A Research about Pattern Recognition of Control Chart Using Improved Neural Networks and Wavelet Features

سال انتشار: 1391
نوع سند: مقاله کنفرانسی
زبان: انگلیسی
مشاهده: 1,681

فایل این مقاله در 6 صفحه با فرمت PDF قابل دریافت می باشد

این مقاله در بخشهای موضوعی زیر دسته بندی شده است:

استخراج به نرم افزارهای پژوهشی:

لینک ثابت به این مقاله:

شناسه ملی سند علمی:

ISCEE15_426

تاریخ نمایه سازی: 3 آذر 1391

چکیده مقاله:

Precise and fast control chart pattern (CCP) recognition is important for monitoring process environments to achieve appropriate control and to produce high qualityproducts. This paper presents a method for recognition of common types of CCP. The proposed method includes two mainmodules: a feature extraction module and a classifier module. Inthe feature extraction module, the multi-resolution wavelets (MRW) are proposed as the effective features for representationof CCPs. In the classifier module, multi layer perceptron neural networks (MLPNNs) are applied. In MLPNNs training,improved back-propagation algorithm is used to help the network avoid the local minima problem due to neuron saturation in the hidden layer. Simulation results show that the proposed system has high recognition accuracy