Structural Optimization Algorithm Research Articles

Lightweight Deep Neural Networks for Ship Target Detection in SAR Imagery.

In recent years, deep convolutional neural networks (DCNNs) have been widely used in the task of ship target detection in synthetic aperture radar (SAR) imagery. However, the vast storage and computational cost of DCNN limits its application to spaceborne or airborne onboard devices with limited resources. In this paper, a set of lightweight detection networks for SAR ship target detection are proposed. To obtain these lightweight networks, this paper designs a network structure optimization algorithm based on the multi-objective firefly algorithm (termed NOFA). In our design, the NOFA algorithm encodes the filters of a well-performing ship target detection network into a list of probabilities, which will determine whether the lightweight network will inherit the corresponding filter structure and parameters. After that, the multi-objective firefly optimization algorithm (MFA) continuously optimizes the probability list and finally outputs a set of lightweight network encodings that can meet the different needs of the trade-off between detection network precision and size. Finally, the network pruning technology transforms the encoding that meets the task requirements into a lightweight ship target detection network. The experiments on SSDD and SDCD datasets prove that the method proposed in this paper can provide more flexible and lighter detection networks than traditional detection networks.

A Modified Quantum-Inspired Genetic Algorithm for Continuum Structural Topology Optimization

Topology optimization and quantum computing have evolved rapidly over the past three decades. Previous topological optimum design methods suffered from financial burden and mathematical complexity. To overcome these shortcomings, a modified quantum-inspired evolutionary algorithm-based topology optimization method is proposed. This nested approach combines the classic solid isotropic microstructure with the penalization method and the double chains quantum genetic algorithm to establish an integral topology optimization framework. The former is utilized to determine the search direction of design variable updating. Meanwhile, the latter ensures abundant search diversity. The validity and feasibility of the developed methodology are eventually demonstrated by several application examples. The results indicate that the proposed optimization framework is independent of initial values and can lead to optimized structures. In addition, it will be more appropriate and effective if this strategy is deployed on a quantum computer in the future.

A structural optimization algorithm with stochastic forces and stresses.

We propose an algorithm for optimizations in which the gradients contain stochastic noise. This arises, for example, in structural optimizations when computations of forces and stresses rely on methods involving Monte Carlo sampling, such as quantum Monte Carlo or neural network states, or are performed on quantum devices that have intrinsic noise. Our proposed algorithm is based on the combination of two ingredients: an update rule derived from the steepest-descent method, and a staged scheduling of the targeted statistical error and step size, with position averaging. We compare it with commonly applied algorithms, including some of the latest machine learning optimization methods, and show that the algorithm consistently performs efficiently and robustly under realistic conditions. Applying this algorithm, we achieve full-degree optimizations in solids using ab initio many-body computations, by auxiliary-field quantum Monte Carlo with plane waves and pseudopotentials. A potential metastable structure in Si is discovered using density-functional calculations with synthetic noisy forces.

Structural optimization method of 6-DOF manipulator based on genetic algorithm

Most of the manipulator is designed under the constraint of motion reversibility, and the optimization of the manipulator structure is often carried out through the study of kinematics. In order to solve the structural optimization problem of a 6-Dof manipulator, this paper proposes a structural optimization method based on a 6-Dof manipulator with comprehensive indexes combining kinematics performance and dynamics performance. On the premise of satisfying the original workspace and taking dynamic performance as evaluation function, genetic algorithm was used to optimize the structural parameters of the manipulator, so that the optimized manipulator not only has the characteristics of the original workspace, but also consumes the least energy. The kinematic equation of the manipulator was derived, the dynamics model was established by Lagrange method, and then the fitness function and the structural optimization algorithm of the manipulator based on genetic algorithm were given.

A broadband loose coupling coupler with discrete structure and hybrid binary particle swarm genetic optimization algorithm

A broadband loose coupling coupler with discrete structure and hybrid binary particle swarm genetic optimization algorithm

Sizing and shape optimization of truss employing a hybrid constraint-handling technique and manta ray foraging optimization

This paper presents an efficient constraint-handling technique (CHT) for metaheuristic algorithms in the size and shape optimization of truss structures. During the search process, the proposed CHT utilizes an improved Deb rule to filter redundant structural analyses and maps the candidate designs onto the feasible boundary for structural optimization to improve its search ability and stability based on the mapping strategy. The performance of the newly developed Manta Ray Foraging Optimization (MRFO) algorithm using the proposed CHT in structural optimization was also examined. Five truss optimization problems are used to examine the efficiency of the hybrid CHT compared with the improved Deb rule, the EDP method, and the mapping strategy. Four widely used metaheuristic algorithms, including HS, PSO, TLBO, and CS, have also been used to evaluate the performance of the MRFO in structural optimization. Numerical results demonstrate that the hybrid CHT can markedly improve both the search capacity and computational efficiency of metaheuristic algorithms. The MRFO does not show obvious weakness compared with existing algorithms in structural optimization. A comparison analysis also shows that the performances of the hybrid CHT vary across optimization algorithms.

