A data-driven predictive model of the grinding wheel wear using the neural network approach
Journal Title: Journal of Machine Engineering - Year 2017, Vol 17, Issue 4
Abstract
Advanced manufacturing depends on the timely acquisition, distribution, and utilization of information from machines and processes. These activities can improve accuracy and reliability in predicting resource needs and allocation, maintenance scheduling, and remaining service life of equipment. Thus, to model the state of tool wear and next to predict its remaining useful life (RUL) significantly increases the sustainability of manufacturing processes. there are many approaches, methods and theories applied to predictive model building. the proposed paper investigates an artificial neural network (ANN) model to predict the wear propagation process of grinding wheel and to estimate the RUL of the wheel when the extrapolated data reaches a predefined final failure value. The model building framework is based on data collected during external cylindrical plunge grinding. Firstly, usefulness of selected features of the measured process variables to be symptoms of grinding wheel state is experimentally verified. Next, issues related to development of an effective MLP model and its use in prediction of the grinding wheel RUL is discussed.
Authors and Affiliations
Pawel LEZANSKI
Keywords
Related Articles
- EP ID EP244322
- DOI 10.5604/01.3001.0010.7006
- Views 90
- Downloads 0
MACHINE TOOL DISTORTION ESTIMATION DUE TO ENVIRONMENTAL THERMAL FLUCTUATIONS ― A FOCUS ON HEAT TRANSFER COEFFICIENT
Thermally induced errors have been approached in multiple ways due to the influence these have over the positional accuracy of a machine tool. Here, approaches regarding environmental thermal fluctuations surrounding a...
INFLUENCE OF LINEAR FEED DRIVE CONTROLLER SETTING IN CNC TURNING LATHE ON THE STABILITY OF MACHINING
The paper deals with the influence of linear feed drive controller setting of a CNC turning lathe on the stability of machining. A coupled simulation model of feed drive control and ball screw drive mechanics with a tra...
A NEW GENERATION OF PRODUCTION WITH CYBER-PHYSICAL SYSTEMS – ENABLING THE BIOLOGICAL TRANSFORMATION IN MANUFACTURING
Within 200 years since the industrial revolution manufacturing systems have often changed their faces. Emerging nations, new markets, new inventions and the changing needs of the society forced them to adapt. Until today...
DEVELOPMENT AND MANUFACTURING OF ARDUINO BASED ELECTROCHEMICAL DISCHARGE MACHINE
The machining of non-conducting materials is very difficult due to its brittleness and hardness properties. The electrochemical discharge machining (ECDM) process is the hybrid non-traditional manufacturing technology b...
Application Of The Hamming Network To The Classification Of Surfaces After Abrasive Machining
The use of artificial neural networks for modelling and inference about surface parameters is a more and more often undertaken research topic. Based on the analysis of the ranges of suitability of surface topography para...