World Academy of Science, Engineering and Technology
[Mechanical and Materials Engineering]
Online ISSN : 1307-6892
210 Optimized Deep Learning-Based Facial Emotion Recognition System
Authors: Erick C. Valverde, Wansu Lim
Abstract:
Facial emotion recognition (FER) system has been recently developed for more advanced computer vision applications. The ability to identify human emotions would enable smart healthcare facility to diagnose mental health illnesses (e.g., depression and stress) as well as better human social interactions with smart technologies. The FER system involves two steps: 1) face detection task and 2) facial emotion recognition task. It classifies the human expression in various categories such as angry, disgust, fear, happy, sad, surprise, and neutral. This system requires intensive research to address issues with human diversity, various unique human expressions, and variety of human facial features due to age differences. These issues generally affect the ability of the FER system to detect human emotions with high accuracy. Early stage of FER systems used simple supervised classification task algorithms like K-nearest neighbors (KNN) and artificial neural networks (ANN). These conventional FER systems have issues with low accuracy due to its inefficiency to extract significant features of several human emotions. To increase the accuracy of FER systems, deep learning (DL)-based methods, like convolutional neural networks (CNN), are proposed. These methods can find more complex features in the human face by means of the deeper connections within its architectures. However, the inference speed and computational costs of a DL-based FER system is often disregarded in exchange for higher accuracy results. To cope with this drawback, an optimized DL-based FER system is proposed in this study.An extreme version of Inception V3, known as Xception model, is leveraged by applying different network optimization methods. Specifically, network pruning and quantization are used to enable lower computational costs and reduce memory usage, respectively. To support low resource requirements, a 68-landmark face detector from Dlib is used in the early step of the FER system.Furthermore, a DL compiler is utilized to incorporate advanced optimization techniques to the Xception model to improve the inference speed of the FER system. In comparison to VGG-Net and ResNet50, the proposed optimized DL-based FER system experimentally demonstrates the objectives of the network optimization methods used. As a result, the proposed approach can be used to create an efficient and real-time FER system.Keywords: deep learning, face detection, facial emotion recognition, network optimization methods
Procedia PDF Downloads 114209 Development of an EEG-Based Real-Time Emotion Recognition System on Edge AI
Authors: James Rigor Camacho, Wansu Lim
Abstract:
Over the last few years, the development of new wearable and processing technologies has accelerated in order to harness physiological data such as electroencephalograms (EEGs) for EEG-based applications. EEG has been demonstrated to be a source of emotion recognition signals with the highest classification accuracy among physiological signals. However, when emotion recognition systems are used for real-time classification, the training unit is frequently left to run offline or in the cloud rather than working locally on the edge. That strategy has hampered research, and the full potential of using an edge AI device has yet to be realized. Edge AI devices are computers with high performance that can process complex algorithms. It is capable of collecting, processing, and storing data on its own. It can also analyze and apply complicated algorithms like localization, detection, and recognition on a real-time application, making it a powerful embedded device. The NVIDIA Jetson series, specifically the Jetson Nano device, was used in the implementation. The cEEGrid, which is integrated to the open-source brain computer-interface platform (OpenBCI), is used to collect EEG signals. An EEG-based real-time emotion recognition system on Edge AI is proposed in this paper. To perform graphical spectrogram categorization of EEG signals and to predict emotional states based on input data properties, machine learning-based classifiers were used. Until the emotional state was identified, the EEG signals were analyzed using the K-Nearest Neighbor (KNN) technique, which is a supervised learning system. In EEG signal processing, after each EEG signal has been received in real-time and translated from time to frequency domain, the Fast Fourier Transform (FFT) technique is utilized to observe the frequency bands in each EEG signal. To appropriately show the variance of each EEG frequency band, power density, standard deviation, and mean are calculated and employed. The next stage is to identify the features that have been chosen to predict emotion in EEG data using the K-Nearest Neighbors (KNN) technique. Arousal and valence datasets are used to train the parameters defined by the KNN technique.Because classification and recognition of specific classes, as well as emotion prediction, are conducted both online and locally on the edge, the KNN technique increased the performance of the emotion recognition system on the NVIDIA Jetson Nano. Finally, this implementation aims to bridge the research gap on cost-effective and efficient real-time emotion recognition using a resource constrained hardware device, like the NVIDIA Jetson Nano. On the cutting edge of AI, EEG-based emotion identification can be employed in applications that can rapidly expand the research and implementation industry's use.Keywords: edge AI device, EEG, emotion recognition system, supervised learning algorithm, sensors
Procedia PDF Downloads 97208 Excitation Density and Energy Dependent Relaxation Dynamics of Charge Carriers in Large Area 2D TMDCs
Authors: Ashish Soni, Suman Kalyan Pal
Abstract:
Transition metal dichalcogenides (TMDCs) are an emerging paradigm for the generation of advanced materials which are capable of utilizing in future device applications. In recent years TMDCs have attracted researchers for their unique band structure in monolayers. Large-area monolayers could become the most appropriate candidate for flexible and thin optoelectronic devices. For this purpose, it is crucial to understand the generation and transport of charge carriers in low dimensions. A deep understanding of photo-generated hot charges and trapped charges is essential to improve the performance of optoelectronic devices. Carrier trapping by the defect states that are introduced during the growth process of the monolayer could influence the dynamical behaviour of charge carriers. Herein, we investigated some aspects of the ultrafast evolution of the initially generated hot carriers and trapped charges in large-area monolayer WS₂ by measuring transient absorption at energies above and below the band gap energy. Our excitation density and energy-dependent measurements reveal the trapping of the initially generated charge carrier. Our results could be beneficial for the development of TMDC-based optoelectronic devices.Keywords: transient absorption, optoelectronics, 2D materials, TMDCs, exciton
Procedia PDF Downloads 60207 F-VarNet: Fast Variational Network for MRI Reconstruction
Authors: Omer Cahana, Maya Herman, Ofer Levi
Abstract:
Magnetic resonance imaging (MRI) is a long medical scan that stems from a long acquisition time. This length is mainly due to the traditional sampling theorem, which defines a lower boundary for sampling. However, it is still possible to accelerate the scan by using a different approach, such as compress sensing (CS) or parallel imaging (PI). These two complementary methods can be combined to achieve a faster scan with high-fidelity imaging. In order to achieve that, two properties have to exist: i) the signal must be sparse under a known transform domain, ii) the sampling method must be incoherent. In addition, a nonlinear reconstruction algorithm needs to be applied to recover the signal. While the rapid advance in the deep learning (DL) field, which has demonstrated tremendous successes in various computer vision task’s, the field of MRI reconstruction is still in an early stage. In this paper, we present an extension of the state-of-the-art model in MRI reconstruction -VarNet. We utilize VarNet by using dilated convolution in different scales, which extends the receptive field to capture more contextual information. Moreover, we simplified the sensitivity map estimation (SME), for it holds many unnecessary layers for this task. Those improvements have shown significant decreases in computation costs as well as higher accuracy.Keywords: MRI, deep learning, variational network, computer vision, compress sensing
Procedia PDF Downloads 145206 Investigating the Viability of Ultra-Low Parameter Count Networks for Real-Time Football Detection
Authors: Tim Farrelly
Abstract:
In recent years, AI-powered object detection systems have opened the doors for innovative new applications and products, especially those operating in the real world or ‘on edge’ – namely, in sport. This paper investigates the viability of an ultra-low parameter convolutional neural network specially designed for the detection of footballs on ‘on the edge’ devices. The main contribution of this paper is the exploration of integrating new design features (depth-wise separable convolutional blocks and squeezed and excitation modules) into an ultra-low parameter network and demonstrating subsequent improvements in performance. The results show that tracking the ball from Full HD images with negligibly high accu-racy is possible in real-time.Keywords: deep learning, object detection, machine vision applications, sport, network design
Procedia PDF Downloads 138205 Wear Progress and -Mechanisms in Torpedo Ladles in Steel Industry
Authors: Mattahias Maj, Fabio Tatzgern, Karl Adam, Damir Kahrimanovic, Markus Varga
Abstract:
Torpedo ladles are necessary transport carriages in steel production to move the molten crude iron from the blast furnace to the steel refining plant. This requires the ladles to be high temperature resistant and insulate well to preserve the temperature and hold the risk of solidification at bay. Therefore, the involved refractories lining the inside of the torpedo ladles are chosen mostly according to their thermal properties, although wear of the materials by the liquid iron is also of major importance. In this work, we combined investigations of the thermal behaviour with wear studies of the lining over the whole lifetime of a torpedo ladle. Additional numerical simulations enabled a detailed model of the mechanical loads and temperature propagation at the various stations (heating, filling, emptying, cooling). The core of the investigation were detailed 3D measurements of the ladle’s cavity and thereby quantitative information of the wear progress at different time intervals during the lifetime of the ladles. The measurements allowed for a separation of different wear zones according to severity, namely the “splash zone” where the melt directly hits the ladle, the “melt zone” where during transport always liquid melt is present, and the “slag zone”, where the slag floats on the melt causing the most severe wear loss. Numerical simulations of the filling process were taken to calculate stress levels and temperature gradients, which led to the different onset of wear on those zones. Thermal imaging and punctual temperature measurements allowed for a study of the thermal consequences entailed by the wear onset. Additional “classical” damage analysis of the worn refractories complete the investigation. Thereby the wear mechanisms leading to the substantial wear loss were disclosed.Keywords: high temperature, tribology, liquid-solid interaction, refractories, thermography
Procedia PDF Downloads 214204 FLIME - Fast Low Light Image Enhancement for Real-Time Video
Authors: Vinay P., Srinivas K. S.
