Single-objective Optimization Method Research Articles

Investigation of the wavy leading edge suppressing suction surface separation in a single-stage axial flow compressor

In order to improve the compressor efficiency, a wavy leading edge design method is introduced. A single objective optimization method is adopted to find the optimal wavy leading edge design and the effect of the wavy leading edge on the suction surface separation of a subsonic compressor stator is investigated by means of numerical simulations and controlling the sinusoidal function. The optimization results indicate that the amplitude has a significant impact on the compressor efficiency. Three amplitude schemes were studied, and the results show that as the amplitude increases, the efficiency of the compressor first increases and then decreases. The optimal schemes can reduce flow loss by 21.8% and increase the peak efficiency of the compressor by 1.46%. The wavy leading edge blades could change the static pressure distribution and induce the formation of leading edge vortex pairs behind the valley to improve the ability of resisting the separation for the flow.

An Experimental Comparison of Self-Adaptive Differential Evolution Algorithms to Induce Oblique Decision Trees

This study addresses the challenge of generating accurate and compact oblique decision trees using self-adaptive differential evolution algorithms. Although traditional decision tree induction methods create explainable models, they often fail to achieve optimal classification accuracy. To overcome these limitations, other strategies, such as those based on evolutionary computation, have been proposed in the literature. In particular, we evaluate the use of self-adaptive differential evolution variants to evolve a population of oblique decision trees encoded as real-valued vectors. Our proposal includes (1) an alternative initialization strategy that reduces redundant nodes and (2) a fitness function that penalizes excessive leaf nodes, promoting smaller and more accurate decision trees. We perform a comparative performance analysis of these differential evolution variants, showing that while they exhibit similar statistical behavior, the Single-Objective real-parameter optimization (jSO) method produces the most accurate oblique decision trees and is second best in compactness. The findings highlight the potential of self-adaptive differential evolution algorithms to improve the effectiveness of oblique decision trees in machine learning applications.

Molecule discovery and optimization via evolutionary swarm intelligence

Since the advent of computational analysis and visualization of chemical compounds, Computer-Aided Drug Design has made significant contributions to drug discovery. Recently, de novo drug design and molecular optimization have garnered considerable attention. Traditional optimization methods often struggle with the discrete nature of molecular space, but evolutionary computations have demonstrated their versatility across various optimization problems, regardless of the nature of the objective functions. This paper introduces a novel evolutionary algorithm, the Swarm Intelligence-Based Method for Single-Objective Molecular Optimization. Several experiments were conducted to showcase the efficiency of the proposed method, which identifies near-optimal solutions in a remarkably short time. The results were then compared with those of other state-of-the-art methods in the field.

Optimization of Rock Breaking Parameters by Combing Mechanical Specific Energy Theory and Random Forest Algorithm

Abstract As the key indicators to evaluate drilling efficiency, mechanical rate of penetration (ROP) and mechanical specific energy (MSE) are affected by many uncertain factors. In the actual drilling process, it is often necessary to adjust the parameters to achieve speed and efficiency. A dual-objective model is established considering the maximization of ROP and the minimization of MSE. Which combined with the theory of mechanical specific energy and the principle of multi-objective optimization, the model parameter weights are determined by the feature importance in the random forest regression model, and the value range of rock breaking parameter is optimized, realize the fusion of physical model and data model. The results show that, in the four strata of well X, the average ROP of T2k1 stratum is increased by 48.6% and the average MSE is decreased by 26.6%, the average ROP of T1b3 stratum is increased by 89.9% and the average MSE is decreased by 33.8%, the average ROP of the T1b2 stratum was increased by 41.3% and the average MSE was decreased by 39.0%, the average ROP of the T1b1 stratum was increased by 29.2% and the average MSE was decreased by 37.3%, which met the dual objectives of maximizing the ROP and minimizing the MSE. Compared with the traditional single-objective optimization method, the established dual-objective model is more in line with the needs of complex drilling engineering, and the fusion of physical model and data model can reduce certain human error.

