International Journal of Man-Machine Studies - Special Issue: Knowledge Acquisition for Knowledge-based Systems. Part 5
Synthetic neural networks for process control
Computers and Industrial Engineering
Learning internal representations by error propagation
Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
Using autocorrelations, cusums and runs rules for control chart pattern recognition: an expert system approach
Design of a knowledge-based expert system for statistical process control
Computers and Industrial Engineering
Back-propagation pattern recognizers for X¯ control charts: methodology and performance
Computers and Industrial Engineering
A multi-layer neural network model for detecting changes in the process mean
Computers and Industrial Engineering
Out-of-control pattern recognition and analysis for quality control charts using LISP-based systems
Computers and Industrial Engineering
Simulation Modeling and Analysis
Simulation Modeling and Analysis
Improved use of continuous attributes in C4.5
Journal of Artificial Intelligence Research
Computers and Industrial Engineering
Engineering Applications of Artificial Intelligence
A mixed integer optimisation model for data classification
Computers and Industrial Engineering
Hi-index | 0.00 |
Unnatural control chart patterns (CCPs) are associated with a particular set of assignable causes for process variation. Therefore, effectively recognizing CCPs can substantially narrow down the set of possible causes to be examined, and accelerate the diagnostic search. In recent years, neural networks (NNs) have been successfully used to the CCP recognition task. The emphasis has been on the CCP detection rather than more detailed quantification of information of the CCP. Additionally, a common problem in existing NN-based CCP recognition methods is that of discriminating between various types of CCP that share similar features in a real-time recognition scheme. This work presents a hybrid learning-based model, which integrates NN and DT learning techniques, to detect and discriminate typical unnatural CCPs, while identifying the major parameter (such as the shift displacement or trend slope) and starting point of the CCP detected. The performance of the model was evaluated by simulation, and numerical and graphical results that demonstrate that the proposed model performs effectively and efficiently in on-line CCP recognition task are provided. Although this work considers the specific application of a real-time CCP recognition model for the individuals (X) chart, the proposed learning-based methodology can be applied to other control charts (such as the X-bar chart).