Abstract:
Low Light Image Enhancement is of utmost impor- tance in computer vision based tasks. Applications include vision systems for autonomous driving, night vision devices for defence systems, low light object detection tasks. Many of the existing deep learning methods are resource intensive during the inference step and take considerable time for processing. The algorithm should take considerably less than 41 milliseconds in order to process a real-time video feed with 24 frames per second and should be even less for a video with 30 or 60 frames per second. The paper presents a fast and efficient solution which has two main advantages, it has the potential to be used for a real-time video feed, and it can be used in low compute environments because of the lightweight nature. The proposed solution is a pipeline of three steps, the first one is the use of a simple function to map input RGB values to output RGB values, the second is to balance the colors and the final step is to adjust the contrast of the image. Hence a custom dataset is carefully prepared using images taken in low and bright lighting conditions. The preparation of the dataset, the proposed model, the processing time are discussed in detail and the quality of the enhanced images using different methods is shown.Keywords: low light image enhancement, real-time video, computer vision, machine learning
Procedia PDF Downloads 188203 A Gyro-stabilized Autonomous Multi-terrain Quadrupedal-wheeled Robot: Towards Edge-enabled Self-balancing, Autonomy, and Terramechanical Efficiency of Unmanned Off-road Vehicles
Authors: Mbadiwe S. Benyeogor, Oladayo O. Olakanmi, Kosisochukwu P. Nnoli, Olusegun I. Lawal, Eric JJ. Gratton
Abstract:
For a robot or any vehicular system to navigate in off-road terrain, its driving mechanisms and the electro-software system must be capable of generating, controlling, and moderating sufficient mechanical power with precision. This paper proposes an autonomous robot with a gyro-stabilized active suspension system in form of a hybrid quadrupedal wheel drive mechanism. This system is to serve as a miniature model for demonstrating how off-road vehicles can be robotized into efficient terramechanical mobile platforms that are capable of self-balanced autonomous navigation and maneuvering on rough and uneven topographies. Results from tests and analysis show that the developed system performs as expected. Therefore, our model and control devices can be adapted to computerizing, automating, and upgrading the operation of unmanned ground vehicles for off-road navigation.Keywords: active suspension, autonomous robots, edge computing, navigational sensors, terramechanics
Procedia PDF Downloads 146202 X-Ray Photoelectron Spectroscopy Analyses of Candidate Materials for Advanced Nuclear Reactors
Authors: Marie Kudrnová, Jana Rejková
Abstract:
The samples of supplied INCONEL 601, 617, 625, and HASTELLOY C-22 alloys and experimental nickel alloy MoNiCr were examined by XPS (X-ray photoelectron spectroscopy) before and after exposure. The experiment was performed in a mixture of LiCl-KCl salt (58.2-41.8 wt. %). The exposure conditions were 440°C, pressure 0.2 MPa, 500 hours in an inert argon atmosphere. The XPS analysis shows that a thin oxide layer composed of metal oxides such as NiO, Cr₂O₃, and Nb₂O₅ was formed. After sputtering the exposed surface with Ar ions, metals were also detected in the elemental state, indicating a very thin protective oxide layer with a thickness in units of up to tens of nanometers.Keywords: XPS, MSR, nickel alloy, metal oxides
Procedia PDF Downloads 65201 Corrosion Behavior of Austempered Ductile Iron Microalloyed with Boron in Rainwater
Authors: S. Gvazava, N. Khidasheli, V. Tediashvili, M. Donadze
Abstract:
The work presented in this paper studied the of austempered ductile iron (ADI) with different combinations of structural composition (upper bainite, lower bainite, retained austenite) in rainwater. A range of structural states of the metal matrix was obtained by changing the regimes of thermal treantments of a high-strength cast iron. The specimens were austenised at 900 0C for 30, 60, 90, 120 minutes. Afterwards, isothermal quenching was performed at 280 and 400 0C for40 seconds. The study was carried out using weight-change (WC), cyclic potentiodynamic polarization (CPP), open-circuit potential (OCP), and electrochemical impedance spectroscopy (EIS) measurements and complemented by scanning electron microscopy (SEM-EDS). According to the results, corrosion resistance of the boron microallyedbainitic ADI greatly depends on the type of the bainitic matrix and the amount of the retained austenite, which is driven by diffusion permeability of interphase and intergrain boundaries.Keywords: austempered ductile iron, corrosion behaviour, retained austenite, corrosion rate, interphase boundary, upper bainite, lower bainite
Procedia PDF Downloads 111200 Corrosion Behavior of Steels in Molten Salt Reactors
Authors: Jana Rejková, Marie Kudrnová
Abstract:
This paper deals with the research of materials for one of the types of reactors IV. generation - reactor with molten salts. One of the advantages of molten salts applied as a coolant in reactors is the ability to operate at relatively low pressures, as opposed to cooling with water or gases. Compared to liquid metal cooling, which also allows lower operating pressures, salt melts are less prone to chemical reactions. The service life of the construction materials used is limited by the operating temperatures of the reactor and the content of impurities in the salts. For the research of corrosion resistance, an experimental device was designed and assembled, enabling exposure at high temperatures without access to oxygen in a flowing atmosphere of inert gas. Nickel alloys Inconel 601, 617, and 625 were tested in a mixture of chloride salts LiCl – KCl (58,2 - 41,8 wt. %). The experiment showed high resistance of the materials used and based on the results and XPS analysis, other construction materials were proposed for the experiments.Keywords: molten salt, corrosion, nuclear reactor, nickel alloy
Procedia PDF Downloads 156199 Feature Selection Approach for the Classification of Hydraulic Leakages in Hydraulic Final Inspection using Machine Learning
Authors: Christian Neunzig, Simon Fahle, Jürgen Schulz, Matthias Möller, Bernd Kuhlenkötter
Abstract:
