Efficient mixture control chart pattern recognition using adaptive RBF neural network
- PDF / 522,841 Bytes
- 10 Pages / 595.276 x 790.866 pts Page_size
- 65 Downloads / 246 Views
ORIGINAL RESEARCH
Efficient mixture control chart pattern recognition using adaptive RBF neural network Sapna Kadakadiyavar1 • Nagaraj Ramrao2 • Manoj Kumar Singh3
Received: 12 November 2018 / Accepted: 1 November 2019 Bharati Vidyapeeth’s Institute of Computer Applications and Management 2019
Abstract In this paper, a stochastic gradient method based adaptive version of the radial basis function neural network has proposed to map the pattern features of the control chart patterns in different categories to recognize their belonging class. Adaptiveness has given over the spreadness and centers of Gaussian basis function appeared in the hidden nodes of the radial basis function neural network. Along with normal abnormalities in patterns, the mixture of different abnormal patterns has also considered capturing the worst possible conditions of abnormalities in real time. The advantages of the proposed method have appeared as very high recognition accuracy, minimum error in learning and generalize performance with small training dataset in control chart pattern recognition. Achieved performance has compared with the state of art results available in the literature which has applied feature based recognition using Support vector machine and Genetic algorithm. The proposed method has enhanced the recognition generalization of control chart patterns with simplicity in design and high level of decision confidence. The performances have achieved through the simulation-based experiments over a huge number of patterns containing ten different types of pattern and on average, 99.99% accuracy has achieved.
& Manoj Kumar Singh [email protected] 1
Jain University, Bangalore, India
2
Kalasalingam Academy of Research and Education, Srivilliputhur, Tamil Nadu, India
3
Manuro Tech Research Pvt. Ltd, #20, 2nd Cross Jyothi Nagar, Near Sambhram Engineering College, Vidyaranyapura, Bangalore 560097, India
Keywords Control chart pattern Pattern recognition Artificial neural network Radial basis function network Support vector machine Genetic algorithm
1 Introduction Control chart pattern (CCP) provides the condition of the process of consideration hence it has been used as a diagnostic tool in maintaining the quality of the process. Generally, a process is considered as out-of-control under two different appearances either sampled data of interest appears beyond the defined control limit or there is unnatural behavior appear in the pattern. It’s easy to detect the defect in the former case while it’s difficult to recognize the latter case condition because of inherent random noise. There are different possibilities of control chart patterns exist, among them there are six basics patterns exist [1] e.g. normal (NOR), cyclic (CYC), increasing trend (UT), decreasing trend (DT), upward shift (US) and downward shift (DS), as shown in Fig. 1 while other possibilities are derived from these six patterns as shown in Fig. 2. Except for the normal pattern, all other patterns are the indication of some kind of problem
Data Loading...
