Non-dominated Sorting Genetic Algorithm Version II Research Articles

Accelerated Design for High-Entropy Alloys Based on Machine Learning and Multiobjective Optimization.

High-entropy alloys (HEAs) with high hardness and high ductility can be considered as candidates for wear-resistant applications. However, designing novel HEAs with multiple desired properties using traditional alloy design methods remains challenging due to the enormous composition space. In this work, we proposed a machine-learning-based framework to design HEAs with high Vickers hardness (H) and high compressive fracture strain (D). Initially, we constructed data sets containing 172,467 data with 161 features for D and H, respectively. Four-step feature selection was performed, with the selection of 12 and 8 features for the D and H prediction models based on the optimal algorithms of the support vector machine (SVR) and light gradient boosting machine (LightGBM), respectively. The R2 of the well-trained models reached 0.76 and 0.90 for the 10-fold cross validation. Nondominated sorting genetic algorithm version II (NSGA-II) and virtual screening were employed to search for the optimal alloying compositions, and four recommended candidates were synthesized to validate our methods. Notably, the D of three candidates have shown significant improvements compared to the samples with similar H in the original data sets, with increases of 135.8, 282.4, and 194.1% respectively. Analyzing the candidates, we have recommended suitable atomic percentage ranges for elements such as Al (2-14.8 at %), Nb (4-25 at %), and Mo (3-9.9 at %) in order to design HEAs with high hardness and ductility.

Dynamic event‐triggered fault‐tolerant control through a new intermediate observer

AbstractThis article presents a new dynamic triggering mechanism for fault‐tolerant control of linear systems. In this mechanism, the dynamic threshold is constructed by instantaneous and averaged triggering errors with its bounds. Consequently, it can be automatically adjusted between the bounds. A new intermediate observer is built in the proportional‐integral form to improve the estimation accuracy. The corresponding fault‐tolerant controller is explored to actively compensate unknown faults. By resorting to the Lyapunov stability theory, a sufficient condition is obtained in terms of linear matrix inequalities to make the closed‐loop system uniformly ultimately bounded with the required performance. The elitist nondominated sorting genetic algorithm version II (NSGA‐II) is adopted to realize the multiobjective optimization of the performance index and the allowable inter‐event time . Finally, the proposed scheme is verified with two simulation examples.

Optimization of high-performance concrete mix ratio design using machine learning

High-durability concrete is required in extremely cold or ocean environments, making the design of concrete mixes highly important and complicated. In this study, a hybrid intelligent framework for multi-objective optimization based on random forest (RF) and the non-dominated sorting genetic algorithm version II (NSGA-II) is developed to efficiently predict concrete durability and optimize the concrete mix ratio. The relative dynamic elastic modulus of concrete after 300 freeze–thaw cycles and the chloride ion permeability coefficient at 28 days are defined as the standard measures of durability. The concrete mix ratio is taken as the influencing parameter, and orthogonal test data and engineering practice data are collected as the datasets. The proposed framework is applied to a realistic expressway project in a cold region of China. The results demonstrate that (1) a hybrid intelligent framework based on RF-NSGA-II can effectively predict concrete durability and optimize the mix ratio. (2) The developed RF model has an excellent regression learning ability, while the goodness of fit (R2) of concrete durability reaches 0.9503 and 0.9551, respectively, with root mean square error (RMSE) values of only 0.096 and 0.043, the mean absolute percentage error (MAPE) values of 2.54% and 2.17%. (3) After optimization, the concrete durability reaches a high standard, with a frost resistance of >95% and a chloride ion permeability coefficient of <3*10−8 cm2/s, at a unit volume cost of only 376.77 yuan. Hence, the proposed framework can be used to effectively optimize the concrete mix design and provide guidance for similar projects.

