Pattern matching in historical data

Abstract

AbstractFor many engineering and business problems, it would be very useful to have a general strategy for pattern matching in large databases. For example, the analysis of an abnormal plant condition would benefit if previous occurrences of the abnormal condition could be located in the historical data. A new pattern‐matching strategy is proposed for multivariate time series based on statistical techniques, especially principal‐component analysis (PCA). The new approach is both data‐driven and unsupervised because neither training data nor a process model is required. Given an arbitrary set of multivariate data, the new approach can be used to locate similar patterns in a large historical database. The proposed pattern‐matching strategy is based on two similarity factors: the standard PCA similarity factor and a new similarity factor that characterizes the pattern of alarm violations. An extensive simulation study for a chemical reactor demonstrates that this strategy is more effective than existing PCA methods and can successfully distinguish between 28 different operating conditions.