Genetic Algorithm Based Optimization Method Research Articles

Optimized array for powering sensors: Thermal and electromagnetic energy harvesting and fusion

Environmental energy harvesting technology has achieved great success in remote sensor power supply applications. However, existing technologies in the power grid neglect the potential of weak energy sources. This study aims to optimize the most reasonable array configurations and create hybrid energy fusion schemes for different weak energy environments. Taking thermal and electromagnetic energy harvesting from cable surfaces and currents in coaxial cables as an example, this paper introduces a genetic algorithm-based optimization method of harvester array configuration under multiple constraints and a dual-source energy fusion system. First, a vector impedance parameter identification method based on the equivalent circuit model of current transformer (CT) is proposed. Later, an optimization model for harvester array is established. Then, a genetic algorithm is used to optimize array combinations. And, a dual-source energy fusion system is proposed. Finally, thermal and electromagnetic energy harvesting and fusion are performed using 3 × 1 TEGs array and 6 × 1CT array. Under the specified conditions of a hot end temperature of 50 ℃ and an effective current value of 2 A, the power supply for the Zigbee wireless sensing system is realized to monitor the temperature of the cable core.

Using AI to decode the behavioral responses of an insect to chemical stimuli: towards machine-animal computational technologies

Orthoptera are insects with excellent olfactory sense abilities due to their antennae richly equipped with receptors. This makes them interesting model organisms to be used as biosensors for environmental and agricultural monitoring. Herein, we investigated if the house cricket Acheta domesticus can be used to detect different chemical cues by examining the movements of their antennae and attempting to identify specific antennal displays associated to different chemical cues exposed (e.g., sucrose or ammonia powder). A neural network based on state-of-the-art techniques (i.e., SLEAP) for pose estimation was built to identify the proximal and distal ends of the antennae. The network was optimised via grid search, resulting in a mean Average Precision (mAP) of 83.74%. To classify the stimulus type, another network was employed to take in a series of keypoint sequences, and output the stimulus classification. To find the best one-dimensional convolutional and recurrent neural networks, a genetic algorithm-based optimisation method was used. These networks were validated with iterated K-fold validation, obtaining an average accuracy of 45.33% for the former and 44% for the latter. Notably, we published and introduced the first dataset on cricket recordings that relate this animal’s behaviour to chemical stimuli. Overall, this study proposes a novel and simple automated method that can be extended to other animals for the creation of Biohybrid Intelligent Sensing Systems (e.g., automated video-analysis of an organism’s behaviour) to be exploited in various ecological scenarios.

Multi-objective niching quantum genetic algorithm-based optimization method for pneumatic hammer structure

Pneumatic down-the-hole (DTH) hammer drilling technology has been used extensively in various drilling applications owing to its high drilling efficiency, low gas consumption, non-polluting nature, and safety. Optimizing the hammer structure using empirical approaches is challenging due to the highly complex nonlinear problem caused by the piston movement. To address it, the intelligent algorithm is introduced for the first time and a multi-objective niching quantum genetic algorithm-based (MNQGA) optimization method for pneumatic hammer structure design is proposed in this study, to simultaneously maximize impact energy and minimize air consumption or optimize these objectives individually. Additionally, a novel niching strategy, corresponding adaptive quantum rotation gate, and mutation strategy are designed for the proposed method. The radial structures of a GQ127-type pneumatic hammer are optimized to maximize impact energy, followed by the optimization of the axial structures to satisfy four working conditions. The results show that different optimization objectives and constraints lead to different axial structural parameter values. After optimization, the hammer air consumption is reduced by at least 50.80 % at a constant impact energy of 350 J. The hammer impact energy is improved by more than 15.93 % if the volumetric flow rate of the supplied air is maintained at 10 m3/min. In addition, the effects of the hammer’s axial structure on its impact energy are investigated in detail based on an analytical model to validate the results of the proposed method. Five axial structure parameters are analyzed that have different effects on the impact energy. Within the given constraints, these parameters have their own optimal values that can be easily obtained using the proposed method. That is, the optimizations using the proposed method are consistent with those of the analytical models published in the literature. Therefore, the proposed method is efficient and accurate and can be used confidently when designing pneumatic hammers.

