Sorting Genetic Algorithm Research Articles

Pareto Optimization of Low‐Density Polyethylene in a Tubular Reactor Using a Hybrid Strategy

AbstractMulti‐objective optimization (MOO) to produce low‐density polyethylene (LDPE) in a tubular reactor is performed for three different purposes, namely, maximizing the monomer exchange rate, lowering operational costs, and increasing the productivity. The ASPEN simulator is used to resolve optimization problems. Here, MOO of particle swamp optimization (MOPSO), non‐dominated sorting genetic algorithm (NSGA‐II), and a hybrid strategy of NSGA II‐MOPSO are employed as a model‐based optimization for LDPE production in a tubular reactor. The results demonstrated that the hybrid strategy of NSGA II‐MOPSO is the most effective MOO strategy. Using the hybrid strategy, the discovered solution set provides the utmost precision and diversity along the Pareto front.

NSGA‐II‐XGB: Meta‐heuristic feature selection with XGBoost framework for diabetes prediction

SummaryDiabetes is one of the most prevalent causes of casualties in the modern world. Early diagnosis of diabetes is the most promising way for increasing the chances of patients' survival. The ever‐growing technology of the current era, machine learning‐based algorithms pave the door in the healthcare industry by delivering efficient decision support services in real‐time. However, high‐dimensionality of the data obtained using multiple sources increases the computation time and significantly impacts the models' efficiency in classifying the results. Feature selection improves learning performance and reduces the computational cost by selecting subsets of features and eliminating unnecessary and irrelevant features. In this article, an attempt has been made to develop a hybrid machine learning model based on non‐dominated sorting genetic algorithm (NSGA‐II) and ensemble learning for the efficient categorization of diabetes. The proposed work uses various data preprocessing techniques, such as missing data handling and normalization, prior to model training. The most prominent and salient features are selected by exploiting the potential of the NSGA‐II in the diabetes dataset. Finally, an ensemble learning‐based extreme gradient boosting (XGBoost) model is modeled using features selected by NSGA‐II to classify patients as diabetic or non‐diabetic. The proposed methodology is experimentally validated using a hybridized dataset comprising 23 features, with 1288 instances of both male and female patients between the ages of 21 and 65. In addition, for performance evaluation, the results of statistical parameters are compared with several state‐of‐the‐art decision‐making models in the current domain. Experiment findings exemplify that the proposed NSGA‐II‐XGB approach gives better classification results with an average accuracy of 98.86%. Furthermore, the statistical results of specificity (88.6%), sensitivity (96.36%), and F‐score (97.84%) also support the utility of the proposed methodology in the early diagnosis of diabetes.

Energy management and system design for fuel cell hybrid unmanned aerial vehicles

AbstractThe growth in the use of unmanned aerial vehicles (UAVs) has created an increasing demand for energy‐efficient and green power systems. In this paper, we have evaluated energy management strategies (EMSs) and system optimization design methodologies for fuel cell/battery‐powered hybrid UAVs (HUAVs). EMSs aimed at the optimization of flight endurance and fuel cell durability were proposed based on fuzzy logic, dynamic programming, equivalent consumption minimization, and Pontryagin's minimum principle (PMP). System optimization design methodologies, including static design and synergistic sizing optimization design, were also devised. The synergistic sizing optimization was based on multiobjective optimization, while optimization of the EMS used a non‐dominated sorting genetic algorithm. The effectiveness of the proposed EMSs and optimization design were then validated by simulation. Results showed that the proposed EMSs have both long flight time and good fuel cell durability, with the improved PMP prolonging the fight endurance by 4.64% and reducing the mean current of the fuel cell by 16.1% compared with fuzzy logic. Substantial improvements were obtained by using sizing optimization, and parameter sensitivity was addressed. The findings of this study can aid in the future development of fuel cell‐powered UAVs.

Analysis and optimization of M‐shaped boom based on response surface method

AbstractThe M‐shaped boom is a support structure that can be packed and launched and deployed in orbit using stored elastic strain energy. This work attempts a method to optimize the M boom. The response surface method was used to fit the finite element (FE) results to obtain surrogate models for the strain storage and the fundamental frequency in the deployed state, and the average errors between the surrogate model results and FE results were 1.56% and 0.9% respectively. The influence of different design variables on the results is analyzed by using surrogate models. Considering the requirements of boom deployment, a non‐dominated sorting genetic algorithm is used for multi‐objective optimization. The optimization targets the maximum strain stored energy and the maximum fundamental frequency, with the constraint of boom mass. The optimization results are at the Pareto frontier.

