Improving the Classification Rate of Insulation Defects in Power Cables by Automatic Features Extraction and Sample Augmentation of Partial Discharge Signal

Conventional pattern recognition methods employed for differentiating the types of insulation defects in power cables usually rely on the manual extraction of partial discharge features, which is inefficient and easily affected by subjective uncertainty. This work addresses this problem by proposing a new framework based on the automatic features extraction of partial discharge signal. The method first applies a sliding time window to convert partial discharge signals in the time domain into two-dimensional images that serve directly as the input to the convolutional neural networks (CNNs). Then a nonlinear encoder is employed to automatically extract the features of the partial discharge image data as the input of CNNs for classification. In addition, we address the overfitting problem associated with the few-shot by applying a deep convolutional generative adversarial network (DCGAN) to augment the original training dataset. Experimental results demonstrate the validity of the proposed algorithm; it increases the classification accuracy by 4.18% relative to that achieved with manually extracted features; the overall accuracy of the proposed algorithm training with the augmented dataset is 3.175% higher than that with the original experimental dataset.

Characterization of Unpleasant Odors in Poultry Houses Using Metal Oxide Semiconductor-Based Gas Sensor Arrays and Pattern Recognition Methods

In this study, the ability of an electronic nose developed to analyze and monitor odor emissions from three poultry farms located in Meknes (Morocco) and Berlin (Germany) was evaluated. Indeed, the potentiality of the electronic nose (e-nose) to differentiate the concentration fractions of hydrogen sulfide, ammonia, and ethanol was investigated. Furthermore, the impact change of relative humidity values (from 15% to 67%) on the responses of the gas sensors was reported and revealed that the effect remained less than 0.6%. Furthermore, the relevant results confirmed that the developed e-nose system was able to perfectly classify and monitor the odorous air of poultry farms.

A CAVE based 3d immersive interactive city with gesture interface

This thesis presents a system that visualizes 3D city data and supports gesture interactions in a fully immersive Cave Automatic Virtual Environment (CAVE). To facilitate more natural interactions in this immersive virtual city, novel techniques are proposed for operations such as object selection, object manipulation, navigation and menu control. These operations form a basis of interactions for most Virtual Reality (VR) applications. The proposed techniques are predominantly controlled using gestures. We also propose the use of pattern recognition methods, specifically a Hidden Markov Model, to support real time dynamic gesture recognition and demonstrate its use for menu control in VR applications. Qualitative and quantitative user studies are conducted to evaluate the proposed techniques. The results of the user studies demonstrate that the interaction techniques for object selection and manipulation are measurably better than traditional techniques. The results also show that the proposed gesture based navigation and menu control techniques are preferred by experienced users. These findings can guide future user interface design in immersive environments.

A CAVE based 3d immersive interactive city with gesture interface

This thesis presents a system that visualizes 3D city data and supports gesture interactions in a fully immersive Cave Automatic Virtual Environment (CAVE). To facilitate more natural interactions in this immersive virtual city, novel techniques are proposed for operations such as object selection, object manipulation, navigation and menu control. These operations form a basis of interactions for most Virtual Reality (VR) applications. The proposed techniques are predominantly controlled using gestures. We also propose the use of pattern recognition methods, specifically a Hidden Markov Model, to support real time dynamic gesture recognition and demonstrate its use for menu control in VR applications. Qualitative and quantitative user studies are conducted to evaluate the proposed techniques. The results of the user studies demonstrate that the interaction techniques for object selection and manipulation are measurably better than traditional techniques. The results also show that the proposed gesture based navigation and menu control techniques are preferred by experienced users. These findings can guide future user interface design in immersive environments.

Particularities of measuring partial discharges in stator windings insulation systems of high-voltage electrical machines

The purpose of the article is to provide potential tools that can make a significant contribution to the identification of partial discharges (PD). Different types of partial discharges occur in stator winding insulation and a few partial discharges may occur simultaneously. Internal partial discharges are electrical discharges that occur in voids in the insulation of the stator winding. In typical stator insulation systems that use epoxy bonded mica tapes, insulation degradation due to internal partial discharges is usually slow (many years or decades). External partial discharges (slot PD and surface PD in the end-winding) are more dangerous and lead to the destruction of the insulation in a short time (several months or years). Therefore, the identification of insulation defects is essential. The analysis of existing methods for identification of defects in the insulation of high-voltage electrical machines using the results of measuring the partial discharges characteristics is carried out. The advantages and disadvantages of each of the groups of identification methods are characterized. It is shown that among the models of knowledge representation in solving problems of diagnostics of insulation systems for high-voltage electrical machines, identification methods, including field tests using training samples, are among the most suitable ones. It is noted that detection of insulation defects and their identification cannot be carried out only by direct measurements of PD characteristics and other dielectric parameters (electrical resistance, dielectric loss, polarization index). For this, special computing programs based on pattern recognition methods should be used. Results are presented of identification of technological defects in the insulation of the stator winding at the stage of factory testing, obtained using the PD identification method developed by the authors

Design and FPGA Implementation of Intelligent Fault Detection in Smart Wireless Sensor Networks

In this paper, both the design and hardware of Fault Detection (FD) in Wireless Sensor Network (WSN) was implemented using FPGA NI myRIO kit, wireless temperature sensors network with small size, low cost, and low power consumption. Work data processing was performed using pattern recognition methods to detect residual generation. LabVIEW software environment was employed for system performance. In this paper. The design of the hardware circuit NI myRIO kit received temperature from the sensors. The examined system showed an ability to monitor and track any fault or fire that may occur; based on the results, if collected data is exceeded predetermined threshold, then the system is responding, a direct connection is using WIFI to process this data by LabVIEW.