Data-Driven Energy Consumption Prediction and Optimization Method for Underwater Soft Robots
Zixin Huang, Jiali Ding, Shengyuan Huang, Junjie Lu, Chengsong Yu, Peng Huang
Wuhan Institute of Technology
阅读操作
确认中在文库中上传 PDF 后可生成中文音频讲解。
摘要与影响
To address the problem of limited operational endurance in underwater soft robots caused by excessive energy consumption, a prediction and optimization method is proposed to reduce the energy usage. This method utilizes an energy consumption dataset for prediction analysis and optimization. Based on the operating mechanism of underwater soft robot, the sources of energy consumption are analyzed, including the drive system, control system, sensing system, and external loads. The processed energy consumption data is used to train and validate back propagation (BP) neural network prediction model, and particle swarm optimization (PSO) is employed to optimize the energy consumption. The simulation results show that the BP neural network algorithm has better prediction accuracy compared to traditional algorithms. Using PSO algorithm, the average energy consumption is reduced by 19.25% compared to actual energy consumption, effectively reducing the energy consumption of underwater soft robots.
逐年被引趋势
暂无年度引用数据
关键指标
同类平均 = 1
同领域 · 同年份 · 同类型
Google Scholar 与 OpenAlex 的被引统计范围不同,数值存在差异属正常。
AI 辅助阅读
依据:摘要
可就本文提问;依据不足时会说明。
学术脉络
学科主题
工程Soft Robotics and Applications
Underwater Vehicles and Communication Systems · Aerospace Engineering and Energy Systems
参考文献 18
此处列出前 3 条