Retracted: Study on Optimization of Interior Ballistic Performance of Cased Telescoped Ammunition Based on Improved Firefly Algorithm

AbstractConsidering that the evolution operators of common optimization algorithms such as genetic algorithm has a poor convergence speed and solution accuracy in the interior ballistic performance optimization of artillery, an improved firefly algorithm is selected for the interior ballistic performance optimization of cased telescoped ammunition (CTA). It is applied to the interior ballistic mathematical model of CTA to carry out single‐objective optimization and multi‐objective optimization respectively. The results show that in the single‐objective optimization, the muzzle velocity obtained by using the improved firefly algorithm is larger than other commonly used optimization algorithms. Under the constraints of maximum chamber pressure and relative burnout point, the muzzle velocity can be increased by about 30 m/s. In the multi‐objective optimization, three sub‐objectives of muzzle velocity, ballistic efficiency and muzzle pressure are considered respectively, and the multi‐objective firefly algorithm is applied to comprehensively optimize the interior ballistic performance of CTA. Then, the results are compared with the commonly used multi‐objective optimization algorithms, such as non‐dominated sorting genetic algorithm version II (NSGA‐II) and non‐dominated sorting genetic algorithm version III (NSGA‐III), the solution results are a series of Pareto optimal solutions. The obtained optimization results improved the interior ballistic performance and launch safety, providing reference for the reasonable matching of charge structure parameters and the selection of optimization algorithm upon the interior ballistic performance optimization of CTA to some extent.

Maximizing the thermal performance index applying evolutionary multi-objective optimization approaches for double pipe heat exchanger

The thermal performance index (TPI) known as the efficiency parameter evaluates the highlight of the heat transfer for the same pumping power requirement. The optimum design of a heat exchanger with minimum pressure drops and efficient heat transfer is a big challenging task from an energy-saving point of view. One way to optimize this efficiency parameter is by changing the geometric parameters of the heat exchanger. For this purpose, the multi-objective reinforcement learner non-dominated sorting genetic algorithm (NSGA-RL) is employed maximizing TPI and Nusselt number and minimizing Fanning friction factor to the optimal design of a double pipe heat exchanger, with perforated baffles in the annulus side. Its performance is compared with a non-dominated sorting genetic algorithm - version II (NSGA-II), and a chaotic non-dominated sorting genetic algorithm (CNSGA). The calculations were carried out using the turbulent shear stress transport k-ω model. The multi-objective optimization techniques presented promising results in terms of the number of nondominated solutions, Euclidean distances to the origin point (reference point), and hypervolume indicators. However, in general, the results based on mean values indicate that the NSGA-RL outperforms the NSGA-II and CNSGA concerning the three performance indicators for the two double pipe heat exchanger evaluated cases. TPI increases 78% for case 1, and 108% for case 2 compared without baffles in a double pipe heat exchanger (DPHE). Numerical results revealed that DPHE employing internal perforated baffles improved heat transfer significantly with Nusselt number increased around 7.93–8.25 times and friction factor increased by 6.5–9.75 times compared with plain DPHE.

All-type optical logic gates using plasmonic coding metamaterials and multi-objective optimization.

In this article, we propose a multiport plasmonic system (MPS) for implementing all-type logic gates based on coding metamaterials and inverse design technology. Compared to traditional plasmonic logic gates, the coding metamaterials based on metal-dielectric-metal (MDM) structures provide powerful programmability for manipulating electromagnetic (EM) waves and have a compact footprint (0.8 µm × 1.1 µm) for integration. To improve the performance of logic gates, the nondominated sorting genetic algorithm version II (NSGA-II) are used to optimize the distributions of coding metamaterials. After the optimization, the simulation results show that all types of logic gates (AND, OR, NOT, NAND, NOR, XNOR, and XOR) can be obtained with an operating wavelength of 1.31 µm. The maximum extinction ratios between logic states "1" and "0" reach 10.15 dB, 57.54 dB, 43.25 dB, 20.76 dB, 10.42 dB, 24.04 dB, and 27.74 dB for the AND, OR, NOT, NAND, NOR, XNOR, and XOR gates, respectively. Moreover, wavelength-tunable logic operations are also demonstrated to work within a wide spectrum. Our proposed plasmonic system not only provides a universal scheme for implementing all-type compact logic gates for optical processing and computing but also demonstrates effective applications of inverse design in nanophotonic devices.

