For access to this article, please select a purchase option:
IET members benefit from discounts to all IET publications and free access to E&T Magazine. If you are an IET member, log in to your account and the discounts will automatically be applied.
Your recommendation has been sent to your librarian.
An on-line monitoring algorithm of tool wear with working step as a unit in machining process based on adaptive learning is proposed. By collecting the motor current signal, the RMS (root mean square) of original current signal is extracted as the characteristic quantity, then the characteristic quantity RMS is statistically analyzed based on the method called SPSS (Statistical Product and Service Solutions), it is concluded that the RMS value of current signal approximately obeys normal distribution during the monitoring time period with working step as a unit, and by introducing the distribution coefficient K , the approximation error is reduced. On this basis, a self-learning algorithm for boundary mathematical model of tool wear monitoring with working step as a unit is proposed. The experimental results show that in semi-finishing and finishing, the monitoring model can be formed quickly and the monitoring effect is satisfactory, which is convenient to apply.
Inspec keywords: condition monitoring; statistical analysis; wear; production engineering computing; signal processing; computerised monitoring; normal distribution; mean square error methods; fault diagnosis; learning (artificial intelligence); machine tools; machining
Subjects: Production equipment; Numerical analysis; Signal processing and detection; Inspection and quality control; Other topics in statistics; Statistics; Tribology (mechanical engineering); Interpolation and function approximation (numerical analysis); Maintenance and reliability; Production engineering computing; Machining; Interpolation and function approximation (numerical analysis); Other topics in statistics; Digital signal processing; Industrial applications of IT