检索
E-mail
RSS

作者投稿 主编审稿 专家审稿 远程编辑

热带海洋学报

• • 上一篇    

基于 BO-CNN 的AUV有害藻华高浓度区域观测算法研究

余桐1, 2, 颜波2, 3, 焦君圣1, 朱心科2

  

  1. 1. 中国计量大学计量测试与仪器学院, 浙江, 杭州, 310018

    2. 自然资源部第二海洋研究所, 浙江 杭州 310012;

    3. 杭州电子科技大学机械工程学院, 浙江, 杭州, 310018


  • 收稿日期:2025-10-23 修回日期:2025-11-27 接受日期:2025-12-08
  • 通讯作者: 朱心科
  • 基金资助:
    浙江省重点研发计划(2021C03186)

Research on AUV Harmful Algal Bloom High-Concentration Area Observation Algorithm Based on BO-CNN

YU Tong1, 2, YAN Bo2,3, JIAO Junsheng1, ZHU Xinke2   

  1. 1. College of Metrology Measurement and Instrument, China Jiliang University, Hangzhou 310018,China;

    2. Second Institute of Oceanography, Hangzhou 310012, China;

    3. School of Mechanical Engineering, Hangzhou Dianzi University, Hangzhou 310018, China;



  • Received:2025-10-23 Revised:2025-11-27 Accepted:2025-12-08
  • Supported by:

    Zhejiang Provincial Key Research and Development Program(2021C03186)

PDF (PC)

赞

摘要： 针对传统AUV(autonomous undersea vehicl)使用预编程观测有害藻华效率低下, 以及传统预测模型对非线性浓度场适应性不足的问题, 设计了一种基于贝叶斯优化卷积神经网络的叶绿素浓度预测算法。基于卷积神经网络和贝叶斯优化算法的混合叶绿素浓度场预测模型, 在已有的预采样数据下对AUV进行卷积神经网络训练, 通过贝叶斯优化算法对CNN(Convolutional Neural Networks)模型中的超参数进行迭代优化, 最后将优化后的超参数带入到模型中, 获得临近位置的叶绿素浓度预测场。通过计算 AUV 当前位置与目标位置的浓度梯度值并结合其与有害藻华热点区域的相对位置, 选择不同的观测策略, 动态引导AUV的运到方向, 使其自主高效的完成对有害藻华高浓度区域的搜索与观测任务。采用真实有害藻华叶绿素浓度场进行仿真测试, 结果显示, 与常规算法相比, 该算法MAE下降30%, MSE下降60%, 能够满足对不同形态的有害藻华热点区域的观测需求。

关键词: 自主水下航行器, 在线路径规划, 自适应采样, 热点区域观测

Abstract: To address the inefficiency of traditional AUVs using pre-programmed observation for harmful algal blooms and the insufficient adaptability of traditional prediction models to nonlinear concentration fields, a chlorophyll concentration prediction algorithm based on Bayesian Optimization Convolutional Neural Network (BO-CNN) was designed. The hybrid chlorophyll concentration field prediction model, based on convolutional neural networks and Bayesian optimization algorithms, trains the CNN on pre-sampled data, iteratively optimizes the hyperparameters of the CNN model using the Bayesian optimization algorithm, and finally input the optimized hyperparameters into the model to obtain the chlorophyll concentration prediction field at neighboring locations. By calculating the concentration gradient value between the current AUV position and the target position and combining it with the relative position to harmful algal bloom hotspots, different observation strategies are selected to dynamically guide the AUV’s movement direction, enabling it to autonomously and efficiently complete the search and observation tasks in high-concentration harmful algal bloom areas. Simulation tests using real harmful algal bloom chlorophyll concentration fields show that, compared to conventional algorithms, this algorithm reduces MAE by 30% and MSE by 60%, meeting the observation requirements for harmful algal bloom hotspot areas of different shapes.

Key words: Autonomous Underwater Vehicle, online path planning, adaptive sampling, hotspot area observation