NSGA-II algorithm-based LQG controller design for nuclear reactor power control

The design of reactor power control system is closely related to the safety and economy of nuclear power plants. To improve its power control performance, this study takes a pressurized water reactor as the research object. The nonlinear dynamic mathematical model and its state space model were first derived; Then the Linear Quadratic Gaussian (LQG) optimal control method was adopted to design the reactor power controller; Furthermore, the multi-objective optimization of the linear quadratic regulator (LQR) weighting coefficient is carried out based on the elitist nondominated sorting genetic algorithm version II (NSGA-II). The results show that the LQG controller optimized based on NSGA-II method not only has fast response, high control accuracy and good stability, but also has good robustness and can obtain superior reactor power control performance.

A multi-objective scheduling method for operational coordination time using improved triangular fuzzy number representation.

In modern warfare, the comprehensiveness of combat domain and the complexity of tasks pose great challenges to operational coordination.To address this challenge, we use the improved triangular fuzzy number to express the combat mission time, first present a new multi-objective operational cooperative time scheduling model that takes the fluctuation of combat coordinative time and the time flexibility between each task into account. The resulting model is essentially a large-scale multi-objective combinatorial optimization problem, intractably complicated to solve optimally. We next propose multi-objective improved Bat algorithm based on angle decomposition (MOIBA/AD) to quickly identify high-quality solutions to the model. Our proposed algorithm improves the decomposition strategy by replacing the planar space with the angle space, which helps greatly reduce the difficulty of processing evolutionary individuals and hence the time complexity of the multi-objective evolutionary algorithm based on decomposition (MOEA/D). Moreover, the population replacement strategy is enhanced utilizing the improved bat algorithm, which helps evolutionary individuals avoid getting trapped in local optima. Computational experiments on multi-objective operational cooperative time scheduling (MOOCTS) problems of different scales demonstrate the superiority of our proposed method over four state-of-the-art multi-objective evolutionary algorithms (MOEAs), including multi-objective bat Algorithm (MOBA), MOEA/D, non-dominated sorting genetic algorithm version II (NSGA-II) and multi-objective particle swarm optimization algorithm (MOPSO). Our proposed method performs better in terms of four performance criteria, producing solutions of higher quality while keeping a better distribution of the Pareto solution set.

Multi-objective optimization design for a magnetorheological damper

As one of the most important components in the semi-active damping system, the performance of MR damper directly determines the damping capacity of the damping system. In order to make the damping system has excellent damping effect, it is necessary to optimize the working performance of the MR damper. Therefore, Non-Dominated Sorting Genetic Algorithm version II (NSGA-II) was applied to optimize the structure of MR dampers in this paper. Firstly, the structural scheme of MR damper was proposed. Secondly, the design principle of MR damper was described, and the magnetic circuit material and MR fluid were selected. Thirdly, taking the maximum dynamic range and the minimum number of turns of electromagnetic coil as the optimization objective, the structure of MR damper was optimized by NSGA-II. The structural parameters of MR damper were determined in the Pareto optimal solution set based on the principle of minimum mass. Finally, through the magnetic simulation and the performance testing of the MR damper, it was verified that the MR damper has reasonable magnetic circuit and excellent performance. And the design results meet the requirements. The proposed optimization method can provide a theoretical basis for the optimal design of related damping devices.