Optimizing Modularization of Residential Housing Designs for Rapid Postdisaster Mass Production of Housing

Postdisaster housing reconstruction (PDHR) is a highly complex process because of the large number of recovery projects for affected communities and the shortage of resources after a disastrous event. PDHR also needs a strategy that reconsiders it as a large-scale integrated portfolio of projects instead of individual building reconstruction projects. However, this complexity and the lack of a holistic, systematic approach for planning frequently lead to an ad-hoc or case-by-case decision-making process. To resolve this critical challenge in postdisaster housing mass production, this study investigates and develops a systematic approach that optimizes the design modularization of housing recovery projects considering manufacturing, transportation, and assembly factors for a cost-efficient and sustainable implication of modular construction (MC) in PDHR. Using the genetic algorithm-based optimization method, the proposed method addresses the possible trade-offs between the commonality and suitability of the module configurations for PDHR projects. In addition, the authors used a set of feasible configurations of a variety of modular housing designs created from the AI-based generative design system and conducted the mass production scenarios after a disaster to validate the accuracy and robustness of the proposed methodology. The results clearly show that the proposed method significantly improved optimization and decision-making of MC design and construction processes and considerably enhanced rapid and logical responses to the demands of the postdisaster recovery process. The newly developed method is expected to assist the planners in formalizing the commonality concept in the PDHR process and achieving an optimal level of modularity and commonality that meet the required variation while maintaining the advantages of mass production.

Stewart-inspired parallel spatial docking robot: design, analysis and experimental results

PurposeThis paper aims to focus on the spatial docking task of unmanned vehicles under ground conditions. The docking task of military unmanned vehicle application scenarios has strict requirements. Therefore, how to design a docking robot mechanism to achieve accurate docking between vehicles has become a challenge.Design/methodology/approachIn this paper, first, the docking mechanism system is described, and the inverse kinematics model of the docking robot based on Stewart is established. Second, the genetic algorithm-based optimization method for multiobjective parameters of parallel mechanisms including workspace volume and mechanism flexibility is proposed to solve the problem of multiparameter optimization of parallel mechanism and realize the docking of unmanned vehicle space flexibility. The optimization results verify that the structural parameters meet the design requirements. Besides, the static and dynamic finite element analysis are carried out to verify the structural strength and dynamic performance of the docking robot according to the stiffness, strength, dead load and dynamic performance of the docking robot. Finally, taking the docking robot as the experimental platform, experiments are carried out under different working conditions, and the experimental results verify that the docking robot can achieve accurate docking tasks.FindingsExperiments on the docking robot that the proposed design and optimization method has a good effect on structural strength and control accuracy. The experimental results verify that the docking robot mechanism can achieve accurate docking tasks, which is expected to provide technical guidance and reference for unmanned vehicles docking technology.Originality/valueThis research can provide technical guidance and reference for spatial docking task of unmanned vehicles under the ground conditions. It can also provide ideas for space docking missions, such as space simulator docking.

Increasing Annual Profit of Wind Farm Using Improved Genetic Algorithm

Wind energy, a prominent renewable source of energy, has expanded rapidly in the past few decades. This paper focuses on raising the yearly profit of a possible wind farm in the Kayathar area of India using an enhanced genetic algorithm. Novel dynamic techniques for assigning the probabilities of crossover and mutation operations have been applied for the genetic algorithm-based optimization method along with the conventional static approach. Non-linear functions have been applied for dynamically allocating the crossover and mutation factors for the genetic algorithm-based optimization process. The analysis outcomes of the proposed technique have been compared with the solutions attained by the genetic algorithm with the standard static approach of allocating the crossover and mutation factors. The evaluation outcomes confirm the superiority of the novel non-linearly incrementing methodology over the non-linearly decrementing and static approach of allocating the crossover and mutation probabilities for attaining a more optimal annual profit.

Multi-Objective Optimization Design of Ladle Refractory Lining Based on Genetic Algorithm.

