Search results for: optimizer

Authors: Hao-Su Liu, Jun-Qing Lei

Abstract:

This study introduces the theory of modified particle swarm optimizer and its application in time-domain expressions for bridge self-excited aerodynamic forces. Based on the indicial function expression and the rational function expression in time-domain expression for bridge self-excited aerodynamic forces, the characteristics of the two methods, i.e. the modified particle swarm optimizer and conventional search method, are compared in flutter derivatives’ fitting process. Theoretical analysis and numerical results indicate that adopting whether the indicial function expression or the rational function expression, the fitting flutter derivatives obtained by modified particle swarm optimizer have better goodness of fit with ones obtained from experiment. As to the flutter derivatives which have higher nonlinearity, the self-excited aerodynamic forces, using the flutter derivatives obtained through modified particle swarm optimizer fitting process, are much closer to the ones simulated by the experimental. The modified particle swarm optimizer was used to recognize the parameters of time-domain expressions for flutter derivatives of an actual long-span highway-railway truss bridge with double decks at the wind attack angle of 0°, -3° and +3°. It was found that this method could solve the bounded problems of attenuation coefficient effectively in conventional search method, and had the ability of searching in unboundedly area. Accordingly, this study provides a method for engineering industry to frequently and efficiently obtain the time-domain expressions for bridge self-excited aerodynamic forces.

Keywords: time-domain expressions, bridge self-excited aerodynamic forces, modified particle swarm optimizer, long-span highway-railway truss bridge

Procedia PDF Downloads 288

Authors: Raed Alnajjar, Mohd Zakree, Ahmad Nazri

Abstract:

In this study, we apply Discrete Group Search Optimizer (DGSO) for solving Traveling Salesman Problem (TSP). The DGSO is a nature inspired optimization algorithm that imitates the animal behavior, especially animal searching behavior. The proposed DGSO uses a vector representation and some discrete operators, such as destruction, construction, differential evolution, swap and insert. The TSP is a well-known hard combinatorial optimization problem, which seeks to find the shortest path among numbers of cities. The performance of the proposed DGSO is evaluated and tested on benchmark instances which listed in LIBTSP dataset. The experimental results show that the performance of the proposed DGSO is comparable with the other methods in the state of the art for some instances. The results show that DGSO outperform Ant Colony System (ACS) in some instances whilst outperform other metaheuristic in most instances. In addition to that, the new results obtained a number of optimal solutions and some best known results. DGSO was able to obtain feasible and good quality solution across all dataset.

Keywords: discrete group search optimizer (DGSO); Travelling salesman problem (TSP); Variable neighborhood search(VNS)

Procedia PDF Downloads 294

Authors: Marius Gavrilescu, Sabina-Adriana Floria, Florin Leon, Silvia Curteanu, Costel Anton

Abstract:

Natural sciences provide a wide range of experimental data whose related problems require study and modeling beyond the capabilities of conventional methodologies. Such problems have solution spaces whose complexity and high dimensionality require correspondingly complex regression methods for proper characterization. In this context, we propose an optimization method which consists in a hybrid dual optimizer setup: a global optimizer based on a modified variant of the popular Imperialist Competitive Algorithm (ICA), and a local optimizer based on a gradient descent approach. The ICA is modified such that intermediate solution populations are more quickly and efficiently pruned of low-fitness individuals by appropriately altering the assimilation, revolution and competition phases, which, combined with an initialization strategy based on low-discrepancy sampling, allows for a more effective exploration of the corresponding solution space. Subsequently, gradient-based optimization is used locally to seek the optimal solution in the neighborhoods of the solutions found through the modified ICA. We use this combined approach to find the optimal configuration and weights of a fully-connected neural network, resulting in regression models used to characterize the process of obtained bricks using silicon-based materials. Installations in the raw ceramics industry, i.e., bricks, are characterized by significant energy consumption and large quantities of emissions. Thus, the purpose of our approach is to determine by simulation the working conditions, including the manufacturing mix recipe with the addition of different materials, to minimize the emissions represented by CO and CH4. Our approach determines regression models which perform significantly better than those found using the traditional ICA for the aforementioned problem, resulting in better convergence and a substantially lower error.

