Tytuł artykułu
Autorzy
Wybrane pełne teksty z tego czasopisma
Identyfikatory
Warianty tytułu
Advanced methods of signal processing in the diagnosis of tool state
Języki publikacji
Abstrakty
Niniejszy artykuł przedstawia wyniki oceny przydatności poszczególnych metod analizy oraz miar sygnałów do diagnostyki stanu narzędzia. Do badań wytypowano szereg miar (różne miary statystyczne, miary przekroczeń progu etc.) oraz metod analizy sygnałów (FFT, PSD, transformata falkowa), których przydatność do diagnostyki stanu narzędzia przy określonym algorytmie szacowania zużycia ostrza przetestowano na wielu różnych eksperymentach (różne odmiany toczenia, frezowanie, wiercenie). Analiza przydatności danej miary polegała na określeniu błędu RMSE szacowanego zużycia ostrza w stosunku do rzeczywistego zużycia, uzyskanego w wyniku uczenia układu nadzoru na danej mierze. Ponadto wykonano analizę korelacji wzajemnej poszczególnych miar i na tej podstawie wytypowano miary, które statystycznie często są skorelowane wzajemnie ze sobą. W ramach badań przeprowadzono również analizę przydatności różnych czujników do diagnostyki stanu ostrza. W wyniku tej analizy stwierdzono, że najbardziej przydatne do stosowanej diagnostyki stanu ostrza są czujniki siły i emisji akustycznej.
This paper presents studies results of usefulness of different signal processing methods and signal features to the tool state diagnosis. There were various different features chosen (various statistical measures, measures of threshold crossings etc.) and the signal processing methods (FFT, PSD, wavelet transform). Their usefulness in the diagnosis of the tool state where a predetermined algorithm for estimating tool wear has been tested on a variety of experiments (different types of turning, milling, drilling). Analysis of the usefulness of the signal feature consisted of determine the error RMSE of the estimated tool wear in relation to actual wear, obtained as a result of learning the diagnostic system for a given signal feature. Furthermore, the cross-correlation analysis was performed, and particular signal features were chosen, which often are statistically correlated with each other. This paper also presents the usability of various sensors to tool state diagnosis. It was found that the most useful for tool state diagnosis are sensors of the forces and acoustic emission.
Czasopismo
Rocznik
Tom
Strony
89--101
Opis fizyczny
Bibliogr. 26 poz., rys., wykr.
Twórcy
autor
- Politechnika Warszawska, Instytut Technik Wytwarzania, Warszawa
autor
- Politechnika Warszawska, Instytut Technik Wytwarzania, Warszawa
autor
- Politechnika Warszawska, Instytut Technik Wytwarzania, Warszawa
Bibliografia
- [1] BOMBIŃSKI S., 2006, Automatyczna ocena zużycia ostrza oparta na wielu miarach sygnałów diagnostycznych, Rozprawa doktorska, OWPW.
- [2] JEMIELNIAK K., KWIATKOWSKI L., WRZOSEK P., 1998, Diagnosis of Tool Wear Based on Cutting Forces and Acoustic Emission Measurements as Inputs to a Neural Network, Journal of Intelligent Manufacturing 9.
- [3] PANDA S.S., SINGH A.K., CHAKRABORTY D., PAL S.K., 2006, Drill wear monitoring using back propagation neural network, Journal of Materials Processing Technology, 172, 283–290.
- [4] CHOUDHURY S.K., JAIN V.K., RAMA RAO CH.V.V., 1999, On-line monitoring of tool wear in turning using a neural network, International Journal of Machine Tools & Manufacture, 39, 489–504.
- [5] PATRA K., PAL S.K., BHATTACHARYYA K., 2007, Artificial neural network based prediction of drill flank wear from motor current signals, Applied Soft Computing, 7, 929–935.
- [6] DIMLA Sr. D.E., LISTER P.M., 2000, On-line metal cutting tool condition monitoring. I: force and vibration analyses, International Journal of Machine Tools & Manufacture , 40, 739–768.
- [7] SILVA R.G., BAKER K.J., WILCOX S.J., 2000, The adaptability of a tool wear monitoring system under changing cutting conditions, Mechanical Systems and Signal Processing, 14/2, 287–298.
