Jing Wang

Fiber optic pressure sensors are widely used in precise or specialized sensing applications due to their high sensitivity and strong immunity to electromagnetic interference. Traditional optimization methods for fiber optic sensors primarily rely on theoretical derivation together with trial-and-error through simulations, which is hardly competent to achieve synergistic optimization across multiple performance metrics. To address this issue, this paper proposes a machine learning-based optimization design method for a balloon-like single-mode fiber and Sagnac interferometric composite pressure sensor. Support vector regression is employed to establish predictive models to infer sensitivity and transmission loss of the optical sensor according to its fiber bending diameter and substrate elastic modulus. These models are then integrated with the NSGA-II multi-objective optimization algorithm for Pareto optimality search. Optimization results indicate that with a bending diameter of 4.0 mm and a substrate made of rubber that gives an elastic modulus at 0.1 GPa, the sensor achieves a sensitivity of 93.4 nm/N and a transmission loss of 13.2 dB, outperforming those equivalents that with substrates made of common materials. Furthermore, cascading the optimized sensing unit with a Sagnac reference sensor enables high pressure sensing sensitivity at ‑518.2 nm/N. This study demonstrates the effectiveness of machine learning in multi-objective collaborative optimization for fiber optic pressure sensors.

Capacitive flexible pressure sensors are limited by the compressibility of dielectric materials, which creates an inherent trade-off between high sensitivity and a wide measurement range. This trade-off makes it challenging to accurately capture physiological signals that require a wide dynamic range. This study presents an iontronic pressure sensor featuring an array of hollow pyramid microstructures. An electric double layer (EDL) with high interface capacitance was created at the junction of the ionic gel and the electrode, providing an intrinsic mechanism for signal amplification in response to pressure loads. The hollow pyramid microstructure array of ionic gel gives the sensor unique compression characteristics, allowing for better interface contact and more effective structural deformation under pressure. This design endows the structure with outstanding compressibility, which in turn enhances the sensor's sensitivity and broadens its linear detection range. This sensor achieves a sensitivity of 227.56 kPa⁻¹ over a range of 0–400 kPa and maintains a sensitivity of 58.64 kPa⁻¹ across a wide measurement range of 400–2000 kPa. The device also demonstrates impressive dynamic performance metrics, including rapid response and recovery times as well as excellent repeatability. It has been successfully deployed for the accurate acquisition of various physiological and movement-related signals, including radial artery pulse, biceps brachii contraction, and finger grasping movements. These results confirm the sensor's ability to serve as a high-performance measurement device for wearable activity monitoring and robotic perception. Furthermore, the hollow pyramid microstructure offers a versatile design principle that can be applied to other sensing modalities to create devices with broader response ranges and improved sensitivity.