Genetic Algorithm-based Optimization Research Articles

Identification and Compensation of Nonlinear Friction Characteristics and Precision Control for a Linear Motor Stage

The main goal of this investigation is to improve the tracking accuracy of the stage of a linear motor. A DC brushless linear motor is used to actuate a gantry stage to perform printing. To compensate for the tracking error of the gantry stage that is associated with nonlinear friction, the dynamics of the nonlinear static friction are formulated using the Hsieh-Pan model. Particle swarm optimization (PSO), genetic algorithm, and real-coded genetic algorithm-based optimization problems are investigated to evaluate the parameters of the nonlinear friction model. The use of PSO-based optimization to tune the parameters of a disturbance-observer-based variable structure controller is also discussed to improve the tracking response. To check the consistency of the proposed controller, it is implemented in real time and an improved positional accuracy better than 0.1 μm is readily achieved.

Study of Flue-Cured Tobacco Classification Model Based on the PSO-SVM

In this study, we study the flue-cured tobacco classification model based on the PSO-SVM. Firstly we use the Gaussian Radial Basis Function (RBF) as the kernel function of SVM and then use the Particle Swarm Optimization algorithm (PSO) to optimize the structural parameters of the SVM classifier, established the flue-cured tobacco classification model based on the PSO-SVM. Collecting a wide range of tobacco data in Qujing Yunnan Province, to train and validate the model. At last, compared with the grid parameter optimization and genetic algorithm-based parameter optimization model, the results show that the proposed model based on particle swarm optimization with high prediction accuracy and better adaptability when used in tobacco grading.

Model Predictive and Genetic Algorithm-Based Optimization of Residential Temperature Control in the Presence of Time-Varying Electricity Prices

This paper presents an optimal control algorithm for residential temperature regulation. The combination of concepts from system identification, model-predictive control, and genetic algorithms result in an optimization methodology capable of achieving an acceptable compromise between comfort and cost in the presence of constant as well as time-varying electricity prices. Simulation results demonstrate that the proposed approach has the potential to achieve substantial energy savings and cost reductions while maintaining acceptable comfort levels with minimal consumer participation.

Hyperspectral Image Classification Using Empirical Mode Decomposition With Spectral Gradient Enhancement

This paper proposes to use empirical mode decomposition (EMD) with spectral gradient enhancement to increase the classification accuracy of hyperspectral images with support vector machine (SVM) classification. Recently, it has been shown that higher hyperspectral image classification accuracy can be achieved by using 2-D EMD that is applied to each hyperspectral band separately to obtain the intrinsic mode functions (IMFs) of each band, while the sum of the IMFs are used as feature data in the SVM classification process. In the previous approach, IMFs have been summed directly, i.e., with equal weights. It is shown in this paper, that it is possible to significantly increase the classification accuracy by using appropriate weights for the IMFs in the summation process. In the proposed approach, the weights of the IMFs are obtained so as to optimize the total absolute spectral gradient, and a genetic algorithm-based optimization strategy has been adopted to obtain the weights automatically in this way. While the 2-D EMD basically provides spatial processing, the proposed method further incorporates spectral enhancement into the process. It is shown that a significant increase in hyperspectral image classification accuracy can be achieved using the proposed approach.

A route for efficient non-resonance cloaking by using multilayer dielectric coating

An approach for designing transmission cloaks by using ordinary dielectrics instead of meta- and plasmonic materials is proposed and demonstrated by the development of a multi-layer cloak for hiding cylindrical objects larger than the wavelengths of incident radiation. The parameters of the cloak layers were found by using the Genetic Algorithm-based optimization procedure, which employed the reciprocal of total scattering cross width of the cloaked target, derived from the solution of the Helmholtz equation, as the fitness function. The proposed cloak demonstrated better cloaking efficiency than did a similarly sized metamaterial cloak designed by using the transformation optics relations.

A framework for medical image retrieval using merging-based classification with dependency probability-based relevance feedback

Content-based image retrieval (CBIR) systems are used to retrieve relevant images from large-scale databases. In this paper, a framework for the image retrieval of a large-scale database of medical X-ray images is presented. This framework is designed based on query image classification into several prespecified homogeneous classes. Using a merging scheme and an iterative classification, the homogeneous classes are formed from overlapping classes in the database. For this purpose, the shape and texture features, selected using the forward selection algorithm, are optimized by a novel genetic algorithm-based feature reduction and optimization algorithm in the feature space. In this algorithm, using a new fitness function, we try to locate similar images in the database together in the feature space. Using the merging-based classification, the m-nearest classes to the query image are selected as a filtered search space. To increase the retrieval efficiency, we integrate a novel dependency probability-based relevance feedback (RF) approach with the proposed CBIR framework. The proposed RF uses a synthetic distance measure based on the weighted Euclidean distance measure and Gaussian mixture model-based dependency probability similarity measure of the database images to the Gaussian mixture distribution function of the positive images. The experimental results are reported based on a database consisting of 10,000 medical X-ray images of 57 classes (ImageCLEF 2005 database). The provided results show the effectiveness of the proposed framework compared to the approaches presented in the literature.

