High Speed Sintering (HSS) Modelling and prediction via Radial Basis Function Neural Network (RBFNN)
DOI:
https://doi.org/10.37375/susj.v15i2.3722Keywords:
High speed sintering (HSS), Radial Basis Function neural network (RBFNN), Fault detection (FD)Abstract
An additive manufacturing technique called High Speed Sintering (HSS) has enormous potential for producing intricate, superior polymer parts on a large scale. HSS process is modelled in this paper using a novel Radial Basis Function neural network (RBFNN) technique. The data gathered from the HSS process was analysed to determine the healthy/unhealthy data that could achieve a good/bad build. A powerful technique is developed for early fault detection (FD) and, consequently, to predict the quality of the parts produced using HSS. The RBFNN model was validated and tested to assess the robustness of the approach, and the simulation outcomes demonstrated that the faults could be clearly identified, and the quality of the produced parts possibly will be predicted.
References
Dongo H, Wang Z, Lam J, Gao H (2012) Fuzzy-model-based robust fault detection with stochastic mixed time delays and successive packet dropouts. IEEE Transactions on System, Man, and Cybernetics-Part B: Cybernetics, Vol. 42, No. 2.
Frank PM (1992) Principles of model-based fault detection. Control, delft the IFAC Artificial intelligence in Real-Time, Netherlands, Vol. 3 pp. 213- 220
Gertler J J (1988) Model-based failure detection and isolation in complex plants. IEEE Control System Magazine, pp. 3-11.
Isermann R (1984) Process fault detection based on modelling and estimation methods- a survey. Automatica, Vol. 20, pp. 387- 404.
Kemnitzer J, Wimmer M, Tarasova A, Döpper F (2024) High Speed Sintering of Polyamide 12: From Powder to Part Properties, Polymers 2024, 16(24), 3605; https://doi.org/10.3390/polym16243605
Lightbody G, Irwin GW (1997) Nonlinear Control Structures Based on Embedded Neural System Models. IEEE Transactions on neural networks, 8(3): 553-567.
Majewski CE, Hobbs BS, Hopkinson N (2007) Effect of bed temperature and infra-red lamp power on the mechanical properties of parts produced using high-speed sintering, Virtual physical prototyping, vol. 2, No. 2, 103-110
Majewski CE, Oduye D, Thomas HR, Hopkinson N (2008) Effect of level on the sintering behavior in the high-speed sintering process. Rapid Prototyping journal, 14/3, 155-160.
Narendra KS, Parthasarathy K (1990) Identification and control of dynamic systems using neural networks. IEEE Trans. Neural Networks , Vol. 1, No.1.
Narendra KS (1996) Neural networks for control: theory and practice. Proc. IEEE, Vol. 84, No. 10, pp. 1385-1406.
Nelles O (2001). Nonlinear system identification. Springer.
Patan K (2008) Artificial neural network for the modelling and fault diagnosis of technical process. Springer- Verlag Berlin Heidelberg.
Stubbs S, Zhang J, Morris J (2012) Fault detection in dynamic processes using a simplified monitoring-specific CVA state space modelling approach. Computer and Chemical Engineering, Elsevier, Vol. 41, pp. 77-87.
Yu DL, Gomm JB, Williams D (1999) Sensor fault diagnosis in a chemical process via RBF neural networks. Control Engineering Practice, Vol. 7, pp. 49-55.
Zhai YJ, Yu DL (2007) Radial Basis Function Based Feeddback Control for Air Fuel Ratio of Spark Ignition. Proc. Instn mech. Engrs, part D: J. automobile engineering, vol 222, pp. 415-428.
