Zhu Zheyu, Wang Jiawei, Yu Kanhua
School of Architecture, Chang'an University, Xi'an 710061, China.
College of Architecture, Xi'an University of Architecture and Technology, Xi'an 710055, China.
Biomimetics (Basel). 2025 Apr 8;10(4):233. doi: 10.3390/biomimetics10040233.
In order to overcome the drawbacks of low search efficiency and susceptibility to local optimal traps in PSO, this study proposes a multi-strategy particle swarm optimization (PSO) with information acquisition, referred to as IA-DTPSO. Firstly, Sobol sequence initialization on particles to achieve a more uniform initial population distribution is performed. Secondly, an update scheme based on information acquisition is established, which adopts different information processing methods according to the evaluation status of particles at different stages to improve the accuracy of information shared between particles. Then, the Spearman's correlation coefficient (SCC) is introduced to determine the dimensions that require reverse solution position updates, and the tangent flight strategy is used to improve the inherent single update method of PSO. Finally, a dimension learning strategy is introduced to strengthen individual particles' activity, thereby ameliorating the entire particle population's diversity. In order to conduct a comprehensive analysis of IA-DTPSO, its excellent exploration and exploitation (ENE) capability is firstly validated on CEC2022. Subsequently, the performance of IA-DTPSO and other algorithms on different dimensions of CEC2022 is validated, and the results show that IA-DTPSO wins 58.33% and 41.67% of the functions on 10 and 20 dimensions of CEC2022, respectively. Finally, IA-DTPSO is employed to optimize parameters of the time-dependent gray model (1,1,,,) (TDGM (1,1,,,)) and applied to simulate and predict total urban water resources (TUWRs) in China. By using four error evaluation indicators, this method is compared with other algorithms and existing models. The results show that the total MAPE (%) value obtained by simulation after IA-DTPSO optimization is 5.9439, which has the smallest error among all comparison methods and models, verifying the effectiveness of this method for predicting TUWRs in China.
为了克服粒子群优化算法（PSO）搜索效率低和易陷入局部最优陷阱的缺点，本研究提出了一种带信息获取的多策略粒子群优化算法（IA-DTPSO）。首先，对粒子进行索博尔序列初始化，以实现更均匀的初始种群分布。其次，建立基于信息获取的更新方案，根据粒子在不同阶段的评估状态采用不同的信息处理方法，提高粒子间共享信息的准确性。然后，引入斯皮尔曼相关系数（SCC）来确定需要反向求解位置更新的维度，并采用切线飞行策略改进PSO固有的单一更新方法。最后，引入维度学习策略来增强单个粒子的活跃度，从而改善整个粒子群的多样性。为了对IA-DTPSO进行全面分析，首先在CEC2022上验证了其出色的勘探与开采（ENE）能力。随后，验证了IA-DTPSO和其他算法在CEC2022不同维度上的性能，结果表明IA-DTPSO在CEC2022的10维和20维上分别赢得了58.33%和41.67%的函数。最后，将IA-DTPSO用于优化时变灰色模型（1,1,,,）（TDGM（1,1,,,））的参数，并应用于模拟和预测中国城市总水资源（TUWRs）。通过使用四个误差评估指标，将该方法与其他算法和现有模型进行比较。结果表明，IA-DTPSO优化后模拟得到的总平均绝对百分比误差（MAPE）（%）值为5.9439，在所有比较方法和模型中误差最小，验证了该方法对中国TUWRs预测的有效性。
