Hybridized neural network inspired behavioural modelling of pneumatic artificial muscles for assistive robotic applications
Author:
Arora Aman,Sarkar Debadrata,Majumder Arunabha,Sen Soumen,Roy Shibendu Shekhar
Abstract
Purpose
This paper aims to devise a first-of-its-kind methodology to determine the design, operating conditions and actuation strategy of pneumatic artificial muscles (PAMs) for assistive robotic applications. This requires extensive characterization, data set generation and meaningful modelling between PAM characteristics and design variables. Such a characterization should cover a wide range of design and operation parameters. This is a stepping stone towards generating a design guide for this highly popular compliant actuator, just like any conventional element of a mechanism.
Design/methodology/approach
Characterization of a large pool of custom fabricated PAMs of varying designs is performed to determine their static and dynamic behaviours. Metaheuristic optimizer-based artificial neural network (ANN) structures are used to determine eight different models representing PAM behaviour. The assistance of knee flexion during level walking is targeted for evaluating the applicability of the developed actuator by attaching a PAM across the joint. Accordingly, the PAM design and the actuation strategy are optimized through a tabletop emulator.
Findings
The dependence of passive length, static contraction, dynamic step response for inflation and deflation of the PAMs on their design dimensions and operating parameters is successfully modelled by the ANNs. The efficacy of these models is investigated to successfully optimize the PAM design, operation parameters and actuation strategy for using a PAM in assisting knee flexion in human gait.
Originality/value
Characterization of static and the dynamic behaviour of a large pool of PAMs with varying designs over a wide range of operating conditions is the novel feature in this article. A lucid customizable fabrication technique is discussed to obtain a wide variety of PAM designs. Metaheuristic-based ANNs are used for tackling high non-linearity in data while modelling the PAM behaviour. An innovative tabletop emulator is used for investigating the utility of the models in the possible application of PAMs in assistive robotics.
Subject
Industrial and Manufacturing Engineering,Computer Science Applications,Control and Systems Engineering
Reference17 articles.
1. A survey on applications of pneumatic artificial muscles,2011
2. A survey on static modeling of miniaturized pneumatic artificial muscles with new model and experimental results;Applied Mechanics Review,2018
3. Effects of bladder geometry in pneumatic artificial muscles;Journal of Medical Devices,2016
4. Advances of metaheuristic algorithms in training neural networks for industrial applications;Soft Computing,2021
5. Measurement and modeling of McKibben pneumatic artificial muscles;IEEE Transactions on Robotics and Automation,1996
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献