Keywords: optimization, biologically inspired algorithm, regression models, bricks, emissions

Procedia PDF Downloads 50

Authors: Eashan Hatti

Abstract:

In software development, programmers often must make a choice between high-level programming and high-performance programs. High-level programming encourages the use of complex, pervasive abstractions. However, the use of these abstractions degrades performance-high performance demands that programs be low-level. In a compiler, the optimizer attempts to let the user have both. The optimizer takes high-level, abstract code as an input and produces low-level, performant code as an output. However, there is a problem with having the optimizer be a built-in part of the compiler. Domain-specific abstractions implemented as libraries are common in high-level languages. As a language’s library ecosystem grows, so does the number of abstractions that programmers will use. If these abstractions are to be performant, the optimizer must be extended with new optimizations to target them, or these abstractions must rely on existing general-purpose optimizations. The latter is often not as effective as needed. The former presents too significant of an effort for the compiler developers, as they are the only ones who can extend the language with new optimizations. Thus, the language becomes more high-level, yet the optimizer – and, in turn, program performance – falls behind. Programmers are again confronted with a choice between high-level programming and high-performance programs. To investigate a potential solution to this problem, we developed Peridot, a prototype programming language. Peridot’s main contribution is that it enables library developers to easily extend the language with new optimizations themselves. This allows the optimization workload to be taken off the compiler developers’ hands and given to a much larger set of people who can specialize in each problem domain. Because of this, optimizations can be much more effective while also being much more numerous. To enable this, Peridot supports metaprogramming designed for implementing program transformations. The language is split into two fragments or “levels”, one for metaprogramming, the other for high-level general-purpose programming. The metaprogramming level supports logic programming. Peridot’s key idea is that optimizations are simply implemented as metaprograms. The meta level supports several specific features which make it particularly suited to implementing optimizers. For instance, metaprograms can automatically deduce equalities between the programs they are optimizing via unification, deal with variable binding declaratively via higher-order abstract syntax, and avoid the phase-ordering problem via non-determinism. We have found that this design centered around logic programming makes optimizers concise and easy to write compared to their equivalents in functional or imperative languages. Overall, implementing Peridot has shown that its design is a viable solution to the problem of writing code which is both high-level and performant.

Keywords: optimization, metaprogramming, logic programming, abstraction

Procedia PDF Downloads 53

Authors: Nima Khosravi

Abstract:

This paper describes an integrated optimization technique with concurrent use of sequential quadratic programming, genetic algorithm, and simulated annealing particle swarm optimization for the design and optimization of a beam column. In this research, the comparison between 4 different types of optimization methods. The comparison is done and it is found out that all the methods meet the required constraints and the lowest value of the objective function is achieved by SQP, which was also the fastest optimizer to produce the results. SQP is a gradient based optimizer hence its results are usually the same after every run. The only thing which affects the results is the initial conditions given. The initial conditions given in the various test run were very large as compared. Hence, the value converged at a different point. Rest of the methods is a heuristic method which provides different values for different runs even if every parameter is kept constant.

Keywords: beam column, genetic algorithm, particle swarm optimization, sequential quadratic programming, simulated annealing

Procedia PDF Downloads 353

Authors: Yuhanis Yusof, Zuriani Mustaffa, Siti Sakira Kamaruddin

Abstract:

Data mining is a fundamental technique in identifying patterns from large data sets. The extracted facts and patterns contribute in various domains such as marketing, forecasting, and medical. Prior to that, data are consolidated so that the resulting mining process may be more efficient. This study investigates the effect of different data normalization techniques, which are Min-max, Z-score, and decimal scaling, on Swarm-based forecasting models. Recent swarm intelligence algorithms employed includes the Grey Wolf Optimizer (GWO) and Artificial Bee Colony (ABC). Forecasting models are later developed to predict the daily spot price of crude oil and gasoline. Results showed that GWO works better with Z-score normalization technique while ABC produces better accuracy with the Min-Max. Nevertheless, the GWO is more superior that ABC as its model generates the highest accuracy for both crude oil and gasoline price. Such a result indicates that GWO is a promising competitor in the family of swarm intelligence algorithms.

Keywords: artificial bee colony, data normalization, forecasting, Grey Wolf optimizer

Procedia PDF Downloads 445

Authors: Safiqul Islam, Anamul Haque, Mohammad Amran Hossain

Abstract:

Aim: To compare the dosimetric parameters of the flattened and flattening filter free (FFF) beam and to validate the beam data using anisotropic analytical algorithm (AAA). Materials and Methods: All the dosimetric data’s (i.e. depth dose profiles, profile curves, output factors, penumbra etc.) required for the beam modeling of AAA were acquired using the Blue Phantom RFA for 6 MV, 6 FFF, 10MV & 10FFF. Progressive resolution Optimizer and Dose Volume Optimizer algorithm for VMAT and IMRT were are also configured in the beam model. Beam modeling of the AAA were compared with the measured data sets. Results: Due to the higher and lover energy component in 6FFF and 10 FFF the surface doses are 10 to 15% higher compared to flattened 6 MV and 10 MV beams. FFF beam has a lower mean energy compared to the flattened beam and the beam quality index were 6 MV 0.667, 6FFF 0.629, 10 MV 0.74 and 10 FFF 0.695 respectively. Gamma evaluation with 2% dose and 2 mm distance criteria for the Open Beam, IMRT and VMAT plans were also performed and found a good agreement between the modeled and measured data. Conclusion: We have successfully modeled the AAA algorithm for the flattened and FFF beams and achieved a good agreement with the calculated and measured value.