Genetic algorithm is widely used in multi-objective mechanical structure optimization. In this paper, a genetic algorithm-based optimization method for ladle refractory lining structure is proposed. First, the parametric finite element model of the new ladle refractory lining is established by using ANSYS Workbench software. The refractory lining is mainly composed of insulating layer, permanent layer and working layer. Secondly, a mathematical model for multi-objective optimization is established to reveal the functional relationship between the maximum equivalent force on the ladle lining, the maximum temperature on the ladle shell, the total mass of the ladle and the structural parameters of the ladle refractory lining. Genetic algorithm translates the optimization process of ladle refractory lining into natural evolution and selection. The optimization results show that, compared with the unoptimized ladle refractory lining structure (insulation layer thickness of 0 mm, permanent layer thickness of 81 mm, and working layer thickness of 152 mm), the refractory lining with insulation layer thickness of 8.02 mm, permanent layer thickness of 76.20 mm, and working layer thickness of 148.61 mm has the best thermal insulation performance and longer service life within the variation of ladle refractory lining structure parameters. Finally, the results of the optimization are verified and analyzed in this paper. The study found that by optimizing the design of the ladle refractory lining, the maximum equivalent force on the ladle lining, the maximum temperature on the ladle shell and the ladle mass were reduced. The thermal insulation performance and the lightweight performance of the ladle are improved, which is very important for improving the service life of the ladle.

The Genetic Algorithm-Based Optimization Method for the Geometric and Material Parameters of Underwater Anechoic Coating

The Genetic Algorithm-Based Optimization Method for the Geometric and Material Parameters of Underwater Anechoic Coating

Aerodynamic design optimization of a bellmouth shaped air intake for jet engine testing purposes and its experiment based validation

Jet engine ground tests are carried out with bellmouth shaped air intakes in order to measure the mass flow rate and the inlet flow quantities while supplying the engine an undisturbed flow. Although there are a variety of design standards and academic guidelines for the design of bellmouths, they can be designed to reach a lower total pressure loss coefficient, a less disturbed radial velocity profiles for the engine and a less thickened boundary layer at the engine inlet. This enhanced design can be achieved with the help of optimization algorithms and computational fluid dynamics (CFD) computations thanks to the increasing average computational power and simplicity of the flow problem. In this study, a genetic algorithm based optimization method and a RANS solver under a commercial software platform are applied to find a bellmouth design with less loss and less disturbed flow. An elliptical bellmouth lip profile with a linear extension part is defined with parametrization and a wide range of parameter space is investigated during the design work. Optimum design candidates are presented comparatively regarding the design purpose. The selected design candidate is produced and tested for CFD validation.

Modeling and optimization of drilling operation of lead-free brass alloys considering various cutting tool geometries and copper content

Machinability, stable productivity, and quality of the components are crucial factors in manufacturing industry. In industrial applications, when cutting parameters and conditions are determined considering experiences gained by engineers which does not resolve the whole problems faced with in case cutting tools and their geometries are involved. Thus, it requires further knowledge that is built through systematic and scientific research. This study presents the results of an experimental investigation of a drilling process of hot forged lead-free brass alloys by using a form cutting tool. Experimental data on cutting forces, dimensional accuracy, and surface quality of the holes is presented considering the tools with different geometries, feed rates and rotational speeds on hot forged lead-free brass alloys with various copper content. Artificial neural networks modelling, and genetic algorithm-based optimization methods have been used to predict and optimize the machining process and related responses. The computational results demonstrated that the developed model and optimization procedure can notably improve the efficiency of the process by reducing the production cost with the obtained optimum machining conditions.

Optimization of arrangement of conducting fins and insulated obstacles inside a cavity: the couple of numerical solutions and genetic algorithm methods

The present work optimized the arrangement of the conducting fins and insulated obstacles in the cavity by coupling numerical simulation and genetic algorithm-based optimization methods. The height and width of the fins and the distance between them, as well as the temperature of the hot surface, were considered as the design variables. The design of the experiment and the response surface method were used in the optimization process. The objective function was defined to maximize the heat transfer coefficient on the hot wall. Based on the results, in the case of installing the conducting fins on the hot wall, the distance between the fins was the most effective geometrical parameter that exhibited the highest effect on heat transfer. By using the insulated obstacles installed on the hot wall, the width of the insulated obstacles has the highest effect on the heat transfer procedure. According to results, in the case of installing the conducting fins on the hot wall, the heat transfer coefficient exhibited the highest sensitivity to the wall temperature. Moreover, at the optimal point, the genetic algorithm predicts the optimum point thermal performance with an error of less than 2%, and the heat transfer in the cavity with insulated obstacles was 1.63 times more than that of the cavity with the conducting fin.