Manufacturing companies are facing global competition and enormous cost pressure. The use of machine learning applications can help reduce production costs and create added value. Predictive quality enables the securing of product quality through data-supported predictions using machine learning models as a basis for decisions on test results. Furthermore, machine learning methods are able to process large amounts of data, deal with unfavourable row-column ratios and detect dependencies between the covariates and the given target as well as assess the multidimensional influence of all input variables on the target. Real production data are often subject to highly fluctuating boundary conditions and unbalanced data sets. Changes in production data manifest themselves in trends, systematic shifts, and seasonal effects. Thus, Machine learning applications require intensive pre-processing and feature selection. Data preprocessing includes rule-based data cleaning, the application of dimensionality reduction techniques, and the identification of comparable data subsets. Within the used real data set of Bosch hydraulic valves, the comparability of the same production conditions in the production of hydraulic valves within certain time periods can be identified by applying the concept drift method. Furthermore, a classification model is developed to evaluate the feature importance in different subsets within the identified time periods. By selecting comparable and stable features, the number of features used can be significantly reduced without a strong decrease in predictive power. The use of cross-process production data along the value chain of hydraulic valves is a promising approach to predict the quality characteristics of workpieces. In this research, the ada boosting classifier is used to predict the leakage of hydraulic valves based on geometric gauge blocks from machining, mating data from the assembly, and hydraulic measurement data from end-of-line testing. In addition, the most suitable methods are selected and accurate quality predictions are achieved.Keywords: classification, achine learning, predictive quality, feature selection
Procedia PDF Downloads 156198 A Deep Learning Approach for the Predictive Quality of Directional Valves in the Hydraulic Final Test
Authors: Christian Neunzig, Simon Fahle, Jürgen Schulz, Matthias Möller, Bernd Kuhlenkötter
Abstract:
The increasing use of deep learning applications in production is becoming a competitive advantage. Predictive quality enables the assurance of product quality by using data-driven forecasts via machine learning models as a basis for decisions on test results. The use of real Bosch production data along the value chain of hydraulic valves is a promising approach to classifying the leakage of directional valves.Keywords: artificial neural networks, classification, hydraulics, predictive quality, deep learning
Procedia PDF Downloads 229197 Highly Robust Crosslinked BIAN-based Binder to Stabilize High-Performance Silicon Anode in Lithium-Ion Secondary Battery
Authors: Agman Gupta, Rajashekar Badam, Noriyoshi Matsumi
Abstract:
Introduction: Recently, silicon has been recognized as one of the potential alternatives as anode active material in Li-ion batteries (LIBs) to replace the conventionally used graphite anodes. Silicon is abundantly present in the nature, it can alloy with lithium metal, and has a higher theoretical capacity (~4200 mAhg-1) that is approximately 10 times higher than graphite. However, because of a large volume expansion (~400%) upon repeated de-/alloying, the pulverization of Si particles causes the exfoliation of electrode laminate leading to the loss of electrical contact and adversely affecting the formation of solid-electrolyte interface (SEI).1 Functional polymers as binders have emerged as a competitive strategy to mitigate these drawbacks and failure mechanism of silicon anodes.1 A variety of aqueous/non-aqueous polymer binders like sodium carboxy-methyl cellulose (CMC-Na), styrene butadiene rubber (SBR), poly(acrylic acid), and other variants like mussel inspired binders have been investigated to overcome these drawbacks.1 However, there are only a few reports that mention the attempt of addressing all the drawbacks associated with silicon anodes effectively using a single novel functional polymer system as a binder. In this regard, here, we report a novel highly robust n-type bisiminoacenaphthenequinone (BIAN)-paraphenylene-based crosslinked polymer as a binder for Si anodes in lithium-ion batteries (Fig. 1). On its application, crosslinked-BIAN binder was evaluated to provide mechanical robustness to the large volume expansion of Si particles, maintain electrical conductivity within the electrode laminate, and facilitate in the formation of a thin SEI by restricting the extent of electrolyte decomposition on the surface of anode. The fabricated anodic half-cells were evaluated electrochemically for their rate capability, cyclability, and discharge capacity. Experimental: The polymerized BIAN (P-BIAN) copolymer was synthesized as per the procedure reported by our group.2 The synthesis of crosslinked P-BIAN: a solution of P-BIAN copolymer (1.497 g, 10 mmol) in N-methylpyrrolidone (NMP) (150 ml) was set-up to stir under reflux in nitrogen atmosphere. To this, 1,6-dibromohexane (5 mmol, 0.77 ml) was added dropwise. The resultant reaction mixture was stirred and refluxed at 150 °C for 24 hours followed by refrigeration for 3 hours at 5 °C. The product was obtained by evaporating the NMP solvent under reduced pressure and drying under vacuum at 120 °C for 12 hours. The obtained product was a black colored sticky compound. It was characterized by 1H-NMR, XPS, and FT-IR techniques. Results and Discussion: The N 1s XPS spectrum of the crosslinked BIAN polymer showed two characteristic peaks corresponding to the sp2 hybridized nitrogen (-C=N-) at 399.6 eV of the diimine backbone in the BP and quaternary nitrogen at 400.7 eV corresponding to the crosslinking of BP via dibromohexane. The DFT evaluation of the crosslinked BIAN binder showed that it has a low lying lowest unoccupied molecular orbital (LUMO) that enables it to get doped in the reducing environment and influence the formation of a thin (SEI). Therefore, due to the mechanically robust crosslinked matrices as well as its influence on the formation of a thin SEI, the crosslinked BIAN binder stabilized the Si anode-based half-cell for over 1000 cycles with a reversible capacity of ~2500 mAhg-1 and ~99% capacity retention as shown in Fig. 2. The dynamic electrochemical impedance spectroscopy (DEIS) characterization of crosslinked BIAN-based anodic half-cell confirmed that the SEI formed was thin in comparison with the conventional binder-based anodes. Acknowledgement: We are thankful to the financial support provided by JST-Mirai Program, Grant Number: JP18077239Keywords: self-healing binder, n-type binder, thin solid-electrolyte interphase (SEI), high-capacity silicon anodes, low-LUMO
