Abstract
Robots are increasingly becoming popular medical devices, helping surgeons and practitioners as surgical, rehabilitation or service robots. Robots have been proved commendable in working together with patients and practitioners to achieve the common goal of well-being. Apart from high power to weight ratio and accuracy, robots are expected to be safe and flexible. At The University of Auckland we had earlier developed robots for ankle joint and lower limb rehabilitation using McKibben pneumatic muscle actuators (PMA) which were safe and flexible. However, these actuators had larger response time and hysteresis apart from compromised actuation limits. As a result of our further research we have been able to develop inhouse pleated PMA (PPMA) in our laboratory which show improved response time with low hysteresis. The newly developed actuators have larger actuation as well. In order to cope with the non-linear and transient nature of these actuators, this paper further proposes a new Artificial Neural Network (ANN) based approach. To optimize ANN model parameters a hybrid approach combing back propagation (BP) algorithm with Modified Genetic Algorithm (MGA) is developed. Results show that the hybrid approach is able to model the PPMA behaviour closely.
| Original language | English |
|---|---|
| Title of host publication | Proceedings of 2012 8th IEEE/ASME International Conference on Mechatronic and Embedded Systems and Applications, MESA 2012 |
| Pages | 190-195 |
| Number of pages | 6 |
| DOIs | |
| Publication status | Published - 2012 |
| Externally published | Yes |
| Event | 2012 8th IEEE/ASME International Conference on Mechatronic and Embedded Systems and Applications, MESA 2012 - Suzhou, China Duration: Jul 8 2012 → Jul 10 2012 |
Other
| Other | 2012 8th IEEE/ASME International Conference on Mechatronic and Embedded Systems and Applications, MESA 2012 |
|---|---|
| Country | China |
| City | Suzhou |
| Period | 7/8/12 → 7/10/12 |
Fingerprint
Keywords
- Artificial Neural Networks
- Dynamic Modelling
- Pleated Pneumatic Muscle Actuators
ASJC Scopus subject areas
- Control and Systems Engineering
- Mechanical Engineering
Cite this
Artificial Neural Network based dynamic modelling of indigenous pneumatic muscle actuators. / Jamwal, Prashant K.; Xie, Sheng Quan.
Proceedings of 2012 8th IEEE/ASME International Conference on Mechatronic and Embedded Systems and Applications, MESA 2012. 2012. p. 190-195 6275560.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Artificial Neural Network based dynamic modelling of indigenous pneumatic muscle actuators
AU - Jamwal, Prashant K.
AU - Xie, Sheng Quan
PY - 2012
Y1 - 2012
N2 - Robots are increasingly becoming popular medical devices, helping surgeons and practitioners as surgical, rehabilitation or service robots. Robots have been proved commendable in working together with patients and practitioners to achieve the common goal of well-being. Apart from high power to weight ratio and accuracy, robots are expected to be safe and flexible. At The University of Auckland we had earlier developed robots for ankle joint and lower limb rehabilitation using McKibben pneumatic muscle actuators (PMA) which were safe and flexible. However, these actuators had larger response time and hysteresis apart from compromised actuation limits. As a result of our further research we have been able to develop inhouse pleated PMA (PPMA) in our laboratory which show improved response time with low hysteresis. The newly developed actuators have larger actuation as well. In order to cope with the non-linear and transient nature of these actuators, this paper further proposes a new Artificial Neural Network (ANN) based approach. To optimize ANN model parameters a hybrid approach combing back propagation (BP) algorithm with Modified Genetic Algorithm (MGA) is developed. Results show that the hybrid approach is able to model the PPMA behaviour closely.
AB - Robots are increasingly becoming popular medical devices, helping surgeons and practitioners as surgical, rehabilitation or service robots. Robots have been proved commendable in working together with patients and practitioners to achieve the common goal of well-being. Apart from high power to weight ratio and accuracy, robots are expected to be safe and flexible. At The University of Auckland we had earlier developed robots for ankle joint and lower limb rehabilitation using McKibben pneumatic muscle actuators (PMA) which were safe and flexible. However, these actuators had larger response time and hysteresis apart from compromised actuation limits. As a result of our further research we have been able to develop inhouse pleated PMA (PPMA) in our laboratory which show improved response time with low hysteresis. The newly developed actuators have larger actuation as well. In order to cope with the non-linear and transient nature of these actuators, this paper further proposes a new Artificial Neural Network (ANN) based approach. To optimize ANN model parameters a hybrid approach combing back propagation (BP) algorithm with Modified Genetic Algorithm (MGA) is developed. Results show that the hybrid approach is able to model the PPMA behaviour closely.
KW - Artificial Neural Networks
KW - Dynamic Modelling
KW - Pleated Pneumatic Muscle Actuators
UR - http://www.scopus.com/inward/record.url?scp=84867453551&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84867453551&partnerID=8YFLogxK
U2 - 10.1109/MESA.2012.6275560
DO - 10.1109/MESA.2012.6275560
M3 - Conference contribution
SN - 9781467323475
SP - 190
EP - 195
BT - Proceedings of 2012 8th IEEE/ASME International Conference on Mechatronic and Embedded Systems and Applications, MESA 2012
ER -