nav emailalert searchbtn searchbox tablepage yinyongbenwen piczone journalimg journalInfo searchdiv qikanlogo popupnotification paper paperNew
2025, 02, v.57 1-7
基于FS-SIA的毁伤预测神经网络超参数优化方法
基金项目(Foundation): 嵩山实验室预研项目(YYYY022022003); 河南省重点研发与推广专项(科技攻关)(212102310039)
邮箱(Email): tianzhao@zzu.edu.cn;
DOI: 10.13705/j.issn.1671-6841.2023180
摘要:

针对毁伤预测中神经网络超参数设置及调试过程较为复杂的问题,提出一种基于特征选择结合群体智能(feature selection and swarm intelligence algorithm, FS-SIA)的超参数优化方法,用于在毁伤预测中对神经网络进行超参数的搜索和优化。首先,通过多种特征排序方法确定毁伤特征的重要性,选取公共的特征偏序子集用于模型训练。其次,针对具体的神经网络模型,分别采用多种群体智能算法进行超参数的搜索和优化。最后,得出特征集性能最优的超参数训练模型。实验结果表明,相较于未经特征排序而单纯采用群体智能算法的其他超参数优化模型,所提方法在毁伤预测中具有更快的收敛速度和更高的准确率。

Abstract:

To address the complexity of neural network hyperparameter setting and tuning process in damage prediction, a hyperparameter optimization method was proposed based on feature selection and swarm intelligence algorithm(FS-SIA). The method was utilized for search and optimization of neural network hyperparameters in damage prediction. Firstly, the importance of damage features was determined through various feature ranking methods, and a common partial subset of features was selected for model training. Secondly, for the specific neural network model, various swarm intelligence algorithms were employed separately to conduct hyperparameter search and optimization. Finally, the hyperparameter trained model was obtained which performed optimally for the feature set. The experimental results showed that the proposed method had faster convergence speed and higher accuracy in damage prediction than other hyperparameter optimization models using swarm intelligence methods alone without feature ordering.

参考文献

[1] 李发陵,彭娟.基于大数据的复杂超参数优化组合方法仿真[J].计算机仿真,2022,39(7):332-336.LI F L,PENG J.Simulation of complex hyperparameter optimization combination method based on big data[J].Computer simulation,2022,39(7):332-336.

[2] ROSTAMIAN A,HEIDARYAN E,OSTADHASSAN M.Evaluation of different machine learning frameworks to predict CNL-FDC-PEF logs via hyperparameters optimization and feature selection[J].Journal of petroleum science and engineering,2022,208:109463.

[3] 高岳林,杨钦文,王晓峰,等.新型群体智能优化算法综述[J].郑州大学学报(工学版),2022,43(3):21-30.GAO Y L,YANG Q W,WANG X F,et al.Overview of new swarm intelligent optimization algorithms[J].Journal of Zhengzhou university (engineering science),2022,43(3):21-30.

[4] LEITE W L,SHEN Z C,MARCOULIDES K,et al.Using ant colony optimization for sensitivity analysis in structural equation modeling[J].Structural equation modeling,2022,29(1):47-56.

[5] SHAMI T M,EL-SALEH A A,ALSWAITTI M,et al.Particle swarm optimization:a comprehensive survey[J].IEEE access,2022,10:10031-10061.

[6] LI Z L,ZHU W M,ZHU B,et al.Thermal error modeling of electric spindle based on particle swarm optimization-SVM neural network[J].The international journal of advanced manufacturing technology,2022,121(11):7215-7227.

[7] 鲍伟,任超.基于GWO-BP神经网络的电池SOC预测方法研究[J].计算机应用与软件,2022,39(9):65-71.BAO W,REN C.Research on prediction method of battery SOC based on GWO-BP network[J].Computer applications and software,2022,39(9):65-71.

[8] HU T,LI X S,YOU J A.The weighted fusion prediction algorithm of acoustic interval optimized by PCA-PSO-BP and MLRM[J].Journal of physics:conference series,2022,2258(1):012004.

[9] 李郅琴,杜建强,聂斌,等.特征选择方法综述[J].计算机工程与应用,2019,55(24):10-19.LI Z Q,DU J Q,NIE B,et al.Summary of feature selection methods[J].Computer engineering and applications,2019,55(24):10-19.

[10] 刘佳敏,吴庆宪,王玉惠,等.基于量子粒子群优化的无人机攻防博弈决策[J].火力与指挥控制,2022,47(9):73-78,84.LIU J M,WU Q X,WANG Y H,et al.UAV game decision based on quantum particle swarm optimization[J].Fire control & command control,2022,47(9):73-78,84.

[11] 冯华丽,刘渊,陈冬.QPSO算法优化BP网络的网络流量预测[J].计算机工程与应用,2012,48(3):102-104.FENG H L,LIU Y,CHEN D.Network traffic prediction based on BPNN optimized by QPSO algorithm[J].Computer engineering and applications,2012,48(3):102-104.

[12] ZHU X T,XU B.Power short-term load forecasting based on QPSO-SVM[J].Advanced materials research,2012,591/592/593:1311-1314.

[13] ZHOU B H,ZHAO Z.An adaptive artificial bee colony algorithm enhanced by deep Q-learning for milk-run vehicle scheduling problem based on supply hub[J].Knowledge-based systems,2023,264:110367.

[14] KASSAYMEH S,AL-LAHAM M,AL-BETAR M A,et al.Backpropagation neural network optimization and software defect estimation modelling using a hybrid salp swarm optimizer-based simulated annealing algorithm[J].Knowledge-based systems,2022,244:108511.

[15] 李慧轩.数理统计在计量检测中的应用[J].统计理论与实践,2021(6):58-61.LI H X.Application of mathematical statistics in metrological detection[J].Statistical theory and practice,2021(6):58-61.

[16] 李亚茹,张宇来,王佳晨.面向超参数估计的贝叶斯优化方法综述[J].计算机科学,2022,49(S1):86-92.LI Y R,ZHANG Y L,WANG J C.Survey on Bayesian optimization methods for hyper-parameter tuning[J].Computer science,2022,49(S1):86-92.

基本信息:

DOI:10.13705/j.issn.1671-6841.2023180

中图分类号:E920.8;TP18

引用信息:

[1]佘维,吕钟毓,邢召伟等.基于FS-SIA的毁伤预测神经网络超参数优化方法[J].郑州大学学报(理学版),2025,57(02):1-7.DOI:10.13705/j.issn.1671-6841.2023180.

基金信息:

嵩山实验室预研项目(YYYY022022003); 河南省重点研发与推广专项(科技攻关)(212102310039)

检 索 高级检索