Design and implementation of an intelligent grinding assistant system

Abstract

In modern competitive manufacturing industry, machining processes are expected to deliver products with high accuracy and assured surface integrity, using shorter cycle times with reduced operator intervention and increased flexibility. To meet such demands, the trend towards increased use of machine intelligence in machining systems and operations is clear and unlikely to be revised. This paper describes the structure, content and relations employed in a fully integrated intelligent grinding system for adaptive controlled cycle optimisation, thermal damage avoidance, dressing interval optimisation and data retention. This system, termed: 'Intelligent Grinding Assistant' (IGA©) is a unique, robust and versatile software system with embedded links and protocols for communication with the Computer Numerical Control (CNC) and instrumentation of a grinding machine. The IGA© was evaluated and implemented on a commercially available production machine and had its international launch in September 2005. The CNC, machine tool instrumentation, process monitoring and data analysis systems, Profibus link, and control strategies all constituted the IGA© system. Grinding performance was monitored and assessed in real time. An intelligent database was also developed to support the IGA© in the provision of optimised and/or safe starting cycle data to the operator/adaptive system and in the selective Design and implementation of an intelligent grinding assistant system 107 retention of data. Importantly, the IGA© has been designed and implemented in a way to ensure that an operator can readily use the system and achieve process improvement without recourse to extensive training.

Sensors as an Enabler for Self-Optimizing Grinding Machines

“…In this study, a holistic measurement set-up is presented, which can be used as a foundation for self-optimizing cup wheel grinding machines. [Tönshoff 1986] Force Grinding contact detection & force controlled grinding [Govekar 2002] Force Chatter detection [Morgan 2007] Power Spark-out time reduction [Inasaki 1991] Power Burn detection & Grinding wheel life detection [Jermolajev 2014] Temperature Prediction of workpiece surface layer properties [Karpuschewski 2000] Acoustic emission Dressing monitoring [Lange 2016] Acoustic emission Detection of run-out error [Yang 2012] Acoustic emission Classification of sharp and dull grinding wheels [Yang 2014] Acoustic emission Grinding burn detection Fig. 3 shows a picture of the used cup wheel grinding machine (Agathon DOM).…”

“…However, this approach may fail or needs recalibration for situations outside the trained scope of the optimization, such as new workpiece, tool, and machine combinations. Another approach was taken by [Morgan 2007], where a combination of sensor data and rules is used to optimize the grinding process. The usage of sensor data is an advantage because it provides feedback to the optimization system.…”

Self-optimizing grinding machines using Gaussian process models and constrained Bayesian optimization

“…These measurements are the input data points to the Gaussian process regression. Figure 1(a) shows the Gaussian process regression for the hyperparameters maximizing the marginal log likelihood using equation (8). It can be seen that with these hyperparameters the fit of the data is very good.…”

Grinding Process Control

“…The particular developments are the techniques employed by many different system developers. As yet, no single comprehensive and integrated system provides all the features of such a system although extensive descriptions of such a system can be found (Morgan et al, 2007). However, the features have been described in the literature by Billatos and Tseng (1992), Kelly et al (1989), Allanson et al (1992), Xiao et al (1992) and Tönshoff et al (1993 Figure 11.16 Levels of interaction in an intelligent grinding system.…”