摘要
精密注塑机模具温度控制的效果直接影响注塑制品的质量,为提高模具温度控制的实时性、精确性,采用改进的CMAC控制算法,以89C51单片机为控制器,利用高温导热油的循环实现模具温度的控制。改进的CMAC神经网络利用激活单元先前学习次数作为可信度,其误差校正值与激活单元先前学习次数的负k次方成比例,当k为一适当数值时,改进CMAC具有较快的学习速度和较高的精度。通过对PP(聚丙烯)塑料件注射模温度的实际控制表明,模具温度控制精度优于±0.1℃。
In the view of the features of precision injection molding,the mould temperature directly affects the quality of products.The control system utilizes a single-chip micro-computer system and improved CMAC neural network model based on balanced learning concept as temperature controller,by using the circulation of heating medium oil with high temperature to adjust the mould temperature in the injection molding.The proposed improved learning approach uses the learned times of the addressed hypercubes as the credibility(confidence) of the learned values.The correcting amounts of errors are proportional to the inverse of the k-th power of learned times.The method provides high learning speed and accuracy when k is an optimal value in the early learning stage especially.The actual performance of PP plastic injection molding showed that the control precision excels the value of.
出处
《西华大学学报（自然科学版）》
CAS
2006年第5期13-15,共3页
Journal of Xihua University:Natural Science Edition
关键词
注射模
单片机
CMAC
温度控制
injection molding machine
single-chip microcomputer
CMAC
temperature control