Reptile search algorithm and kriging surrogate model for structural design optimization with natural frequency constraints

Abstract This study explores the use of a recent metaheuristic algorithm called a reptile search algorithm (RSA) to handle engineering design optimization problems. It is the first application of the RSA to engineering design problems in literature. The RSA optimizer is first applied to the design of a bolted rim, which is constrained optimization. The developed algorithm is then used to solve the optimization problem of a vehicle suspension arm, which aims to solve the weight reduction under natural frequency constraints. As function evaluations are achieved by finite element analysis, the Kriging surrogate model is integrated into the RSA algorithm. It is revealed that the optimum result gives a 13% weight reduction compared to the original structure. This study shows that RSA is an efficient metaheuristic as other metaheuristics such as the mayfly optimization algorithm, battle royale optimization algorithm, multi-level cross-entropy optimizer, and red fox optimization algorithm.

Enhanced optimization algorithm for the structural design of an air‐cooled battery pack considering battery lifespan and consistency

Electric scooters are increasingly popular for short-distance commuting. To improve the thermal safety, performance, and lifespan of their batteries, their heat needs to be managed. This study proposes a method for optimizing the air channels in a scooter battery pack. It includes an electro-thermal-degradation model for predicting the battery's electrical and thermal behaviors and capacity loss, a heat transfer model for predicting convective heat exchange between the battery and the air, and a genetic algorithm for structural optimization of an air-cooled battery thermal management system (BTMS). Unlike conventional optimization of a BTMS, the proposed algorithm aims to improve the electrical consistency, lifespan, and thermal safety of the battery via rapid global optimization of its air ducts. The optimization algorithm was tested on a 3P4S air-cooled battery pack from an electric scooter. It improved the pack's consistency of state of charge (SOC) and its lifespan by reducing its heat and temperature gradient. Under on-design conditions, the optimized air ducts reduced the maximum pack temperature by 0.45°C and the difference between the average temperatures of the cells in a branch to 15.9% that of the original pack. Moreover, the optimized air ducts decrease the SOC difference by 81.1% and improved the state of health by 0.03%. Hence, the proposed air duct optimization method can improve the pack's thermal performance, SOC distribution, and lifespan under off-design conditions.

A firefly metaheuristic algorithm for structural size and shape optimization with dynamic constraint

A firefly metaheuristic algorithm for structural size and shape optimization with dynamic constraint

Adaptive Broad Echo State Network for Nonstationary Time Series Forecasting

Time series forecasting provides a vital basis for the control and management of various systems. The time series data in the real world are usually strongly nonstationary and nonlinear, which increases the difficulty of reliable forecasting. To fully utilize the learning capability of machine learning in time series forecasting, an adaptive broad echo state network (ABESN) is proposed in this paper. Firstly, the broad learning system (BLS) is used as a framework, and the reservoir pools in the echo state network (ESN) are introduced to form the broad echo state network (BESN). Secondly, for the problem of information redundancy in the reservoir structure in BESN, an adaptive optimization algorithm for the BESN structure based on the pruning algorithm is proposed. Thirdly, an adaptive optimization algorithm of hyperparameters based on the nonstationary test index is proposed. In brief, the structure and hyperparameter optimization algorithms are studied to form the ABESN based on the proposed BESN model in this paper. The ABESN is applied to the data forecasting of air humidity and electric load. The experiments show that the proposed ABESN has a better learning ability for nonstationary time series data and can achieve higher forecasting accuracy.

