Search results for: tilt-rotor modeling and simulation
3474 Three-Dimensional Jet Refraction Simulation Using a Gradient Term Suppression and Filtering Method
Authors: Lican Wang, Rongqian Chen, Yancheng You, Ruofan Qiu
Abstract:
In the applications of jet engine, open-jet wind tunnel and airframe, there wildly exists a shear layer formed by the velocity and temperature gradients between jet flow and surrounded medium. The presence of shear layer will refract and reflect the sound path that consequently influences the measurement results in far-field. To investigate and evaluate the shear layer effect, a gradient term suppression and filtering method is adopted to simulate sound propagation through a steady sheared flow in three dimensions. Two typical configurations are considered: one is an incompressible and cold jet flow in wind tunnel and the other is a compressible and hot jet flow in turbofan engine. A numerically linear microphone array is used to localize the position of given sound source. The localization error is presented and linearly fitted.Keywords: aeroacoustic, linearized Euler equation, acoustic propagation, source localization
Procedia PDF Downloads 2093473 Design of a Sliding Mode Control Using Nonlinear Sliding Surface and Nonlinear Observer Applied to the Trirotor Mini-Aircraft
Authors: Samir Zeghlache, Abderrahmen Bouguerra, Kamel Kara, Djamel Saigaa
Abstract:
The control of the trirotor helicopter includes nonlinearities, uncertainties and external perturbations that should be considered in the design of control laws. This paper presents a control strategy for an underactuated six degrees of freedom (6 DOF) trirotor helicopter, based on the coupling of the fuzzy logic control and sliding mode control (SMC). The main purpose of this work is to eliminate the chattering phenomenon. To achieve our purpose we have used a fuzzy logic control to generate the hitting control signal, also the non linear observer is then synthesized in order to estimate the unmeasured states. Finally simulation results are included to indicate the trirotor UAV with the proposed controller can greatly alleviate the chattering effect and remain robust to the external disturbances.Keywords: fuzzy sliding mode control, trirotor helicopter, dynamic modelling, underactuated systems
Procedia PDF Downloads 5393472 Investigating Smoothness: An In-Depth Study of Extremely Degenerate Elliptic Equations
Authors: Zahid Ullah, Atlas Khan
Abstract:
The presented research is dedicated to an extensive examination of the regularity properties associated with a specific class of equations, namely extremely degenerate elliptic equations. This study holds significance in unraveling the complexities inherent in these equations and understanding the smoothness of their solutions. The focus is on analyzing the regularity of results, aiming to contribute to the broader field of mathematical theory. By delving into the intricacies of extremely degenerate elliptic equations, the research seeks to advance our understanding beyond conventional analyses, addressing challenges posed by degeneracy and pushing the boundaries of classical analytical methods. The motivation for this exploration lies in the practical applicability of mathematical models, particularly in real-world scenarios where physical phenomena exhibit characteristics that challenge traditional mathematical modeling. The research aspires to fill gaps in the current understanding of regularity properties within solutions to extremely degenerate elliptic equations, ultimately contributing to both theoretical foundations and practical applications in diverse scientific fields.Keywords: investigating smoothness, extremely degenerate elliptic equations, regularity properties, mathematical analysis, complexity solutions
Procedia PDF Downloads 663471 The Relationships between the Feelings of Bullying, Self- Esteem, Employee Silence, Anger, Self- Blame and Shame
Authors: Şebnem Aslan, Demet Akarçay
Abstract:
The objective of this study is to investigate the feelings of health employees occurred by bullying and the relationships between these feelings at work place. In this context, the relationships between bullying and the feelings of self-esteem, employee silence, anger, self- blame and shame. This study was conducted among 512 health employees in three hospitals in Konya by using survey method and simple random sampling. The scales of bullying, self-esteem, employee silence, anger, self-blame, and shame were performed within the study. The obtained data were analyzed with descriptive analysis, correlation, confirmative factor analysis, structural equation modeling and path analysis. The results of the study showed that while bullying had a positive effect on self-esteem (.61), employee silence (.41), anger (.18), a negative effect on self-blame and shame (-.26) was observed. Employee silence affected self-blame and shame (.83) as positively. Besides, self-esteem impacted on self- blame and shame (.18), employee silence (.62) positively and self-blame and shame was observed as negatively affecting on anger (-.20). Similarly, self-esteem was found as negatively affected on anger (-.13).Keywords: bullying, self-esteem, employee silence, anger, shame and guilt, healthcare employee
