Study on dynamic model of magnetically controlled shape memory alloy sensor

Subtitle:

Article type: Research Article

Authors: Lu, Jun^* | Wu, Litian

Affiliations: School of Information Science and Engineering, Shenyang Ligong University, Shenyang, Liaoning, China

Correspondence: [*] Corresponding author: Jun Lu, School of Information Science and Engineering, Shenyang Ligong University, Shenyang 110159, Liaoning, China. E-mail:lujunst@126.com

Abstract: Magnetically controlled shape memory alloy (MSMA) is a new type of functional materials, which has inverse magnetic shape memory effect under the action of external force. MSMA sensor can be made by utilizing MSMA inverse effect. According to the characteristics of MSMA sensor, the dynamic model and predictive method of MSMA sensor are presented based on Back Propagation (BP) neural network. Based on the experimental data of MSMA sensor, the estimate accuracy and predictive ability of the dynamic model are simulated by using the neural network in MATLAB. The simulation results indicate that the proposed model has better training effect, higher consistency, and smaller prediction error by using BP neural network.

Keywords: MSMA sensor, BP neural network, dynamic model, simulation, prediction

DOI: 10.3233/JCM-150531

Journal: Journal of Computational Methods in Sciences and Engineering, vol. 15, no. 2, pp. 171-181, 2015