Multi-objective online driving strategy optimization for energy storage tram considering battery life

Compared with the traditional overhead contact grid or third-rail power supply, energy storage trams equipped with lithium batteries have been developed rapidly because of their advantages of flexible railway laying and high regenerative braking energy utilization. However, trams may face expensive battery replacement costs due to battery degradation. Therefore, this paper proposes a multi-objective optimization method for the tram's driving strategy to reduce operational energy consumption and extend battery life. The method describes the optimization problem as second-order cone programming (SOCP). It uses the interior point algorithm for fast solving, thus obtaining the theoretical optimal speed trajectory in real-time. This feature enables the method to be applied online. To verify the effectiveness and robustness of the proposed method, we conducted simulations under actual operating conditions. The simulation results show that the proposed multi-objective optimization method can extend the battery life by 40 % compared to the single-objective optimization method for energy saving. As a result, the total cost of the whole life cycle is reduced by 6.54 %. Furthermore, this online optimization driving strategy method can effectively deal with unexpected conditions during the actual operation of the tram to ensure the secure operation, punctual arrival, and precise parking of trams. Finally, the effectiveness of the proposed method is further verified by a hardware-in-the-loop (HIL) test.

Multi-objective optimization of cable-road layouts in smart forestry

ABSTRACT Current cable-road layouts for timber harvesting in steep terrain are often based on either manual planning or automated layouts generated from low-resolution GIS data, limiting potential benefits and informed decision-making. In this paper, we present a novel approach to improve cable-road design using multi-objective optimization based on realistic cable-road representations. We systematically compare the effectiveness of single-objective and multi-objective optimization methods for generating layouts using these representations. We implement and evaluate the performance of a weighted single-objective approach, the AUGMECON2 and NSGA-II multi-objective methods in comparison to a layout manually created by a forestry expert, taking into account installation costs, harvesting volumes, residual stand damage and lateral yarding workload. In addition to implementing the first linear programming multi-objective optimization for realistic cable-road representations by adapting AUGMECON2, we also present the first implementation of a multi-objective genetic algorithm (NSGA-II) with simulated annealing for this purpose and evaluate their respective strengths. We find that the use of multi-objective optimization provides advantages in terms of cost-effective, balanced and adaptable cable-road layouts while allowing economic and environmental considerations to be incorporated into the design phase.

Single-objective and multi-objective mixed-variable grey wolf optimizer for joint feature selection and classifier parameter tuning

Feature selection plays an essential role in data preprocessing, which can extract valuable information from extensive data, thereby enhancing the performance of machine learning classification. However, existing feature selection methods primarily focus on selecting feature subsets without considering the impact of classifier parameters on the optimal subset. Different from these works, this paper considers jointly optimizing the feature subset and classifier parameters to minimize the number of features and achieve a low classification error rate. Since feature selection is an optimization problem with binary solution space while classifier parameters involve both continuous and discrete variables, our formulated problem becomes a complex multi-objective mixed-variable problem. To address this challenge, we consider a single-objective optimization method and a multi-objective optimization approach. Specifically, in the single-objective optimization method, we adopt the linear weight method to convert our multiple objectives into a fitness function and then propose a mixed-variable grey wolf optimizer (MGWO) to optimize the function. The proposed MGWO introduces Chaos-Faure initialization, Log convergence factor adjustment, and optimal solution adaptive update operators to enhance its adaptability and balance the global and local search of the algorithm. Subsequently, an improved multi-objective grey wolf optimizer (IMOGWO) is introduced to directly address the problem. The proposed IMOGWO introduces improved initialization, local search, and binary variable mutation operators to balance its exploration and exploitation abilities, making it more suitable for our mixed-variable problem. Extensive simulation results show that our MGWO and IMOGWO outperform recent and classic baselines. Moreover, we also find that jointly optimizing classifier parameters can significantly improve classification accuracy.

