Paul M. Lister

On-line metal cutting tool condition monitoring.: I: force and vibration analyses

Excessive wear on cutting tools give rise to distortions in dimension of manufactured components, sometimes increasing scrapped levels thereby incurring additional costs. Methods for detecting and monitoring the wear on a cutting tool is therefore crucial in most metal cutting processes and several research efforts have striven to develop on-line tool condition monitoring systems. This paper describes an experimental and analytical method for one such technique involving the use of three mutually perpendicular components of the cutting forces (static and dynamic) and vibration signature measurements. The ensuing analyses in time and frequency domains showed some components of the measured signals to correlate well to the accrued tool wear.

Neural network solutions to the tool condition monitoring problem in metal cutting—A critical review of methods

A wide range of cutting tool monitoring techniques have been proposed and developed in the last decade, but only a few have found industrial applications, and a truly universally applicable system has still to be developed. In this paper a review of tool condition monitoring (TCM) systems, developed or implemented through application of neural networks, is provided. The review seeks to illustrate the extent of application of neural networks and the need for multiple source sensor signals in TCM systems. A critical analysis of methods is included and the trend in obtained results outlined.

On-line metal cutting tool condition monitoring.: II: tool-state classification using multi-layer perceptron neural networks

This paper outlines a neural networks based modular tool condition monitoring system for cutting tool-state classification. Test cuts were conducted on EN24 alloy steel using P15 and P25 coated cemented carbide inserts and on-line cutting forces and vibration data acquired. Simultaneously the wear lengths on the cutting edges were measured, and these together with the processed data were fed to a neural network trained to distinguish tool-state. The first part of the investigation concentrated on tool-state classification using a single wear indicator and progressing to two wear indicators. The developed system was tested for a variety of cutting conditions and its ability to distinguish changes in tooling material and cutting conditions from those arising from tool wear was assessed. The system was found to be capable of accurate tool state classification in excess of 90% accuracy but deteriorated when the cutting conditions were significantly changed.

Application and evaluation of VR-based CAPP system

Abstract This paper proposes an approach to an integrated CAPP/VR system. A desktop VR environment is used to explore the machining process element of CAPP. An architecture of a virtual CAPP system is proposed based on an incorporated VR design interface, which can respond to the dynamic manufacturing process. The key problems under discussion are to find an effective method to quickly capture the 3D information from the manufacturing environment, and to define a uniform and well-organised structure of the program layout for achieving improved sharing of VR resources. Examples of the simulation for cutting process are supplied to demonstrate and verify the proposed CAPP/VR integration system.

Investigation into the Relationship between Tool-Wear and Cutting Environments when Turning En32 Steel

New environmental legislation is forcing companies to realign their use of metalworking fluids in favour of non‐polluting cutting environments that will return acceptable tool wear rates and reduced costs. Studies have been undertaken to determine the effectiveness of various environments on tool wear, in order to either reduce or even eliminate totally, the dependency on flood coolants. Industrially reproducible cutting tests were devised, where an EN32 case hardening steel material was turned in a range of different cutting environments and tool life measured. Low oxygen gaseous environments were compared with conventional cutting environments and a 55 per cent flank wear reduction has been recorded using uncoated tooling.

The future role of metalworking fluids in metal cutting operations

As more stringent environmental legislation is enforced throughout Europe manufacturing businesses, employing metal cutting processes, can no longer ignore the growing importance of environmental aspects relating to cutting fluids. Businesses, through market forces, are being forced into offering a “clean solution” to the metal cutting processes which they operate. Cutting fluids despite playing an important role in metal cutting, have considerable environmental impact. There is a need therefore to understand the role of cutting fluids within the cutting process in order to evaluate possible environmentally friendly alternatives to the use of cutting fluids. In order to achieve this the operating environment in which the process is being carried out, and the consequences of removing the cutting fluid from the process altogether has to be assessed. This paper therefore, reflects on the role of cutting fluid and the implications of their use. Viable methods of reducing cutting fluid consumption are also reported, together with efficient methods of cutting fluid utilisation (e.g. minimum quantity delivery systems). Finally, the difficulties experienced in removing cutting fluids from the metal cutting process are highlighted through the consideration of dry cutting technologies.

Automatic tool state identification in a metal turning operation using MLP neural networks and multivariate process parameters

This paper describes results of the application of feed-forward Multi-Layer Perceptron (MLP) neural networks for cutting tool state identification in a metal turning operation. Test cuts were conducted using P25 carbide inserts with and without wear (i.e. nominally sharp) on EN24 alloy steel. The acquired data were used to train, cross-validate and test the generalisation capabilities of two MLP configurations. Both networks had exactly the same input and output nodes but differing number of nodes in a single middle layer. Training was achieved via back-propagation of error enhanced by the addition of a momentum term and adaptive learning rate. Different error goal targets during training of the MLP were used, and the validation results of the model investigation analysed and presented. Obtained results for successful classification of the tool state with respect to only two classes (worn or sharp) were between 83 and 96%.

E-manufacturing in networked virtual environments

E-manufacturing as a new generation of product development solution allows manufacturers all over the world to speed up and slim down everything from design to manufacturing. It has been employed in a wide range of manufacturing activities. Networked Virtual Environments (Net-VEs) have already begun to foster an insightful, intuitive and interactive system that allows effective communication among multiple users. After exploring the architecture and features of Net-VEs, a cost-effective approach to create an e-manufacturing system in Net-VEs is proposed in this paper. The World Wide Web (WWW) as the delivery mechanism has made such systems widely available and affordable. We also evaluate an e-manufacturing system in Net-VEs by comparison with a traditional product development approach.

Sensor Fusion for Cutting Tool State Identification in Metal Turning Through the Application of Perceptron Neural Networks

Abstract The demand on better returns by investors and the quest for continued customer satisfaction through assured quality products, have culminated in a rapid increase in factory automation processes within the last 20 years. This paper outlines an investigative study, where Artificial Neural Networks are applied to automatically detect the state of a cutting tool. The ensuing wear on the tool is chosen as the parameter to be detected, and process parameters from the cutting environment are measured on-line, fused through the network and its output gives an indication of tool wear level. The implemented Single and Multiple Layer Perceptron Neural Networks achieved success accuracy rates of > 75% and > 95% respectively.

Application of a Back-Propagation Neural Network to Tool Condition Monitoring in a Metal Turning Process

Artificial Neural Networks (ANN) are robust tools for data classification, modelling and dynamic control. This paper presents the initial results of an investigative study of sensor integration through the application of multiple feed-forward neural networks for the accomplishment of Tool Condition Monitoring (TCM). Progressive wear test studies were conducted on a conventional centre-lathe, with P25 uncoated and P15 coated carbide inserts, and an EN24T work-piece material. The cutting forces and vibration signatures were recorded, together with the nose and flank wear lengths. A signal processing method was employed to calculate the energy contained in the dynamic forces and vibration signals spectra which, together with the static forces, were used as inputs to a neural network. Additionally, the cutting speed, feed rate and depth of cut were incorporated into the input vector sets. Limiting the tool states to either sharp or worn, results obtained from off-line investigations using a 12-20-1 feed-forward Multi-Layer Perceptron (MLP) neural network showed a successful classification rate of between 75–87.5%.