改进粒子群优化算法结合BP神经网络模型的水体透射光谱总磷浓度预测研究

张国浩; 王彩玲; 王洪伟; 于涛

doi:doi:10.3964/j.issn.1000-0593(2025)02-0394-09

光谱学与光谱分析, 2025, 45 (2): 394, 网络出版: 2025-05-21

改进粒子群优化算法结合BP神经网络模型的水体透射光谱总磷浓度预测研究【增强内容出版】

Improved Particle Swarm Optimization Algorithm Combined With BP Neural Network Model for Prediction of Total Phosphorus Concentration in Water Body Using Transmittance Spectral Data

论文大纲

张国浩 ¹王彩玲 ^1,*王洪伟 ²于涛 ³

作者单位

¹ 西安石油大学计算机学院，陕西　西安　710065

² 西北工业大学光电与智能研究院，陕西　西安　710065

³ 中国科学院西安光学精密机械研究所，陕西　西安　710065

AI高清视频导读

AI一图读本文 AI语音精读 AI语音超短摘要

注：本部分内容由 AI 自动生成，仅供您参考。对于您使用本站 AI 自动生成内容所产生的一切后果，本网站及平台运营方概不承担任何商业和法律责任，请您知悉。

摘要

使用光谱数据结合融合算法对水体污染物含量进行准确检测以保护水资源已成为一个关键问题。然而，光谱数据的高维特性以及模型的不稳定常常导致预测效果不佳，无法准确的进行检测。本研究提出了一种环保和准确的方法，实现对长江水体中总磷浓度含量的预测。具体而言，首先对测得的长江水质光谱数据进行最大最小归一化和均值中心化两种预处理操作，在消除不同数据量级差异的同时去除了噪声，确保了数据的一致性和可靠性。其次，为了解决光谱数据的高维度问题，采用了核主成分分析（KPCA）方法来降低数据维度并提取特征。KPCA方法通过在高维度的空间中找到一个分类平面，选出能代表原始数据99.42%信息量的前6个主成分，用于后续预测模型的训练。接着在原始粒子群算法的基础上引入了粒子初始化规则、多种群竞争策略、参数自适应更新策略、种群多样性引导策略和粒子变异机制，提高了粒子群的寻优能力，降低粒子陷入局部最优解的概率。并使用改进后的粒子群算法对BP神经网络（BPNN）中的初始化权重和参数大小进行寻优，从而加快网络的收敛效果，提高预测能力。最后，使用本研究所提出的预测模型对测试集中的样本进行总磷浓度的预测，实验结果得到R²为0.975 786，RMSE为0.002 242，MAE为0.001 612。将本模型与当前预测性能较好的其他基准模型进行预测效果的对比，本研究所提出的模型对长江水体总磷浓度预测拟合效果更好，精确度更高。在水资源保护和环境管理领域中使用光谱数据结合融合算法进行预测模型的研究和实践提供了新的思路和观点。

Abstract

The accurate detection of pollution levels in water bodies using transmission spectrum data and fusion algorithms has become crucial for safeguarding water resources. Inaccurate predictions and detection frequently result from the high-dimension of transmission spectrum data and model instability. The Yangtze River water body's total phosphorus concentration content is predicted in this study, and an accurate and environmentally friendly approach is suggested to achieve this goal. In particular, maxi-min normalization and mean-centering are two preprocessing operations carried out on the Yangtze River's measured water quality transmission spectrum data. These operations remove noise while eradicating differences between different data magnitudes, guaranteeing the consistency and reliability of the data. In addition, to solve the problem of the high dimension of the transmission spectrum data, the KPCA method is used to reduce the dimension of the data and extract the features. The KPCA method is used to select the top 6 principal components that represent 99.42% of the information content of the original data for subsequent prediction model training by finding a classification plane in a high-dimension space. Then, on the foundation of the initial particle swarm algorithm, the particle initialization rule, multiple swarm competition strategy, parameter adaptive update strategy, population diversity guidance strategy, and particle variation mechanism are added to improve the particle swarm's capacity for optimization and prevent particles from trapping in the local optimal solution. Additionally, the improved particle swarm algorithm optimizes the initialized weights and parameter values in the BP neural network to accelerate the convergence of the network and improve prediction performances. Finally, the total phosphorus content of the samples in the test set was predicted using the IMCPSO-BPNN model. The experimental results showed an R² of 0.975 786, an RMSE of 0.002 242, and an MAE of 0.001 612. The IMCPSO-BPNN model suggested in this work has a better fitting effect and better accuracy in forecasting the total nitrogen concentration in the Yangtze River water body when compared to other models such as the RF model, the BPNN model, and the PSO-BPNN model. It offers fresh concepts and viewpoints for studying and applying predictive modeling using transmission spectrum data and fusion algorithms to protect water resources and environmental management.

参考文献

[1] WANG Cai-ling, WANG Bo, JI Tong, et al (王彩玲, 王波, 纪童, 等). Spectroscopy and Spectral Analysis (光谱学与光谱分析), 2022, 42(7): 2181.

[2] FENG Tian-shi, PANG Zhi-guo, JIANG Wei, et al (冯天时, 庞治国, 江威, 等). Journal of Geo-information Science (地球信息科学学报), 2021, 23(9): 1646.

[3] HUANG Hua, LI Mao-yi, CHEN Yin-hui, et al (黄华, 李茂亿, 陈吟晖, 等). Water Resources Protection (水资源保护), 2021, 37(5): 36.

[4] CHEN Jun-ying, XING Zheng, ZHANG Zhi-tao, et al (陈俊英, 邢正, 张智韬, 等). Transactions of the Chinese Society for Agricultural Machinery (农业机械学报), 2019, 50(11): 200.