A parallel programming approach to the solution of the location-inventory and multi-echelon routing problem in the humanitarian supply chain

Disasters around the world are becoming more frequent, diverse, complex and extremely challenging, causing millions of casualties and affecting both human development and available resources. Consequently, the present study addresses a multi-objective location, inventory and multi-scale routing (2E-LIRP) problem, which supports comprehensive decision making, so that the logistics network designer and manager can obtain adequate strategic planning in the face of uncertainty and the negative impact that an adverse event can generate. Moreover, the problem is formulated as an integer linear programming model, having as main objectives to minimize private logistics costs and maximize the welfare of the affected areas, considering dynamic demand, multiple products and heterogeneous fleet. Due to the computational complexity associated with the model, new solution approaches are proposed, based on the design of evolutionary metaheuristic algorithms; the first one, known as Non-dominated Sorting Genetic Algorithm version II (NSGA-II), the second one, Strength Pareto Evolutionary Algorithm version II (SPEA-II) and the third one, called Genetic Algorithm (GA), programmed in parallel and executed individually under a cooperative environment.

Vehicle Routing Optimization of Instant Distribution Routing Based on Customer Satisfaction

Since the actual factors in the instant distribution service scenario are not considered enough in the existing distribution route optimization, a route optimization model of the instant distribution system based on customer time satisfaction is proposed. The actual factors in instant distribution, such as the soft time window, the pay-to-order mechanism, the time for the merchant to prepare goods before delivery, and the deliveryman’s order combining, were incorporated in the model. A multi-objective optimization framework based on the total cost function and time satisfaction of the customer was established. Dual-layer chromosome coding based on the deliveryman-to-node mapping and the access order was conducted, and the nondominated sorting genetic algorithm version II (NSGA-II) was used to solve the problem. According to the numerical results, when time satisfaction of the customer was considered in the instant distribution routing problem, the customer satisfaction increased effectively and the balance between customer satisfaction and delivery cost in the means of Pareto optimization were obtained, with a minor increase in the delivery cost, while the number of deliverymen slightly increased to meet the on-time delivery needs of customers.

Comparative study on the reservoir operation planning with the climate change adaptation

The management planning of Pedu–Muda reservoir, Kedah, was investigated in the context of the climate change evolution. The aim of this study was to evaluate the impact of the climate change to the reservoir operating management system and its sustainability. The study was divided into two sections; Analysis 1 refers to the reservoir optimization adapted with the climate assessment. The statistical downscaling model reacted as the climate model to generate the long-term pattern of the local climates affected by the greenhouse gases. Analysis 2 refers to the reservoir optimization but excluded the climate changes assessment in the analyses. The non-dominated sorting genetic algorithm version II (NSGA-II) was applied in both analyses to optimize the water use due to the multi-objectives demand, maximizing water release, minimizing water shortage and maximizing reservoir storage. The formation of Pareto optimal solutions from both analyses was measured and compared. The results showed the Analysis 1 potential to produce consistence monthly flow with lesser error and higher correlation values. It also produced better Pareto optimal solution set and considered all the objectives demands. The NSGA-II also successfully improves and re-manages the reservoir storage efficiently and reduce the dependancy of these reservoirs.

An efficient methodology for multi-objective optimization of water alternating CO2 EOR process

Water Alternating CO2 injection (WAG CO2) is one of the most promising EOR techniques for further recovery improvement. A successful implementation of this method depends mainly on its optimal design parameters, which are determined using a significant number of routinely numerical simulations. However, these latter are very time-consuming and their analysis can put a considerable strain on the flexibility of application. The aim of this study is to develop a new method to optimize WAG processes in presence of multiple conflicting criteria and time-depending constraints. To this end, a hybrid model based on multilayer perceptron (MLP), which was used as a replica of the simulator in mimicking the outputs, and Non-Dominated Sorting Genetic Algorithm version II (NSGA-II) was applied. Three different MLP models were built by implementing LMA, BR and SCG algorithms during the MLP training phase. The results showed that MLP-LMA model is the most accurate proxy. In addition, the proposed MLP-LMA emulates the outputs in real-time (dynamic proxy) with a high accuracy and a tiny running-time. The hybridization NSGA II-proxy ensures the approximation of the Pareto front to the formulated WAG problem. The generated Pareto front provided many WAG scenarios yielding to practical decision-making capabilities. The findings of this review can help for better understanding and studying multi-objective based WAG optimization problems in presence of time-depending constraints.