A new approach toward modeling of mixed‐gas sorption in glassy polymers based on metaheuristic algorithms

AbstractModeling mixed‐gas sorption has always been associated with computational challenges due to the existence of two or more conflicting objective functions. This study aims to use an artificial intelligence approach toward modeling mixed‐gas sorption in PIM‐1 and TZ‐PIM polymeric membranes. Non‐dominated sorting genetic algorithm (NSGA‐II) has been applied to identify the extended Henry‐Langmuir (EHL) isotherm based on CO2‐CH4 mixed‐gas sorption data. Also, the group method of data handling (GMDH) neural network is implemented to obtain a formula for the calculation of equilibrium partial pressure corresponding to three effective parameters, which are easily measurable. The formula provides an accurate estimation from the equilibrium relationship between the partial pressure of each gas in the binary gas mixtures over the PIM‐1 and TZ‐PIM membranes. Eventually, the calculated coefficients of EHL isotherm and obtained formula for computing the partial pressure of each component are simultaneously applied into the isotherm model to predict the mixed‐gas sorption behavior. The results showed that the computed lines well reproduce the experimental data points, proving that the applied artificial intelligence approach offers a suitable approximation for mixed‐gas sorption.

Contract bundling considerations in urban road project scheduling

AbstractRoad project scheduling and contract bundling are two separate concepts that profoundly influence project delivery consequences to key stakeholders. Therefore, agencies espouse initiatives for contract bundling (to reduce project costs) and project scheduling (to reduce user delay costs). Bundling combined with scheduling could potentially yield benefits to both the agency and urban road users. This paper investigates the overall benefits (to the two stakeholders) of optimal schedules with bundling considerations, compared to the optimal schedules for unbundled contracts. The agency's objective is to make scheduling‐with‐bundling decisions that minimize system‐wide travel time and project costs, and the users’ objective is to minimize their travel times in the network with work zones. The problem is solved using the non‐dominated sorting genetic algorithm. The numerical experiments suggest that with well‐designed bundling, optimal scheduling can significantly reduce not only the project cost but also the total system cost (project and travel delay).

Urban Rail Train Scheduling With Smoothing Energy Consumption Peaks and Synchronization Time Minimization: Using Novel Time-Shift Control Scheme

Considering operators of the urban rail transit systems are often faced with cost control, passengers required high service quality, which has inter-affection between each other in congestion issues for the peak period. A good cooperative timetable associated with time-based shift radios is proposed to achieve a mutually beneficial win-win situation for operators required low energy consumption (costs), and passengers required short waiting time in high peak level with different time-shift control schemes by shifting passengers’ travel times. By seeking the optimal shift radios, we focus on generating a favorable train schedule by taking the optimal decisions in the presence of trade-offs between two conflicting objectives. Subsequently, an improved non-dominated sorting in genetic algorithms (INSGA-II) was presented to solve the multi-objective programming model. Finally, the computational results show that the optimized time-shift control scheme brings a significant effect on reducing congestion during the peak periods.

An application of evolutionary computation algorithm in multidisciplinary design optimization of battery packs for electric vehicle

AbstractThe increased concerns of climate change are driving a shift in the transport sector from fossil to green fuels and electric vehicles (EVs) systems capable of delivering long‐term sustainability. However, there are some challenges remaining related to batteries used in EVs. These challenges exist in four different levels, that is, cell, module, pack, and EV level which can be easily solved by evolutionary computation (EC) techniques rather than using conventional modeling or optimization methods. In this study, a framework, using EC is proposed to solve the problems of EV applications. Firstly, a multi‐gene genetic programming is proposed to analyze the data in cell level and formulate a model for lithium‐ion battery capacity. The second case study targets optimization of battery encloser design at pack level using non‐dominated sorting genetic algorithm (NSGA‐II). Validation results manifest the outstanding optimization function of NSGA‐II and improved performance of the enclosure. Moreover, the results show improved performance of NSGA‐II when combined with other artificial intelligence algorithms. The results suggest that EC can be integrated in the EV system for monitoring its performance and ensure its safety.