Procedia PDF Downloads 3003470 Optimization Analysis of a Concentric Tube Heat Exchanger with Field Synergy Principle
Abstract:
The paper investigates the optimization analysis to the heat exchanger design, mainly with response surface method and genetic algorithm to explore the relationship between optimal fluid flow velocity and temperature of the heat exchanger using field synergy principle. First, finite volume method is proposed to calculate the flow temperature and flow rate distribution for numerical analysis. We identify the most suitable simulation equations by response surface methodology. Furthermore, a genetic algorithm approach is applied to optimize the relationship between fluid flow velocity and flow temperature of the heat exchanger. The results show that the field synergy angle plays vital role in the performance of a true heat exchanger.Keywords: optimization analysis, field synergy, heat exchanger, genetic algorithm
Procedia PDF Downloads 3143469 A Multilevel Authentication Protocol: MAP in VANET for Human Safety
Authors: N. Meddeb, A. M. Makhlouf, M. A. Ben Ayed
Abstract:
Due to the real-time requirement of message in Vehicular Ad hoc NETworks (VANET), it is necessary to authenticate vehicles to achieve security, efficiency, and conditional privacy-preserving. Privacy is of utmost relevance in VANETs. For this reason, we have proposed a new protocol called ‘Multilevel Authentication Protocol’ (MAP) that considers different vehicle categories. The proposed protocol is based on our Multilevel Authentication protocol for Vehicular networks (MAVnet). But the MAP leads to human safety, where the priority is given to the ambulance vehicles. For evaluation, we used the Java language to develop a demo application and deployed it on the Network Security Simulation (Nessi2). Compared with existing authentication protocols, MAP markedly enhance the communication overhead and decreases the delay of exchanging messages while preserving conditional privacy.Keywords: Vehicular Ad hoc NETworks (VANET), vehicle categories, safety, databases, privacy, authentication, throughput, delay
Procedia PDF Downloads 3043468 Optimization and Operation of Charging and Discharging Stations for Hybrid Cars and their Effects on the Electricity Distribution Network
Authors: Ali Heydarimoghim
Abstract:
In this paper, the optimal placement of charging and discharging stations is done to determine the location and capacity of the stations, reducing the cost of electric vehicle owners' losses, reducing the cost of distribution system losses, and reducing the costs associated with the stations. Also, observing the permissible limits of the bus voltage and the capacity of the stations and their distance are considered as constraints of the problem. Given the traffic situation in different areas of a city, we estimate the amount of energy required to charge and the amount of energy provided to discharge electric vehicles in each area. We then introduce the electricity distribution system of the city in question. Following are the scenarios for introducing the problem and introducing the objective and constraint functions. Finally, the simulation results for different scenarios are compared.Keywords: charging & discharging stations, hybrid vehicles, optimization, replacement
Procedia PDF Downloads 1413467 Reliability Analysis for Cyclic Fatigue Life Prediction in Railroad Bolt Hole
Authors: Hasan Keshavarzian, Tayebeh Nesari
Abstract:
Bolted rail joint is one of the most vulnerable areas in railway track. A comprehensive approach was developed for studying the reliability of fatigue crack initiation of railroad bolt hole under random axle loads and random material properties. The operation condition was also considered as stochastic variables. In order to obtain the comprehensive probability model of fatigue crack initiation life prediction in railroad bolt hole, we used FEM, response surface method (RSM), and reliability analysis. Combined energy-density based and critical plane based fatigue concept is used for the fatigue crack prediction. The dynamic loads were calculated according to the axle load, speed, and track properties. The results show that axle load is most sensitive parameter compared to Poisson’s ratio in fatigue crack initiation life. Also, the reliability index decreases slowly due to high cycle fatigue regime in this area.Keywords: rail-wheel tribology, rolling contact mechanic, finite element modeling, reliability analysis
Procedia PDF Downloads 3833466 Intelligent Computing with Bayesian Regularization Artificial Neural Networks for a Nonlinear System of COVID-19 Epidemic Model for Future Generation Disease Control
Authors: Tahir Nawaz Cheema, Dumitru Baleanu, Ali Raza