[5] FU Yu, WAN Xiao-xia, LIU Zhi-hong, et al (付玉, 万晓霞, 刘志宏, 等). Printing and Digital Media Technology Study (印刷与数字媒体技术研究), 2023, (2): 22.

[6] YANG Feng (杨峰). Computer Simulation (计算机仿真), 2019, 36(8): 435.

[7] DONG Jun-shuo, WU Ling-da (董隽硕, 吴玲达). Computer Engineering and Design (计算机工程与设计), 2023, 44(4): 1122.

[8] LI Chang-yuan, LIU Guo-dong, TAN Bo (李昌元, 刘国栋, 谭博). Geospatial Information (地理空间信息), 2022, 20(7): 89.

[9] ZHANG Qin-yu, HU Zhi-gang, XU Zi-jian, et al (张沁宇, 胡志刚, 徐子健, 等). Journal of Food Safety & Quality (食品安全质量检测学报), 2023, 14(22): 200.

[10] HU Jin-hua, ZHENG Bing-li, DENG Yu-jing, et al (胡劲华, 郑炳理, 邓玉静, 等). Laser & Optoelectronics Progress (激光与光电子学进展), 2023, 60(21): 149.

[11] YANG Yang, XU Xi-ping, XUE Hang, et al (杨洋, 徐熙平, 薛航, 等). Laser Technology (激光技术), 2024, 48(4): 556.

[12] SUN Wei, ZHU Ying, LI Chang-xiu, et al (孙巍, 朱颖, 李长秀, 等). Environmental Pollution & Control (环境污染与防治), 2022, 44(12): 1628.

[13] LIN Nan, LIU Han-lin, MENG Xiang-fa, et al (林楠, 刘翰霖, 孟祥发, 等). Transactions of the Chinese Society for Agricultural Machinery (农业机械学报), 2021, 52(3): 218.

[14] XU Han-qiu, LI Chun-qiang, LIN Meng-jing (徐涵秋, 李春强, 林梦婧). Geomatics and Information Science of Wuhan University [武汉大学学报(信息科学版)], 2023, 48(4): 506.

[15] DUAN Yi-fan, LIU Xiao-jie, LI Xin, et al (段一凡, 刘小杰, 李欣, 等). China Metallurgy (中国冶金), 2023, 33(11): 114.

[16] KANG Yan-song, ZANG Shun-lai (康岩松, 臧顺来). Journal of Northeastern University (Natural Science)[东北大学学报(自然科学版)], 2023, 44(8): 1089.

[17] LIU Gong-zhi, WU Qiong, WANG Guang-yi, et al (刘公致, 吴琼, 王光义, 等). Journal of Electronics & Information Technology (电子与信息学报), 2022, 44(10): 3602.

[18] WANG Zhen-dao, ZHANG Yi-ming, SHI Xue-qian (王镇道, 张一鸣, 石雪倩). Journal of Hunan University (Natural Sciences)[湖南大学学报(自然科学版)], 2021, 48(6): 80.

[19] ZHANG Hu, ZHANG Heng, HUANG Zi-lu, et al (张虎, 张衡, 黄子路, 等). Journal of System Simulation (系统仿真学报), 2024, 36(4): 844.

[20] GUAN Ren-chu, HE Bao-run, LIANG Yan-chun, et al (管仁初, 贺宝润, 梁艳春, 等). Journal of Jilin University (Engineering and Technology Edition)[吉林大学学报(工学版)], 2022, 52(8): 1842.

[21] LI Wei, DING Shu-hui, CHEN Xun-jun (李伟, 丁书慧, 陈勋俊). Application Research of Computers (计算机应用研究), 2023, 40(11): 3254.

[22] WEI Hai-bin, WEI Dong-sheng, JIANG Bo-yu, et al (魏海斌, 魏东升, 蒋博宇, 等). Journal of South China University of Technology (Natural Science Edition)[华南理工大学学报(自然科学版)], 2023, 51(6): 62.

[23] SHI Jing-can, TANG Shou-feng, ZHAO Zhi-wei, et al (史经灿, 唐守锋, 赵志伟, 等). Transducer and Microsystem Technologies (传感器与微系统), 2023, 42(7): 70.

[24] CHENG Mei-ying, QIAN Qian, NI Zhi-wei (程美英, 钱乾, 倪志伟). Control and Decision (控制与决策), 2024, 39(3): 728.

[25] WANG Kun, HOU Shu-xian, WANG Li (王坤, 侯树贤, 王力). Systems Engineering and Electronics (系统工程与电子技术), 2021, 43(2): 526.

[26] SONG Yu-cun, GE Quan-bo, ZHU Jun-long, et al (宋玉存, 葛泉波, 朱军龙, 等). Acta Aeronautica et Astronautica Sinica (航空学报), 2023, 44(14): 327951.

张国浩, 王彩玲, 王洪伟, 于涛. 改进粒子群优化算法结合BP神经网络模型的水体透射光谱总磷浓度预测研究[J]. 光谱学与光谱分析, 2025, 45(2): 394. ZHANG Guo-hao, WANG Cai-ling, WANG Hong-wei, YU Tao. Improved Particle Swarm Optimization Algorithm Combined With BP Neural Network Model for Prediction of Total Phosphorus Concentration in Water Body Using Transmittance Spectral Data[J]. Spectroscopy and Spectral Analysis, 2025, 45(2): 394.

改进粒子群优化算法结合BP神经网络模型的水体透射光谱总磷浓度预测研究【增强内容出版】

关于本站 Cookie 的使用提示

全站搜索

改进粒子群优化算法结合BP神经网络模型的水体透射光谱总磷浓度预测研究【增强内容出版】

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索