Engineering optimization problems are often nonlinear, high-dimensional, and constrained, making them challenging for conventional optimization techniques. Although L-SHADE, an adaptive differential evolution (DE) algorithm with success-history based parameter adaptation, has demonstrated competitive performance, it still suffer from limited population diversity and weak local exploitation, leading to an imbalance between exploration and exploitation in complex optimization. To address these limitations, this paper proposes LCO-LSHADE-GSRL, a novel DE variant that enhances both global exploration and local exploitation capabilities. The proposed algorithm integrates three key components: (1) a Logistic Chaos Orthogonal Initialization mechanism that improves initial population diversity and ensures uniform coverage of the search space. (2) a GAN-driven Specular Reflection Learning (SRL) mechanism that effectively escapes from local optima. (3) a design that adapts effectively to constrained optimization scenarios. Comprehensive experiments conducted on the CEC 2019 and 2022 benchmark suites demonstrate that LCO-LSHADE-GSRL exhibits superior convergence performance, solution accuracy, and robustness compared to L-SHADE, LSHADE-cnEpSin, and WOA, GJO, PO, PIMO, and CDO. Furthermore, in three real-world engineering problems–speed reducer, step-cone pulley, and hydrostatic thrust bearing, which reduces system weight and power loss while satisfying all design constraints. These results demonstrate its potential for solving complex engineering optimization tasks with high reliability and efficiency.

Neural Architecture Search (NAS) has emerged as an important area in deep learning since it can automatically design high performance network architectures, where Evolution-based NAS (EvoNAS) has made great progress due to the efficient optimization ability of evolutionary algorithms. However, EvoNAS requires evaluating the architectures formed by individuals in the population, and it is inevitable to consume a large amount of evaluation time and computational resources, resulting in restricting the applicability of EvoNAS. To solve the above problems, this paper proposes a Weight Inheritance and Guided Strategy based Evolutionary Network Architecture Search (WIGEvoNAS). Firstly, based on existing manually designed networks, an expanded search space is designed, which includes new convolution operations. Secondly, a weight inheritance strategy is proposed to reduce the training time of candidate architectures in each generation. Finally, a guidance mutation strategy is proposed to direct population evolution towards architectures with superior for the purpose of generating better offspring. The proposed method is compared with several state-of-the-art NAS methods and manual networks on the CIFAR-10, CIFAR-100 and the NASBench-201 benchmark datasets. The empirical results demonstrate that the proposed method achieves promising performance, with error rates of 2.52% on CIFAR-10 and 15.43% on CIFAR-100 respectively. Moreover, the proposed method significantly reduces search costs to 0.9 GPU-days.

Dynamic multiobjective optimization problems (DMOPs) are characterized by their multiple objectives, constraints, and parameters that may change over time. The challenge in solving DMOPs is how to track the varying Pareto optimal solution sets quickly and accurately. Therefore, an inter-individual correlation and dimension-based dual learning method is proposed in this paper. Two learning strategies, decomposition-based inter-individual correlation transfer learning (DICTL) and dimension-wise learning (DL), are developed to respectively generate one-half of the initial population in the new environment. More specifically, DICTL learns the inter-individual correlation from the final population of the adjacent environment and then transfers it to the new environment, aiming to maintain the diversity and distribution of the predicted population. While DL extracts the changing pattern of dynamic environments from the high-quality solutions of historical environments in the perspective of variable dimension, trying to improve the quality of the population and accelerate the convergence. The designed two learning strategies (DICTL&DL) work complementarily and collaboratively to make the algorithm adapt to dynamic environments better and faster. Comprehensive experiments have been conducted by comparing the proposed method with four state-of-the-art algorithms on 14 benchmark problems. The results demonstrate the superiority of the proposed method.

A modified multi-objective harmony search algorithm called Niching Multi-objective Harmony Search Algorithm (NMOHSA) is proposed to solve multimodal multi-objective optimization problems. It adopts the neighborhood information to build dynamic harmony memory for maintaining the population diversity. A new memory consideration rule is also applied to prevent the algorithm be trapped into local optimal solution. Moreover, two key parameters, harmony memory consideration rate (HMCR) and pitch adjustment rate (PAR), are dynamically adjusted. Empirical results show that the proposed algorithm performs much better than the other existing multimodal multi-objective algorithms in terms of the solution quality.

A modified multi-objective bat algorithm called Performance Enhanced Niching Multi-objective Bat algorithm (PEN-MOBA) is proposed to solve multimodal multi-objective optimization problems. It adopts a dynamic ring topology to form stable niches for maintaining the population diversity, and integrates the stagnation detection strategy to improve the searching ability. The algorithm is compared with a number of state-of-the-art multimodal multi-objective optimizers on twelve multimodal multi-objective test functions. The experimental results verify that the proposed algorithm is effective multimodal multi-objective optimizers and outperforms the existing algorithms on the test functions.