Keywords: commissioning of a Flattening Filter Free (FFF) , using an Anisotropic Analytical Algorithm (AAA), flattened beam, parameters

Procedia PDF Downloads 272

Authors: Golak Bihari Mahanta, Bibhuti Bhusan Biswal, B. B. V. L. Deepak, Amruta Rout, Gunji Balamurali

Abstract:

Robots are widely used in the manufacturing industry for rapid production with higher accuracy and precision. With the help of End-of-Arm Tools (EOATs), robots are interacting with the environment. Robotic grippers are such EOATs which help to grasp the object in an automation system for improving the efficiency. As the robotic gripper directly influence the quality of the product due to the contact between the gripper surface and the object to be grasped, it is necessary to design and optimize the gripper mechanism configuration. In this study, geometric and kinematic modeling of the parallel gripper is proposed. Grey wolf optimizer algorithm is introduced for solving the proposed multiobjective gripper optimization problem. Two objective functions developed from the geometric and kinematic modeling along with several nonlinear constraints of the proposed gripper mechanism is used to optimize the design variables of the systems. Finally, the proposed methodology compared with a previously proposed method such as Teaching Learning Based Optimization (TLBO) algorithm, NSGA II, MODE and it was seen that the proposed method is more efficient compared to the earlier proposed methodology.

Keywords: gripper optimization, metaheuristics, , teaching learning based algorithm, multi-objective optimization, optimal gripper design

Procedia PDF Downloads 155

Authors: Youssef Mazloum, Haytham Sayah, Maroun Nemer

Abstract:

The penetration of renewable energy sources into the electric grid is significantly increasing. However, the intermittence of these sources breaks the balance between supply and demand for electricity. Hence, the importance of the energy storage technologies, they permit restoring the balance and reducing the drawbacks of intermittence of the renewable energies. This paper discusses the modeling and the cost-effectiveness of an isobaric adiabatic compressed air energy storage (IA-CAES) system. The proposed system is a combination among a compressed air energy storage (CAES) system with pumped hydro storage system and thermal energy storage system. The aim of this combination is to overcome the disadvantages of the conventional CAES system such as the losses due to the storage pressure variation, the loss of the compression heat and the use of fossil fuel sources. A steady state model is developed to perform an energy and exergy analyses of the IA-CAES system and calculate the distribution of the exergy losses in the latter system. A sensitivity analysis is also carried out to estimate the effects of some key parameters on the system’s efficiency, such as the pinch of the heat exchangers, the isentropic efficiency of the rotating machinery and the pressure losses. The conducted sensitivity analysis is a local analysis since the sensibility of each parameter changes with the variation of the other parameters. Therefore, an exergoeconomic study is achieved as well as a cost optimization in order to reduce the electricity cost produced during the production phase. The optimizer used is OmOptim which is a genetic algorithms based optimizer.

Keywords: cost-effectiveness, Exergoeconomic analysis, isobaric adiabatic compressed air energy storage (IA-CAES) system, thermodynamic modeling

Procedia PDF Downloads 214

Authors: Yehjune Heo

Abstract:

As biometric systems become widely deployed, the security of identification systems can be easily attacked by various spoof materials. This paper contributes to finding a reliable and practical anti-spoofing method using Convolutional Neural Networks (CNNs) based on the types of loss functions and optimizers. The types of CNNs used in this paper include AlexNet, VGGNet, and ResNet. By using various loss functions including Cross-Entropy, Center Loss, Cosine Proximity, and Hinge Loss, and various loss optimizers which include Adam, SGD, RMSProp, Adadelta, Adagrad, and Nadam, we obtained significant performance changes. We realize that choosing the correct loss function for each model is crucial since different loss functions lead to different errors on the same evaluation. By using a subset of the Livdet 2017 database, we validate our approach to compare the generalization power. It is important to note that we use a subset of LiveDet and the database is the same across all training and testing for each model. This way, we can compare the performance, in terms of generalization, for the unseen data across all different models. The best CNN (AlexNet) with the appropriate loss function and optimizers result in more than 3% of performance gain over the other CNN models with the default loss function and optimizer. In addition to the highest generalization performance, this paper also contains the models with high accuracy associated with parameters and mean average error rates to find the model that consumes the least memory and computation time for training and testing. Although AlexNet has less complexity over other CNN models, it is proven to be very efficient. For practical anti-spoofing systems, the deployed version should use a small amount of memory and should run very fast with high anti-spoofing performance. For our deployed version on smartphones, additional processing steps, such as quantization and pruning algorithms, have been applied in our final model.

