Liu Mian, Wang Zhiwu, Jiang Pingping, Yan Guozheng
School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China.
School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China.
Sensors (Basel). 2024 Aug 21;24(16):5394. doi: 10.3390/s24165394.
Piezoresistive pressure sensors have broad applications but often face accuracy challenges due to temperature-induced drift. Traditional compensation methods based on discrete data, such as polynomial interpolation, support vector machine (SVM), and artificial neural network (ANN), overlook the thermal hysteresis, resulting in lower accuracy. Considering the sequence-dependent nature of temperature drift, we propose the RF-IWOA-GRU temperature compensation model. Random forest (RF) is used to interpolate missing values in continuous data. A combination of gated recurrent unit (GRU) networks and an improved whale optimization algorithm (IWOA) is employed for temperature compensation. This model leverages the memory capability of GRU and the optimization efficiency of the IWOA to enhance the accuracy and stability of the pressure sensors. To validate the compensation method, experiments were designed under continuous variations in temperature and actual pressure. The experimental results show that the compensation capability of the proposed RF-IWOA-GRU model significantly outperforms that of traditional methods. After compensation, the standard deviation of pressure decreased from 10.18 kPa to 1.14 kPa, and the mean absolute error and root mean squared error were reduced by 75.10% and 76.15%, respectively.
压阻式压力传感器有着广泛的应用，但由于温度引起的漂移，常常面临精度挑战。基于离散数据的传统补偿方法，如多项式插值、支持向量机（SVM）和人工神经网络（ANN），忽略了热滞现象，导致精度较低。考虑到温度漂移的序列依赖性，我们提出了RF-IWOA-GRU温度补偿模型。随机森林（RF）用于对连续数据中的缺失值进行插值。采用门控循环单元（GRU）网络和改进的鲸鱼优化算法（IWOA）相结合的方式进行温度补偿。该模型利用GRU的记忆能力和IWOA的优化效率来提高压力传感器的精度和稳定性。为了验证补偿方法，在温度和实际压力连续变化的情况下设计了实验。实验结果表明，所提出的RF-IWOA-GRU模型的补偿能力明显优于传统方法。补偿后，压力的标准差从10.18 kPa降至1.14 kPa，平均绝对误差和均方根误差分别降低了75.10%和76.15%。