Abstract:
In this research work, we design intelligent computing through Bayesian Regularization artificial neural networks (BRANNs) introduced to solve the mathematical modeling of infectious diseases (Covid-19). The dynamical transmission is due to the interaction of people and its mathematical representation based on the system's nonlinear differential equations. The generation of the dataset of the Covid-19 model is exploited by the power of the explicit Runge Kutta method for different countries of the world like India, Pakistan, Italy, and many more. The generated dataset is approximately used for training, testing, and validation processes for every frequent update in Bayesian Regularization backpropagation for numerical behavior of the dynamics of the Covid-19 model. The performance and effectiveness of designed methodology BRANNs are checked through mean squared error, error histograms, numerical solutions, absolute error, and regression analysis.Keywords: mathematical models, beysian regularization, bayesian-regularization backpropagation networks, regression analysis, numerical computing
Procedia PDF Downloads 1523465 Potential Impact of Climate Change on Suspended Sediment Changes in Mekong River Basin
Authors: Zuliziana Suif, Nordila Ahmad, Sengheng Hul
Abstract:
This paper evaluates the impact of climate change on suspended sediment changes in the Mekong River Basin. In this study, the distributed process-based sediment transport model is used to examine the potential impact of future climate on suspended sediment dynamic changes in the Mekong River Basin. To this end, climate scenarios from two General Circulation Model (GCMs) were considered in the scenario analysis. The simulation results show that the sediment load and concentration shows 0.64% to 69% increase in the near future (2041-2050) and 2.5% to 95% in the far future (2090- 2099). As the projected climate change impact on sediment varies remarkably between the different climate models, the uncertainty should be taken into account in sediment management. Overall, the changes in sediment load and concentration can have a great implication for related sediment management.Keywords: climate change, suspended sediment, Mekong River Basin, GCMs
Procedia PDF Downloads 4453464 Modeling and Optimization of Algae Oil Extraction Using Response Surface Methodology
Authors: I. F. Ejim, F. L. Kamen
Abstract:
Aims: In this experiment, algae oil extraction with a combination of n-hexane and ethanol was investigated. The effects of extraction solvent concentration, extraction time and temperature on the yield and quality of oil were studied using Response Surface Methodology (RSM). Experimental Design: Optimization of algae oil extraction using Box-Behnken design was used to generate 17 experimental runs in a three-factor-three-level design where oil yield, specific gravity, acid value and saponification value were evaluated as the response. Result: In this result, a minimum oil yield of 17% and maximum of 44% was realized. The optimum values for yield, specific gravity, acid value and saponification value from the overlay plot were 40.79%, 0.8788, 0.5056 mg KOH/g and 180.78 mg KOH/g respectively with desirability of 0.801. The maximum point prediction was yield 40.79% at solvent concentration 66.68 n-hexane, temperature of 40.0°C and extraction time of 4 hrs. Analysis of Variance (ANOVA) results showed that the linear and quadratic coefficient were all significant at p<0.05. The experiment was validated and results obtained were with the predicted values. Conclusion: Algae oil extraction was successfully optimized using RSM and its quality indicated it is suitable for many industrial uses.Keywords: algae oil, response surface methodology, optimization, Box-Bohnken, extraction
Procedia PDF Downloads 3443463 Point Estimation for the Type II Generalized Logistic Distribution Based on Progressively Censored Data
Authors: Rana Rimawi, Ayman Baklizi
Abstract:
Skewed distributions are important models that are frequently used in applications. Generalized distributions form a class of skewed distributions and gain widespread use in applications because of their flexibility in data analysis. More specifically, the Generalized Logistic Distribution with its different types has received considerable attention recently. In this study, based on progressively type-II censored data, we will consider point estimation in type II Generalized Logistic Distribution (Type II GLD). We will develop several estimators for its unknown parameters, including maximum likelihood estimators (MLE), Bayes estimators and linear estimators (BLUE). The estimators will be compared using simulation based on the criteria of bias and Mean square error (MSE). An illustrative example of a real data set will be given.Keywords: point estimation, type II generalized logistic distribution, progressive censoring, maximum likelihood estimation