Keywords: anti-spoofing, CNN, fingerprint recognition, loss function, optimizer

Procedia PDF Downloads 103

Authors: Armin Nabaei, M. Omair Ahmad, M. N. S. Swamy

Abstract:

Many facial expression and emotion recognition methods in the traditional approaches of using LDA, PCA, and EBGM have been proposed. In recent years deep learning models have provided a unique platform addressing by automatically extracting the features for the detection of facial expression and emotions. However, deep networks require large training datasets to extract automatic features effectively. In this work, we propose an efficient emotion detection algorithm using face images when only small datasets are available for training. We design a deep network whose feature extraction capability is enhanced by utilizing several parallel modules between the input and output of the network, each focusing on the extraction of different types of coarse features with fined grained details to break the symmetry of produced information. In fact, we leverage long range dependencies, which is one of the main drawback of CNNs. We develop this work by introducing a Dynamic Soft-Margin SoftMax.The conventional SoftMax suffers from reaching to gold labels very soon, which take the model to over-fitting. Because it’s not able to determine adequately discriminant feature vectors for some variant class labels. We reduced the risk of over-fitting by using a dynamic shape of input tensor instead of static in SoftMax layer with specifying a desired Soft- Margin. In fact, it acts as a controller to how hard the model should work to push dissimilar embedding vectors apart. For the proposed Categorical Loss, by the objective of compacting the same class labels and separating different class labels in the normalized log domain.We select penalty for those predictions with high divergence from ground-truth labels.So, we shorten correct feature vectors and enlarge false prediction tensors, it means we assign more weights for those classes with conjunction to each other (namely, “hard labels to learn”). By doing this work, we constrain the model to generate more discriminate feature vectors for variant class labels. Finally, for the proposed optimizer, our focus is on solving weak convergence of Adam optimizer for a non-convex problem. Our noteworthy optimizer is working by an alternative updating gradient procedure with an exponential weighted moving average function for faster convergence and exploiting a weight decay method to help drastically reducing the learning rate near optima to reach the dominant local minimum. We demonstrate the superiority of our proposed work by surpassing the first rank of three widely used Facial Expression Recognition datasets with 93.30% on FER-2013, and 16% improvement compare to the first rank after 10 years, reaching to 90.73% on RAF-DB, and 100% k-fold average accuracy for CK+ dataset, and shown to provide a top performance to that provided by other networks, which require much larger training datasets.

Keywords: computer vision, facial expression recognition, machine learning, algorithms, depp learning, neural networks

Procedia PDF Downloads 49

Authors: Mehdi Jalalpour, Mazdak Tootkaboni

Abstract:

We present a computationally efficient method for reliability-based topology optimization under material properties uncertainty, which is assumed to be lognormally distributed and correlated within the domain. Computational efficiency is achieved through estimating the response statistics with stochastic perturbation of second order, using these statistics to fit an appropriate distribution that follows the empirical distribution of the response, and employing an efficient gradient-based optimizer. The proposed algorithm is utilized for design of new structures and the changes in the optimized topology is discussed for various levels of target reliability and correlation strength. Predictions were verified thorough comparison with results obtained using Monte Carlo simulation.

Keywords: material uncertainty, stochastic perturbation, structural reliability, topology optimization

Procedia PDF Downloads 567

Authors: Félix David Suárez Bonilla

Abstract:

A sentiment analysis service to detect polarity (positive, neural, and negative), based on transfer learning, was built using a Spanish version of BERT and applied to tweets written in Spanish. The dataset that was used consisted of 11975 reviews, which were extracted from Google Play using the google-play-scrapper package. The BETO trained model used: the AdamW optimizer, a batch size of 16, a learning rate of 2x10⁻⁵ and 10 epochs. The system was tested using tweets of three presidential pre-candidates from Costa Rica. The system was finally validated using human labeled examples, achieving an accuracy of 83.3%.

Keywords: NLP, transfer learning, BERT, sentiment analysis, social media, opinion mining

Procedia PDF Downloads 137

Authors: El Hassene Osmani, Mounir Haddou, Naceurdine Bensalem

Abstract:

In this paper, we investigate optimal control problems governed by semilinear elliptic variational inequalities involving constraints on the state, and more precisely, the obstacle problem. We present a relaxed formulation for the problem using smoothing functions. Since we adopt a numerical point of view, we first relax the feasible domain of the problem, then using both mathematical programming methods and penalization methods, we get optimality conditions with smooth Lagrange multipliers. Some numerical experiments using IPOPT algorithm (Interior Point Optimizer) are presented to verify the efficiency of our approach.

