An Efficient Technique for Control Chart Pattern Recognition Using RBF-OLS Method
Publish place: 15th Iranian Student Conference on Electrical Engineering
Publish Year: 1391
نوع سند: مقاله کنفرانسی
زبان: English
View: 1,591
This Paper With 6 Page And PDF Format Ready To Download
- Certificate
- من نویسنده این مقاله هستم
استخراج به نرم افزارهای پژوهشی:
شناسه ملی سند علمی:
ISCEE15_427
تاریخ نمایه سازی: 3 آذر 1391
Abstract:
Control chart pattern(CCP) are important statistical process control tools for determining whether a process is running in its intended mode or in the presence ofunnatural pattern. Accurate recognition of control chart pattern is essential for efficient system monitoring to maintain high-quality products. This paper, present an intelligentrecognition system using radial basis function neural networks (RBFNN) model for classification of CCP signals withorthogonal least square method to training the network. This recognition system consist of two main modules: feature extraction module and classifier module. In the featureextraction module, shape features are applied as the effective features for representation of the CCPs and in classifiermodule ,RBFNN is applied . With using of the orthogonal least square method, chooses radial basis function centers one by one in a rational way until an sufficient network has been constructed. The algorithm has the property that each selected center maximizes the increment to the explained variance orenergy of the desired output and does not suffer numerical illconditioning problems . The aim of the improving classifier'sperformance is to represent the best classification system with high accuracy rate for CCP signals. Simulation results confirmthat the proposed system outperforms other system and show high recognition accuracy about 99.15%.
Keywords:
Authors
مراجع و منابع این Paper:
لیست زیر مراجع و منابع استفاده شده در این Paper را نمایش می دهد. این مراجع به صورت کاملا ماشینی و بر اساس هوش مصنوعی استخراج شده اند و لذا ممکن است دارای اشکالاتی باشند که به مرور زمان دقت استخراج این محتوا افزایش می یابد. مراجعی که مقالات مربوط به آنها در سیویلیکا نمایه شده و پیدا شده اند، به خود Paper لینک شده اند :