Procedia PDF Downloads 2023462 Fall Avoidance Control of Wheeled Inverted Pendulum Type Robotic Wheelchair While Climbing Stairs
Authors: Nan Ding, Motoki Shino, Nobuyasu Tomokuni, Genki Murata
Abstract:
The wheelchair is the major means of transport for physically disabled people. However, it cannot overcome architectural barriers such as curbs and stairs. In this paper, the authors proposed a method to avoid falling down of a wheeled inverted pendulum type robotic wheelchair for climbing stairs. The problem of this system is that the feedback gain of the wheels cannot be set high due to modeling errors and gear backlash, which results in the movement of wheels. Therefore, the wheels slide down the stairs or collide with the side of the stairs, and finally the wheelchair falls down. To avoid falling down, the authors proposed a slider control strategy based on skyhook model in order to decrease the movement of wheels, and a rotary link control strategy based on the staircase dimensions in order to avoid collision or slide down. The effectiveness of the proposed fall avoidance control strategy was validated by ODE simulations and the prototype wheelchair.Keywords: EPW, fall avoidance control, skyhook, wheeled inverted pendulum
Procedia PDF Downloads 3363461 Modelling for Temperature Non-Isothermal Continuous Stirred Tank Reactor Using Fuzzy Logic
Authors: Nasser Mohamed Ramli, Mohamad Syafiq Mohamad
Abstract:
Many types of controllers were applied on the continuous stirred tank reactor (CSTR) unit to control the temperature. In this research paper, Proportional-Integral-Derivative (PID) controller are compared with Fuzzy Logic controller for temperature control of CSTR. The control system for temperature non-isothermal of a CSTR will produce a stable response curve to its set point temperature. A mathematical model of a CSTR using the most general operating condition was developed through a set of differential equations into S-function using MATLAB. The reactor model and S-function are developed using m.file. After developing the S-function of CSTR model, User-Defined functions are used to link to SIMULINK file. Results that are obtained from simulation and temperature control were better when using Fuzzy logic control compared to PID control.Keywords: CSTR, temperature, PID, fuzzy logic
Procedia PDF Downloads 4643460 A New Approach for Improving Accuracy of Multi Label Stream Data
Authors: Kunal Shah, Swati Patel
Abstract:
Many real world problems involve data which can be considered as multi-label data streams. Efficient methods exist for multi-label classification in non streaming scenarios. However, learning in evolving streaming scenarios is more challenging, as the learners must be able to adapt to change using limited time and memory. Classification is used to predict class of unseen instance as accurate as possible. Multi label classification is a variant of single label classification where set of labels associated with single instance. Multi label classification is used by modern applications, such as text classification, functional genomics, image classification, music categorization etc. This paper introduces the task of multi-label classification, methods for multi-label classification and evolution measure for multi-label classification. Also, comparative analysis of multi label classification methods on the basis of theoretical study, and then on the basis of simulation was done on various data sets.Keywords: binary relevance, concept drift, data stream mining, MLSC, multiple window with buffer
Procedia PDF Downloads 5913459 The Status of BIM Adoption in Six Continents
Authors: Wooyoung Jung, Ghang Lee
Abstract:
This paper paper reports the worldwide status of building information modeling (BIM) adoption from the perspectives of the engagement level, the Hype Cycle model, the technology diffusion model, and BIM-uses. An online survey was distributed, and 156 experts from six continents responded. Overall, North America was the most advanced continent, followed by Oceania and Europe. Countries in Asia perceived their phase mainly as slope of enlightenment (mature) in the Hype Cycle model. In the technology diffusion model, the main BIM-users worldwide were “early majority” (third phase), but those in the Middle East/Africa and South America were “early adopters” (second phase). In addition, the more advanced the country, the more number of BIM services employed in general. In summary, North America, Europe, Oceania, and Asia were advancing rapidly toward the mature stage of BIM, whereas the Middle East/Africa and South America were still in the early phase. The simple indexes used in this study may be used to track the worldwide status of BIM adoption in long-term surveys.Keywords: BIM adoption, BIM services, hype cycle model, technology diffusion model
Procedia PDF Downloads 5623458 Design and Analysis of a Rear Bumper of an Automobile with a Hybrid Polymer Composite of Oil Palm Empty Fruit Bunch Fiber/Banana Fibres
Authors: S. O. Ologe, U. P. Anaidhuno, Duru C. A.