Keywords: complementarity problem, IPOPT, Lagrange multipliers, mathematical programming, optimal control, smoothing methods, variationally inequalities

Procedia PDF Downloads 136

Authors: Mohammad Ruhul Amin, Nusrat Jahan

Abstract:

Natural gas is a cleaner fuel compared to the others. But it needs some treatment before it is in a state to be used. So natural gas purification is an integral part of any process where natural gas is used as raw material or fuel. There are several impurities in natural gas that have to be removed before use. CO2 is one of the major contaminants. In this project we have removed CO2 by amine process by using MEA solution. We have built up the whole amine process for removing CO2 in Aspen Hysys and simulated the process. At the end of simulation we have got very satisfactory results by using MEA solution for the removal of CO2. Simulation result shows that amine absorption process enables to reduce CO2 content from NG by 58%. HYSYS optimizer allowed us to get a perfect optimized plant. After optimization the profit of existing plant is increased by 2.34 %.Simulation and optimization by Aspen-HYSYS simulator makes available us to enormous information which will help us to further research in future.

Keywords: Aspen–Hysys, CO2 removal, flowsheet development, MEA solution, natural gas optimization

Procedia PDF Downloads 457

Authors: Hamid Nikzad, Shinta Yoshitomi

Abstract:

In this paper, nonlinear static pushover analysis is performed on 15 storied RC building structure with a shear wall to evaluate the seismic performance of the building. Section sizes of the members are obtained based on structural optimization method utilizing MATLAB frame optimizer, then the structure is simulated and designed in ETABS program conforming ACI 318-14 design code. The pushover curve has been generated by pushing the top node of the structure to the limited target displacement. Members failure due to the formation of plastic hinges, considering shear wall-frame structure was observed and the result of this study is presented based on current regulation of FEMA356, ASCE7-10, and ACI 318-14 design criteria

Keywords: structural optimization, linear static analysis, ETABS, MATLAB, RC moment frame, RC shear wall structures

Procedia PDF Downloads 129

Authors: Maha BenHamad, Ali Snoussi, Ammar Ben Brahim

Abstract:

A steady-state analysis of triple-effect thermal vapor compressor desalination unit was performed. A mathematical model based on mass, salinity and energy balances is developed. The purpose of this paper is to develop a connection between process simulator and process optimizer in order to study the influence of several operating variables on the performance and the produced water cost of the unit. A MATLAB program is used to solve the model equations, and Aspen HYSYS is used to model the plant. The model validity is examined against a commercial plant and showed a good agreement between industrial data and simulations results. Results show that the pressures of the last effect and the compressed vapor have an important influence on the produced cost, and the increase of the difference temperature in the condenser decreases the specific heat area about 22%.

Keywords: steady-state, triple effect, thermal vapor compressor, Matlab, Aspen Hysys

Procedia PDF Downloads 149

Authors: Mohammadali Abedini Sanigy, Jiangang Fei

Abstract:

In this paper, a mathematical optimization model was developed to maximize the profit in a vegetable production planning problem. It serves as a decision support system that assists farmers in land allocation to crops and harvest scheduling decisions. The developed model can handle different rotation rules in two consecutive cycles of production, which is a common practice in organic production system. Moreover, different production methods of the same crop were considered in the model formulation. The main strength of the model is that it is not restricted to predetermined production periods, which makes the planning more flexible. The model is classified as a mixed integer programming (MIP) model and formulated in PYOMO -a Python package to formulate optimization models- and solved via Gurobi and CPLEX optimizer packages. The model was tested with secondary data from 'Australian vegetable growing farms', and the results were obtained and discussed with the computational test runs. The results show that the model can successfully provide reliable solutions for real size problems.

Keywords: crop rotation, harvesting, mathematical model formulation, vegetable production

Procedia PDF Downloads 152

Authors: R. Rajabpour, N. Talebbeydokhti, M. H. Ahmadi

Abstract:

Carefully scheduling the operations of pumps can be resulted to significant energy savings. Schedules can be defined either implicit, in terms of other elements of the network such as tank levels, or explicit by specifying the time during which each pump is on/off. In this study, two new explicit representations based on time-controlled triggers were analyzed, where the maximum number of pump switches was established beforehand, and the schedule may contain fewer switches than the maximum. The optimal operation of pumping stations was determined using a Jumping Particle Swarm Optimization (JPSO) algorithm to achieve the minimum energy cost. The model integrates JPSO optimizer and EPANET hydraulic network solver. The optimal pump operation schedule of VanZyl water distribution system was determined using the proposed model and compared with those from Genetic and Ant Colony algorithms. The results indicate that the proposed model utilizing the JPSP algorithm outperformed the others and is a versatile management model for the operation of real-world water distribution system.

