The application of machine learning to sensor signals for machine tool and process health assessment

Abstract

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.

Prediction of tool wear based on GA-BP neural network

“…The sample size is 322 mm (L), 80 mm (W) and 40 mm (H), as shown in Figure 3. The material is composed of 50% wood flour, 25% polyethylene and 25% adhesive, with a density of 1.19 g/cm 3 . The general characteristics of the material are shown in Table 1.…”

“…This algorithm has the processing ability of parallel distributed information and is suitable for applications in prediction, classification and diagnosis. 2,3 Singh et al 4 pointed out that BPNN can effectively learn the wear law of the tool and can be used in the actual tool wear prediction. Many scholars have investigated the relationship between cutting factors and tool wear.…”

Missingness analysis of manufacturing systems: A case study

“…There is considerable interest in utilising machine learning techniques to exploit this such as detecting and categorising faults in a milling machine tool. 11 In manufacturing, preprocessing of this data can constitute around 80% of project analysis time. 12 Research has been undertaken into the impact of missing data on analysis tasks, but most manufacturing work has tended to concentrate on mechanisms to detect abnormalities.…”

A seven-question based critical thinking framework for cultivating innovation talents in engineering research and its implementation perspectives

“…4 In the current dynamic era with big challenges, disruptions and uncertainties, new requirements and technologies are emerging at an unprecedented speed. 5,6 In engineering area, new manufacturing equipment and technologies, measurement methods and technologies as well as related upstream technologies are emerging day by day, [7][8][9] only the researchers with innovation capability can keep up with the development pace of new technologies. The lack of originality will lead to weak competitiveness for a person, a company as well as for a country.…”