Due to the latest advancements in monitoring technologies, interest in the possibility of early-detection of quality issues in components has grown considerably in the manufacturing industry. However, implementation of such techniques has been limited outside of the research environment due to the more demanding scenarios posed by production environments. This paper proposes a method of assessing the health of a machining process and the machine tool itself by applying a range of machine learning (ML) techniques to sensor data. The aim of this work is not to provide complete diagnosis of a condition, but to provide a rapid indication that the machine tool or process has changed beyond acceptable limits; making for a more realistic solution for production environments. Prior research by the authors found good visibility of simulated failure modes in a number of machining operations and machine tool fingerprint routines, through the defined sensor suite. The current research set out to utilise this system, and streamline the test procedure to obtain a large dataset to test ML techniques upon. Various supervised and unsupervised ML techniques were implemented using a range of features extracted from the raw sensor signals, principal component analysis and continuous wavelet transform. The latter were classified using convolutional neural networks (CNN); both custom-made networks, and pre-trained networks through transfer learning. The detection and classification accuracies of the simulated failure modes across all classical ML and CNN techniques tested were promising, with all approaching 100% under certain conditions.
Maintaining minimal levels of geometric error in the finished workpiece is of increasing importance in the modern production environment; there is considerable research on the identification, verification and calibration of machine tool kinematic error, and the development of Postprocessor implementations to generate NC-code optimised for machining accuracy. The choice of multi-axis positioning function at the controller, however, is an often-overlooked potential source of kinematic error which can be responsible for costly mistakes in the production environment. This paper presents an investigation into how mis-management of the positional error parameters that define the rotary-axes’ pivot point can lead to unintended variations in multi-axis positioning. Four approaches for kinematic positioning on a Fanuc-based controller are considered, which reference two separate parameter locations to define the pivot point – managing the kinematics within the Postprocessor itself, full five-axis positioning with a fixture offset, full five-axis with rotation tool centre point control and 3+2-axis with a tilted workplane. Error vectors across four sets of rotary-axis indexations are simulated based on the theoretical kinematic model, to highlight the expected differences in geometric error attributable to mismatched pivot point parameters. Finally, the simulation results are verified experimentally, demonstrating the importance of maintaining a consistent approach in both programming and operation environments.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.