Browsing by Subject "Particle swarm optimization"

Now showing 1 - 8 of 8

Open Access
Experiment-based optimization of an energy-efficient heat pump integrated water heater for household appliances
(Elsevier, 2022-04-15) Kütük, E.; Çetin, Barbaros; Bayer, Ö.
Novel experimental-based study aims to determine the extent to which performance parameters of water heater system are altered when the heat pump is integrated and to clarify the optimum values of system variables by means of an optimization procedure using reliable experimental data. Considering compressor speed, air flow over evaporator as variables, experiments for both conventional electrical resistance and proposed heat pump integrated water heater for household appliances were conducted. Energy consumption, noise level and operating time were recorded. Experimental results reveal that energy consumption for heating 4 L water up to 50 °C is decreased by up to 26% in heat pump integrated water heater system, whereas noise level and operating time is increased by minimum 0.9 dBA and 65 min, respectively. Time-averaged COP value ranges in between 3.0 and 3.54 in the experiments, but for more realistic ambient temperature cases it may increase up to 7.5. Multi Objective Particle Swarm Optimization algorithm was performed for system components using curve fitted experimental data for the optimum values of system variables by considering energy consumption, noise level and operating time as objectives. Results lead to 17% decrease in energy consumption, 3.9 dBA increase in noise level and 82 min longer operating time.
Open Access
Improvements in deterministic error modeling and calibration of inertial sensors and magnetometers
(Elsevier B.V., 2016) Secer, G.; Barshan, B.
We consider the deterministic modeling, calibration, and model parameter estimation of two commonly employed inertial measurement units based on real test data acquired from a flight motion simulator. Each unit comprises three tri-axial devices: an accelerometer, a gyroscope, and a magnetometer. We perform the deterministic error modeling and calibration of accelerometers based on an improved measurement model, and the technique we propose for gyroscopes lowers costs by eliminating the need for additional sensors and relaxing the test bed requirement. We present an extended measurement model for magnetometers that reduces calibration errors by modeling orientation-dependent hard-iron errors in a gimbaled angular position-control machine. While we employ the model-based Levenberg-Marquardt optimization algorithm for the parameter estimation of accelerometers and magnetometers, we use a model-free evolutionary optimization algorithm (particle swarm optimization) for estimating the calibration parameters of gyroscopes. Errors are considerably reduced as a result of proper modeling and calibration. © 2016 Elsevier B.V.
Open Access
Maximum likelihood estimation of Gaussian mixture models using stochastic search
(Elsevier BV, 2012) Ar, C.; Aksoy, S.; Arıkan, Orhan
Gaussian mixture models (GMM), commonly used in pattern recognition and machine learning, provide a flexible probabilistic model for the data. The conventional expectationmaximization (EM) algorithm for the maximum likelihood estimation of the parameters of GMMs is very sensitive to initialization and easily gets trapped in local maxima. Stochastic search algorithms have been popular alternatives for global optimization but their uses for GMM estimation have been limited to constrained models using identity or diagonal covariance matrices. Our major contributions in this paper are twofold. First, we present a novel parametrization for arbitrary covariance matrices that allow independent updating of individual parameters while retaining validity of the resultant matrices. Second, we propose an effective parameter matching technique to mitigate the issues related with the existence of multiple candidate solutions that are equivalent under permutations of the GMM components. Experiments on synthetic and real data sets show that the proposed framework has a robust performance and achieves significantly higher likelihood values than the EM algorithm. © 2012 Elsevier Ltd. All rights reserved.
Open Access
Modeling and optimization of multi-scale machining operations
(2012) Yılmaz, Fevzi
Minimization of production time, cost and energy while improving the part quality is the main goal in manufacturing. In order to be competitive in today’s global markets, it is crucial to develop high precision machine tools and maintain high productive operation of the machine tools through intelligent and effective selection of machining parameters. A recent shift in manufacturing industry is towards the production of high value added micro parts which are mainly used in biomedical and electronics industries. However, the knowledge base for micro machining operations is quite limited compared to macro scale machining processes. Metal cutting, which allows production of parts with complex shapes made from engineering materials, constitutes a large portion in all manufacturing activities and expected to remain so in upcoming years. In this thesis, modeling and optimization of macro scale turning and micro scale milling operations have been considered. A well known multi pass turning problem from the literature is used as a benchmark tool to test the performances of Particle Swarm Optimization (PSO) technique and nonlinear optimization algorithms. It is shown that acceptable results can be obtained through PSO in short time. Micro scale milling operation is thoroughly investigated through experimental techniques where the influences of machining parameters on the process outputs (machining forces, surface quality, and tool life) have been investigated and factors affecting the process outputs are identified. A minimum unit cost optimization problem is formulated based on the pocketing operation and machining strategies are proposed for different machining scenarios using PSO technique.
