The application of statistical methods to monitor a process is critical to ensure its stability. Statistical process control aims to detect and identify abnormal patterns that disrupt the natural behaviour of a process. Most studies in the literature are focused on recognising single abnormal patterns. However, in many industrial processes, more than one unusual control chart pattern may appear simultaneously, i.e., concurrent control chart patterns (CCP). Therefore, this paper aims to present a classification framework based on categories to systematically organise and analyse the existing literature regarding concurrent CCP recognition to provide a concise summary of the developments performed so far and a helpful guide for future research. The search only included journal articles and proceedings in the area. The literature search was conducted using Web of Science and Scopus databases. As a result, 41 studies were considered for the proposed classification scheme. It consists of categories designed to assure an in-depth analysis of the most relevant topics in this research area. Results concluded a lack of research in this research field. The main findings include the use of machine learning methods; the study of non-normally distributed processes; and the consideration of abnormal patterns different from the shift, trend, and cycle behaviours.
Current global conditions and challenges in industrial manufacturing, marked by dynamism, competition, and the need for responsible resource management, have increased the demand for sustainable manufacturing practices. The integration of Industry 4.0 and the recent development of Industry 5.0 have added dynamism, which has generated profound implications for quality control and process monitoring, focusing mainly on recognising control patterns within the manufacturing environment. This study introduces a novel methodology for evaluating the performance of pattern classification models used in advanced quality control. Our approach incorporates robust performance metrics, early detection, window size, network hyperparameters, and concurrent patterns within a simulated monitoring environment. Unlike previous research, our evaluation methodology addresses the sensitivity of classification models to various factors, emphasising the critical balance between early detection and minimising false alarms. The findings reveal that window size significantly impacts the model’s sensitivity to pattern changes, highlighting that measuring early detection alone is impractical in real-world applications. Furthermore, optimal hyperparameter selection enhances the model’s practical applicability.