Optimal sizing and cost analysis of hybrid energy storage system for EVs using metaheuristic PSO and firefly algorithms

This paper presents a single-objective function optimization method for the optimal sizing and cost of a hybrid energy storage system (HESS) that integrates lithium-ion batteries (LIB) and supercapacitors (SC) for electric vehicle (EV) applications. The study introduces a comprehensive framework for EV modeling, incorporating simulated EV data to enhance accuracy. A key achievement involves adapting the modified–WLTC driving cycle, iteratively employed in EV simulations to accurately capture the spectrum of power and energy profiles within the designated range, ensuring adherence to BMW-i3's top speed requisites. The proposed method's validity is established by comparing optimization results using Particle Swarm Optimization (PSO) and Firefly Algorithm (FA), indicating comparable HESS sizing and cost outcomes. Notably, the PSO algorithm demonstrates superior accuracy and computational efficiency. Through PSO, the optimal LIB-SC HESS weight is determined at 160 kg with an optimal cost of $27,660, while FA yields 161 kg and $28,270, surpassing LIB-Only EV models by approximately 21 % in improved sizing. This research significantly contributes by establishing a robust EV modeling paradigm, employing simulated data for optimization, and successfully implementing PSO to determine optimal HESS parameters, advancing the field of efficient EV energy storage and promoting cost-effective, sustainable electric transportation.

Design of intelligent drill bit embedded structure based on multi-objective topology optimization method

To address the issues of mechanical performance changes, stress concentration, and displacement in the original drill bit structure caused by the design of embedded structures in intelligent drill bits, the optimal topology of the drill bit was calculated using multi-objective topology optimization methods. Optimal values under various load conditions were obtained using single-objective topology optimization methods combined with penalty functions. Based on these optimal values, calculations for the intelligent drill bit embedded structure were performed using a trade-off planning method. Following this, the initially optimized results were redesigned using NURBS modeling methods to create an embedded structure that meets structural performance requirements. The embedded structure meeting these requirements was then tested through orthogonal simulation to verify its mechanical performance under various complex load conditions. The results show that the embedded structure drill bits designed based on multi-objective optimization generally surpass traditional drill bit structures and those optimized using multi-objective methods in terms of maximum Mises stress and maximum deformation, particularly in external and internal petal configurations, demonstrating good performance in enhancing structural strength.

Optimal design of mixed dielectric coaxial-annular TSV using GWO algorithm based on artificial neural network

The single-objective and single-parameter optimization method is commonly used in the structure optimization of TSV to improve the transmission characteristics, for which a structure design scheme that simultaneously satisfies multiple target requirements is difficult to obtain. Moreover, the method cannot simultaneously optimize different design parameters. Aiming at the above problems, a global optimization method based on the grey wolf optimization (GWO) algorithm and artificial neural network (ANN) model is proposed. With the presented mixed dielectric coaxial-annular TSV model, firstly six key design parameters A-F are selected as optimization variables by the control variable method. The L25(56) orthogonal experiment is designed for Taguchi analysis and analysis of variance (ANOVA). Then, three prediction models, ANN, support vector machine (SVM), and extreme learning machine (ELM), are developed with the extended orthogonal data as the training sets. It is found that the ANN model performed best. To search for the global optimal solution, the genetic algorithm (GA) and GWO algorithm, combined with the ANN model are applied, respectively. The results show that the GWO algorithm is more successful in solving the problem of falling into the local optimum than GA, and the convergence speed is faster and more stable. After GWO-ANN optimization, the performance of each S-parameter index is greatly improved, S11 reduces by 14.05 dB, S21 increases by 0.33 dB, and S31 reduces by 12.50 dB at 30 GHz.

A New Multi-Objective Optimization Strategy for Improved C3MR Liquefaction Process

