摘要
针对传统的最小二乘板形模式识别方法的抗干扰能力差、精度低和神经网络方法存在网络学习时间长、易陷入局部最小值等问题,把模糊理论和神经网络的优点融合在一起,通过三个自适应神经模糊推理系统的有效拟合,提出了一种基于自适应神经模糊推理系统的板形模式识别方法。研究结果表明,该方法能够很好地克服以上缺点,而且能够有效识别出常见的板形缺陷,识别速度和精度有所提高,识别结果跟板形仪的实测板形也非常接近。
As the antijamming ability of the traditional least squares flatness pattern recognition method is poor,its precision is low,the result of the neural network flatness pattern recognition method has a long time network studying,being easy to fall into the local minimum and many other problems like these.The research fuses the merits of the fuzzy theories and neural network,fitting effectively three adaptive neuro-fuzzy inference system,and proposes a kind of flatness pattern recognition method based on adaptive neuro-fuzzy inference system. The findings indicate that this method can overcome the above flaw very well, and can distinguish the common flatness flaw effectively, the recognition speed and the precision can be improved to some degree, and the recognition result is also very close to the actual value of flatness control meter.
出处
《钢铁研究学报》
CAS
CSCD
北大核心
2009年第9期59-62,共4页
Journal of Iron and Steel Research
基金
国家自然科学基金资助项目(50675186)
关键词
板形
模式识别
自适应神经模糊推理系统
flatness
pattern recognition
adaptive neuro-fuzzy inference system