Procedia PDF Downloads 154196 Hyperspectral Image Classification Using Tree Search Algorithm
Authors: Shreya Pare, Parvin Akhter
Abstract:
Remotely sensing image classification becomes a very challenging task owing to the high dimensionality of hyperspectral images. The pixel-wise classification methods fail to take the spatial structure information of an image. Therefore, to improve the performance of classification, spatial information can be integrated into the classification process. In this paper, the multilevel thresholding algorithm based on a modified fuzzy entropy function is used to perform the segmentation of hyperspectral images. The fuzzy parameters of the MFE function have been optimized by using a new meta-heuristic algorithm based on the Tree-Search algorithm. The segmented image is classified by a large distribution machine (LDM) classifier. Experimental results are shown on a hyperspectral image dataset. The experimental outputs indicate that the proposed technique (MFE-TSA-LDM) achieves much higher classification accuracy for hyperspectral images when compared to state-of-art classification techniques. The proposed algorithm provides accurate segmentation and classification maps, thus becoming more suitable for image classification with large spatial structures.Keywords: classification, hyperspectral images, large distribution margin, modified fuzzy entropy function, multilevel thresholding, tree search algorithm, hyperspectral image classification using tree search algorithm
Procedia PDF Downloads 163195 Structural Performance Evaluation of Electronic Road Sign Panels Reflecting Damage Scenarios
Authors: Junwon Seo, Bipin Adhikari, Euiseok Jeong
Abstract:
This paper is intended to evaluate the structural performance of welded electronic road signs under various damage scenarios (DSs) using a finite element (FE) model calibrated with full-scale ultimate load testing results. The tested electronic road sign specimen was built with a back skin made of 5052 aluminum and two channels and a frame made of 6061 aluminum, where the back skin was connected to the frame by welding. The size of the tested specimen was 1.52 m long, 1.43 m wide, and 0.28 m deep. An actuator applied vertical loads at the center of the back skin of the specimen, resulting in a displacement of 158.7 mm and an ultimate load of 153.46 kN. Using these testing data, generation and calibration of a FE model of the tested specimen were executed in ABAQUS, indicating that the difference in the ultimate load between the calibrated model simulation and full-scale testing was only 3.32%. Then, six different DSs were simulated where the areas of the welded connection in the calibrated model were diminished for the DSs. It was found that the corners at the back skin-frame joint were prone to connection failure for all the DSs, and failure of the back skin-frame connection occurred remarkably from the distant edges.Keywords: computational analysis, damage scenarios, electronic road signs, finite element, welded connections
Procedia PDF Downloads 83194 Evaluation of Iron Oxide-Functionalized Multiwall Carbon Nanotube Self-Standing Electrode for Symmetric Supercapacitor Application
Authors: B. V. Bhaskara Rao, Rodrigo Espinoza
Abstract:
The rapid development of renewable energy sources has drawn great attention to energy storage devices, especially supercapacitors, because of their high power density and rate performance. This work focus on Fe₃O₄ nanoparticles synthesized by reverse co-precipitation and MWCNTs functionalized by –COOH acid functionalization. The results show that Optimized 25wt% Fe₃O₄@FMWCNT show high specific capacitance 100 mF/cm² at one mA/cm² whereas 15wt% Fe₃O₄@FMWCNT showed high stability (80% retention capacity) over 5000 cycles. The electrolyte used in the coin cell is LiPF6 and the thickness of the electrode is 30 microns. The optimized Fe₃O₄@FMWCNT bucky papers coin cell electrochemical studies suggest that 25wt% Fe₃O₄@FMWCNT could be a good candidate for high-capacity supercapacitor devices. This could be further tested for flexible and planar supercapacitor device application with gel electrolytes.Keywords: self-standing electrode, Fe₃O4@FMWCNT, supercapacitor, symmetric coin-cell
Procedia PDF Downloads 149193 Determination of Stress-Strain Curve of Duplex Stainless Steel Welds
Authors: Carolina Payares-Asprino
Abstract:
Dual-phase duplex stainless steel comprised of ferrite and austenite has shown high strength and corrosion resistance in many aggressive environments. Joining duplex alloys is challenging due to several embrittling precipitates and metallurgical changes during the welding process. The welding parameters strongly influence the quality of a weld joint. Therefore, it is necessary to quantify the weld bead’s integral properties as a function of welding parameters, especially when part of the weld bead is removed through a machining process due to aesthetic reasons or to couple the elements in the in-service structure. The present study uses the existing stress-strain model to predict the stress-strain curves for duplex stainless-steel welds under different welding conditions. Having mathematical expressions that predict the shape of the stress-strain curve is advantageous since it reduces the experimental work in obtaining the tensile test. In analysis and design, such stress-strain modeling simplifies the time of operations by being integrated into calculation tools, such as the finite element program codes. The elastic zone and the plastic zone of the curve can be defined by specific parameters, generating expressions that simulate the curve with great precision. There are empirical equations that describe the stress-strain curves. However, they only refer to the stress-strain curve for the stainless steel, but not when the material is under the welding process. It is a significant contribution to the applications of duplex stainless steel welds. For this study, a 3x3 matrix with a low, medium, and high level for each of the welding parameters were applied, giving a total of 27 weld bead plates. Two tensile specimens were manufactured from each welded plate, resulting in 54 tensile specimens for testing. When evaluating the four models used to predict the stress-strain curve in the welded specimens, only one model (Rasmussen) presented a good correlation in predicting the strain stress curve.Keywords: duplex stainless steels, modeling, stress-stress curve, tensile test, welding