Keywords: JPSO, operation, optimization, water distribution system

Procedia PDF Downloads 216

Authors: Jiin-Yuh Jang, Yu-Feng Gan

Abstract:

In order to improve the comprehensive mechanical properties of the steel, the cooling rate, and the temperature distribution must be controlled in the cooling process. A three-dimensional numerical model for the prediction of the heat transfer coefficient distribution of H-beam in the controlled cooling process was performed in order to obtain the uniform temperature distribution and minimize the maximum stress and the maximum deformation after the controlled cooling. An algorithm developed with a simplified conjugated-gradient method was used as an optimizer to optimize the heat transfer coefficient distribution. The numerical results showed that, for the case of air cooling 5 seconds followed by water cooling 6 seconds with uniform the heat transfer coefficient, the cooling rate is 15.5 (℃/s), the maximum temperature difference is 85℃, the maximum the stress is 125 MPa, and the maximum deformation is 1.280 mm. After optimize the heat transfer coefficient distribution in control cooling process with the same cooling time, the cooling rate is increased to 20.5 (℃/s), the maximum temperature difference is decreased to 52℃, the maximum stress is decreased to 82MPa and the maximum deformation is decreased to 1.167mm.

Keywords: controlled cooling, H-Beam, optimization, thermal stress

Procedia PDF Downloads 337

Authors: Anna Ouskova Leonteva, Michel Risser, Anne Jeannin-Girardon, Pierre Parrend, Pierre Collet

Abstract:

This paper proposes an efficient optimization tool for an active magnetic regenerator (AMR) model, operating in two modes: magnetic refrigeration system (MRS) and thermo-magnetic generator (TMG). The aim of this optimizer is to improve the design of the AMR by applying a multi-physics multi-scales numerical model as a core of evaluation functions to achieve industrial requirements for refrigeration and energy conservation systems. Based on the multi-objective non-dominated sorting genetic algorithm 3 (NSGA3), it maximizes four different objectives: efficiency and power density for MRS and TMG. The main contribution of this work is in the simultaneously application of a CPU-parallel NSGA3 version to the AMR model in both modes for studying impact of control and design parameters on the performance. The parametric study of the optimization results are presented. The main conclusion is that the common (for TMG and MRS modes) optimal parameters can be found by the proposed tool.

Keywords: ecological refrigeration systems, active magnetic regenerator, thermo-magnetic generator, multi-objective evolutionary optimization, industrial optimization problem, real-world application

Procedia PDF Downloads 87

Authors: Paffrath Meinhard, Zhou Yayun, Guo Yiqing, Ertl Harald

Abstract:

Winding geometry design is an important part of power transformer electrical design. Conventionally, the winding geometry is designed manually, which is a time-consuming job because it involves many iteration steps in order to meet all cost, manufacturing and electrical requirements. Here a method is presented which automatically generates the winding geometry for given user parameters and allows the user to interactively set and change parameters. To achieve this goal, the winding problem is transferred to a mixed integer nonlinear optimization problem. The relevant geometrical design parameters are defined as optimization variables. The cost and other requirements are modeled as constraints. For the solution, a stochastic ant colony optimization algorithm is applied. It is well-known, that an optimizer can get stuck in a local minimum. For the winding problem, we present efficient strategies to come out of local minima, furthermore a reduced variable search range helps to accelerate the solution process. Numerical examples show that the optimization result is delivered within seconds such that the user can interactively change the variable search area and constraints to improve the design.

Keywords: ant colony optimization, mixed integer nonlinear programming, power transformer, winding design

Procedia PDF Downloads 348

Authors: A. Ramalho, L. Romeiro, R. Ventura, A. Suleman

Abstract:

A real-time path planning framework for Unmanned Air Vehicles, and in particular multi-rotors is proposed. The framework is designed to provide feasible trajectories from the current UAV position to a goal state, taking into account constraints such as obstacle avoidance, problem kinematics, and vehicle limitations such as maximum speed and maximum acceleration. The framework computes feasible paths online, allowing to avoid new, unknown, dynamic obstacles without fully re-computing the trajectory. These features are achieved using an iterative process in which the robot computes and optimizes the trajectory while performing the mission objectives. A first trajectory is computed using a modified Rapidly-Exploring Random Tree (RRT) algorithm, that provides trajectories that respect a maximum curvature constraint. The trajectory optimization is accomplished using the Interior Point Optimizer (IPOPT) as a solver. The framework has proven to be able to compute a trajectory and optimize to a locally optimal with computational efficiency making it feasible for real-time operations.

