperspectral image datacube, which feeds the deep learning (DL) algorithms. Instead of considering all spectral bands in region of interest around a contamin…
Getting insights into the behavior of variable speed direct expansion air conditioning systems under faulty operating conditions
2019
Direct expansion air conditioning systems, such as rooftop units, are widely adopted in small and medium scale commercial buildings. In order to increase the energy performance of these systems during part-load operation, variable-speed compressors and fans have been adopted in the last two decades. However, profitable energy saving could be achieved not only by optimizing the design and the control of these systems, but also by scheduling a proper maintenance strategy. In fact, if not properly maintained, no benefits would be achieved even when more sophisticated systems are adopted. In order to support plant owners in scheduling cost-effective maintenance program, Fault Detection and Diag…
INNOVATIVE APPLICATIONS OF EXERGY ANALYSIS AND THERMOECONOMICS IN CHEMICAL, THERMAL AND COOLING ENERGY CONVERSION SYSTEMS
Since 70s, the world has been becoming more and more concerned about energy and environmental issues. The need of meeting the current energy demand by guaranteeing the ability of future generation to satisfy theirs have been pushing research not only to exploit alternative energy sources such as renewable energies, but also to improve the efficiency of energy conversion systems. To this regard, developing systems that use efficiently energy is of paramount importance especially in those countries which rely on non-renewable energy sources such as oil, natural gas, and coal. In fact, the reduction of energy consumption will lead not only to the saving of unrestorable and limited energy resou…
Robust synchronization and fault detection of uncertain master-slave systems with mixed time-varying delays and nonlinear perturbations
2010
In this paper, the problem of robust synchronization and fault detection for a class of master-slave systems subjected to some nonlinear perturbations and mixed neutral and discrete time-varying delays is investigated based on an H ∞ performance condition. By introducing a descriptor technique, using Lyapunov-Krasovskii functional and a suitable change of variables, new required sufficient conditions are established in terms of delay-dependent linear matrix inequalities to synthesize the residual generation scheme. The explicit expression of the synchronization law is derived for the fault such that both asymptotic stability and a prescribed level of disturbance attenuation are satisfied fo…
HEALTH MONITORING, FAULT DETECTION AND DIAGNOSIS IN INDUSTRIAL ROTATING MACHINERY BY ADVANCED VIBRATION ANALYSIS
Thermoeconomic Diagnosis of Air conditioning Systems: an Innovative Approach for Improved Reliability of the Technique
2018
Thermoeconomic diagnosis is an exergy-based fault detection and diagnosis technique which has been recently extended to air conditioning systems. One of the main features of this technique is to provide quantitative information of the impact of each fault on the increased energy consumption of a system. This information is then used for programming cost-effective maintenance strategies. Only few papers have focused on it and a lot of work is needed for further improvements. In this work, the approach was developed by means of experimental activities carried out on a 17.5 kW packaged rooftop air conditioning unit (RTU). The RTU was tested in psychrometric chambers under a wide range of opera…
Robust fault detection filter design for a class of linear systems with mixed time-varying delays and nonlinear perturbations
2009
In this note, the problem of robust fault detection filter (RFDF) design for a class of linear systems subjected to some nonlinear perturbations and mixed neutral and discrete time-varying delays is investigated based on an H ∞ performance condition. By introducing a descriptor technique, using Lyapunov-Krasovskii functional and a suitable change of variables, new required sufficient conditions are established in terms of delay-dependent linear matrix inequalities (LMIs) to synthesize the residual generation scheme. Based on Luenberger type observers, the explicit expression of the filters is derived for the fault such that both asymptotic stability and a prescribed level of disturbance att…
2014
This paper investigates the proficiency of support vector machine (SVM) using datasets generated by Tennessee Eastman process simulation for fault detection. Due to its excellent performance in generalization, the classification performance of SVM is satisfactory. SVM algorithm combined with kernel function has the nonlinear attribute and can better handle the case where samples and attributes are massive. In addition, with forehand optimizing the parameters using the cross-validation technique, SVM can produce high accuracy in fault detection. Therefore, there is no need to deal with original data or refer to other algorithms, making the classification problem simple to handle. In order to…