基于 CBAM-CNN 和压电悬臂梁的温度解耦质量感知方法

悬臂梁结构广泛用于微小质量测量,而温度变化会引起测量结果漂移。 传统测量方法需要在温度稳定的环境中进行,但实际应用中通常难以满足此要求,且温度漂移对测量的影响难以直接解耦。 本文提出了一种基于数据驱动,CBAM-CNN 和压电悬臂梁的自适应温度解耦质量感知方法。 首先,搭建谐振式压电悬臂梁温控测量平台采集不同质量负载下的阻抗响应信号,设计自适应加权预处理方法以增强结构特征并突出有限样本中的关键信息;其次,设计基于混合领域注意力机制的 CBAM-CNN 网络来评估信号中多个谐振峰的相对关系,实现温度解耦和质量感知。 实验结果表明,该方法在 25℃ 至55℃ 的温度范围内的对 0. 1 ~ 1 g 的质量感知准确率高达 99. 70% ,无需进行温度补偿即可实现大跨度温度下的精确质量感知。

Temperature decoupled mass sensing based on CBAM-CNN and piezoelectric cantilever beam

The cantilever beam structure serves as a prevalent platform for micro-mass measurements. Conventional measurementmethodologies necessitate a stable temperature environment, posing practical challenges. Temperature fluctuations profoundly impactmeasurement outcomes and pose difficulties in direct decoupling from the cantilever beam′s characteristic equation. This paper introducesa temperature decoupled mass sensing method, leveraging CBAM-CNN and a piezoelectric cantilever beam. Initially, a temperature-controlled measurement platform employing a resonant piezoelectric cantilever beam is established to capture impedance response signalsacross varied mass loads. An adaptive weighted preprocessing method is tailored to augment structural features and accentuate criticalinformation within confined samples. Subsequently, a CBAM-CNN network, incorporating a hybrid domain attention mechanism, isdevised to evaluate the relative relationships of multiple resonance peaks in the signals, achieving concurrent temperature decoupled masssensing. Experimental findings underscore the method′s prowess, attaining an impressive 99. 70% accuracy in mass measurementsranging from 0. 1 g to 1 g within a temperature range spanning 25℃ to 55℃ . Moreover, the method exhibits precise mass sensing acrossa broad temperature spectrum, obviating the need for temperature compensation.