Recognition of control chart concurrent patterns using a neural network approach

Pattern recognition is an important issue in Statistical Process Control, as unnatural patterns exhibited by control charts can be associated with specific assignable causes adversely affecting the process. Neural network approaches to recognition of control chart patterns have been developed by several researchers in recent years, but to date these have been focused on recognition and analysis of single patterns such as sudden shifts, linear trends of cyclic patterns. This paper investigates the detection of concurrent patterns where more than one pattern exists simultaneously. The topology and training of a Pack-Propagation Network (BPN) system is described. Extensive performance evaluation has been carried out using simulated data to develop a range of average run length-related performance indices, including new performance indices that are proposed to describe concurrent patterns recognition performance. Two evaluation scenarios were evaluated: in the first, unnatural patterns are already present; while in the second, patterns may appear progressively at any time. Numerical results are provided that indicate that the pattern recognizer can perform very well in the first scenario, while it performs effectively but not without deficiencies for some specific pattern combinations in the second evaluation approach. Limitations and potential improvements in the concurrent pattern recognition scheme are also discussed.