Abstract:
This research investigated the design and analysis of a rear bumper of an automobile with a hybrid polymer composite of OPEBF/Banana fibre. OPEBF/Banana fibre hybrid polymers composite is of low cost, lightweight, as well as possesses satisfactory mechanical properties. In this research work, hybrid composites have been developed using the hand layup technique based on the percentage combination of OPEBF/Banana fibre at 10:90, 20:80, 30:70, 40:60, 50:50. 60:40, 70:30. 20:80, 90:10, 95:5. The mechanical properties in the context of compressive strength of 65MPa, a flexural strength of 20MPa, and impact strength of 3.25Joule were observed, and the simulation analysis on the induction of 500N load at the factor of safety of 3 was observed to have displayed a good strength suitable for automobile bumper with the advantages of weight reduction.Keywords: OPEBF, Banana, fibre, hybrid
Procedia PDF Downloads 1223457 Efficient Tuning Parameter Selection by Cross-Validated Score in High Dimensional Models
Authors: Yoonsuh Jung
Abstract:
As DNA microarray data contain relatively small sample size compared to the number of genes, high dimensional models are often employed. In high dimensional models, the selection of tuning parameter (or, penalty parameter) is often one of the crucial parts of the modeling. Cross-validation is one of the most common methods for the tuning parameter selection, which selects a parameter value with the smallest cross-validated score. However, selecting a single value as an "optimal" value for the parameter can be very unstable due to the sampling variation since the sample sizes of microarray data are often small. Our approach is to choose multiple candidates of tuning parameter first, then average the candidates with different weights depending on their performance. The additional step of estimating the weights and averaging the candidates rarely increase the computational cost, while it can considerably improve the traditional cross-validation. We show that the selected value from the suggested methods often lead to stable parameter selection as well as improved detection of significant genetic variables compared to the tradition cross-validation via real data and simulated data sets.Keywords: cross validation, parameter averaging, parameter selection, regularization parameter search
Procedia PDF Downloads 4173456 Experimental and CFD of Desgined Small Wind Turbine
Authors: Tarek A. Mekail, Walid M. A. Elmagid
Abstract:
Many researches have concentrated on improving the aerodynamic performance of wind turbine blade through testing and theoretical studies. A small wind turbine blade is designed, fabricated and tested. The power performance of small horizontal axis wind turbines is simulated in details using Computational Fluid Dynamic (CFD). The three-dimensional CFD models are presented using ANSYS-CFX v13 software for predicting the performance of a small horizontal axis wind turbine. The simulation results are compared with the experimental data measured from a small wind turbine model, which designed according to a vehicle-based test system. The analysis of wake effect and aerodynamic of the blade can be carried out when the rotational effect was simulated. Finally, comparison between experimental, numerical and analytical performance has been done. The comparison is fairly good.Keywords: small wind turbine, CFD of wind turbine, CFD, performance of wind turbine, test of small wind turbine, wind turbine aerodynamic, 3D model
Procedia PDF Downloads 5473455 Comparison between Continuous Genetic Algorithms and Particle Swarm Optimization for Distribution Network Reconfiguration
Authors: Linh Nguyen Tung, Anh Truong Viet, Nghien Nguyen Ba, Chuong Trinh Trong
Abstract:
This paper proposes a reconfiguration methodology based on a continuous genetic algorithm (CGA) and particle swarm optimization (PSO) for minimizing active power loss and minimizing voltage deviation. Both algorithms are adapted using graph theory to generate feasible individuals, and the modified crossover is used for continuous variable of CGA. To demonstrate the performance and effectiveness of the proposed methods, a comparative analysis of CGA with PSO for network reconfiguration, on 33-node and 119-bus radial distribution system is presented. The simulation results have shown that both CGA and PSO can be used in the distribution network reconfiguration and CGA outperformed PSO with significant success rate in finding optimal distribution network configuration.Keywords: distribution network reconfiguration, particle swarm optimization, continuous genetic algorithm, power loss reduction, voltage deviation