Open Access
Noise enhanced parameter estimation using quantized observations
(2010) Balkan, Gökçe Osman
In this thesis, optimal additive noise is characterized for both single and multiple parameter estimation based on quantized observations. In both cases, first, optimal probability distribution of noise that should be added to observations is formulated in terms of a Cramer-Rao lower bound (CRLB) minimization problem. In the single parameter case, it is proven that optimal additive “noise” can be represented by a constant signal level, which means that randomization of additive signal levels (equivalently, quantization levels) are not needed for CRLB minimization. In addition, the results are extended to the cases in which there exists prior information about the unknown parameter and the aim is to minimize the Bayesian CRLB (BCRLB). Then, numerical examples are presented to explain the theoretical results. Moreover, performance obtained via optimal additive noise is compared to performance of the commonly used dither signals. Furthermore, mean-squared error (MSE) performances of maximum likelihood (ML) and maximum a-posteriori probability (MAP) estimates are investigated in the presence and absence of additive noise. In the multiple parameter case, the form of the optimal random additive noise is derived for CRLB minimization. Next, the theoretical result is supported with a numerical example, where the optimum noise is calculated by using the particle swarm optimization (PSO) algorithm. Finally, the optimal constant noise in the multiple parameter estimation problem in the presence of prior information is discussed.
Open Access
Optimization of linear wire antenna arrays to increase MIMO capacity using swarm intelligence
(Institution of Engineering and Technology, 2007) Olgun, Uğur; Tunç, Celal Alp; Aktaş, Defne; Ertürk, Vakur B.; Altıntaş, Ayhan
Free standing linear arrays (FSLA) are analyzed and optimized to increase MIMO capacity. A MIMO channel model based on electric fields is used. The effects of mutual interactions among the array elements are included into the channel matrix using method of moments (MoM) based full-wave solvers. A tool to design an antenna array of superior MIMO capacity for any specified volume is developed. Particle swarm optimization is used as the main engine for the optimization tasks of the tool. Uniform linear arrays, uniform circular arrays and non-uniform arrays are analyzed and compared in terms of their channel capacity.
Open Access
Optimized stillinger-weber potentials for 1H, 1T and 1T′ phases of WS2 for molecular dynamics studies: thermal transport as an example
(2024-01) Waheed, Alim Mohamed
The advent of graphene has poured numerous amount of research effort into the study 2D materials and utilizing it for device fabrication. Monolayer Transition Metal Dichalcogenides are one such class of polymorphic material with high prospect in versatile device applications due to its unique properties exhibited across the various phases. Classical Molecular Dynamics is a powerful tool that can be utilized to study the thermal and mechanical properties of these phases. Considering this, we optimise Stillinger-Weber type Potential for the seperate 1H, 1T and 1T′ phases of WS2 using Particle Swarm Optimization. These potentials are validated by comparison of phonon dispersion curves, Density Functional Theory (DFT) based target characteristic data and through an accuracy assessment conducted using Non-Equilibrium Molecular Dynamic (NEMD) simulations to evaluate thermal conductivity of the polymorphic structures. Thermal conductivity results obtained for 1H and 1T′ are in good agreement with first principle predictions calculated using Boltzmann Transport Equation. NEMD simulation of 1T phase prove to be challenging due to its dynamic instability with incoherent buckle structure formation along the symmetric directions.
Open Access
Representing and evaluating ultrasonic maps using active snake contours and Kohonen's self-organizing feature maps
(Springer, 2010-05-04) Altun, K.; Barshan, B.
Active snake contours and Kohonen's self-organizing feature maps (SOMs) are employed for representing and evaluating discrete point maps of indoor environments efficiently and compactly. A generic error criterion is developed for comparing two different sets of points based on the Euclidean distance measure. The point sets can be chosen as (i) two different sets of map points acquired with different mapping techniques or different sensing modalities, (ii) two sets of fitted curve points to maps extracted by different mapping techniques or sensing modalities, or (iii) a set of extracted map points and a set of fitted curve points. The error criterion makes it possible to compare the accuracy of maps obtained with different techniques among themselves, as well as with an absolute reference. Guidelines for selecting and optimizing the parameters of active snake contours and SOMs are provided using uniform sampling of the parameter space and particle swarm optimization (PSO A demonstrative example from ultrasonic mapping is given based on experimental data and compared with a very accurate laser map, considered an absolute reference. Both techniques can fill the erroneous gaps in discrete point maps. Snake curve fitting results in more accurate maps than SOMs because it is more robust to outliers. The two methods and the error criterion are sufficiently general that they can also be applied to discrete point maps acquired with other mapping techniques and other sensing modalities.