The complex wiring, bulky data collection devices, and difficulty in fast and on-site data interpretation significantly limit the practical application of flexible strain sensors as wearable devices. To tackle these challenges, this work develops an artificial intelligence-assisted, wireless, flexible, and wearable mechanoluminescent strain sensor system (AIFWMLS) by integration of deep learning neural network-based color data processing system (CDPS) with a sandwich-structured flexible mechanoluminescent sensor (SFLC) film. The SFLC film shows remarkable and robust mechanoluminescent performance with a simple structure for easy fabrication. The CDPS system can rapidly and accurately extract and interpret the color of the SFLC film to strain values with auto-correction of errors caused by the varying color temperature, which significantly improves the accuracy of the predicted strain. A smart glove mechanoluminescent sensor system demonstrates the great potential of the AIFWMLS system in human gesture recognition. Moreover, the versatile SFLC film can also serve as a encryption device. The integration of deep learning neural network-based artificial intelligence and SFLC film provides a promising strategy to break the "color to strain value" bottleneck that hinders the practical application of flexible colorimetricstrain sensors, which could promote the development of wearable and flexible strain sensors from laboratory research to consumer markets.
Read full abstract