Procedia PDF Downloads 1943454 Vulnerability of Groundwater to Pollution in Akwa Ibom State, Southern Nigeria, using the DRASTIC Model and Geographic Information System (GIS)
Authors: Aniedi A. Udo, Magnus U. Igboekwe, Rasaaq Bello, Francis D. Eyenaka, Michael C. Ohakwere-Eze
Abstract:
Groundwater vulnerability to pollution was assessed in Akwa Ibom State, Southern Nigeria, with the aim of locating areas with high potentials for resource contamination, especially due to anthropogenic influence. The electrical resistivity method was utilized in the collection of the initial field data. Additional data input, which included depth to static water level, drilled well log data, aquifer recharge data, percentage slope, as well as soil information, were sourced from secondary sources. The initial field data were interpreted both manually and with computer modeling to provide information on the geoelectric properties of the subsurface. Interpreted results together with the secondary data were used to develop the DRASTIC thematic maps. A vulnerability assessment was performed using the DRASTIC model in a GIS environment and areas with high vulnerability which needed immediate attention was clearly mapped out and presented using an aquifer vulnerability map. The model was subjected to validation and the rate of validity was 73% within the area of study.Keywords: groundwater, vulnerability, DRASTIC model, pollution
Procedia PDF Downloads 2113453 A Model Predictive Control Based Virtual Active Power Filter Using V2G Technology
Authors: Mahdi Zolfaghari, Seyed Hossein Hosseinian, Hossein Askarian Abyaneh, Mehrdad Abedi
Abstract:
This paper presents a virtual active power filter (VAPF) using vehicle to grid (V2G) technology to maintain power quality requirements. The optimal discrete operation of the power converter of electric vehicle (EV) is based on recognizing desired switching states using the model predictive control (MPC) algorithm. A fast dynamic response, lower total harmonic distortion (THD) and good reference tracking performance are realized through the presented control strategy. The simulation results using MATLAB/Simulink validate the effectiveness of the scheme in improving power quality as well as good dynamic response in power transferring capability.Keywords: electric vehicle, model predictive control, power quality, V2G technology, virtual active power filter
Procedia PDF Downloads 4373452 Simulated Microgravity Inhibits L-Type Calcium Channel Currents by Up-Regulation of miR-103 in Osteoblasts
Authors: Zhongyang Sun, Shu Zhang
Abstract:
In osteoblasts, L-type voltage sensitive calcium channels (LTCCs), especially the Cav1.2 LTCCs, play fundamental roles in cellular responses to external stimuli including both mechanical forces and hormonal signals. Several lines of evidence have revealed that the density of bone is increased and the resorption of bone is decreased when these calcium channels in osteoblasts are activated. And numerous studies have shown that mechanical loading promotes bone formation in the modeling skeleton, whereas removal of this stimulus in microgravity results in a reduction in bone mass. However, the effect of microgravity on LTCCs in osteoblasts is still unknown. The aim of this study was to determine whether microgravity exerts influence on LTCCs in osteoblasts and the possible mechanisms underlying. In this study, we demonstrate that simulated microgravity substantially inhibits LTCCs in osteoblast by suppressing the expression of Cav1.2. Then we show that the up-regulation of miR-103 is involved in the down-regulation of Cav1.2 expression and inhibition of LTCCs by simulated microgravity in osteoblasts. Our study provides a novel mechanism of simulated microgravity-induced adverse effects on osteoblasts, offering a new avenue to further investigate the bone loss caused by microgravity.Keywords: L-type voltage sensitive calcium channels, Cav1.2, osteoblasts, microgravity
