A novel methodology is proposed for matching patterns in time-series databases based on unsupervised learning and multivariate statistical techniques. The new approach provides a preliminary screening of large amounts of historical data in order to generate a candidate pool of similar periods of operation. This much smaller number of records can then be further evaluated by someone familiar with the process. A new distance similarity factor is proposed that complements the standard principal component analysis similarity factor. The two similarity factors and a moving-window approach are used to characterize the degree of similarity between the current period of interest and windows of historical data. A simulation case study has demonstrated that the proposed pattern matching technique can successfully distinguish between 28 operating conditions for a variety of disturbances, faults, and process changes.