A Decomposition based Multi-Objective Heat Transfer Search algorithm for structure optimization

Multi-objective (MO) problems are complex and challenging to solve due to multiple conflicting objectives and incommensurate constraints. Heat Transfer Search is a recently introduced thermodynamic laws-based algorithm for solving many single objective problems. But it faces criticism due to its shortcomings including local optima trap, computational complexity, and reliability issues while solving MO problems. Decompositions is a simple yet efficient framework that aids in resolving fitness assignments and diversity maintenance issues of MO problems. It is also popular for reducing computational complexity and improving solution quality. Therefore, this work proposes and investigates a novel, simple, and robust Decomposition-based Multi-Objective Heat Transfer Search (MOHTS/D) for solving real-world structural problems. To achieve the Pareto optimal solutions and to confirm their coverage behaviour, the evenly generated weight vectors sorting and Euclidean distance strategies were employed in the proposed posteriori method. The performance of MOHTS/D is investigated through eight constrained widely accepted benchmarks. The results contrast with the MOHTS, MO evolutionary algorithm based on decomposition, MO passing vehicle search, MO slime mould, MO symbiotic organisms search, and MO multi-verse optimization. The efficacy of MOHTS/D is evaluated based on hyper-volume, coverage, inverted generational distance, pure diversity, spacing, spread, coverage Pareto front, diversity maintenance, generational distance, and runtime metrics. The results reveal that MOHTS/D is a robust optimization approach compared to others for optimizing real-life structural problems. MOHTS/D was able to find the optimal solution with minor computational complexity, and the obtained solutions demonstrate a better convergence, coverage, diversity, and spread behaviour over Pareto fronts

Real-time topology optimization based on deep learning for moving morphable components

The moving morphable component (MMC) method, an important engineering structural optimization algorithm, achieves a boundary evolution through the migration and superposition of a series of moving morphable display components, resulting in structural optimization. Instead of the original linear skeleton thickness quadratic variation component, an elliptical initial component is used for topology optimization, which reduces the number of design variables of the initial component itself to achieve the purpose of reducing the computational time cost. As the number of initial components increases, the intermediate iterative computation becomes increasingly time-consuming; the initial components of the different parameters generate significant differences in the topological configuration. To obtain an optimal topology in an accurate and real-time manner, a Pyramid Attention U-Net (PA-U-Net) deep learning model is proposed to improve the optimization design and to avoid intermediate iterative computations. The dataset is generated by an improved MMC method for training. According to the results, the method not only obtains the optimal topology of the initial components under various parameter conditions in an accurate and timely manner and in a negligible amount of computing time, but it also achieves an accuracy of 90.89%, which is superior to other deep learning models. The organic combination of deep learning and topology optimization has many prospects in the design optimization of large engineering structures.

The Mosaic of Metaheuristic Algorithms in Structural Optimization

The Mosaic of Metaheuristic Algorithms in Structural Optimization

LPI waveform design for radar system against cyclostationary analysis intercept processing

Low probability of intercept (LPI) property has provided the radar system with superior survivability on the practical battlefield. In this paper, we put forward a waveform design approach to enhance the LPI performance for radar systems by considering the intercept processing of the electronic reconnaissance (ER) systems. Based on this approach, an LPI waveform design problem against the typical cyclostationary analysis (CSA) widely performed by the ER systems is studied and further formulated as an optimization problem. In this problem, the deviation between the cyclic spectrum of the designed waveform and that of the Gaussian white noise is minimized to improve the LPI performance. Meanwhile, the optimal detection signal-to-noise ratio (SNR) restriction is enforced to ensure detection ability. The resulting optimization problem is shown to be a non-convex quartic programming that is intractable in general. To solve the problem efficiently, a structural sequential greedy optimization (S-SGO) algorithm is proposed. The proposed algorithm performs an ingenious reparameterization of the radar waveform vector and solves related problems in a polynomial-time based on the thought of alternation optimization. The convergence of the proposed S-SGO is also investigated. Numerical results verify the effectiveness of the proposed approach for the LPI waveform design as well as the proposed algorithm.

Adaptive Salp Swarm Algorithm for Optimization of Geotechnical Structures

Based on the salp swarm algorithm (SSA), this paper proposes an efficient metaheuristic algorithm for solving global optimization problems and optimizing two commonly encountered geotechnical engineering structures: reinforced concrete cantilever retaining walls and shallow spread foundations. Two new equations for the leader- and followers-position-updating procedures were introduced in the proposed adaptive salp swarm optimization (ASSA). This change improved the algorithm’s exploration capabilities while preventing it from converging prematurely. Benchmark test functions were used to confirm the proposed algorithm’s performance, and the results were compared to the SSA and other effective optimization algorithms. A Wilcoxon’s rank sum test was performed to evaluate the pairwise statistical performances of the algorithms, and it indicated the significant superiority of the ASSA. The new algorithm can also be used to optimize low-cost retaining walls and foundations. In the analysis and design procedures, both geotechnical and structural limit states were used. Two case studies of retaining walls and spread foundations were solved using the proposed methodology. According to the simulation results, ASSA outperforms alternative models and demonstrates the ability to produce better optimal solutions.

