A fuzzy c-means algorithm based on the relationship among attributes of data and its application in tunnel boring machine

In recent years, a number of operation data from engineering systems have been measured and recorded, which promotes the development of engineering data mining. However, the operating state of the engineering system usually changes greatly, which results that the patterns of operation data vary considerably as well. Thus, partitioning these data can provide useful references to the design and analysis of engineering systems. In this paper, a new clustering algorithm based on support vector regression and fuzzy c-means algorithm (SVR–FCM) is proposed to accomplish this work. The SVR–FCM algorithm is based on the framework of fuzzy c-means algorithm (FCM), in which the differences between the clusters are evaluated by the relationship among attributes of data. In the proposed algorithm, support vector regression (SVR) is utilized to describe the relationship among attributes of, and an alteration optimization method is designed to optimize the new designed clustering objective function. A series of experiments on synthetic datasets and real-world datasets are conducted to evaluate the performance of the SVR–FCM algorithm, which shows the higher effectiveness and advances of the SVR–FCM algorithm compared with other popular clustering algorithms. The SVR–FCM algorithm is applied to a tunnel boring machine (TBM) operation dataset collected from a real TBM project in China. The experimental results show that the proposed algorithm performs well in TBM operation data clustering. This paper also highlights the applicability and potential of data clustering in the analysis of other complex engineering systems similar to TBMs.