Understanding the Impact of Machine Learning Models on the Performance of Different Flexible Strain Sensor Modalities

Abstract

Fibre strain sensors commonly use three major modalities to transduce strain—piezoresistance, capacitance, and inductance. The electrical signal in response to strain differs between these sensing technologies, having varying sensitivity, maximum measurable loading rate, and susceptibility to deleterious effects like hysteresis and drift. The wide variety of sensor materials and strain tracking applications makes it difficult to choose the best sensor modality for a wearable device when considering signal quality, cost, and difficulty of manufacture. Fibre strain sensor samples employing the three sensing mechanisms are fabricated and subjected to strain using a tensile tester. Their mechanical and electrical properties are measured in response to strain profiles designed to exhibit particular shortcomings of sensor behaviour. Using these data, the sensors are compared to identify materials and sensing technologies well suited for different textile motion tracking applications. Several regression models are trained and validated on random strain pattern data, providing guidance for pairing each sensor with a model architecture that compensates for non-ideal effects. A thermoplastic elastomer-core piezoresistive sensor had the highest sensitivity (average gauge factor: 12.6) and a piezoresistive sensor of similar construction with a polyether urethane-urea core had the largest bandwidth, capable of resolving strain rates above 300% s−1 with 36% signal amplitude attenuation. However, both piezoresistve sensors suffered from larger hysteresis and drift than a coaxial polymer sensor using the capacitive strain sensing mechanism. Machine learning improved the piezoresistive sensors’ root-mean-squared error when tracking a random strain signal by up to 58% while maintaining their high sensitivity, bandwidth, and ease of interfacing electronically.