In the traditional C3MR process (T-C3MR), the boiling gas (BOG) output from the last stage of the gas–liquid separator is directly discharged, in which the excellent low-temperature capability is not utilized, and the system efficiency is decreased. In liquefied natural gas (LNG), single-objective optimization methods are commonly used to optimize system parameters, which may result in incomplete system analysis. To solve the above problems, this paper proposes a multi-objective optimization strategy for the improved C3MR process(I-C3MR) based on a new multi-objective optimization algorithm called EHR-GWO-GA. Firstly, the main work proposes an I-C3MR structure. Secondly, an optimization strategy of the I-C3MR with the maximization of liquefaction amount, minimization of unit energy consumption and minimization of exergy loss as objective functions are proposed. Based on the optimization results, the influence of decision variables on liquefaction amount, unit energy consumption and exergy loss are analyzed, and the results show that the decision variables have good adaptability. Finally, a detailed exergy analysis of the equipment used is made, and the results show that the main exergy losses come from the water coolers and compressors, accounting for 32% and 34%, respectively. Compared to the T-C3MR, the improved C3MR based on EHR-GWO-GA(E-C3MR) has an approximate 8% increase in liquefaction amount—a roughly 23% decrease in unit energy consumption and a decrease of nearly 24% in exergy loss.

Kriging and Radial Basis Function Models for Optimized Design of UAV Wing Fences to Reduce Rolling Moment

In the present study, the effects of the wing fence on the wing tip vortices and control surfaces located at the tip of the wing in a flying wing aircraft have been investigated using a numerical method. For the size of the fences, the average dimensions extracted from the wing tip vortices at different angles of attack are used. The basic determining parameter is the rolling torque coefficient, which is tried to be shown by employing a parametric study of the flow behavior in different situations of fence placement. These effects on the rolling torque of the aircraft are measured due to the presence of the split drag rudder control system. In this study, the fences were installed at three different heights and three different positions along the length of the wing, which were investigated at angles of attack of 7 to 16 degrees. The next stage of the research is to design the dimensions of the fence using the single-objective optimization method (a method to find the best solution for a problem with a specific goal). The designing of the fences at three points based on the dimensions of the wing tip vortex is carried out with the computational fluid dynamics (CFD) method (CFD is a computational method that uses physical laws to predict the behavior of fluids.). The aim of this research is to achieve the best design that converges to an optimal solution with minimum time and cost (CFD solution is long). However, CFD analysis requires a lot of computational time. To address this challenge, we employed a hybrid learning model comprising the radial basis function (RBF), a type of artificial neural network, and Kriging, a Gaussian process-based interpolation technique. The dataset for training the hybrid model was obtained from numerical solutions of CFD simulations involving a fence placed at various locations on the wing. Additionally, a genetic algorithm was employed as the optimization method in all instances where it was required. Using the power of machine learning techniques helped us identify the optimal placement of the fence to prevent it from being engulfed by the vortex and to optimize the utilization of the split drag system, yielding significant improvements.

Simulation Analysis and Optimization Design of Paddy Field Mud Spreader Blades for Uniform Dispersion

To improve the distribution of mud particles collected in the tray during the operation of paddy field mud spreader blades, the optimal combination of parameters for the blades that results in the best uniformity of mud dispersion needs to be identified. In this study, a thorough force analysis was conducted on the spreading process, and computational equations were formulated to describe the motion of mud particles. By utilizing the discrete element simulation technique, a simulation model was developed to accurately represent the intricate interaction between the blades and mud particles. Through the single-factor simulation experiments, the ranges of key parameters such as the rotation radius, bending angle, sub-blade tilt angle, forward velocity, and rotational speed of the blade were determined. A secondary orthogonal rotational combination design was employed to establish a regression prediction model between the non-uniformity of mud dispersion and the key blade parameters. Subsequently, a multivariate single-objective optimization method was used to develop an optimization model for the non-uniformity of mud dispersion. The results indicate that the hierarchical order of factors influencing the non-uniformity of mud dispersion is as follows: rotation radius > rotation speed > bending angle > forward velocity > sub-blade tilt angle. To achieve a minimum spreading non-uniformity of 29.63%, a specific configuration is required, which includes a blade rotation radius of 188 mm, a bending angle of 121°, a sub-blade tilt angle of 30°, a forward velocity of 400 mm/s, and a rotation speed of 191 r/min. Finally, the accuracy of the optimization results was verified by means of bench tests. The research results provide a crucial reference for enhancing the uniformity of mud dispersion in paddy field mud spreader blades.

