Han Li

Bio: Han Li is an academic researcher from Shanghai Jiao Tong University. The author has contributed to research in topics: Particle swarm optimization & Premature convergence. The author has an hindex of 2, co-authored 4 publications receiving 26 citations.

Diversity enhanced particle swarm optimization algorithm and its application in vehicle lightweight design

Abstract: Particle swarm optimization, a widely used metaheuristic algorithm, mimics the cooperation behavior among species. The PSO algorithm has become a new trend owing to its simplicity and strong optimization capacity. However, premature convergence problem is also a serious issue for PSO comparable with other evolutionary algorithms. Diversity loss is generally known as one of the major causes. For enhancing the diversity of swarms during optimization procedure, an improved PSO algorithm named OLAR-PSO-d is proposed, which incorporates design of experiment technique as well as adaptive reset operator into standard PSO. The OLAR-PSO-d algorithm is compared with other 10 heuristic algorithms. The numerical experiments’ results demonstrate the priority of OLAR-PSO-d both in optimization ability and algorithm stability. The proposed algorithm is also used in a vehicle lightweight design problem. The auto-body achieves 20.25 kg weight reduction with meeting all the performance requirements of crashworthiness.

An improved multi-objective optimization algorithm with mixed variables for automobile engine hood lightweight design

Abstract: Engine hood is one of the important parts of the vehicles, which has influences on the lightweight, structural safety, pedestrian protection, and aesthetics. The optimization design of engine hood is a high-dimensional, multi-objective, and mixed-variable optimization problem. In order to reduce the physical test investment in the development and improve the efficiency of optimization, this article proposes a data-driven method for optimal hood design. A newly proposed single-objective optimization algorithm is improved by several strategies for multi-objective constrained problem with mixed variables. Then the hood is optimized through the specially designed machine learning model. Finally, both the hood's weight and pedestrian injury are reduced while maintaining structural stiffness and frequency in the desired range. The comparative study and final hood optimization results prove the effectiveness of the proposed method.

Diversity-enhanced particle swarm optimization algorithm based on the group behaviour of social spiders

Abstract: Particle swarm optimization (PSO) is a representative swarm intelligence algorithm, which has the drawback of being restricted by premature convergence To make PSO less likely to be restricted by

A data-driven self-adaptive parameter tuning framework for composite automobile part optimization design

Abstract: Population-based heuristic optimization algorithms are wildly used in the automobile optimization design. However, the hyper-parameter tuning has a significant effect on the performance of the most of the heuristic algorithms. In order to take full advantages of the heuristic optimization algorithms, this article proposes a data-driven framework for self-adaptive parameters tuning, which named DSPT. The DSPT framework divides the optimization process into two phases. In the learning phase, the knowledge is learned from abundant benchmark functions. The specifically designed performance metrics are used to relate the characteristics of different problems and algorithm performances. In the optimizing phase, the characteristics of a new problem are firstly extracted. According to the knowledge gained from the learning phase and the problem characteristics gained in this phase, rather than predetermined parameters based on experience, the key parameters are tuned automatically. Therefore, the optimization can continue more efficiently. Based on the newly proposed social spider inspired particle swarm optimization algorithm, the proposed framework is successfully applied to the multi-scale lightweight design of four different composite automobile parts.

An enhanced sitting–sizing scheme for shunt capacitors in radial distribution systems using improved atom search optimization

Abstract: In this paper, an enhanced sitting–sizing scheme for shunt capacitors (4SCs) in a radial distribution system (RDS) based on an improved atom search optimization (IASO) algorithm is proposed. IASO emulates the model of atomic motion in nature based on interaction forces among atoms. The main goal of the 4SCs problem is to reduce the line losses and minimize the capacitor installation cost by searching for the optimal location and sizing of the capacitors. This leads to improvements in the voltage profile and reliability of the system. The IASO algorithm is introduced to achieve the optimal sitting and sizing of capacitors for RDSs. The proposed IASO algorithm is benchmarked and validated on different radial systems, including the IEEE 33-bus, IEEE 34-bus, IEEE 65-bus, IEEE 85-bus and Marsa Matrouh networks, to demonstrate its performance in real-world applications. The results obtained by the proposed IASO algorithm are compared with the standard ASO, PSO, SCA, GWO and SSA algorithms. Furthermore, the significance of the obtained results is confirmed by performing a nonparametric statistical test, i.e., the Wilcoxon’s rank-sum at the 5% significance level. The comprehensive results demonstrate that the results obtained by the proposed IASO algorithm denominate the results obtained by the other algorithms and that IASO minimizes the operating costs while achieving better voltage profiles.

Ant Colony Optimization

Abstract: Ant Colony Optimization (ACO) is a stochastic local search method that has been inspired by the pheromone trail laying and following behavior of some ant species [1]. Artificial ants in ACO essentially are randomized construction procedures that generate solutions based on (artificial) pheromone trails and heuristic information that are associated to solution components. Since the first ACO algorithm has been proposed in 1991, this algorithmic method has attracted a large number of researchers and in the meantime it has reached a significant level of maturity. In fact, ACO is now a well-established search technique for tackling a wide variety of computationally hard problems.

An Improved Equilibrium Optimizer with Application in Unmanned Aerial Vehicle Path Planning

Abstract: The unmanned aerial vehicle (UAV) path planning problem is a type of complex multi-constraint optimization problem that requires a reasonable mathematical model and an efficient path planning algorithm. In this paper, the fitness function including fuel consumption cost, altitude cost, and threat cost is established. There are also four set constraints including maximum flight distance, minimum flight altitude, maximum turn angle, and maximum climb angle. The constrained optimization problem is transformed into an unconstrained optimization problem by using the penalty function introduced. To solve the model, a multiple population hybrid equilibrium optimizer (MHEO) is proposed. Firstly, the population is divided into three subpopulations based on fitness and different strategies are executed separately. Secondly, a Gaussian distribution estimation strategy is introduced to enhance the performance of MHEO by using the dominant information of the populations to guide the population evolution. The equilibrium pool is adjusted to enhance population diversity. Furthermore, the Levy flight strategy and the inferior solution shift strategy are used to help the algorithm get rid of stagnation. The CEC2017 test suite was used to evaluate the performance of MHEO, and the results show that MHEO has a faster convergence speed and better convergence accuracy compared to the comparison algorithms. The path planning simulation experiments show that MHEO can steadily and efficiently plan flight paths that satisfy the constraints, proving the superiority of the MHEO algorithm while verifying the feasibility of the path planning model.