An isogeometric analysis based design of highly sensitive and precise omnidirectional piezoelectric-fiber accelerometer

Measuring omnidirectional acceleration is highly important for robust control of the vehicle states. A novel omnidirectional accelerometer with three piezoelectric curved-fibers is designed by using the genetic algorithm based optimization method. The isogeometric analysis (IGA) is utilized to analyze the strain induced voltage outputs of curved piezoelectric fibers, which can also guarantee high computation accuracy and significantly reduce the amounts of calculation in the optimization procedure compared to the finite element method. Employing cylindrical piezoelectric three fibers, the cross-axis sensitivities of the x and z axes of the omnidirectional accelerometer is eliminated completely in theory, which ensures the detection precision of magnitude and direction of 3D acceleration. The output voltages of proposed curved three-fiber accelerometer in x and y axes respective are higher than the fully decoupled accelerometer with three orthogonal fibers. The sensor also exhibits high sensitivity in very low frequency range of [0.01 Hz, 5 Hz], and numerical simulated sensitivity can reach 7.42 to 13.41 V/g, which is 78% to 155% higher than that of the omnidirectional accelerometer with three parallel straight-fibers.

Influence analysis of slot parameters and high torque density optimisation for dual redundant permanent magnet motor in aerospace application

This study proposes an optimisation approach of high torque density with guaranteed anti-short-circuit performance for the dual redundant permanent magnet synchronous motor (PMSM) in an aerospace application. The 10-pole/12-slot dual redundant PMSM with concentrated single-layer windings is firstly proposed, which can restrain the short-circuit current by the slot design to increase the phase inductance. Since the anti-short-circuit design may result in the torque density degradation of the dual redundant PMSM, the influence of the slot parameters on the torque performance of the dual redundant PMSM is thoroughly investigated, including the electromagnetic torque, braking torque, and no-load torque. Furthermore, the genetic algorithm-based optimisation method is proposed to maximise the torque density of the dual redundant PMSM, while the anti-short-circuit performance can also be guaranteed. Simulation and experimental results are conducted to verify the effectiveness of the proposed optimisation method.

Driving Strategy Optimization and Field Test on an Urban Rail Transit System

The reduction of train energy consumption is becoming more important due to increasing worldwide environmental concerns. This paper presents a driving strategy optimization study and field test results on an urban rail transit system. A genetic algorithm based optimization method has been developed specifically for this purpose. In order to identify and evaluate the practicability and performance of the optimization results, a field test has been carried out on Guangzhou Metro Line No. 7. A driver training study has been developed to help drivers to implement the energy saving features of the optimization. The field test results show that by applying the optimal driver strategy the train traction energy consumption can be significantly reduced within the given journey time constant, proving the developed optimization method is practicable and effective.

Genetic algorithm based optimization method for reactive power management

Genetic algorithm based optimization method for reactive power management

Application of machine learning in optimized distribution of dampers for structural vibration control

This paper presents machine learning methods using Support Vector Machine (SVM) and Multilayer Perceptron (MLP) to analyze optimal damper distribution for structural vibration control. Regarding different building structures, a genetic algorithm based optimization method is used to determine optimal damper distributions that are further used as training samples. The structural features, the objective function, the number of dampers, etc. are used as input features, and the distribution of dampers is taken as an output result. In the case of a few number of damper distributions, multi-class prediction can be performed using SVM and MLP respectively. Moreover, MLP can be used for regression prediction in the case where the distribution scheme is uncountable. After suitable post-processing, good results can be obtained. Numerical results show that the proposed method can obtain the optimized damper distributions for different structures under different objective functions, which achieves better control effect than the traditional uniform distribution and greatly improves the optimization efficiency.

Computer aided Genetic Algorithm based Optimization of Electrical Discharge Drilling in Titanium alloy (Grade-5) Sheet

Abstract Precise and micro holes in the different advanced materials such as Ti and their alloys is a very challenging task due to unfavourable characteristics of these materials by conventional machining. These problems may be minimised upto some extent by using new class of machining processes such as advanced machining processes. In the category of advanced machining processes, the electrical discharge drilling is the efficient and cost effective machining process for the machining of these materials. But some quality characteristics such as hole circularity, hole taper and hole dilation are the main problem associated during the machining of these materials by using electrical discharge machining. These may be minimized by selecting the optimum process parameter levels. In this study, the experiments have been conducted by using L27 orthogonal array. The discharge current, pulse on time, pulse off time and dielectric pressure have been selected as input process parameters and hole circularity, hole taper and hole dilation as output parameters. The multi regression models for hole circularity, hole dilation and hole taper have been developed by using the experimental data. The statistical analysis for the developed models shows that the models are reliable and adequate and may be used for predicting these quality characteristics satisfactorily. These quality characteristics have been optimized by using computer aided genetic algorithm based optimization method. For the optimization, the multi regression models for circularity, dilation and taper have been considered as objective function. The multi-objective optimization result obtained by computer aided genetic algorithm based optimization method, show improvements in all of the quality characteristics.

