Author : Y D Chethan 1
Date of Publication :12th April 2017
Abstract: Turning is an important and widely used manufacturing process in engineering industries. The study of metal removal focuses on the features of tools, work materials, and machining parameter settings. Nickel-based super alloys are widely used in aircraft industry as they are exceptionally thermal resistant and retaining mechanical properties up to 700°C. By virtue of the above they induce tool wear while machining which seriously affect the life of the component, and it is a serious concern, since it is used in critical applications. In order to monitor the tool status in turning process, tool status dependent machine vision and AE features were extracted during machining and an attempt was made to obtain a clear insight of the parameters involved. But these simpler methods of analysis did not provide sufficient information about tool status and hence there was a requirement for more sophisticated method of signal analysis. This paper is the report of an investigation of an approach for machine vision signals estimation in turning for tool status monitoring. Tool status models were defined utilizing feed forward neural networks based on back propagation algorithm. The cutting test data were provided to the designed neural networks in order to train, validate and test them. Several configurations of networks, characterized by different number of hidden layers and number of neurons in the hidden layers, were trained for carrying out the best arrangement for the status parameters prediction, in terms of resulting errors. The input neurons are the investigated parameters (Machining time, AE RMS, AE count and perimeter), in estimating vision features i.e. wear area: perimeter, machining time, AE RMS, AE count are considered as the independent variables and vice versa in order to have the performance well in multi sensory situations. This ANN model could predict the vision and AE features by knowing the input data at time t. Also, this ANN model and multisensory system were coupled for on-line monitoring of the tool status.
- Segreto T. ,Simeone A. and Teti R., “Multiple sensor monitoring in nickel alloy turning for tool wear assessment via sensor fusion”, 8th CIRP Conference on Intelligent Computation in Manufacturing Engineering Journals of Science Direct,Procedia CIRP 12 (2013), Page no 85 – 90.
- C.Leone,D.D’Addona, R.Teti“Tool wear modelling throughregression analysis and intelligent methods for nickel base alloy machining” CIRP Journal of Manufacturing Science and Technology Volume 4, Issue 3, 2011, Pages 327– 331
- Samik Dutta, Surjya K. Pal , Ranjan Sen “On-machine tool prediction of flank wear from machined surface images using texture analyses and support vector regression” Precision Engineering Volume 43, January 2016, Pages 34–42
- Bulent Kaya, CuneytOysu, Huseyin M. Ertunc, “Force-torque based on-line tool wear estimation system for CNC milling of Inconel 718 using neural networks”, Journals of Elsevier, Advances in Engineering Software 42 (2011) 76 84
- Chethan YD, Venkatadas R, Krishne Gowda YT. Estimation of Machine Vision and Acoustic Emission Parameters for Tool Status Monitoring in Turning Using Artificial Neural Network. ASME. ASME International Mechanical Engineering Congress and Exposition, Volume2A:AdvancedManufacturing :V02AT02A 050. doi:10.1115/IMECE2015-50445.