Newly Developed Nonlinear Vehicle Model for an Active Anti-roll Bar System

This paper presents the development of a newly developed nonlinear vehicle model is used in the validation process of the vehicle model. The parameters chosen in a newly developed vehicle model is developed based on CARSIM vehicle model by using non-dominated sorting genetic algorithm version II (NSGA-II) optimization method. The ride comfort and handling performances have been one of the main objective to fulfil the expectation of customers in the vehicle development. Full nonlinear vehicle model which consists of ride, handling and Magic tyre subsystems has been derived and developed in MATLAB/Simulink. Then, optimum values of the full nonlinear vehicle parameters are investigated by using NSGA-II. The two objective functions are established based on RMS error between simulation and benchmark system. A stiffer suspension provides good stability and handling during manoeuvres while softer suspension gives better ride quality. The final results indicated that the newly developed nonlinear vehicle model is behaving accurately with input ride and manoeuvre. The outputs trend are successfully replicated.

Wind turbine blade geometry design based on multi-objective optimization using metaheuristics

The application of evolutionary algorithms to wind turbine blade design can be interesting, by reducing the number of aerodynamic-to-structural design loops in the conventional design process, hence reducing the design time and cost. Recent developments showed satisfactory results with this approach, mostly combining genetic algorithms with the blade element momentum theory. The general objective of the present work is to define and evaluate a design methodology for the rotor blade geometry in order to maximize the energy production of wind turbines and minimize the mass of the blade itself, using for that purpose stochastic multi-objective optimization methods. An optimization benchmark problem was proposed, which represents the wind conditions and present wind turbine concepts found in Brazil. A variable speed pitch-controlled 2.5 MW direct-drive synchronous generator turbine with a rotor diameter of 120 m was chosen as concept. Four different multi-objective evolutionary algorithms were selected for evaluation in solving this benchmark problem: Non-dominated Sorting Genetic Algorithm version II (NSGA-II), Quantum-inspired Multi-objective Evolutionary Algorithm (QMEA), Multi-objective Evolutionary Algorithm Based on Decomposition (MOEA/D), and Multi-objective Optimization Differential Evolution Algorithm (MODE). Detailed analysis of the best compromise blade design showed that the output of the design methodology is feasible for manufacturing.

Modeling and design optimization of a robot gripper mechanism

Structure modeling and optimizing are important topics for the design and control of robots. In this paper, we propose a process for modeling robots and optimizing their structure. This process is illustrated via a case study of a robot gripper mechanism that has a closed-loop and a single degree of freedom (DOF) structure. Our aim is to conduct a detailed study of the gripper in order to provide an in-depth step-by-step demonstration of the design process and to illustrate the interactions among its steps. First, geometric model is established to find the relationship between the operational coordinates giving the location of the end-effector and the joint coordinates. Then, equivalent Jacobian matrix is derived to find the kinematic model; and the dynamic model is obtained using Lagrange formulation. Based on these models, a structural multi-objective optimization (MOO) problem is formalised in the static configuration of the gripper. The objective is to determine the optimum force extracted by the robot gripper on the surface of a grasped rigid object under geometrical and functional constraints. The optimization problem of the gripper design is solved using a non-dominated sorting genetic algorithm version II (NSGA-II). The Pareto-optimal solutions are investigated to establish some meaningful relationships between the objective functions and variable values. Finally, design sensitivity analysis is carried out to compute the sensitivity of objective functions with respect to design variables. A general robot modeling and optimal design process is proposed.A case study of a robot gripper is carried out in details to illustrate the proposed process.Data flow and interactions between the geometric, kinematic, and dynamic models are emphasized.A multi-objective optimization design of the gripper is realized using NSGA-II algorithm.A local sensitivity analysis of an optimal solution is performed to identify the most critical links of the gripper.

