Vision based supervised restricted Boltzmann machine helps to actuate novel shape memory alloy accurately

Dutta, Ritaban; Chen, Cherry C.; Renshaw, D.; Liang, Daniel

doi:10.1038/s41598-021-95939-y

Cited by 6 publications

(3 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, introducing control strategy to current work can help to improve position control more precisely. As such approach was considered in some research, [61,62] particularly, by introducing a neural network and deep learning, [63,64] we expect that our future work including control strategy will make SMA artificial muscles faster and faster.…”

Section: Discussionmentioning

confidence: 99%

Cooling‐Accelerated Nanowire‐Nitinol Hybrid Muscle for Versatile Prosthetic Hand and Biomimetic Retractable Claw

Tabassian

Thangasamy

et al. 2021

Adv Funct Materials

View full text Add to dashboard Cite

As strong and shape‐conformable as biological muscles, nitinol shape memory alloys (SMAs) artificial muscles have great merit when applied for bio‐inspired robots. However, the low bandwidth and slow actuation speed of SMAs due to their sluggish cooling have long been troublesome, limiting possible applications. Here, to expedite the cooling rate, a Cu nanowire forest is directly grown on the surfaces of 3D shaped SMA coil (SMAc) to increase the surface area by 15 times and boost thermal convection. As a result, the Cu nanowire forest grown SMA coil (CuNF‐SMAc) shows accelerated cooling compared to bare SMAc (B‐SMAc): the actuation speed of CuNF‐SMAc is 100% faster than that of bare SMAc (B‐SMAc) under natural cooling and 170% faster under forced‐air cooling. With this faster actuation, CuNF‐SMAc artificial muscles are employed in a versatile prosthetic hand to bend and flex fingers. The proposed prosthetic hand successfully demonstrates a series of sign language within 4 s for each letter, and rhythmically plays a grand piano. Moreover, unique retractable feline claws are mimicked which demonstrate a fully tunable frictional force just like how cats do it, expanding the potential of a cooling‐accelerated SMAc artificial muscle.

show abstract

Section: Discussionmentioning

confidence: 99%

Cooling‐Accelerated Nanowire‐Nitinol Hybrid Muscle for Versatile Prosthetic Hand and Biomimetic Retractable Claw

Tabassian

Thangasamy

et al. 2021

Adv Funct Materials

View full text Add to dashboard Cite

show abstract

“…This rapid solidification can form additional metastable phase [ 10 , 11 ], which would affect the actuating behaviours of the NiTi SMA foils. The actuating characteristics of the planar-flow-casted NiTi SMA foil was investigated in terms of phase transformation temperature, shape memory effects in terms of actuation force, response time, and degree of actuation [ 12 – 14 ].…”

Section: Introductionmentioning

confidence: 99%

Artificial intelligence automates the characterization of reversibly actuating planar-flow-casted NiTi shape memory alloy foil

Dutta

Chen²,

Renshaw³

et al. 2022

PLoS ONE

View full text Add to dashboard Cite

Nickel-Titanium (NiTi) shape memory alloys (SMAs) are smart materials able to recover their original shape under thermal stimulus. Near-net-shape NiTi SMA foils of 2 meters in length and width of 30 mm have been successfully produced by a planar flow casting facility at CSIRO, opening possibilities of wider applications of SMA foils. The study also focuses on establishing a fully automated experimental system for the characterisation of their reversible actuation, significantly improving SMA foils adaptation into real applications. Artificial Intelligence involving Computer Vision and Machine Learning based methods were successfully employed in the development of the automation SMA characterization process. The study finds that an Extreme Gradient Boosting (XGBoost) Regression model based predictive system experimented with over 175,000 video samples could achieve 99% overall prediction accuracy. Generalisation capability of the proposed system makes a significant contribution towards the efficient optimisation of the material design to produce high quality 30 mm SMA foils.

show abstract

“…This rapid solidi cation can form additional metastable phase [10,11], which would affect the actuating behaviours of the NiTi SMA foils. The actuating characteristics of the planar-ow-casted NiTi SMA foil was investigated in terms of phase transformation temperature, shape memory effects in terms of actuation force, response time, and degree of actuation [12][13][14].…”

Section: Introductionmentioning

confidence: 99%

XGBoost automates the characterisation of reversibly actuating planar-flow-casted NiTi shape memory alloy foil

Dutta¹,

Chen²,

Renshaw³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Nickel-Titanium (NiTi) shape memory alloys (SMAs) are smart materials able to recover their original shape under thermal stimulus. Near-net-shape NiTi SMA foils of 2 meters in length and width of 30 mm have been successfully produced by a planar flow casting facility at CSIRO, opening possibilities of wider applications of SMA foils. The study also focuses on establishing a fully automated experimental system for the characterisation of their reversible actuation, significantly improving SMA foils adaptation into real applications. Artificial Intelligence involving Computer Vision and Machine Learning based methods were successfully employed in the development of the automation SMA characterisation process. The study finds that an Extreme Gradient Boosting (XGBoost) Regression model based predictive system experimented with over 175,000 video samples could achieve 99% overall prediction accuracy. Generalisation capability of the proposed system makes a significant contribution towards the efficient optimisation of the material design to produce high quality 30 mm SMA foils.

show abstract

Vision based supervised restricted Boltzmann machine helps to actuate novel shape memory alloy accurately

Cited by 6 publications

References 40 publications

Cooling‐Accelerated Nanowire‐Nitinol Hybrid Muscle for Versatile Prosthetic Hand and Biomimetic Retractable Claw

Cooling‐Accelerated Nanowire‐Nitinol Hybrid Muscle for Versatile Prosthetic Hand and Biomimetic Retractable Claw

Artificial intelligence automates the characterization of reversibly actuating planar-flow-casted NiTi shape memory alloy foil

XGBoost automates the characterisation of reversibly actuating planar-flow-casted NiTi shape memory alloy foil

Contact Info

Product

Resources

About