Procedia PDF Downloads 161192 Structural, Magnetic, Electrical and Dielectric Properties of Pr0.8Na0.2MnO3 Manganite
Authors: H. Ben Khlifa, W. Cheikhrouhou, R. M'nassri
Abstract:
The Orthorhombic Pr0.8Na0.2MnO3 ceramic was prepared in Polycrystalline form by a Pechini sol–gel method and its structural, magnetic, electrical, and dielectric properties were investigated experimentally. A structural study confirms that the sample is a single phase. Magnetic measurements show that the sample is a charge ordered Manganite. The sample undergoes two successive magnetic phase transitions with the variation of temperature: a charge ordering transition occurred at TCO = 212 K followed by a Paramagnetic (PM) to ferromagnetic (FM) transition around TC = 115 K. From an electrical point of view, a saturation region was marked in the conductivity as a function of Temperature s(T) curves at a specific temperature. The dc-conductivity (sdc) reaches a maximum value at 240 K. The obtained results are in good agreement with the temperature dependence of the average normalized change (ANC). We found that the conduction mechanism was governed by small polaron hopping (SPH) in the high-temperature region and by variable range hopping (VRH) in the low-temperature region. Complex impedance analysis indicates the presence of a non-Debye relaxation phenomenon in the system. Also, the compound was modeled by an electrical equivalent circuit. Then, the contribution of the grain boundary in the transport properties was confirmed.Keywords: manganites, preparation methods, magnetization, magnetocaloric effect, electrical and dielectric
Procedia PDF Downloads 156191 A Hardware-in-the-loop Simulation for the Development of Advanced Control System Design for a Spinal Joint Wear Simulator
Authors: Kaushikk Iyer, Richard M Hall, David Keeling
Abstract:
Hardware-in-the-loop (HIL) simulation is an advanced technique for developing and testing complex real-time control systems. This paper presents the benefits of HIL simulation and how it can be implemented and used effectively to develop, test, and validate advanced control algorithms used in a spinal joint Wear simulator for the Tribological testing of spinal disc prostheses. spinal wear simulator is technologically the most advanced machine currently employed For the in-vitro testing of newly developed spinal Discimplants. However, the existing control techniques, such as a simple position control Does not allow the simulator to test non-sinusoidal waveforms. Thus, there is a need for better and advanced control methods that can be developed and tested Rigorouslybut safely before deploying it into the real simulator. A benchtop HILsetupis was created for experimentation, controller verification, and validation purposes, allowing different control strategies to be tested rapidly in a safe environment. The HIL simulation aspect in this setup attempts to replicate similar spinal motion and loading conditions. The spinal joint wear simulator containsa four-Barlinkpowered by electromechanical actuators. LabVIEW software is used to design a kinematic model of the spinal wear Simulator to Validatehow each link contributes towards the final motion of the implant under test. As a result, the implant articulates with an angular motion specified in the international standards, ISO-18192-1, that define fixed, simplified, and sinusoid motion and load profiles for wear testing of cervical disc implants. Using a PID controller, a velocity-based position control algorithm was developed to interface with the benchtop setup that performs HIL simulation. In addition to PID, a fuzzy logic controller (FLC) was also developed that acts as a supervisory controller. FLC provides intelligence to the PID controller by By automatically tuning the controller for profiles that vary in amplitude, shape, and frequency. This combination of the fuzzy-PID controller is novel to the wear testing application for spinal simulators and demonstrated superior performance against PIDwhen tested for a spectrum of frequency. Kaushikk Iyer is a Ph.D. Student at the University of Leeds and an employee at Key Engineering Solutions, Leeds, United Kingdom, (e-mail: [email protected], phone: +44 740 541 5502). Richard M Hall is with the University of Leeds, the United Kingdom as a professor in the Mechanical Engineering Department (e-mail: [email protected]). David Keeling is the managing director of Key Engineering Solutions, Leeds, United Kingdom (e-mail: [email protected]). Results obtained are successfully validated against the load and motion tolerances specified by the ISO18192-1 standard and fall within limits, that is, ±0.5° at the maxima and minima of the motion and ±2 % of the complete cycle for phasing. The simulation results prove the efficacy of the test setup using HIL simulation to verify and validate the accuracy and robustness of the prospective controller before its deployment into the spinal wear simulator. This method of testing controllers enables a wide range of possibilities to test advanced control algorithms that can potentially test even profiles of patients performing various dailyliving activities.Keywords: Fuzzy-PID controller, hardware-in-the-loop (HIL), real-time simulation, spinal wear simulator
Procedia PDF Downloads 162190 Estimation and Restoration of Ill-Posed Parameters for Underwater Motion Blurred Images
Authors: M. Vimal Raj, S. Sakthivel Murugan
Abstract:
Underwater images degrade their quality due to atmospheric conditions. One of the major problems in an underwater image is motion blur caused by the imaging device or the movement of the object. In order to rectify that in post-imaging, parameters of the blurred image are to be estimated. So, the point spread function is estimated by the properties, using the spectrum of the image. To improve the estimation accuracy of the parameters, Optimized Polynomial Lagrange Interpolation (OPLI) method is implemented after the angle and length measurement of motion-blurred images. Initially, the data were collected from real-time environments in Chennai and processed. The proposed OPLI method shows better accuracy than the existing classical Cepstral, Hough, and Radon transform estimation methods for underwater images.Keywords: image restoration, motion blur, parameter estimation, radon transform, underwater
Procedia PDF Downloads 168189 Local Directional Encoded Derivative Binary Pattern Based Coral Image Classification Using Weighted Distance Gray Wolf Optimization Algorithm
Authors: Annalakshmi G., Sakthivel Murugan S.