Genetic Algorithm-based Optimization of Cutting Parameters in Turning Processes

An optimization paradigm based on genetic algorithms (GA) for the determination of the cutting parameters in machining operations is proposed. In metal cutting processes, cutting conditions have an influence on reducing the production cost and time and deciding the quality of a final product. In order to find optimal cutting parameters during a turning process, the genetic algorithm has been used as an optimal solution finder. Process optimization has to yield minimum production time, while considering technological and material constrains.

Genetic Algorithm-Based Optimization of 3rd Order Multiple Feedback Low Pass Filter

Modern IC design industry nowadays demands a lot of engineers to produce circuit design with certain specification of outputs. In order to achieve these specifications, the input parameters need to be optimized. Conventional circuit parameter tuning involves trial and error adjustment which required large amount of time to achieve desired specifications. Furthermore, to build up filter circuits that meeting specification requires experience and knowledge about filter characteristic itself. Intense mathematical knowledge in terms of filter performance calculation might be necessary. This paper proposed Genetic Algorithm (GA) based optimization method for optimizing the design variables of the 3 rd order multiple feedback low pass filter. The 3 rd order multiple feedback low pass filter is synthesized using LTspiceIV whereas the GA model is developed using MATLAB. There are eight design variables to be optimized for achieving the required output gain, pass-band ripple, and targeted cut-off frequency.

Estimation of forest biomass by means of genetic algorithm-based optimization of airborne laser scanning and digital aerial photograph features

Information on forest biomass is required for several purposes, including estimation of forest bioenergy resources and forest carbon stocks. Airborne laser scanning is today considered the most accurate remote sensing method for forest inventory. The three-dimensional nature of laser scanning data enables estimation of the volumes of the tree canopies. The dimensions of the tree canopies show high correlation with the amount of forest biomass. Optical aerial photographs are often used to complement laser data, for improved distinction between tree species. The paper reports on a study testing the estimation of forest biomass variables in two study areas in Southern Finland. The biomass variables were derived on the basis of tree-level field measurements, with biomass models used for pine, spruce, and birch. The sample-plot-level biomass components were derived on the basis of tree-level data and used as reference data for airborne-laser- and aerial‑photograph-based estimation. Results were slightly better for total biomass (RMSE 22.5% and 23.6% for the two study areas) than total volume (RMSE: 23.4% and 26.1%). Species-specific estimation errors were large in general but varied between the study areas, because of differences in their forest structures.

A Methodology for Transforming an Existing Distribution Network Into a Sustainable Autonomous Micro-Grid

A distribution network with renewable and fossil-based resources can be operated as a micro-grid, in autonomous or nonautonomous modes. Autonomous operation of a distribution network requires cautious planning. In this context, a detailed methodology to develop a sustainable autonomous micro-grid is presented in this paper. The proposed methodology suggests novel sizing and siting strategies for distributed generators and structural modifications for autonomous micro-grids. The optimal sites and corresponding sizes of renewable resources for autonomous operation are obtained using particle swarm optimization and genetic algorithm-based optimization techniques. Structural modifications based on ranking of buses have been attempted for improving the voltage profile of the system, resulting in reduction of real power distribution losses. The proposed methodology is adopted for a standard 33-bus distribution system to operate as an autonomous micro-grid. Results confirm the usefulness of the proposed approach in transforming an existing radial distribution network into an autonomous micro-grid.

Multi-objective optimization design of a fixture layout considering locator displacement and force–deformation

The fixture determines the workpiece position in a machining process; therefore, an increasing amount of attention has been given to fixture layout design. While machining, the workpiece position is affected by two major sources: (a) the locator displacement and (b) the force–deformation of the workpiece–fixture system. In the beginning of this paper, a geometric model considering the shape of a locator is developed to analyze the location performance, followed by the presentation of a simplified solving method and a location layout performance index. Second, to complete the force–deformation analysis, a finite element method-based force–deformation model is built and accelerated by a new method with a lower computer memory cost. Based on these two models, multiple objects of fixture layout optimization problems are proposed, and a multi-objective genetic algorithm-based optimization method is constructed. Finally, testing examples are approved to examine the validity of the method represented in this paper. These methods can provide a more accurate prediction of the locating performance in more widely used cases, and they have faster calculating speeds with lower computer memory costs.