Fast atomic structure optimization with on-the-fly sparse Gaussian process potentials *

We apply on-the-fly machine learning potentials (MLPs) using the sparse Gaussian process regression (SGPR) algorithm for fast optimization of atomic structures. Great acceleration is achieved even in the context of a single local optimization. Although for finding the exact local minimum, due to limited accuracy of MLPs, switching to another algorithm may be needed. For random gold clusters, the forces are reduced to ∼0.1 eV Å−1 within less than ten first-principles (FP) calculations. Because of highly transferable MLPs, this algorithm is specially suitable for global optimization methods such as random or evolutionary structure searching or basin hopping. This is demonstrated by sequential optimization of random gold clusters for which, after only a few optimizations, FP calculations were rarely needed.

An SQP Algorithm for Structural Topology Optimization Based on Majorization–Minimization Method

When applying the sequential quadratic programming (SQP) algorithm to topology optimization, using the quasi-Newton methods or calculating the Hessian matrix directly will result in a considerable amount of calculation, making it computationally infeasible when the number of optimization variables is large. To solve the above problems, this paper creatively proposes a method for calculating the approximate Hessian matrix for structural topology optimization with minimum compliance problems. Then, the second-order Taylor expansion transforms the original problem into a series of separable and easy-to-solve convex quadratic programming (QP) subproblems. Finally, the quadratic programming optimality criteria (QPOC) method and the QP solver of MATLAB are used to solve the subproblems. Compared with other sequential quadratic programming methods, the advantage of the proposed method is that the Hessian matrix is diagonally positive definite and its calculation is simple. Numerical experiments on an MBB beam and cantilever beam verify the feasibility and efficiency of the proposed method.

A structural reanalysis assisted harmony search for the optimal design of structures

Structural optimization usually requires a large amount of time-consuming structural analyses to evaluate the feasibility of the designs, which obstructs its application in large-scale problems. This study proposed a structural reanalysis-assisted harmony search (RAHS) algorithm for structural optimization. The RAHS utilizes the combined approximation (CA) technique instead of direct finite element analysis to evaluate the performances of the modified structures generated in iterations. Different from existing approaches, the proposed RAHS will update the reanalysis design point set and select the best reanalysis design point based on the similarity of the design vectors to improve the accuracy of the CA in a large search space. The RAHS also develops a diversity-based error criterion to accommodate the accuracy requirements of CA in different search phases of the harmony search. Five benchmark examples are utilized to examine the performances of the proposed RAHS. The results demonstrate that the Cosine distance outperforms the other four design point selection approaches, and the diversity-based error criterion can significantly reduce the computational cost. Compared with the penalty-based method and the improved Deb rule, the number of FE-based structural analyses can be lessened by about 90% and 50%, respectively, while yielding similar optimal designs.

A Novel Implementation of Energy-Based Homogenization Method

This paper develops a novel implementation of energy-based homogenization method, which has rigorous mathematical foundation of the homogenization method, and also efficiently and accurately predict the mechanical performance of composite materials. The feature extraction, domain discretization and periodic boundary condition application are carried out automatically in this method. Besides, this model remains a fairly small scale and it could be directly embedded into structure optimization algorithms. The numerical calculation could be easily implemented with a commercial computer aided engineering (CAE) software and the integration algorithm was realized by the third-party language. This article explains the scheme of the CAE/CAD integration in homogenization method and the theoretical model of the energy-based homogenization for cellular solid element and shell element. Furthermore, two examples for cellular solid and stiffened plate, and its implementation in cellular material design are presented to illustrate the verification of the proposed method.

A hybrid arithmetic optimization algorithm and differential evolution for optimization of truss structures subjected to frequency constraints

A new hybrid arithmetic optimization algorithm (AOA) associated with differential evolution (DE) is developed for truss optimization. The development is named as ADE with the goal of maintaining a balance between low computational cost and good solution quality. Besides, several limitations of the AOA, which include the inefficiency of the exploration phase and the inconvenient use of two parameters MOA and MOP to find the optimal solution, as well as how to overcome them are also discussed. In terms of AOA in ADE, the exploration phase is removed, and both math optimizer accelerated (MOA) and math optimizer probability (MOP) parameters are adjusted to be independent of the maximum number of iterations. Moreover, the exploitation phase is modified to exploration which helps to limit local solutions and maintain a balance between exploitation and exploration in ADE algorithm. Through a probability parameter, the DE with DE/best/1 operator is executed in ADE to improve exploitation capability as well as convergence rate. Four truss structures with continuous design variables are considered to demonstrate the performance of the current algorithm. The obtained results show that the developed algorithm has a low computational cost, indicating its computational efficiency.