Research on Cantilever Beam Roller Tension Sensor Based on Surface Acoustic Wave

• Published in: Micromachines (Basel) Vol. 16; no. 9; p. 1044
• Main Authors: Feng, Yang, Zhang, Bingkun, Chen, Yang, Wang, Ben, Xia, Hua, Yu, Haoda, Yu, Xulehan, Yang, Pengfei
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 11.09.2025
• Subjects: Accuracy; Algorithms; Back propagation; Back propagation networks; cantilever beam; Cantilever beams; Finite element method; GA-PSO-BP; Measuring instruments; Network management systems; Neural networks; Optimization; Principles; Product quality; Propagation; Sensors; Silk; surface acoustic wave; Surface acoustic waves; Temperature; Temperature compensation; tension sensors; Yarn; tension sensors; temperature compensation; finite element method; GA-PSO-BP; cantilever beam; surface acoustic wave
• ISSN: 2072-666X; 2072-666X
• DOI: 10.3390/mi16091044

This paper presents a design method for a continuous tension detection sensor based on a cantilever beam structure and compensates for the temperature drift of a SAW sensor based on a neural network algorithm. Firstly, a novel cantilever beam roller structure is proposed to significantly enhance the sensitivity of the transmission of silk thread tension to a SAW tension sensor. Secondly, to improve the sensitivity of the SAW tension sensor, the COMSOL finite element method (FEM) is employed for simulation to determine the optimal IDT placement. An unbalanced split IDT design is utilized to suppress potential parasitic responses. Finally, the designed sensor is tested, and a GA-PSO-BP algorithm is employed to fit the test data for temperature compensation. The experimental results demonstrate that the temperature sensitivity coefficient of the data optimized by the GA-PSO-BP algorithm is reduced by an order of magnitude compared to the raw data, with reductions of 6.0409×10−3 °C−1 and 3.0312×10−3 °C−1 compared to the BP neural network and the PSO-BP algorithm, respectively. The average output error of the optimized data is reduced by 5.748% compared to the sensor measurement data, and it is also lower than both the BP neural network and the PSO-BP algorithm. It provides new design ideas for the development of tension sensors.