Multi-criterion based well placement and control in the water-flooding of naturally fractured reservoir

In the optimization of naturally fractured reservoirs, it is required to take into account their complex flow behavior due to high conductivity fractures. In this regard, the possible effects of fractures must be included in the optimization procedure. In a water-flooding project, fast water breakthrough from injection to production wells may be occurred because of high permeability fractures. To consider the effect of the fracture system, a multi-criterion optimization procedure is proposed in this work. For this contribution, Non-dominated Sorting Genetic Algorithm version II (NSGA-II) is implemented for the optimization purposes. Considering the effect of the fracture system on the flow behavior and consequently, development scenarios, the water breakthrough time is regarded as the objective in addition to ultimate oil recovery. The procedure is applied for well placement and control problems subject to maximization of the cumulative oil production and minimization of water front velocity (or respectively maximization of water breakthrough time). The problems cover design of well configuration and also time-varying bottom-hole pressures. Geological fracture uncertainty in terms of fracture permeability realizations is taken into account for the last optimization problem. This enables decision-makers to select the best scenario by a trade-off between the objectives which are maximization of expected reservoir performance and reducing the risk associated with the worst-case scenario. For this optimization problem under uncertainty, the significance of water breakthrough time expected value as an objective on the robust optimization problem is investigated.

Performance Optimization of Vehicle Handling and Stability Using Multiple Surrogate Models

Abstract Handling and stability are key performances characteristics of vehicles. A vehicle with good handling performance can be controlled precisely by drivers and help avoid accidents. In this paper, the handling and stability optimization was conducted based on a multi-body dynamic vehicle model. Considering the large computational assumption numerical model calculation, surrogate modeling techniques were introduced in this study. The non-dominated sorting genetic algorithm version II (NSGA-II) method was applied in the optimization of each surrogate model. A comparison study on three different surrogate models was conducted to understand their performance in engineering problems. It showed that the simultaneous usage of different surrogate models was essential for obtaining the best possible design.

Design of heat exchangers using a novel multiobjective free search differential evolution paradigm

Free search (FS) is a recently proposed population-based metaheuristic algorithm, inspired from the animals' behavior. FS can be applied to real value numerical optimization problems, as well as evolutionary algorithms and swarm intelligence techniques. In this paper, a novel multiobjective FS approach combined with differential evolution (MOFSDE) to heat exchanger optimization is presented. Two case studies of heat exchanger design are carried out to illustrate the efficiency of the MOFSDE. Simulation results for the two multiobjective case studies using the proposed MOFSDE are compared with those obtained by using the nondominated sorting genetic algorithm, version II (NSGA-II). The results from this comparison indicate that the MOFSDE performs better than the NSGA-II. The results illustrate that MOFSDE efficiently achieves two goals of multiobjective optimization problems: to find the solutions that converge to an approximated Pareto-front which is well spread, having the advantage of no parameter tuning apart from the population size and the number of generations.

GIS-modelling based coal-fired power plant site identification and selection

Coal-fired power plant (CPP) site identification and selection plays a significant role in the safe operation of a project and the sustainable development of a region. This study proposes a GIS-modelling methodology for CPP site identification and selection. Specifically, potential feasible sites are identified using a Geographical Information System (GIS) technique based on a spatial analysis of many factors, such as roads, available electric networks, fuel supplies and land use. Alternative sites are then ranked and the most suitable site selected. In contrast to previous studies, this study is among the first to rank and select sites based on the resolution of the conflicts between the local authority and the CPP owner, a vital consideration in the CPP site selection process. Instead of establishing a multi-criteria framework, a modelling technique is used, in which a bi-level model is established to resolve the conflicts and address the practical constraints. Subsequently, interactive fuzzy programming and Non-dominated Sorting Genetic Algorithm Version II (NSGA-II) are applied to solve the complex model to select the most suitable site. Finally, a practical application in China demonstrates the applicability, effectiveness and robustness of the proposed methodology. By considering stakeholder interest and energy efficiency, this methodology provides a method for a better understanding of CPP site identification and selection to ensure sustainable development. This methodology could be used in many developing countries by making minor modifications to some parameters.