Retraction

Retraction: Pnömatik Yapay Kaslar için Yapay Sinir Ağı Esaslı Ters Modelleme

Year 2022, Issue: 36, 323 - 323, 31.05.2022
This is a retraction to: Neural Network Based Inverse Modelling for Pneumatic Artificial Muscles https://dergipark.org.tr/en/pub/ejosat/issue/56356/779538

Retraction Note

Yayının farklı bir sayıda yayınlanma tercihinden kaynaklı olarak geri çekilmiştir.

Abstract

Pnömatik Yapay Kaslar (PAM), yüksek kuvvet / ağırlık oranı, esnek yapı ve düşük maliyet gibi avantajlara sahip yumuşak aktüatörlerdir. Pnömatik Yapay Kaslar, dış iskelet ve rehabilitasyon robotlarında kullanımını mümkün kılan doğal bir uyumluluğa sahiptir. Bununla birlikte, doğrusal olmayan karakteristik özellikleri, modelleme ve kontrol eylemlerinde zorluklar sağlayan ve kullanımını kısıtlayan önemli bir faktördür. PAM doğal uyumluluğu, doğrusal olmayan, histerezis ve zamanla değişen özellikleri ile ilişkilidir, bu durum da PAM dinamik davranışını ve modele dayalı yüksek performanslı kontrolörlerle çalışmasını modellenmesini zorlaştırır. Literatürde modelleme sorununun üstesinden gelmek için, sanal iş, ampirik ve fenomenolojik modeller gibi birçok çalışma olmasına rağmen, bu çalışmalar çok karmaşık veya doğrusal olmayan değişken bir sertlikli yay için giriş-çıkış ilişkisi olan model gibi çok yaklaşıktır. PAM test düzeneğimizde gerçekleştirdiğimiz iyi bilinen önceki modelleme çalışmalarının deneysel analizine dayanarak, bu yöntemlerin etkinliğinin PAM'ın fiziksel davranışını temsil etmek için sınırlı olduğu ve hala basit, etkili modellere ihtiyaç duyulduğu gözlemlenmiştir. Bu çalışmada, önceki modelleme yaklaşımlarından farklı olarak, PAM'ın davranışı, giriş işareti olarak basınç uygulandığında, eşzamanlı kuvvet ve kas uzunluğu değişikliğine yol açan entegre bir sistem tepkisi olarak öngörülmüştür. Bu nedenle, standart doğrudan giriş-çıkış tanımlama yöntemleri bu davranışı modellemek için uygun değildir. Bu çalışmada, kontrol uygulamalarında etkin kullanmak için bir tersine modelleme yaklaşımı önerilmektedir. Önerilen kapalı kutu model ve PAM test yatağından toplanan deneysel veriler kullanılarak Yapay Sinir Ağı (YSA) yapısı tarafından uygulanmaktadır. Uygulama sonuçlarına göre, YSA tabanlı bir tersine model, PAM modelleme ve kontrol sorunu için basit ve etkili bir çözüm olabileceğini düşündüren tatmin edici bir performans sağlamıştır.

References

  • Ahn K.K., Anh H.P.H. (2008). Comparative study of modeling and identification of the pneumatic artificial muscle (PAM) manipulator using recurrent neural networks, Journal of Mechanical Science and Technology 22 ,1287-1298.
  • Chavoshian M., Taghizadeh, M. (2020) Recurrent neuro-fuzzy model of pneumatic artificial muscle position. J Mech. Sci. Technology 34, 499–508.
  • Chou C.P. , Hannaford B. (1996). Measurement and modeling of McKibben pneumatic artificial muscles, IEEE Trans. Robot. Automation, 12(1), 90–102.
  • Daerden F., Lefeber D. (2002). Pneumatic artificial muscles: actuators for robotics and automation, European Journal of Mechanical and Environmental Engineering, 47, 10-21.
  • E. Kelasidi, G. Andrikopoulos, G. Nikolakopoulos and S. Manesis (2011). A survey on pneumatic muscle actuators modeling, in Proc. IEEE ISIE-2011, 1263-1269.
  • Festo (2018) Fluidic Muscle DMSP/MAS Info 501, https://www.festo.com/rep/en_corp/assets/pdf/info_501_en.pdf
  • Ishikawa T., Nishiyama Y., Kogiso K. (2018). Characteristic Extraction for Model Parameters of McKibben Pneumatic Artificial Muscles, SICE Journal of Control, Measurement, and System Integration, 11(4), 357-364.
  • Martens M., Boblan I. (2017). Modeling the Static Force of a Festo Pneumatic Muscle Actuator: A New Approach and a Comparison to Existing Models. Actuators 2017, 6, 33.
  • Reynolds D.B., ReppergerD.W., Phillips C.A., Bandry G. (2003). Modeling the dynamic characteristics of pneumatic muscle, Ann. Biomed. Eng., 31(3), 310–317.
  • Song C., Xie S, Zhou Z., Hu Y. (2015), Modeling of pneumatic artificial muscle using a hybrid artificial neural network approach, Mechatronics, 31, 124-131.
  • Tondu, B. (2012). Modelling of the McKibben artificial muscle: A review. Journal of Intelligent Material Systems and Structures, 23(3), 225–253.
  • Wickramatunge K.C, Leephakpreeda T. (2013). Empirical modeling of dynamic behaviors of pneumatic artificial muscle actuators, ISA Transactions, 52(6).
  • Xing K., Huang J., Wang Y., Wu J, Xu Q, He J. (2010). Tracking control of pneumatic artificial muscle actuators based on sliding mode and non-linear disturbance observer, IET Control Theory & Applications,4(10) 2058-2070.
  • Zhang D., X. Zhao, and J. Han (2016). Active modeling for pneumatic artificial muscle, in Proc. IEEE 14th Int. Workshop Adv. Motion Control, 44–50.

