Search research articles

关于 JoVE

概览领导团队博客 JoVE 帮助中心

作者

出版流程编辑委员会范围与政策同行评审常见问题投稿

图书馆员

用户评价订阅访问资源图书馆顾问委员会常见问题

研究

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments 存档

教育

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual 教师资源中心教师网站

使用条款与条件

相关概念视频

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序

Same author

Online Sensor Fault Detection Using Machine Learning Algorithms on a Laboratory-Scale Batch Reactor: LSTM Approach.

ACS omega·2026

Same author

Reinforcement Learning-Based Nonlinear Model Predictive Controller for a Jacketed Reactor: A Machine Learning Concept Validation Using Jetson Orin.

ACS omega·2025

Same author

Q‑Learning-Based Multivariate Nonlinear Model Predictive Controller: Experimental Validation on Batch Reactor for Temperature Trajectory Tracking.

ACS omega·2025

Same author

CNN-LSTM-Based Nonlinear Model Predictive Controller for Temperature Trajectory Tracking in a Batch Reactor.

ACS omega·2024

Same author

Machine Learning Based Fault Classification in Pilot Plant Batch Reactor: Using Support Vector Machine.

ACS omega·2024

Same author

Development of a Nonlinear Model Predictive Control-Based Nonlinear Three-Mode Controller for a Nonlinear System.

ACS omega·2022

Same journal

NMR Spectroscopy: Molecular Insights into Cell Wall Collapse and Oxidative Stress of <i>Escherichia coli</i> Induced by Imidazole-Activated Eutectic Solvents.

ACS omega·2026

Same journal

Enhanced Arsenite Remediation in Synthetic FeS<sub>2</sub>/Fe(II)-Containing Arsenic Wastewater via Epigallocatechin Gallate-Initiated Persulfate Activation.

ACS omega·2026

Same journal

Defect and Particle-Size Engineering as Mechanistic Drivers for Dye Uptake in a Zirconium Metal-Organic Framework.

ACS omega·2026

Same journal

Biogeochemical Assessment of Short-Term Hydrogen Storage in Methane Reservoirs with Field Sample Characterization and Reactor Experiments.

ACS omega·2026

Same journal

Combined Effects of Halloysite Nanotubes, Nucleating Agent, and Thermal Annealing on the Printability and Mechanical Performances of 3D-Printable Polypropylene Random Copolymer-Based Composites.

ACS omega·2026

Same journal

Effect of MoS<sub>2</sub> Interfacial Engineering across MAPbI<sub>3</sub>, FAPbI<sub>3</sub>, and CsPbI<sub>3</sub> Perovskite Solar Cells.

ACS omega·2026

查看所有相关文章

Search research articles

相关实验视频

Updated: Jul 5, 2025

Power Input Measurements in Stirred Bioreactors at Laboratory Scale

Power Input Measurements in Stirred Bioreactors at Laboratory Scale

Published on: May 16, 2018

基于神经网络的汉默斯坦模型识别实验室规模的批量反应堆.

Murugan Balakrishnan¹, Vinodha Rajendran¹, Shettigar J Prajwal²

¹Department of Electronics and Instrumentation Engineering, Annamalai University, Annamalainagar 608 002, Tamil Nadu, India.

|January 15, 2024

概括

此摘要是机器生成的。

本研究介绍了两种神经网络方法,用于识别批量反应堆聚合中的汉默斯坦模型. 这些技术为改进控制器设计提供了高效的非线性系统建模.

更多相关视频

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Published on: March 2, 2015

Process Optimization using High Throughput Automated Micro-Bioreactors in Chinese Hamster Ovary Cell Cultivation

Process Optimization using High Throughput Automated Micro-Bioreactors in Chinese Hamster Ovary Cell Cultivation

Published on: May 18, 2020

相关实验视频

Last Updated: Jul 5, 2025

Power Input Measurements in Stirred Bioreactors at Laboratory Scale

Power Input Measurements in Stirred Bioreactors at Laboratory Scale

Published on: May 16, 2018

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Published on: March 2, 2015

Process Optimization using High Throughput Automated Micro-Bioreactors in Chinese Hamster Ovary Cell Cultivation

Process Optimization using High Throughput Automated Micro-Bioreactors in Chinese Hamster Ovary Cell Cultivation

Published on: May 18, 2020

科学领域:

化学工程是化学工程的重要组成部分.
人工智能的人工智能
控制系统控制系统

背景情况:

批量反应堆过程,如烯胺聚合,表现出复杂的非线性动态.
准确的系统识别对于有效的控制器设计至关重要.
传统的汉默斯坦模型识别可以是计算密集的.

研究的目的:

开发和比较两个基于神经网络的方法,用于哈默斯坦模型的识别.
为了简化控制器设计,有效地识别非线性系统.
探索工艺控制中的先进机器学习应用.

主要方法:

基于梯度的反向传播算法用于训练多层神经网络.
极端学习机器 (ELM) 用于训练代表非线性块的单一隐藏层前网络.
使用神经网络权重对哈默斯坦模型块进行直接参数化.

主要成果:

这两种神经网络方法都成功地确定了批量反应堆过程的汉默斯坦模型.
基于ELM的方法在没有梯度计算的情况下证明了高效的训练.
已识别的模型使线性和非线性控制器设计更容易.

结论:

基于神经网络的汉默斯坦模型识别为复杂的非线性系统提供了有效的方法.
ELM方法为参数估计提供了一个计算效率高的替代方案.
未来的工作包括实施基于机器学习的非线性模型预测控制.