摘要
针对压力传感器在应用中存在温度漂移这一缺点,提出了一种基于蚁群聚类算法的RBF(Radial Basis Function)神经网络温度补偿方法。利用蚁群算法的并行寻优特征和一种自适应调整挥发系数的方法作为聚类算法来确定RBF神经网络的基函数的位置,并通过裁减的方法约简隐层的神经元达到简化网络结构的目的。通过仿真可以看出,该算法具有误差小,精度高等优点,对压力传感器的温度漂移有较好的补偿效果。
Aiming at the drawback of temperature drift of the pressure sensor, a temperature compensation method of RBF Neural Networks based on ant colony clustering is proposed. Based on the feature of parallel search optimum of the ant colony algorithm and a dynamic method to adjust the parameter of evaporation coefficient,the center of each basis function of RBF can be defined by using a new proposed clustering algorithm;in order to simplify the structure of RBF network, we use a pruning method to remove those hidden units. The simulation results showed that the method has the features of small error,high precision and a good compensation effect for the pressure sensor＇s tem- perature drift.
出处
《传感技术学报》
CAS
CSCD
北大核心
2013年第6期806-809,共4页
Chinese Journal of Sensors and Actuators
基金
国家自然科学基金项目(61204127)
黑龙江省教育厅2013科学技术研究项目(12531762)
齐齐哈尔大学青年教师科研启动支持计划项目(2012k-M10)