Procedia PDF Downloads 3093451 Comparative Analysis of Predictive Models for Customer Churn Prediction in the Telecommunication Industry
Authors: Deepika Christopher, Garima Anand
Abstract:
To determine the best model for churn prediction in the telecom industry, this paper compares 11 machine learning algorithms, namely Logistic Regression, Support Vector Machine, Random Forest, Decision Tree, XGBoost, LightGBM, Cat Boost, AdaBoost, Extra Trees, Deep Neural Network, and Hybrid Model (MLPClassifier). It also aims to pinpoint the top three factors that lead to customer churn and conducts customer segmentation to identify vulnerable groups. According to the data, the Logistic Regression model performs the best, with an F1 score of 0.6215, 81.76% accuracy, 68.95% precision, and 56.57% recall. The top three attributes that cause churn are found to be tenure, Internet Service Fiber optic, and Internet Service DSL; conversely, the top three models in this article that perform the best are Logistic Regression, Deep Neural Network, and AdaBoost. The K means algorithm is applied to establish and analyze four different customer clusters. This study has effectively identified customers that are at risk of churn and may be utilized to develop and execute strategies that lower customer attrition.Keywords: attrition, retention, predictive modeling, customer segmentation, telecommunications
Procedia PDF Downloads 633450 A Deep Learning-Based Pedestrian Trajectory Prediction Algorithm
Authors: Haozhe Xiang
Abstract:
With the rise of the Internet of Things era, intelligent products are gradually integrating into people's lives. Pedestrian trajectory prediction has become a key issue, which is crucial for the motion path planning of intelligent agents such as autonomous vehicles, robots, and drones. In the current technological context, deep learning technology is becoming increasingly sophisticated and gradually replacing traditional models. The pedestrian trajectory prediction algorithm combining neural networks and attention mechanisms has significantly improved prediction accuracy. Based on in-depth research on deep learning and pedestrian trajectory prediction algorithms, this article focuses on physical environment modeling and learning of historical trajectory time dependence. At the same time, social interaction between pedestrians and scene interaction between pedestrians and the environment were handled. An improved pedestrian trajectory prediction algorithm is proposed by analyzing the existing model architecture. With the help of these improvements, acceptable predicted trajectories were successfully obtained. Experiments on public datasets have demonstrated the algorithm's effectiveness and achieved acceptable results.Keywords: deep learning, graph convolutional network, attention mechanism, LSTM
Procedia PDF Downloads 783449 Simulation the Stress Distribution of Wheel/Rail at Contact Region
Authors: Norie A. Akeel, Z. Sajuri, A. K. Ariffin
Abstract:
This paper discusses the effect of different loading analysis on crack initiation life of wheel/rail in the contact region. A simulated three dimensional (3D) elasto plastic model of a wheel/rail contact is modeled using the fine mesh technique in the contact region by using Finite Element Method FEM code ANSYS 11.0 software. Different loads of approximately from 70 to 140 KN was applied on the wheel tread through the running surface on the railhead surface to simulate stress distribution (Von Mises) and a life prediction of the crack initiation under rolling contact motion. Stress analysis is achieved and the fatigue life to the rail head surface is calculated numerically by using a multi-axial fatigue life of crack initiation model. All results obtained from the previous researches are compared with this research.Keywords: FEM, rolling contact, rail track, stress distribution, fatigue life
Procedia PDF Downloads 5583448 Artificial Neural Networks Controller for Active Power Filter Connected to a Photovoltaic Array
Authors: Rachid Dehini, Brahim Berbaoui
Abstract:
