Abstract: Control Chart Pattern Recognition (CCPR) is a critical task in Statistical Process Control (SPC). Abnormal patterns exhibited in control charts can be associated with certain assignable causes adversely affecting the process stability. In fact, numerous CCPR studies have been developed according to various objectives and hypotheses. Despite the research, efforts are keeping continue to increase the efficiency and recognition model simplicity. Application of different CCPR is obvious in an industrial production process where many process parameters have to monitor to meet the objectives. In this research, rather than having several numbers of CCP recognizer, a multi-process CCP recognition using a single recognition model has presented to save the solution cost. Recognition model has applied feedforward neural architecture along with gradient descent learning. In previous research over CCPR, effects of faults in recognition model have generally ignored which is very important from real-time application point of view. In this study, the effects of faults over the efficiency of CCP recognition are also presented and observed that the proposed model has very high levels of fault tolerance against different types of faults. Test simulation has applied over the huge number of control chart patterns and observed that the proposed method has delivered the superior recognition accuracy in a robust manner in comparison with other existing works in literature.