TUTCRIS - Tampereen teknillinen yliopisto


Real-time online drilling vibration analysis using data mining



OtsikkoProceedings of the 2019 2nd International Conference on Data Science and Information Technology, DSIT 2019
ISBN (elektroninen)9781450371414
DOI - pysyväislinkit
TilaJulkaistu - 19 heinäkuuta 2019
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisussa
TapahtumaInternational Conference on Data Science and Information Technology - Seoul, Etelä-Korea
Kesto: 19 heinäkuuta 201921 heinäkuuta 2019


ConferenceInternational Conference on Data Science and Information Technology


While the data mining intermediaries play a critical role in the rock drilling industry, they also tend to provide an optimized real-time model for the drilling systems. In addition, proper online tool condition monitoring (OTOM) methods can improve the drilling performance by accessing real-time data. Hence, OTOM methods assist depreciating error and detect unspecified faults at early stages. In this study, we proposed appropriate OTOM algorithms to develop and enhance the quality of real-time systems and provide a solution to detect and categorize various stages of drilling operation with the aid of vibration signals (especially in terms of acceleration or velocity). In particular, the proposed methods in this article perform based on statistical approaches. Therefore, in order to recognize the drilling stages, we measured the Root Mean Square (RMS) values corresponding to the acceleration signals. In the meantime, we also succeeded to distinguish the drilling stages by employing estimated power spectral density (PSD) in the frequency domain. The acquired results in this publication confirm the real-time prediction and classification potential of the proposed methods for the different drilling stages and especially for the rock drilling engineering.