Breeding Cell Penetrating Peptides: Optimization of Cellular Uptake by a Function-Driven Evolutionary Process.

In nature, building block-based biopolymers can adapt to functional and environmental demands by recombination and mutation of the monomer sequence. We present here an analogous, artificial evolutionary optimization process which we have applied to improve the functionality of cell-penetrating peptide molecules. The "evolution" consisted of repeated rounds of in silico peptide sequence alterations using a genetic algorithm followed by in vitro peptide synthesis, experimental analysis, and ranking according to their "fitness" (i.e., their ability to carry the cargo carboxyfluorescein into cultured cells). The genetic algorithm-based optimization method was customized and adapted from former successful applications in the lab to realize an early convergence and a minimum number of in vitro and in silico processing steps by configured settings derived from empirical in silico simulation. We started out with 20 "lead peptides" which we had previously identified as top performers regarding their ability to enter cultured cells. Ten breeding rounds comprising 240 peptides each yielded a peptide population of which the top 10 candidates displayed a 6-fold (median values) increase in its cell-penetration capability compared with the top 10 lead peptides, and two consensus sequences emerged which represent local fitness optima. In addition, the cell-penetrating potential could be proven independently of the carboxyfluorescein cargo in an alternative setting. Our results demonstrate that we have established a powerful optimization technology that can be used to further improve peptides with known functionality and adapt them to specific applications.

A Genetic Algorithm based Optimization Method in 3D Solid Reconstruction from 2D Multi-View Engineering Drawings

There are mainly two categories for a 3D reconstruction from 2D drawings: B-Rep and CSG that both these methods have serious weaknesses despite being useful. B-Rep method which has been older and have wider function range is problematic because of high volume of calculations and vagueness in answers and CSG method has problem in terms of very limited range of volumes and drawings that it can analyze. Proposed method in this paper is an innovative method based on B-Rep in which optimization of genetic algorithm has been used to identify the relationship among the components of various views in 2D drawings. Using genetic algorithm that is a stochastic algorithm contributes that high volume of calculation that is one of main weaknesses of B-Rep method is solved. Moreover, considering correspondence condition of one to one among response in this method has caused that vagueness problem which is another weakness of B-Rep method to be almost solved so it can be said in addition to having wide range, present method doesn’t have common problems of B-Rep method and it even turns it to an effective method.

Inverse prediction and optimization analysis of a solar pond powering a thermoelectric generator

A given temperature difference across the upper and the lower convective zone of a solar pond is commonly sought in thermoelectric power generation. Based on this consideration, this work is aimed at predicting the lengths of various zones of a solar pond to ensure a minimum temperature potential throughout the year between its upper and lower convective zones. For predicting the critical lengths of various zones of the solar pond, at first, the heat energy conservation-based model available in the literature is modified by accounting the effect of salinity and temperature on various thermal parameters. The model is satisfactorily-validated with similar model and experimental data reported in the literature. Thereafter, considering the requirement of a thermoelectric power generator (TEG), an inverse problem is solved with the aid of a genetic algorithm-based optimization method to predict feasible lengths of various zones satisfying a minimum temperature potential across TEG considering suitable thermal resistances. The present results reveal improved pond dimensions achieving a better temperature profile at a lower total height than that available in the literature. Further, case studies of diverse meteorological conditions of India are carried out and it becomes apparent that, around the year, multiple combinations of convective and non-convective regions of the solar pond can ensure the required minimum (or more) temperature difference across relevant zones of the solar pond. Finally, the present study also reveals that the temperature of the upper convective zone is largely governed by the thickness of this zone, whereas, the thickness of the non-convective zone is largely responsible for the temperature within the storage zone. The present study provides a novel inverse methodology to predict and optimize the suitable dimensions of various regions of a salt-gradient solar pond to ensure a minimum temperature potential across the year for thermoelectric power generation.