Retraction: Neural Network Based Inverse Modelling for Pneumatic Artificial Muscles

Year 2022, Issue: 36, 323 - 323, 31.05.2022
This is a retraction to: Neural Network Based Inverse Modelling for Pneumatic Artificial Muscles https://dergipark.org.tr/en/pub/ejosat/issue/56356/779538

Retraction Note

Abstract

Pneumatic Artificial Muscles (PAM) are soft actuators with advantages such as high force to weight ratio, flexible structure and low cost. Pneumatic Artificial Muscles have inherent compliance that makes them feasible for exoskeletons and rehabilitation robots. However, their inherent nonlinear characteristics yield difficulties in modelling and control actions, which is an important factor restricting use of PAM. The compliance of PAM is associated with nonlinearity, hysteresis, and time varying characteristics, which makes it more difficult to model the dynamics and operation with model based high-performance controllers. Although there are many studies to overcome the modelling issue such as virtual work , empirical and phenomenological models, they are either much complicated or very approximate ones as a variable stiffness spring for model with nonlinear input-output relationship. Based on the analysis of well known previous modeling works in our PAM test bed, it has been observed that efficacy of the those methods are limited for representing the physical behaviour of PAM and thus there is still requirement for simple and effective models . In this work, apart from previous modeling approaches, the behaviour of PAM is foreseen as an integrated response to pressure input, which results in simultaneous force and muscle length change. Therefore, standard direct input-output identification methods are not suitable for modelling that behaviour. An inverse modeling approach is proposed in order to utilize it in control applications. The black box model is implemented by an Artificial Neural Network (ANN) structure using the experimental data collected from the PAM test bed. According to implementation results, an ANN based inverse model has yielded satisfactory performance deducing that it could be a simple and effective solution for PAM modelling and control .

References

  • Ahn K.K., Anh H.P.H. (2008). Comparative study of modeling and identification of the pneumatic artificial muscle (PAM) manipulator using recurrent neural networks, Journal of Mechanical Science and Technology 22 ,1287-1298.
  • Chavoshian M., Taghizadeh, M. (2020) Recurrent neuro-fuzzy model of pneumatic artificial muscle position. J Mech. Sci. Technology 34, 499–508.
  • Chou C.P. , Hannaford B. (1996). Measurement and modeling of McKibben pneumatic artificial muscles, IEEE Trans. Robot. Automation, 12(1), 90–102.
  • Daerden F., Lefeber D. (2002). Pneumatic artificial muscles: actuators for robotics and automation, European Journal of Mechanical and Environmental Engineering, 47, 10-21.
  • E. Kelasidi, G. Andrikopoulos, G. Nikolakopoulos and S. Manesis (2011). A survey on pneumatic muscle actuators modeling, in Proc. IEEE ISIE-2011, 1263-1269.
  • Festo (2018) Fluidic Muscle DMSP/MAS Info 501, https://www.festo.com/rep/en_corp/assets/pdf/info_501_en.pdf
  • Ishikawa T., Nishiyama Y., Kogiso K. (2018). Characteristic Extraction for Model Parameters of McKibben Pneumatic Artificial Muscles, SICE Journal of Control, Measurement, and System Integration, 11(4), 357-364.
  • Martens M., Boblan I. (2017). Modeling the Static Force of a Festo Pneumatic Muscle Actuator: A New Approach and a Comparison to Existing Models. Actuators 2017, 6, 33.
  • Reynolds D.B., ReppergerD.W., Phillips C.A., Bandry G. (2003). Modeling the dynamic characteristics of pneumatic muscle, Ann. Biomed. Eng., 31(3), 310–317.
  • Song C., Xie S, Zhou Z., Hu Y. (2015), Modeling of pneumatic artificial muscle using a hybrid artificial neural network approach, Mechatronics, 31, 124-131.
  • Tondu, B. (2012). Modelling of the McKibben artificial muscle: A review. Journal of Intelligent Material Systems and Structures, 23(3), 225–253.
  • Wickramatunge K.C, Leephakpreeda T. (2013). Empirical modeling of dynamic behaviors of pneumatic artificial muscle actuators, ISA Transactions, 52(6).
  • Xing K., Huang J., Wang Y., Wu J, Xu Q, He J. (2010). Tracking control of pneumatic artificial muscle actuators based on sliding mode and non-linear disturbance observer, IET Control Theory & Applications,4(10) 2058-2070.
  • Zhang D., X. Zhao, and J. Han (2016). Active modeling for pneumatic artificial muscle, in Proc. IEEE 14th Int. Workshop Adv. Motion Control, 44–50.
There are 14 citations in total.

Details

Primary Language English
Subjects Engineering
Journal Section Articles
Authors

Cabbar Veysel Baysal 0000-0003-1490-8725

Early Pub Date April 11, 2022
Publication Date May 31, 2022
Published in Issue Year 2022 Issue: 36