Keywords: interior point optimization, multi-rotors, online path planning, rapidly exploring random trees, trajectory optimization

Procedia PDF Downloads 107

Authors: Seyedehsomayeh Hosseini

Abstract:

Much attention has been paid over centuries to understanding and solving the problem of minimization of functions. Compared to linear programming and nonlinear unconstrained optimization problems, nonlinear constrained optimization problems are much more difficult. Since the procedure of finding an optimizer is a search based on the local information of the constraints and the objective function, it is very important to develop techniques using geometric properties of the constraints and the objective function. In fact, differential geometry provides a powerful tool to characterize and analyze these geometric properties. Thus, there is clearly a link between the techniques of optimization on manifolds and standard constrained optimization approaches. Furthermore, there are manifolds that are not defined as constrained sets in R^n an important example is the Grassmann manifolds. Hence, to solve optimization problems on these spaces, intrinsic methods are used. In a nondifferentiable problem, the gradient information of the objective function generally cannot be used to determine the direction in which the function is decreasing. Therefore, techniques of nonsmooth analysis are needed to deal with such a problem. As a manifold, in general, does not have a linear structure, the usual techniques, which are often used in nonsmooth analysis on linear spaces, cannot be applied and new techniques need to be developed. This paper presents necessary and sufficient conditions for a strict local minimum of extended real-valued, nonsmooth functions defined on Riemannian manifolds.

Keywords: Riemannian manifolds, nonsmooth optimization, lower semicontinuous functions, subdifferential

Procedia PDF Downloads 331

Authors: Mohammad Hossein Bayati Chaleshtari, Hadi Khoramishad

Abstract:

Minimizing the stress concentration around triangular cutout in infinite perforated plates subjected to a uniform heat flux induces thermal stresses is an important consideration in engineering design. Furthermore, understanding the effective parameters on stress concentration and proper selection of these parameters enables the designer to achieve a reliable design. In the analysis of thermal stress, the effective parameters on stress distribution around cutout include fiber angle, flux angle, bluntness and rotation angle of the cutout for orthotropic materials. This paper was tried to examine effect of these parameters on thermal stress analysis of infinite perforated plates with central triangular cutout. In order to achieve the least amount of thermal stress around a triangular cutout using a novel swarm intelligence optimization technique called dragonfly optimizer that inspired by the life method and hunting behavior of dragonfly in nature. In this study, using the two-dimensional thermoelastic theory and based on the Likhnitskiiʼ complex variable technique, the stress analysis of orthotropic infinite plate with a circular cutout under a uniform heat flux was developed to the plate containing a quasi-triangular cutout in thermal steady state condition. To achieve this goal, a conformal mapping function was used to map an infinite plate containing a quasi- triangular cutout into the outside of a unit circle. The plate is under uniform heat flux at infinity and Neumann boundary conditions and thermal-insulated condition at the edge of the cutout were considered.

Keywords: infinite perforated plate, complex variable method, thermal stress, optimization method

Procedia PDF Downloads 111

Authors: Muftah H. El-Naas, Ameera F. Mohammad, Mabruk I. Suleiman, Mohamed Al Musharfy, Ali H. Al-Marzouqi

Abstract:

CO₂ capture and storage technologies play a significant role in contributing to the control of climate change through the reduction of carbon dioxide emissions into the atmosphere. The present study evaluates and optimizes CO₂ capture through a process, where carbon dioxide is passed into pH adjusted high salinity water and reacted with sodium chloride to form a precipitate of sodium bicarbonate. This process is based on a modified Solvay process with higher CO₂ capture efficiency, higher sodium removal, and higher pH level without the use of ammonia. The process was tested in a bubble column semi-batch reactor and was optimized using response surface methodology (RSM). CO₂ capture efficiency and sodium removal were optimized in terms of major operating parameters based on four levels and variables in Central Composite Design (CCD). The operating parameters were gas flow rate (0.5–1.5 L/min), reactor temperature (10 to 50 ^oC), buffer concentration (0.2-2.6%) and water salinity (25-197 g NaCl/L). The experimental data were fitted to a second-order polynomial using multiple regression and analyzed using analysis of variance (ANOVA). The optimum values of the selected variables were obtained using response optimizer. The optimum conditions were tested experimentally using desalination reject brine with salinity ranging from 65,000 to 75,000 mg/L. The CO₂ capture efficiency in 180 min was 99% and the maximum sodium removal was 35%. The experimental and predicted values were within 95% confidence interval, which demonstrates that the developed model can successfully predict the capture efficiency and sodium removal using the modified Solvay method.