Robust design optimization of a multi-body system with aleatory and epistemic uncertainty

There are several issues in robust design optimization of the multi-body system with aleatory and epistemic uncertainty, such as the difficulty in the multi-source uncertainty characterization and low efficiency in dynamic modeling, analysis and the corresponding solving strategy for its robust design optimization. To address these problems, this paper firstly constructs a unified analysis framework for aleatory and epistemic uncertainty for the multi-body system based on probability theory and evidence theory. Taking a multi-body system of a shipborne artillery model as an example, the transfer matrix method is next employed to rapidly calculate the dynamic response of the muzzle. The results are compared with those by the finite element method to verify the accuracy and efficiency of the transfer matrix method. A decision model of the robust design optimization with both aleatory and epistemic uncertainty is proposed. Based on the polynomial chaos expansion-Kriging model, subset simulation optimization method and a weighted single-objective solving strategy, the multi-objective robust design optimization problem involving aleatory and epistemic uncertainty is then transformed into a single-objective optimization one. Finally, results of both the multi-objective and weighted single-objective robust design optimization methods for the shipborne artillery model are compared to demonstrate the performance of the proposed method.

Improvement of Blocked Long-Straight Flow Channels in Proton Exchange Membrane Fuel Cells Using CFD Modeling, Artificial Neural Network, and Genetic Algorithm

To further improve the performance of the Proton Exchange Membrane Fuel Cell (PEMFC), in this paper, we designed a blocked flow channel with trapezoidal baffles, and geometric parameters of the baffle were optimized based on CFD simulation, Artificial Neural Network (ANN), and single-objective optimization methods. The analysis of velocity, pressure, and oxygen distribution in the cathode flow channel shows that the optimized trapezoidal baffle can improve oxygen transport during the reaction. The comparison of the optimization model with the straight flow channel model and the rectangular baffle model shows that the power density of the optimized model is 4.0% higher than that of the straight flow channel model at a voltage of 0.3 V, and the pressure drop is only 37.83% of that of the rectangular baffle model. For on-road PEMFC with a voltage of 0.6 V, the influence of pump power is significant, and the optimized trapezoidal baffle model has a net power increase of 1.47% compared to the rectangular baffle model at 50% pump efficiency and 3.94% at 30% pump efficiency.

Enhancing infectious disease prediction model selection with multi-objective optimization: an empirical study.

As the pandemic continues to pose challenges to global public health, developing effective predictive models has become an urgent research topic. This study aims to explore the application of multi-objective optimization methods in selecting infectious disease prediction models and evaluate their impact on improving prediction accuracy, generalizability, and computational efficiency. In this study, the NSGA-II algorithm was used to compare models selected by multi-objective optimization with those selected by traditional single-objective optimization. The results indicate that decision tree (DT) and extreme gradient boosting regressor (XGBoost) models selected through multi-objective optimization methods outperform those selected by other methods in terms of accuracy, generalizability, and computational efficiency. Compared to the ridge regression model selected through single-objective optimization methods, the decision tree (DT) and XGBoost models demonstrate significantly lower root mean square error (RMSE) on real datasets. This finding highlights the potential advantages of multi-objective optimization in balancing multiple evaluation metrics. However, this study's limitations suggest future research directions, including algorithm improvements, expanded evaluation metrics, and the use of more diverse datasets. The conclusions of this study emphasize the theoretical and practical significance of multi-objective optimization methods in public health decision support systems, indicating their wide-ranging potential applications in selecting predictive models.

Interval Pareto front-based multi-objective robust optimization for sensor placement in structural modal identification

Considering the multi-performance development of complex systems and the requirement of structural modal identification with typical uncertainties, the nominal single-objective optimization method is not suitable for sensor placement. Therefore, by combining conventional optimal sensor placement with non-probabilistic theory, this study proposes an uncertainty-oriented multi-objective robust optimization method for optimal sensor placement. The Fisher information matrix and ill-posedness comprise one eigenvalue-based optimization objective, and the mean and minimum off-diagonal values in the modal assurance criterion comprise another. Considering the high-cost limitation of the statistical method for handling uncertainties, uncertainty propagations are realized by a dimension-wise analysis with better accuracy and efficiency, thus avoiding the overestimation incurred by the classical Taylor expansion method. The multi-objective robust optimization is established by uncertain eigenvalue- and eigenvector-based indices with interval numbers and solved using the multi-objective optimization algorithm. Considering the solution sets located at the Pareto front, an interval possibility was developed using interval Pareto fronts to determine the optimal number of sensors. A numerical example demonstrated the validity of the proposed method with an optimal number of sensors and corresponding configurations.