Online model-based fault detection and diagnosis strategy for VAV air handling units

An online model-based fault detection and diagnosis (FDD) strategy is presented in this paper to diagnose abrupt faults of variable-air-volume (VAV) air handling units (AHU). The FDD strategy proposed adopts a hybrid approach integrating model-based FDD method and rule-based FDD method. Self-tuning model is used to detect the faults in AHU systems. Model parameters are adjusted by a genetic algorithm-based optimization method to reduce the residual between prediction and measurement. If the residual exceeds the corresponding fault detection threshold, it indicates the occurrence of fault or abnormality in AHU systems. Meanwhile, an online adaptive scheme is proposed to estimate the fault detection threshold, which varies with system operating conditions. Furthermore, three rule-based fault classifiers are developed and utilized to find fault sources. The FDD strategy proposed was tested and validated on real VAV air-conditioning systems involving multiple faults. The validation results show that the FDD strategy proposed can provide an effective tool for detecting and diagnosing the faults of air handling units.

De Novo Design of Potential RecA Inhibitors Using MultiObjective Optimization

De novo ligand design involves optimization of several ligand properties such as binding affinity, ligand volume, drug likeness, etc. Therefore, optimization of these properties independently and simultaneously seems appropriate. In this paper, the ligand design problem is modeled in a multiobjective using Archived MultiObjective Simulated Annealing (AMOSA) as the underlying search algorithm. The multiple objectives considered are the energy components similarity to a known inhibitor and a novel drug likeliness measure based on Lipinski's rule of five. RecA protein of Mycobacterium tuberculosis, causative agent of tuberculosis, is taken as the target for the drug design. To gauge the goodness of the results, they are compared to the outputs of LigBuilder, NEWLEAD, and Variable genetic algorithm (VGA). The same problem has also been modeled using a well-established genetic algorithm-based multiobjective optimization technique, Nondominated Sorting Genetic Algorithm-II (NSGA-II), to find the efficacy of AMOSA through comparative analysis. Results demonstrate that while some small molecules designed by the proposed approach are remarkably similar to the known inhibitors of RecA, some new ones are discovered that may be potential candidates for novel lead molecules against tuberculosis.

Color image segmentation using parallel OptiMUSIG activation function

Segmentation of the different feature based data in a dataset is a challenging proposition in the image processing community. There exist different techniques to solve this problem satisfactorily. A color image is an example of three-dimensional dataset and it consists of a collection of three primary color intensity features. In this article, we focus on the segmentation of true color test images, based on all possible combination of color intensity features. A multilevel sigmoidal (MUSIG) activation function that is applied in the self-organizing neural network architecture is quite efficient enough to segment multilevel gray level intensity images. The function uses equal and fixed class responses, ignoring the heterogeneity of image information content. The optimized version of MUSIG (OptiMUSIG) activation function for the self-organizing neural network architecture can be generated with the optimized class responses from the image content and can be used to effectively segment multilevel gray level intensity images as well.This article proposes a parallel version of the OptiMUSIG (ParaOptiMUSIG) activation function with the optimized class responses for the individual features with a parallel self-organizing neural network architecture to segment true color images. The optimized class responses are generated in parallel using a genetic algorithm based optimization technique. A standard objective function is applied to measure the quality of the segmented images in the proposed genetic algorithm-based optimization method. Results of segmentation of two real life true color images by the ParaOptiMUSIG activation function show better performances over those obtained with a conventional non-optimized MUSIG activation applied separately on the color gamut.

Numerical simulation and optimization of CO2 sequestration in saline aquifers for vertical and horizontal well injection

With heightened concerns on CO2 emissions from pulverized-coal (PC) power plants, there has been major emphasis in recent years on the development of safe and economical geological carbon sequestration (GCS) technology. Saline aquifers are considered very attractive for GCS because of their large storage capacity in U.S. and other parts of the world for long-term sequestration. However, uncertainties about storage efficiency as well as leakage risks remain major areas of concern that need to be addressed before the saline aquifers can be fully exploited for carbon sequestration. A genetic algorithm-based optimizer has been developed and coupled with the well-known multiphase numerical solver TOUGH2 to optimally examine various injection strategies for increasing the CO2 storage efficiency as well as for reducing its plume migration. The optimal injection strategies for CO2 injection employing a vertical injection well and a horizontal injection well are considered. To ensure the accuracy of the results, the combined hybrid numerical solver/optimizer code was validated by conducting simulations of three widely used benchmark problems employed by carbon sequestration researchers worldwide. The validated code is then employed to optimize the proposed water-alternating-gas injection scheme for CO2 sequestration using both the vertical and the horizontal injection wells. The results suggest the potential benefits of CO2 migration control and dissolution. The optimization capability of the hybrid code holds a great promise in studying a host of other problems in GCS, namely how to optimally enhance capillary trapping, accelerate the dissolution of CO2 in water or brine, and immobilize the CO2 plume.