Abstract:
This paper presents a local directional encoded derivative binary pattern (LDEDBP) feature extraction method that can be applied for the classification of submarine coral reef images. The classification of coral reef images using texture features is difficult due to the dissimilarities in class samples. In coral reef image classification, texture features are extracted using the proposed method called local directional encoded derivative binary pattern (LDEDBP). The proposed approach extracts the complete structural arrangement of the local region using local binary batten (LBP) and also extracts the edge information using local directional pattern (LDP) from the edge response available in a particular region, thereby achieving extra discriminative feature value. Typically the LDP extracts the edge details in all eight directions. The process of integrating edge responses along with the local binary pattern achieves a more robust texture descriptor than the other descriptors used in texture feature extraction methods. Finally, the proposed technique is applied to an extreme learning machine (ELM) method with a meta-heuristic algorithm known as weighted distance grey wolf optimizer (GWO) to optimize the input weight and biases of single-hidden-layer feed-forward neural networks (SLFN). In the empirical results, ELM-WDGWO demonstrated their better performance in terms of accuracy on all coral datasets, namely RSMAS, EILAT, EILAT2, and MLC, compared with other state-of-the-art algorithms. The proposed method achieves the highest overall classification accuracy of 94% compared to the other state of art methods.Keywords: feature extraction, local directional pattern, ELM classifier, GWO optimization
Procedia PDF Downloads 152188 Enhancement of Underwater Haze Image with Edge Reveal Using Pixel Normalization
Authors: M. Dhana Lakshmi, S. Sakthivel Murugan
Abstract:
As light passes from source to observer in the water medium, it is scattered by the suspended particulate matter. This scattering effect will plague the captured images with non-uniform illumination, blurring details, halo artefacts, weak edges, etc. To overcome this, pixel normalization with an Amended Unsharp Mask (AUM) filter is proposed to enhance the degraded image. To validate the robustness of the proposed technique irrespective of atmospheric light, the considered datasets are collected on dual locations. For those images, the maxima and minima pixel intensity value is computed and normalized; then the AUM filter is applied to strengthen the blurred edges. Finally, the enhanced image is obtained with good illumination and contrast. Thus, the proposed technique removes the effect of scattering called de-hazing and restores the perceptual information with enhanced edge detail. Both qualitative and quantitative analyses are done on considering the standard non-reference metric called underwater image sharpness measure (UISM), and underwater image quality measure (UIQM) is used to measure color, sharpness, and contrast for both of the location images. It is observed that the proposed technique has shown overwhelming performance compared to other deep-based enhancement networks and traditional techniques in an adaptive manner.Keywords: underwater drone imagery, pixel normalization, thresholding, masking, unsharp mask filter
Procedia PDF Downloads 187187 Possibility of Making Ceramic Models from Condemned Plaster of Paris (Pop) Moulds for Ceramics Production in Edo State Nigeria
Authors: Osariyekemwen, Daniel Nosakhare
Abstract:
Some ceramic wastes, such as discarded (condemn) Plaster of Paris (POP) in Auchi Polytechnic, Edo State, constitute environmental hazards. This study, therefore, bridges the forgoing gaps by undertaking the use of these discarded (POP) moulds to produced ceramic models for making casting moulds for mass production. This is in line with the possibility of using this medium to properly manage the discarded (condemn) Plaster of Paris (POP) that littered our immediate environment. Presently these are major wastes disposal in the department. Hence, the study has been made to fabricate sanitary miniature models and contract fuse models, respectively. Findings arising from this study show that discarded (condemn) Plaster of Paris (POP) can be carved when to set it neither shrink nor expand; hence warping is quite unusual. Above all, it also gives good finishing with little deterioration with time when compared to clay models.Keywords: plaster of Paris, condemn, moulds, models, production
Procedia PDF Downloads 178186 The Impact of Liquid Glass-Infused Lignin Waste Particles on Performance of Polyurethane Foam for Building Industry
Authors: Agnė Kairyte, Saulius Vaitkus
Abstract:
The gradual depletion of fossil feedstock and growing environmental concerns attracted extensive attention to natural resources due to their low cost, high abundance, renewability, sustainability, and biodegradability. Lignin is a significant by-product of the pulp and paper industry, having unique functional groups. Recently it became interesting for the manufacturing of high value-added products such as polyurethane and polyisocyanurate foams. This study focuses on the development of high-performance polyurethane foams with various amounts of lignin as a filler. It is determined that the incorporation of lignin as a filler material results in brittle and hard products due to the low molecular mobility of isocyanates and the inherent stiffness of lignin. Therefore, the current study analyses new techniques and possibilities of liquid glass infusion onto the surface of lignin particles to reduce the negative aspects and improve the performance characteristics of the modified foams. The foams modified with sole lignin and liquid glass-infused lignin had an apparent density ranging from 35 kg/m3 to 45 kg/m3 and closed-cell content (80–90%). The incorporation of sole lignin reduced the compressive and tensile strengths and increased dimensional stability and water absorption, while the contrary results were observed for polyurethane foams with liquid glass-infused lignin particles. The effect on rheological parameters of lignin and liquid glass infused lignin modified polyurethane premixes and morphology of polyurethane foam products were monitored to optimize the conditions and reveal the significant influence of the interaction between particles and polymer matrix.Keywords: filler, lignin waste, liquid glass, polymer matrix, polyurethane foam, sustainability
Procedia PDF Downloads 198185 Multi-Sensor Target Tracking Using Ensemble Learning
Authors: Bhekisipho Twala, Mantepu Masetshaba, Ramapulana Nkoana
Abstract:
Multiple classifier systems combine several individual classifiers to deliver a final classification decision. However, an increasingly controversial question is whether such systems can outperform the single best classifier, and if so, what form of multiple classifiers system yields the most significant benefit. Also, multi-target tracking detection using multiple sensors is an important research field in mobile techniques and military applications. In this paper, several multiple classifiers systems are evaluated in terms of their ability to predict a system’s failure or success for multi-sensor target tracking tasks. The Bristol Eden project dataset is utilised for this task. Experimental and simulation results show that the human activity identification system can fulfill requirements of target tracking due to improved sensors classification performances with multiple classifier systems constructed using boosting achieving higher accuracy rates.Keywords: single classifier, ensemble learning, multi-target tracking, multiple classifiers
Procedia PDF Downloads 249184 Study on Temperature Distribution throughout the Continuous Casting Process of Copper Magnesium Alloys
Authors: Paweł Strzępek, Małgorzata Zasadzińska, Szymon Kordaszewski, Wojciech Ściężor
Abstract:
The constant tendency toward the materials properties improvement nowadays creates opportunities for the scientists, and furthermore the manufacturers all over the world to design, form and produce new alloys almost every day. Considering the fact that companies all over the world look for alloys with the highest values of mechanical properties coexisting with a reasonable electrical conductivity made it necessary to develop new materials based on copper, such as copper magnesium alloys with over 2 wt. % of Mg. Though, before such new material may be mass produced it must undergo a series of tests in order to determine the production technology and its parameters. The presented study is based on the numerical simulations calculated with the use of finite element method analysis, where the geometry of the cooling system, the material used to produce the cooling system and the surface quality of the graphite crystallizer at the place of contact with the cooling system and its influence on the temperatures throughout the continuous casting process is being investigated. The calculated simulations made it possible to propose the optimal set of equipment necessary for the continuous casting process to be carried out in laboratory conditions with various casting parameters and to determine basic materials properties of the obtained alloys such as hardness, electrical conductivity and homogeneity of the chemical composition. The authors are grateful for the financial support provided by The National Centre for Research and Development – Research Project No. LIDER/33/0121/L-11/19/NCBR/2020.Keywords: CuMg alloys, continuous casting, temperature analysis, finite element method
Procedia PDF Downloads 199183 Mathematical Modeling and Optimization of Burnishing Parameters for 15NiCr6 Steel
Authors: Tarek Litim, Ouahiba Taamallah
Abstract:
The present paper is an investigation of the effect of burnishing on the surface integrity of a component made of 15NiCr6 steel. This work shows a statistical study based on regression, and Taguchi's design has allowed the development of mathematical models to predict the output responses as a function of the technological parameters studied. The response surface methodology (RSM) showed a simultaneous influence of the burnishing parameters and observe the optimal processing parameters. ANOVA analysis of the results resulted in the validation of the prediction model with a determination coefficient R=90.60% and 92.41% for roughness and hardness, respectively. Furthermore, a multi-objective optimization allowed to identify a regime characterized by P=10kgf, i=3passes, and f=0.074mm/rev, which favours minimum roughness and maximum hardness. The result was validated by the desirability of D= (0.99 and 0.95) for roughness and hardness, respectively.Keywords: 15NiCr6 steel, burnishing, surface integrity, Taguchi, RSM, ANOVA
Procedia PDF Downloads 186182 Hardware Implementation for the Contact Force Reconstruction in Tactile Sensor Arrays
Authors: María-Luisa Pinto-Salamanca, Wilson-Javier Pérez-Holguín
Abstract:
Reconstruction of contact forces is a fundamental technique for analyzing the properties of a touched object and is essential for regulating the grip force in slip control loops. This is based on the processing of the distribution, intensity, and direction of the forces during the capture of the sensors. Currently, efficient hardware alternatives have been used more frequently in different fields of application, allowing the implementation of computationally complex algorithms, as is the case with tactile signal processing. The use of hardware for smart tactile sensing systems is a research area that promises to improve the processing time and portability requirements of applications such as artificial skin and robotics, among others. The literature review shows that hardware implementations are present today in almost all stages of smart tactile detection systems except in the force reconstruction process, a stage in which they have been less applied. This work presents a hardware implementation of a model-driven reported in the literature for the contact force reconstruction of flat and rigid tactile sensor arrays from normal stress data. From the analysis of a software implementation of such a model, this implementation proposes the parallelization of tasks that facilitate the execution of matrix operations and a two-dimensional optimization function to obtain a vector force by each taxel in the array. This work seeks to take advantage of the parallel hardware characteristics of Field Programmable Gate Arrays, FPGAs, and the possibility of applying appropriate techniques for algorithms parallelization using as a guide the rules of generalization, efficiency, and scalability in the tactile decoding process and considering the low latency, low power consumption, and real-time execution as the main parameters of design. The results show a maximum estimation error of 32% in the tangential forces and 22% in the normal forces with respect to the simulation by the Finite Element Modeling (FEM) technique of Hertzian and non-Hertzian contact events, over sensor arrays of 10×10 taxels of different sizes. The hardware implementation was carried out on an MPSoC XCZU9EG-2FFVB1156 platform of Xilinx® that allows the reconstruction of force vectors following a scalable approach, from the information captured by means of tactile sensor arrays composed of up to 48 × 48 taxels that use various transduction technologies. The proposed implementation demonstrates a reduction in estimation time of x / 180 compared to software implementations. Despite the relatively high values of the estimation errors, the information provided by this implementation on the tangential and normal tractions and the triaxial reconstruction of forces allows to adequately reconstruct the tactile properties of the touched object, which are similar to those obtained in the software implementation and in the two FEM simulations taken as reference. Although errors could be reduced, the proposed implementation is useful for decoding contact forces for portable tactile sensing systems, thus helping to expand electronic skin applications in robotic and biomedical contexts.Keywords: contact forces reconstruction, forces estimation, tactile sensor array, hardware implementation
Procedia PDF Downloads 186181 Development of Multilayer Capillary Copper Wick Structure using Microsecond CO₂ Pulsed Laser
Authors: Talha Khan, Surendhar Kumaran, Rajeev Nair
Abstract:
The development of economical, efficient, and reliable next-generation thermal and water management systems to provide efficient cooling and water management technologies is being pursued application in compact and lightweight spacecraft. The elimination of liquid-vapor phase change-based thermal and water management systems is being done due to issues with the reliability and robustness of this technology. To achieve the motive of implementing the principle of using an innovative evaporator and condenser design utilizing bimodal wicks manufactured using a microsecond pulsed CO₂ laser has been proposed in this study. Cylin drical, multilayered capillary copper wicks with a substrate diameter of 39 mm are additively manufactured using a pulsed laser. The copper particles used for layer-by-layer addition on the substrate measure in a diameter range of 225 to 450 micrometers. The primary objective is to develop a novel, high-quality, fast turnaround, laser-based additive manufacturing process that will eliminate the current technical challenges involved with the traditional manufacturing processes for nano/micro-sized powders, like particle agglomeration. Raster-scanned, pulsed-laser sintering process has been developed to manufacture 3D wicks with controlled porosity and permeability.Keywords: liquid-vapor phase change, bimodal wicks, multilayered, capillary, raster-scanned, porosity, permeability
Procedia PDF Downloads 178