CAD/CAM/CAE systems, OMV technologies and neural network based data analysis algorithms at the aviation industry enterprises

Mathematica modeling, numerical technique and program complexes


Аuthors

Chigrinets E. G.1*, Verchenko A. V.2**

1. Don State Technical University, DSTU, 1, Gagarin square, Rostov-on-Don, 344003, Russia
2. Rostvertol Helicopters, 5, Novatorov st., Rostov-on-Don, 344038, Russia

*e-mail: egchigrinets@gmail.com
**e-mail: alex290292@mail.ru

Abstract

In modern tough competition, aviation enterprises seek to maximize the capabilities computers application for products designing and manufacturing. To automatize these tasks, digital technologies such as CAD/CAM/CAE systems can be employed.

A technique for a 3D model of a helicopter dustproof device developing in the CAD system based on the coordinate measurement with account for real manufacturing deviations is presented.

The overview of milling technology of a helicopter part with the uneven hardness was performed. Optimization method of machining technology based on the finite element method with CAE implementation for the engineering analysis system is proposed. Computation results of unwanted deviations of the non-rigid thin-walled elements under the impact of the load direction were processed.

The problem of performing adaptive machining to program the milling of the detail contours on the CNC machine in case of virtual workpiece location was solved. The CNC-program correction by measuring the workpiece actual position on the machine table is proposed. The control program correction can be implemented as the result of solving the task of minimax, while searching such state of its position in space, so that the maximum allowance on the machined contour would be minimal. A mathematical model is developed, that unambiguously identifies the workpiece position on the machine table according to the measured coordinates of the three points. The developed algorithms of automatic search for the of the CNC-program correction to implement the principle of adaptive machining solution of the minimax problem. The program was created, and the method for the CNC-program designing for virtual workpiece locating on the CNC machine is developed. Experimental testing has confirmed efficiency of the developed technique

Manufacturing of the new aircrafts requires development and improvement of new materials and technologies, imposing ever-increasing demands for quality and operation reliability. Most carrying aircraft structures made of polymeric composites are machined to ensure the high quality holes providing reliable fixation and assembly of the composite structure (e.g., spars of the main and tail helicopter rotors blades). Delamination, which can reduce the structural integrity of the material, is the important technological problem occurring while fiber reinforced composite materials drilling. The tool geometry and machining conditions are the most important factors affecting the quality of the processed holes.

Using a series of experimental data that include the delamination sizes depending on the machining conditions, the database for the further modeling has been developed in a matrix form. The first attempt to build an empirical description of the sizes of delamination that depends on two design variables (cutting speed and drilling feed) was unsuccessful, probably, due to the nonlinearity, which is generic for the drilling process.

To overcome this difficulty we proposed and tested an approach, which is based on the the artificial neural networks (ANN) employing to predict the quality of the holes drilled in the titanium foil reinforced glass fiber epoxy-based plastics. ANN training was being conducted using an errors back-propagation algorithm. Testing of the prediction accuracy was shown that ANN can provide quality of size prediction that exceeds 97%.

The obtained results allow recommend the artificial neural network application to predict the size of the drilling holes delamination in GFRP. In the process of statistics accumulation the ANN are able to perform the self-training to produce the results based on the newly obtained information, thus, adequately predicting the quality of the machined holes.

Keywords:

CAD/CAM/CAE systems, OMV technologies, adaptive machining, artificial neural networks

References

  1. Astapov V.Yu., Khoroshko L.L., Afshari P., Khoroshko A.L. Trudy MAI, 2016, no. 87, available at: http://trudymai.ru/eng/published.php?ID=69638

  2. Efimov E.N., Shevgunov T.Ya. Trudy MAI, 2012, no. 51, available at: http://trudymai.ru/eng/published.php?ID=29159

  3. Medvedev V.S., Potemkin V.G. Neironnye seti. MATLAB 6 (Neural networks. MATLAB 6), Moscow, DIALOG-MIFI, 2002, 496 p.

  4. Shevtsov S.N., Sibirskii V.V., Chigrinets E.G. Trudy MAI, 2016, no. 91, available at: http://trudymai.ru/eng/published.php?ID=75572

  5. Grishchenko S.V. Trudy MAI, 2015, no. 84, available at: http://trudymai.ru/eng/published.php?ID=63011

  6. Abu-Mahfouz I. Drilling wear detection and classification using vibration signals and artificial neural network, International Journal of Machine Tools and Manufacture, 2003, no. 43, pp. 707 – 720.