The main objectives of shunt active power filter (SAPF) is to preserve the power system from unwanted harmonic currents produced by nonlinear loads, as well as to compensate the reactive power. The aim of this paper is to present a (PAPF) supplied by the Photovoltaic cells ,in such a way that the (PAPF) feeds the linear and nonlinear loads by harmonics currents and the excess of the energy is injected into the power system. In order to improve the performances of conventional (PAPF) This paper also proposes artificial neural networks (ANN) for harmonics identification and DC link voltage control. The simulation study results of the new (SAPF) identification technique are found quite satisfactory by assuring good filtering characteristics and high system stability.Keywords: SAPF, harmonics current, photovoltaic cells, MPPT, artificial neural networks (ANN)
Procedia PDF Downloads 3373447 Response of Solar Updraft Power Plants Incorporating Material Nonlinearity
Authors: Areeg Shermaddo
Abstract:
Solar updraft power plants (SUPP) provide a great potential for green and environmentally friendly renewable power generation. An up to 1000 m high chimney represents one of the major parts of each SUPP, which consist of the main shell structure and the stiffening rings. Including the nonlinear material behavior in a simulation of the chimney is computationally a demanding task. However, allowing the formation of cracking in concrete leads to a more economical design of the structure. In this work, an FE model of a SUPP is presented incorporating the nonlinear material behavior. The effect of wind loading intensity on the structural response is explored. Furthermore, the influence of the stiffness of the ring beams on the global behavior is as well investigated. The obtained results indicate that the minimum reinforcement is capable of carrying the tensile stresses provided that the ring beams are rather stiff.Keywords: ABAQUS, nonlinear analysis, ring beams, SUPP
Procedia PDF Downloads 2253446 Experimental Investigation of the Effect of Material Composition on Landslides
Authors: Mengqi Wu, Haiping Zhu, Chin J. Leo
Abstract:
In this study, six experimental cases with different components (dry and wet soils and rocks) were considered to elucidate the influence of material composition on landslide profiles. The results show that the accumulation zone for all cases considered has a quadrilateral shape with two different bottom angles. The asymmetry of the accumulation zone can be attributed to the fact that soils in different parts of the landslide sliding can produce different speeds and suffer different resistances. The higher soil moisture can generate stronger cohesion between soils to reduce the volume of the sliding body during the landslide. The rock content can increase the accumulation angles to improve slope stability. The interaction between the irregular shapes of rocks and soils provides more resistance than that between spherical rocks and soils, which causes the slope with irregular rocks and soils to have higher stability.Keywords: landslide, soil moisture, rock content, experimental simulation
Procedia PDF Downloads 1083445 Minimization Entropic Applied to Rotary Dryers to Reduce the Energy Consumption
Authors: I. O. Nascimento, J. T. Manzi
Abstract:
The drying process is an important operation in the chemical industry and it is widely used in the food, grain industry and fertilizer industry. However, for demanding a considerable consumption of energy, such a process requires a deep energetic analysis in order to reduce operating costs. This paper deals with thermodynamic optimization applied to rotary dryers based on the entropy production minimization, aiming at to reduce the energy consumption. To do this, the mass, energy and entropy balance was used for developing a relationship that represents the rate of entropy production. The use of the Second Law of Thermodynamics is essential because it takes into account constraints of nature. Since the entropy production rate is minimized, optimals conditions of operations can be established and the process can obtain a substantial gain in energy saving. The minimization strategy had been led using classical methods such as Lagrange multipliers and implemented in the MATLAB platform. As expected, the preliminary results reveal a significant energy saving by the application of the optimal parameters found by the procedure of the entropy minimization It is important to say that this method has shown easy implementation and low cost.Keywords: thermodynamic optimization, drying, entropy minimization, modeling dryers
Procedia PDF Downloads 265