- [8] ABU-ZAHRA N.H., YU G., 2003, Gradual wear monitoring of turning inserts using wavelet analysis of ultrasound waves, International Journal of Machine Tools & Manufacture, 43, 2003.
- [9] SCHEFFER C., HEYNS P.S., 2001, Wear monitoring in turning operations using vibration and strain measurements, Mechanical Systems and Signal Processing 15.
- [10] LIU Q., ALTINTAS Y., 1999, On-line monitoring of flank wear in turning with multilayered feed-forward neural network, International Journal of Machine Tools & Manufacture, 39, 1945–1959.
- [11] CHOUDHURY S.K., KISHORE K.K., 2000, Tool wear measurement in turning using force ratio, International Journal of Machine Tools & Manufacture, 40, 899–909.
- [12] GHASEMPOOR A., JESWIET J., MOORE T.N., 1999, Real time implementation of on-line tool condition monitoring in turning, International Journal of Machine Tools & Manufacture, 39, 1883–1902.
- [13] ORABY S.E., HAYHURST D.R., 2004, Tool life determination based on the measurement of wear and tool force ratio variation, International Journal of Machine Tools & Manufacture, 44, 1261–1269.
- [14] LEE J.H., LEE S.J., 1999, One-step-ahead prediction of flank wear using cutting force, International Journal of Machine Tools & Manufacture, 39, 1747–1760.
- [15] SHARMA V.S., SHARMA S.K., SHARMA A.K., An approach for condition monitoring of a turning tool, Proc. IMechE Vol. 221 Part B: J. Engineering Manufacture.
- [16] KUO R.J., 2000, Multi-sensor integration for on-line tool wear estimation through artificial neural networks and fuzzy neural network, Engineering Applications of Artificial Intelligence, 13, 249–261.
- [17] LEZANSKI P., 2001, An intelligent system for grinding wheel condition monitoring, Journal of Materials Processing Technology, 109, 258–263.
- [18] ZHOU J.M., ANDERSSON M., STAHL J. E., 2003, The monitoring of flank wear on the CBN tool in the hard turning process, International Journal of Advanced Manufacturing Technology, 22.
- [19] SCHEFFER C., KRATZ H., HEYNS P.S., KLOCKE F., 2003, Development of a tool wear-monitoring system for hard turning, International Journal of Machine Tools & Manufacture, 43, 973–985.
- [20] ABU-MAHFOUZ I., 2005, Drill flank wear estimation using supervised vector quantization neural networks, Neural Comput & Applic, 14.
- [21] NOORI-KHAJAVI A., KOMANDURI R., 1995, Frequency and time domain analyses of sensor signals in drilling-Part I, International Journal of Machine Tools and Manufacture, 35/6, 775–793.
- [22] JEMIELNIAK K., KOSSAKOWSKA J., T URBAŃSKI., S. BOMBIŃSKI., 2012, Tool condition monitoring based on numerous signal features, Int J Adv Manuf Technol, 59, 73–81.
- [23] JEMIELNIAK K., KOSSAKOWSKA J., 2010, Tool wear monitoring based on wavelet transform of raw acoustic emission signal, Advances in Manufacturing Science and Technology, 34, 3, 5–16.
- [24] JEMIELNIAK K., KOSSAKOWSKA J., URBAŃSKI T., BOMBIŃSKI S., 2010, Multi-feature fusion based tool condition monitoring in rough turning of Inconel 625, Proceedings of 4th CIRP International Conference on High Performance Cutting, Gifu, Japan, 2, 285–290.
- [25] BŁAŻEJAK K., BOMBIŃSKI S., 2013, Segmentacja sygnałów diagnostycznych i selekcja segmentów do wyznaczania miar, Projekt kluczowy „Nowoczesne technologie materiałowe stosowane w przemyśle lotniczym” Warszawa.
- [26] CZARNIAK P., GÓRSKI J., NEJMAN M., WILKOWSKI J., 2005, The acoustic noise signal as an indirect source of information about the tool wear during the milling of chipboard and MDF, Annals of Warsaw Agricultural University – SGGW, Forestry and Wood Technology, 56, 123–125.
Typ dokumentu
Bibliografia
Identyfikator YADDA
bwmeta1.element.baztech-4f73db39-d4b6-40c9-84a4-21e7f6732190