  7. Arraiza A.L. et al. Experimental analysis of drilling damage in carbon-fiber reinforced thermoplastic laminates manufactured by resin transfer molding, Journal of Composite Materials, 2011, no. 46(6), pp. 717 – 725.

  8. Chen W.C. Some experimental investigations in the drilling of carbon fiber-reinforced plastic (CFRP) composite laminates, International Journal of Machine Tools and Manufacture, 1997, no. 37(8), pp. 1097 – 1108.

  9. Durao L.M. et al. Comparative analysis of drills for composite laminates, Journal of Composite Materials, 2011, no. 46(14), pp. 1649 – 1659.

  10. Gaitonde V.N. A study aimed at minimizing delamination during drilling of CFRP composites, Journal of Composite Materials, 2011, no. 45(22), pp. 2359 – 2368.

  11. Ghasemi F.A. et al. Effects of Drilling Parameters on Delamination of Glass-Epoxy Composites, Australian Journal of Basic and Applied Sciences, 2011, no. 5(12), pp. 1433 – 1440.

  12. Hocheng H., Dharan C.K.H. Delamination during drilling in composite laminates, Transactions of the ASME: Journal of Engineering for Industry, 1999, no. 112, pp. 236 – 239.

  13. Kilickap E. Investigation into the effect of drilling parameters on delamination in drilling GFRP, Journal of Reinforced Plastics and Composites, 2010, no. 29(23), pp. 3498 – 3503.

  14. Mishra R., Malik J., Singh I. Singh Prediction of drilling-induced damage in unidirectional glass-fibre-reinforced plastic laminates using an artificial neural network // Proceedings of the Institution of Mechanical Engineers. Part B, Journal of Engineering Manufacture, 2010, no. 224(5), pp. 733 – 738.

  15. Murugesh, M.C., Sadashivappa K. Influence of filler material on Glass fiber epoxy composite laminates during drilling, International Journal of Advances in Engineering & Technology, 2012, vol. 3, issue 1, pp. 233 – 239.

  16. Singh I., Bhatnagar N. Drilling-induced damage in uni-directional glass fiber reinforced plastic (UD-GFRP) composite laminates, International Journal of Advanced Manufacturing Technology, 2006, no. 27, pp. 877 – 882.

  17. Stone R., Krishnamurthy K. A Neural network thrust force controller to minimize delamination during drilling of graphite–epoxy laminates, International Journal of Machine Tools and Manufacture, 1996, no. 36, pp. 985 – 1003.

  18. Tagliaferri V., Caprino G., Diterlizzi A. Effect of drilling parameters on the finish and mechanical properties of GFRP composites, International Journal of Machine Tools and Manufacture, 1990, no. 30(1), pp. 77 – 84.

  19. Wang B. et al. Mechanism of damage generation during drilling of carbon/epoxy composites and titanium alloy stacks, Engineering Manufacture, 2014, vol. 228(7), pp. 698 – 706.

  20. Zitoune R., Krishnaraj V., Collombet F. Study of drilling of composite material and aluminium stack, Composites Structure, 2010, vol. 92, pp. 1246 – 1255.

  21. Zhang Z., Friedrich K. Artificial neural networks applied to polymer composites: a review, Journal of Composites Science and Technology, 2003, no. 63, pp. 2029 – 2044.


Download

mai.ru — informational site MAI

Copyright © 2000-2021 by MAI

Вход