Maintenance scheduling incorporating dynamics of production system and real-time information from workstations

In this paper, a new approach to maintenance scheduling for a multi-component production system which takes into account the real-time information from workstations including remaining reliability of equipments as well as work-in-process inventories in each workstation is proposed. To model dynamics of the system, other information like production line configuration, cycle times, buffers' capacity and mean time to repair of machines are also considered. Using factorial experiment design the problem is formulated to comprehensively monitor the effects of each possible schedule on throughput of the production system. The optimal maintenance schedule is searched by genetic algorithm-based optimization engine implemented in a simulation optimization platform. The proposed approach exploits all of makespans of planning horizon to find the best opportunity to perform maintenance actions on degrading machines in a way that maximizes the system throughput and mitigates the production losses caused by imperfect traditional maintenance strategies. Finally the proposed method is tested in a real production line to magnify the accuracy of proposed scheduling method. The experimental results indicate that the proposed approach guarantees the operational productivity and scheduling efficiency as well.

Open‐ITC: an alternate computational approach to analyze the isothermal titration calorimetry data of complex binding mechanisms

Isothermal titration calorimetry (ITC) is an important technique used in quantitatively analyzing the global mechanism of protein-protein or protein-ligand interactions through thermodynamic measurements. Among different binding mechanisms, the parallel and ligand induced protein oligomerization mechanisms are technically difficult to analyze compared with a sequential binding mechanism. Here, we present a methodology implemented as a program "Open-ITC" that eliminates the need for exact analytical expressions for free ligand concentrations [L] and mole fractions of bound ligand θ that are required for the thermogram analysis. Adopting a genetic algorithm-based optimization, the thermodynamic parameters are determined, and its standard error is evaluated at the global minimum by calculating the Jacobian matrix. This approach yielded a statistically consistent result for a single-site and a two-site binding protein-ligand system. Further, a comparative simulation of a two-step sequential, a parallel, and a ligand induced oligomerization model revealed that their mechanistic differences are discernable in ITC thermograms, only if the first binding step is weaker compared with the second binding step (K(1) <K(2)). We find this to be valid even for the cases where the enthalpies of each of the binding process did not vary significantly.

Optimisation Design of Six-Bar Double Dwell Mechanisms: A New Approach

This paper introduces a new approach for me-chanical design of planar six-bar linkages with rotary joints which produce two dwells in each cycle of the input crank. The approach builds on the concept of function generation in a simple manner. The synthesis problem is posed as a single-objective constrained optimisation problem. A genetic algorithm-based optimisation scheme, namely the Non-dominated Sorting Genetic Algorithm-II (NSGA-II) has been used for solving the optimisation problem. The proposed method has been illustrated by means of an example problem from a recent contribution to literature. It is seen that the results compare favourably with the existing work.

Design and fabrication of high-efficiency photonic crystal power beam splitters

Efficient beam splitters in a planar photonic crystal waveguide with corrugated terminators were designed, fabricated, and characterized. Experimental results showed that these beam splitters have high splitting efficiency and power intensity in the propagation direction, an achievement made possible through a design method employing a genetic algorithm-based optimization method. High-efficiency power beam splitters are useful components in integrated optics, and the design implemented here is particularly suited for integration with other optical components.

A genetic algorithm-based optimization design on self-sensing active constrained layer damped rotating plates

This article investigates the vibration of a rotating constrained layer damped plate system. Although, currently, most existing research utilizes rotating structures as modeled beams, this work, however, models rotating structures as plates with constrained layer damping. Through the models investigated, this article develops a single-layer plate finite element model for a rotating structure to improve in both accuracy and versatility. Concurrently, existing research shows that the damping of the active constrained layer can provide more damping than the damping of the passive constrained layer. Therefore, in this study, the constraining layer is made of piezoelectric material and, thus, will work as both the self-sensing sensor and the actuator. In addition, a proportional control strategy is implemented to effectively control the damping in the rotating plate. Furthermore, due to a large number of design variables in the complex model incorporating viscoelastic damping, this study examines the application of genetic algorithm (GA) in optimizing the first two resonance amplitudes of the driving point mobility at the center of the rotating plate. A GA is applied to simultaneously determine several design parameters that maximize an objective function. Compared with a typical gradient search approach, Quasi-Newton method, GA can be more efficient and effective in finding the optimum configuration with the highest objective function value in the numerical example.