卤化物
材料科学
复合数
限制
热的
降级(电信)
工作(物理)
复合材料
卷积神经网络
结构健康监测
结构完整性
混合材料
光电子学
红外线的
结构工程
温度循环
纳米技术
作者
Huilin Chen,Chenliang Li,Yuzhen Wang,Zhiguo Xia
摘要
ABSTRACT Fracto‐mechanoluminescence (FML) materials have recently demonstrated great potential as next‐generation interactive optoelectronic systems, while they generally suffer from irreversible fatigue degradation under long‐term cyclic stress, severely limiting their practical applications. Here we design the flexible FML composite films based on the manganese‐based hybrid halide EPB 2 MnBr 4 (EPB = ethyltriphenylphosphonium), exhibiting intense green emission under mechanical stimuli. Notably, the FML intensity that degrades after repeated mechanical cycles can be effectively recovered to approximately 75.5% of its original value through thermal treatment, which can be attributed to Ostwald ripening within the used resin matrix. Furthermore, a one‐dimensional convolutional neural network has been developed to classify mechanical events based on FML signals for structural health monitoring in mining, achieving 98.75% accuracy across four mechanical events and demonstrating the pattern‐recognition capability of machine learning. This work establishes a Mn‐based hybrid halide FML device with thermal recovery capability, providing new strategies for designing fatigue‐resistant sensing materials and demonstrating potential for structural health monitoring.
科研通智能强力驱动
Strongly Powered by AbleSci AI