designing a model - based neural networks for recognition and analysis of unnatural patterns in process control charts

neural networks because of their abilities are used to patterns recognition. in statistical process control charts, a common cause variation distort expected form of unnatural patterns and so detection of assignable causes efficiently and precisely in a real-time is difficult. therefore it would be logical to propose models based neural networks for recognition and analysis of patterns in process control charts. nearly most of investigations of the application of neural networks to control chart patterns recognition solely have emphasized the detection of patterns and have not considered analysis and extraction detailed information which is important for effectively determining the assignable causes. moreover, some of the patterns generator functions do not represent completely the real world situation. this paper proposes a model for discrimination and analysis of basic and concurrent patterns. this model first recognizes unnatural patterns. then it estimates their starting point and finally determines the values of corresponding parameters. in design of proposed model, the development of areas of application has been emphasized. numerical results indicate that the components of proposed model have suitable and effective performance