In-process endpoint detection of weld seam removal in robotic abrasive belt grinding process
- 66 Downloads
This paper proposes a novel approach for in-process endpoint detection of weld seam removal during robotic abrasive belt grinding process using discrete wavelet transform (DWT) and support vector machine (SVM). A virtual sensing system is developed consisting of a force sensor, accelerometer sensor and machine learning algorithm. This work also presents the trend of the sensor signature at each stage of weld seam evolution during its removal process. The wavelet decomposition coefficient is used to represent all possible types of transients in vibration and force signals generated during grinding over weld seam. “Daubechies-4” wavelet function was used to extract features from the sensors. An experimental investigation using three different weld profile conditions resulting from the weld seam removal process using abrasive belt grinding was identified. The SVM-based classifier was employed to predict the weld state. The results demonstrate that the developed diagnostic methodology can reliably predict endpoint at which weld seam is removed in real time during compliant abrasive belt grinding.
KeywordsAbrasive belt grinding DWT Surface finish/integrity SVM Weld seam removal
Unable to display preview. Download preview PDF.
- 1.Islam MU, Xue L, McGregor G (2001) Process for manufacturing or repairing turbine engine or compressor components. U.S. Patent 6,269,540Google Scholar
- 2.Heitman PW, Hammond SN, Brown LE (1991) Method for joining single crystal turbine blade halves. U.S. Patent 5,071,059Google Scholar
- 5.(2011) Automated weld seam removal system promises removal rates over 20 times faster than manual grinding. Industrial Robot: An International Journal 38 (4). doi: 10.1108/ir.2011.04938daa.002
- 6.Ito Y (2014) In-process measurement for machining states: sensing technology in noisy space. In: Thought-evoking approaches in engineering problems. Springer International Publishing, Cham, p 17–40. doi: 10.1007/978-3-319-04120-9_2
- 7.Chen JC, Huang L, Lan A, Lee S (1999) Analysis of an effective sensing location for an in-process surface recognition system in turning operations. J Ind Technol 15(3):1–6Google Scholar
- 10.Luo RC, Kay MG (1990) A tutorial on multisensor integration and fusion. In: Industrial electronics society. IECON'90., 16th Annual Conference of IEEE, 1990. IEEE, p 707–722Google Scholar
- 11.Dornfeld D (1986) Acoustic emission process monitoring for untended manufacturing. In: Proc. Japan-USA Symposium on Flexible Automation, p 831–836Google Scholar
- 18.Nurprasetio P, Bagiasna K, Suharto D, Tjahjowidodo T (2010) The development of a novel fault identification technique by combining minimum-distance pattern-recognition and discrete wavelet transform. In: Proceedings of international conference on intelligent unmanned systemsGoogle Scholar
- 24.Schölkopf B, Smola AJ (2001) Learning with kernels: support vector machines, regularization, optimization, and beyond. MIT press Cambridge, MAGoogle Scholar
- 29.Shukla KK, Tiwari AK (2013) Filter banks and DWT. In: Efficient algorithms for discrete wavelet transform: With applications to denoising and fuzzy inference systems. Springer London, London, pp 21–36. doi: 10.1007/978-1-4471-4941-5_2
- 30.Vapnik V (1998) The support vector method of function estimation. In: Suykens JAK, Vandewalle J (eds) Nonlinear modeling: Advanced black-box techniques. Springer US, Boston, MA, pp 55–85. doi: 10.1007/978-1-4615-5703-6_