A fuzzy multi-objective model for a cellular manufacturing system with layout designing in a dynamic condition

Cellular manufacturing system (CMS) plays a remarkably significant role in modern production systems. This paper presents a novel and practical fuzzy multi-objective mathematical model for a CMS in a dynamic condition considering the flexibility in allocating machines. The proposed model seeks to determine the best layout design in each production period. Two conflicting objectives are considered including minimising the cost of manufacturing system due to the amount of production loss caused by waste, as well as minimising the variance of fuzzy costs. Due to the complexity of the problem, non-dominate sorting genetic algorithm-II and multi-objective particle swarm optimisation algorithm are designed to solve the model and to obtain the effective solutions. In order to demonstrate the efficiency of the algorithms and to choose the premier algorithm, both algorithms are evaluated in several A fuzzy multi-objective model for a cellular manufacturing system 515 random problems and then compared based on the existing measurement indicators. Then, the algorithms are tuned to solve the problem, based on which their performances are analysed statistically. The applicability of the proposed approach and the solution methodologies are demonstrated as well.

A Hybrid Approach of NSGA-II and TOPSIS for Minimizing Vibration and Surface Roughness in Machining process

Increasing vibration amplitude during end milling process can seriously affect the life of end mills and reduces surface finish. Spindle and worktable vibration has a significant influence on surface quality of machined components. This paper confronts and investigates the effect of machining and geometrical parameters (spindle speed, feed rate, axial depth of cut, radial depth of cut and radial rake angle) on spindle and worktable vibration in terms of acceleration amplitude and surface roughness. Experiments were conducted on aluminium alloy 6061-T6 with high-speed steel (HSS) end mill cutter based on the central composite design (CCD). Response surface methodology (RSM) was used to develop the predictive models and the adequacy of the models were verified using analysis of variance (ANOVA). Non-dominated sorting of genetic algorithm (NSGA-II) was adopted to solve the multi objective optimisation problem and the optimised results were resulted with a set of Pareto-optimal solutions. The multi criteria decision making method (MCDM) such as technique for order preference by similarity to ideal solution (TOPSIS) and analytical hierarchy process (AHP) were designed to rank the Pareto optimal solutions based on response of closeness coefficient values.

Five Objective Optimization Using Naïve & Sorting Genetic Algorithm (NSGA) for Green Microalgae Culture Conditions for Biodiesel Production

Background:Renewable sources of energy like biodiesel are substitute energy fuel which are made from renewable bio sources or biomasses. Due to many advantages of using algae (Chlorella sp), we performed design of experiments in terms of functional and biochemical factors such as biomass, chlorophyll content, protein moiety and carbohydrate and lipid contents.Objective:Our objective is maximization of lipid accumulation (y1) and chlorophyll content (y2) and minimization of carbohydrate consumption (y3), protein (y4) and biomass (y5) contents. By using the experimental data, the regression model has been developed in order to obtain the desired response (biomass, chlorophyll, protein, carbohydrate and lipid) therefore it is necessary to optimize input conditions. The pre-optimization stage is an important part and useful for the production of biodiesel as biomass which is renewable energy to improve the quality.Methodology:The corresponding input and output conditions with multi-objective optimisation using naïve & sorting genetic algorithm (NSGA) is X1=0.99, X2=0.001, X3=-1.111, X4=0.01 and Lipid= 42.34, Chlorophyll=1.1212 (µgmL-1), Carbohydrate= 24.54%, Protein= 0.0742 (mgmL-1), Biomass=0.999 (gL-1).Conclusion:The multi-objective optimization NSGA prediction is compared with the response surface model combined with a genetic algorithm (RSM-GA) and we observed better productivity with NSGA.

An ERNSGA‐III algorithm for the production and distribution planning problem in the multiagent supply chain

AbstractNowadays, new issues have been emerged in industry by increasing the supply chain boundaries, especially when some supply chain members seek their own interests. In the literature, this case is referred to as a multiagent problem in which each agent has his/her own set of jobs and objectives. Here, an integrated production scheduling and distribution problem in a multisite supply chain is investigated from the three‐agent perspective of the manufacturer, distributor, and customer. Due to the complexity of the problem, a novel evolutionary‐based reference point determination of the third version of the non‐dominated sorting genetic algorithm (ERNSGA‐III) is proposed. In this algorithm, some modifications to the classic version of NSGA‐III have been made and a novel reference point determination method based on Bees algorithm is used in the selection operation. Some statistical tests are performed to compare the proposed algorithm with three other algorithms in the literature. The results show that the proposed algorithm is more effective than other algorithms.