Keywords: CO2 capture, water desalination, Response Surface Methodology, bubble column reactor

Procedia PDF Downloads 256

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 134

Authors: Oumaima Khlifati, Khadija Baba

Abstract:

Pavement distress is the main factor responsible for the deterioration of road structure durability, damage vehicles, and driver comfort. Transportation agencies spend a high proportion of their funds on pavement monitoring and maintenance. The auscultation of pavement distress was based on the manual survey, which was extremely time consuming, labor intensive, and required domain expertise. Therefore, the automatic distress detection is needed to reduce the cost of manual inspection and avoid more serious damage by implementing the appropriate remediation actions at the right time. Inspired by recent deep learning applications, this paper proposes an algorithm for automatic road distress detection and classification using on the Deep Convolutional Neural Network (DCNN). In this study, the types of pavement distress are classified as transverse or longitudinal cracking, alligator, pothole, and intact pavement. The dataset used in this work is composed of public asphalt pavement images. In order to learn the structure of the different type of distress, the DCNN models are trained and tested as a multi-label classification task. In addition, to get the highest accuracy for our model, we adjust the structural optimization hyper parameters such as the number of convolutions and max pooling, filers, size of filters, loss functions, activation functions, and optimizer and fine-tuning hyper parameters that conclude batch size and learning rate. The optimization of the model is executed by checking all feasible combinations and selecting the best performing one. The model, after being optimized, performance metrics is calculated, which describe the training and validation accuracies, precision, recall, and F1 score.

Keywords: distress pavement, hyperparameters, automatic classification, deep learning

Procedia PDF Downloads 55

Authors: Hadjer Sadoune, Liza Lamini, Scherazade Krim, Amel Djouadi, Rachida Rihani

Abstract:

Deep neural networks are highly regarded for their accuracy in predicting intricate fermentation processes. Their ability to learn from a large amount of datasets through artificial intelligence makes them particularly effective models. The primary obstacle in improving the performance of these models is to carefully choose the suitable hyperparameters, including the neural network architecture (number of hidden layers and hidden units), activation function, optimizer, learning rate, and other relevant factors. This study predicts biogas production from real wastewater treatment plant data using a sophisticated approach: hybrid Bayesian optimization with a tree-structured Parzen estimator (BO-TPE) for an optimised deep neural network (DNN) model. The plant utilizes an Upflow Anaerobic Sludge Blanket (UASB) digester that treats industrial wastewater from soft drinks and breweries. The digester has a working volume of 1574 m3 and a total volume of 1914 m3. Its internal diameter and height were 19 and 7.14 m, respectively. The data preprocessing was conducted with meticulous attention to preserving data quality while avoiding data reduction. Three normalization techniques were applied to the pre-processed data (MinMaxScaler, RobustScaler and StandardScaler) and compared with the Non-Normalized data. The RobustScaler approach has strong predictive ability for estimating the volume of biogas produced. The highest predicted biogas volume was 2236.105 Nm³/d, with coefficient of determination (R2), mean absolute error (MAE), and root mean square error (RMSE) values of 0.712, 164.610, and 223.429, respectively.

Keywords: anaerobic digestion, biogas production, deep neural network, hybrid bo-tpe, hyperparameters tuning

Procedia PDF Downloads 7

Authors: Sinarwati Mohamad Suhaili, Naomie Salim, Mohamad Nazim Jambli

Abstract:

Sequence-to-sequence (seq2seq) models augmented with attention mechanisms are playing an increasingly important role in automated customer service. These models, which are able to recognize complex relationships between input and output sequences, are crucial for optimizing chatbot responses. Central to these mechanisms are neural attention weights that determine the focus of the model during sequence generation. Despite their widespread use, there remains a gap in the comparative analysis of different attention weighting functions within seq2seq models, particularly in the domain of chatbots using the customer support Twitter (CST) dataset. This study addresses this gap by evaluating four distinct attention-scoring functions -dot, multiplicative/general, additive, and an extended multiplicative function with a tanh activation parameter- in neural generative seq2seq models. Utilizing the CST dataset, these models were trained and evaluated over 10 epochs with the AdamW optimizer. Evaluation criteria included validation loss and BLEU scores implemented under both greedy and beam search strategies with a beam size of k=3. Results indicate that the model with the tanh-augmented multiplicative function significantly outperforms its counterparts, achieving the lowest validation loss (1.136484) and the highest BLEU scores (0.438926 under greedy search, 0.443000 under beam search, k=3). These results emphasize the crucial influence of selecting an appropriate attention-scoring function in improving the performance of seq2seq models for chatbots. Particularly, the model that integrates tanh activation proves to be a promising approach to improve the quality of chatbots in the customer support context.

Keywords: attention weight, chatbot, encoder-decoder, neural generative attention, score function, sequence-to-sequence

Procedia PDF Downloads 44