CNN based tool monitoring system to predict life of cutting tool
- PDF / 3,088,663 Bytes
- 11 Pages / 595.276 x 790.866 pts Page_size
- 93 Downloads / 210 Views
CNN based tool monitoring system to predict life of cutting tool P. K. Ambadekar1,2 · C. M. Choudhari3 Received: 23 November 2019 / Accepted: 25 March 2020 © Springer Nature Switzerland AG 2020
Abstract In this study, we present tool wear prediction system to monitor the flank wear of a cutting tool by Machine Learning technique namely, Convolutional Neural Network (CNN). Experimentations were performed on mild steel components under dry cutting condition by carbide inserts as cutting tool. Images of cutting tool and turned component were taken at regular interval using an inverted microscope to measure the progression of flank wear and the corresponding image of component was noted. These images were used as an input to the CNN model that extract the features and classify cutting tool in one of the three wear class namely, low, medium and high. The result of the CNN training set was used to monitor the life of cutting tool and predict its remaining useful life. In this work which is first of its kind, the CNN model gives an accuracy of 87.26% to predict the remaining useful life of a cutting tool. In particular, the study exhibits that CNN method gives good response to the data in the form of images, when used as an indicator of tool wear classification in different classes. Keywords CNN · TCM · Cutting tool · Flank wear
1 Introduction Manufacturing which is an age old technology went on to become ‘Intelligent Manufacturing’ (IM) after the advent of CAD, CAM and CAE as well as robot. In early twentyfirst century with invent of smart sensors and internet, the IM system emerged to ‘Smart Manufacturing’ to provide a better quality and improved productivity with a reduced lead time [1]. This has been described as the fourth industrial revolution ‘Industry 4.0’. Smart design, smart machines, smart monitoring, smart control and finally smart scheduling can be achieved by Industry 4.0 that should take automation to the highest level [2]. Apart from this, to fulfill the highest level of automation in manufacturing industry, the work piece handling time and machine downtime should be reduced by fully automating the concerned hardware. Tool monitoring system is one such solution that reduces the downtime required to check the tool status. But at
present, indirect methods of monitoring tool wear are the best alternatives to direct methods. These methods save a considerable amount of time as the tool need not be removed to check its wear and thus is economic to industry. The cost of tool monitoring system can be justified against the amount spend in machine downtime for checking the tool status. Artificial Intelligence (AI) plays an important role in Industry 4.0 by providing capability of self-learning networks by using component data to predict its future [3]. A combination of indirect TCM methods with latest AI technology like the Convolutional Neural Network can greatly improve the performance of the manufacturing system. Thus the use of IoT and cloud system for smart manufacturing units can fulfill the objectives def
Data Loading...