Multi‐criteria workflow scheduling on clouds under deadline and budget constraints

SummaryCloud Computing is increasingly favored by scientists for executing large‐scale workflow applications due to its appealing features such as availability of huge infrastructure, low operating costs, easy accessibility, and high scalability. Moreover, the resources in cloud are provisioned as per user's requirement following pay‐per‐use model. Scheduling workflows in cloud requires orchestration of tasks onto heterogeneous resources while complying with the task dependencies as well as user's Quality of Service (QoS) demands. The problem becomes challenging if there are multiple QoS requirements which conflict with each other. Recent studies attempted to minimize the makespan and execution cost under deadline and/or budget constraints. However, the failure of resources in cloud poses a serious threat to successful execution of these applications. Hence, it becomes essential to consider reliability of resources in addition to other parameters. This paper presents a workflow scheduling policy which minimizes makespan and execution cost while maximizing the reliability of executing workflows under user specified deadline and budget restraints. We have devised a hybrid of Intelligent Water Drops algorithm and Genetic Algorithm (IWD‐GA) to accomplish the desired goal. It provides a set of non‐dominated solutions with different makespan, cost, and reliability to offer users more flexibility in selecting a solution as per their preferences. The evaluation of the proposed algorithm has been carried based on two performance metrics, ie, hypervolume and two set coverage. The simulation results thus obtained using four diverse scientific workflows confirm that IWD‐GA outperforms non‐dominated sort genetic algorithm (NSGA‐II) and hybrid particle swarm optimization (HPSO) with regard to accuracy and diversity.

An Advanced Genetic Algorithm Applied to a Rare Uplifting Earth and Rockfill Dam

A rare uplifting earth and rockfill dam case is introduced. The preliminary analysis on the formation mechanism indicates the uplift of dam body is very likely influenced by water swelling minerals in bedrock. In order to verify the swelling feature of the bedrock, a back analysis on dam surface displacement through Genetic Algorithm (GA) is carried out. Considering the discovered distribution characteristics of the bedrock expansibility, an advanced Sorting Genetic Algorithm (SGA) is proposed by adding a bubble sort procedure to maintain the relations between back analyzed parameters. The Finite Element Method (FEM) is embedded in SGA process as a single displacement calculating module. And two back analysis methods, fixed expansion distribution simulation and free GA simulation, are applied to simulate the uplift displacement of the dam body. The displacement prediction in verification dam section by adopting back analyzed parameters is later carried out to verify this method. The results demonstrate that the back analyzed vertical displacement (uplift) through both methods are in good agreement with the observed ones which verifies the reliability of the proposed method and the existence of swelling bedrock.

Multi-Objective Optimization in Electrical Discharge Machining of 6061 Al/SiC<sub>p </sub>Using RSM and NSGA-II

In this paper, response surface methodology (RSM) and non sorting genetic algorithm (NSGA-II) are used to optimize the multi-responses of electrical discharge machining of Aluminum Alloy 6061/10%SiCp composite. Experiment is performed to evaluates the effects of process parameters namely peak current, pulse on time, pulses off time and gap voltage on the responses material removal rate (MRR) and tool wear rate (TWR). The central composite rotatable design (CCRD) is utilized to design the experiment using RSM. Analysis of Variance (ANOVA) test is performed to validate model and to further establish the mathematical relation between process parameters and responses. Results are analyzed using ANOVA models. NSGA-II is used to optimize two conflicting responses i.e MRR and TWR. Finally results are validated by confirmatory experiment.

Self-adaptive NGSA algorithm and optimal design of inductors for magneto-fluid hyperthermia

PurposeThis paper aims to present the optimal design of an inductor used to heat a magnetic nanoparticle fluid injected in a cell culture inside a Petri dish.Design/methodology/approachThe inductor design is driven by means of a multi-objective optimization algorithm that generalizes the migration-non-dominated sorting genetic algorithm (NSGA); it is called self-adapting migration-NSGA.FindingsThe optimized device is able to synthesize a uniform magnetic field in a nanoparticle fluid, substantially helping its heating capability. The ultimate scope is to assist the cancer therapy based on magnetic fluid hyperthermia (MFH).Originality/valueThe optimal design of an inductor for MFH applications has been carried out by applying an improved version of migration-based NSGA-II algorithm including automatic stop and a self-adapting concept. The modified optimization algorithm is suitable to find better optimal solutions with respect to a standard version of NSGA-II.