Community Detection in Modular Complex Networks Using an Improved Particle Swarm Optimization Algorithm

Community detection is an important and interesting topic for better understanding and analyzing complex network structures. Detecting hidden partitions in complex networks is proven to be an NP-hard problem that may not be accurately resolved using traditional methods. So it is solved using evolutionary computation methods and modeled in the literature as an optimization problem. In recent years, many researchers have directed their research efforts toward addressing the problem of community structure detection by developing different algorithms and making use of single-objective optimization methods. In this study, we have continued that research line by improving the Particle Swarm Optimization (PSO) algorithm using a local improvement operator to effectively discover community structure in the modular complex networks when employing the modularity density metric as a single-objective function. The framework of the proposed algorithm consists of three main steps: an initialization strategy, a movement strategy based on perturbation genetic operators, and an improvement operator. The key idea behind the improvement operator is to determine and reassign the complex network nodes that are located in the wrong communities if the majority of their topological links do not belong to their current communities, making it appear that these nodes belong to another community. The performance of the proposed algorithm has been tested and evaluated when applied to publicly-available modular complex networks generated using a flexible and simple benchmark generator. The experimental results showed the effectiveness of the suggested method in discovering community structure over modular networks of different complexities and sizes.

Application of multiobjective optimization methods for solving of a ship design problem

In the present paper we demonstrate the application of single-objective and multi-objective optimization methods for solving the problem of ship design characteristics optimization. The impact analysis of local criteria on the values of design characteristics and elements of a ship has been carried out. The most frequently used methods of multicriteria optimization and their application to solving the problem of ship design characteristics substantiation, with taking into account the requirements to seakeeping and economic efficiency are considered. The multicriteria optimization results obtained by different methods are compared with the results of single-criteria optimization. Finally, numerical examples are implemented to demonstrate that an attempt to find a compromise solution often decrease the values of local criteria of optimality. It is established that the application of multi-criteria optimization methods for solving the ship design problems makes clear the role of each local optimality criteria and assess it influence on functional efficiency and design characteristics values.

Multi-level model predictive control based multi-objective optimal energy management of integrated energy systems considering uncertainty

Integrated energy systems (IES) with renewable energy systems (RES), carbon capture systems (CCS) and energy storage systems (ESS) are considered efficient in supporting the low-carbon energy supply with both economic and environmental benefits. Effective energy management is required to ensure the economical, environmental and reliable operation of the IES. However, the optimal IES operation is considered a non-trivial task due to the renewable generation uncertainty and the optimization of multiple contradictory objectives (e.g. economic, environmental and risk costs). This paper aims to provide a multi-level optimization model for the real-time optimal IES operation consisting of RES, ESS and CCS. This work quantifies the uncertainty by the Conditional Value at Risk (CVaR) theory in the optimization model. The uncertainty is further reduced by improving the operation strategy through a model predictive control (MPC)-based method. Also, the multi-objective optimization model is adopted to minimize the economic cost, carbon dioxide emissions (CDE) and primary energy consumption (PEC) for optimal energy scheduling in the intra-day stage. Based on the result of the intra-day stage, the feedback correction model is applied to adjust the schedule to balance the difference between the forecasting and actual values. Numerical results show that the proposed solution can provide the trade-off between economical and environmental performance. Through ablation experiments, the proposed method with feedback correction can carry out demand response with lower costs, CDE and PEC. The proposed solution is further confirmed with outperformed performance compared with single-objective optimization methods and other stochastic optimization methods. In addition, a robustness analysis is conducted to quantify the benefits of RES, ESS and CCS in IES.