Multi-Objective Soft Computing-Based Approaches to Optimize Inventory-Queuing-Pricing Problem under Fuzzy Considerations

Due to uncertain environment, various parameters such as price, queuing length, warranty, and so on influence on inventory models. In this paper, an inventory-queuing-pricing problem with continuous review inventory control policy and batch arrival queuing approach, is presented. To best of our knowledge, (I) demand function is stochastic and price dependent; (II) due to the uncertainty in real-world situations, a fuzzy programming approach is applied. Therefore, the presented model with goal of maximizing total profit of system analyzes the price and order quantity decision variables. Since the proposed model belongs to NP-hard problems, Pareto-based approaches based on non-dominated ranking and sorting genetic algorithm are proposed and justified to solve the model. Several numerical illustrations are generated to demonstrate the model validity and algorithms performance. The results showed the applicability and robustness of the proposed soft-computing-based approaches to analyze the problem.

A Specific Heuristic Dedicated to a Coverage/Tracking Bi-objective Problem for Wireless Sensor Deployment

In recent years, wireless sensor networks (WSN) have become very attractive for surveillance applications and particularly for target tracking. When a target has to be located by a WSN, accuracy is an important constraint. Most of the studies made in the WSNs problems deal with either coverage or tracking focus objectives. In this paper, we propose a modification of a previously studied bi-objective sensor placement problem taking into account both coverage and accuracy. The objectives are the minimization of the number of deployed sensors and the minimization of the tracking constraints violations, under the coverage constraints. The non sorting genetic algorithm and multi objective particle swarm optimization have been implemented to solve the problem. A specific heuristic (H3P) based on the mathematical decomposition of the problem has also been proposed. The performances of these algorithms are checked with integer programming results for small size instances, and they are compared on large size instances by multi-objective metrics. Results have shown that implemented metaheuristics provide less optimal solutions than the H3P for the small size instances. The comparison between the algorithms on large size instances set show that the H3P dominates the other implemented methods.

Application of multi‐objective evolutionary algorithms for the rehabilitation of storm sewer pipe networks

AbstractIn recent decades, evolutionary optimisation algorithms have been used successfully for a wide variety of water resources engineering problems and their applications are still increasing. In this research work, a hybrid harmony search algorithm, ‘Non‐dominated Sorting Harmony Search’ algorithm is developed and compared with two state‐of‐the‐art multi‐objective evolutionary algorithms – the non‐dominated sorting genetic algorithm (NSGA)‐II and multi‐objective particle swarm optimisation (MOPSO) algorithms – for assigning optimal rehabilitation plans for sewer pipe networks. The algorithms considered were validated using some standard test functions reported in the literature and compared with each other in terms of several metrics. These algorithms were then linked to the SWMM‐EPA hydraulic model and applied to a storm sewer pipe network case study in Seoul, South Korea, to obtain the best rehabilitation plans for pipe replacements. The results showed that the algorithms considered have different behaviours in solving the benchmark tests and rehabilitation problem. The proposed hybrid multi‐objective harmony search algorithm provides better optimal solutions in terms of different metrics and clearly outperforms the other two algorithms for the rehabilitation of the storm sewer pipe networks.

The Use Of The Corner Sorting Method In The Nsga-ii In Comparison With Spea-ii In The Simultaneous Optimization, The Size, Shape And Topology Of Two-dimensional Trusses

In this study, we are trying to do Non-dominated Sorting in simultaneous optimization at three levels the size, deformation and topology in two-dimensional trusses by using a new technique for Corner Sorting in genetic algorithms. Also, using this method and comparison with strong SPEA-II evolutionary algorithms in parameter, accuracy and extent of the Pareto curve occurs. Therefore, first we examine the algorithm in terms of numerical in the mathematics problems. And then, in ten-bars and three -bars trusses, we examine three levels of size, deformation and topology. The results show that the algorithm has very high accuracy to find solutions closer to the true Pareto optimal. Also, the algorithm has high