Data-Driven Online Health Assessment for Electronic Systems: A Portable Solution Exploiting Real-World Field Data
Keywords:
Prognostics and Health Monitoring, Internet-of-Things, Maintenance planning, Electrical component reliabilityAbstract
The field of Prognostics and Health Monitoring (PHM) for electronic systems is continually evolving to meet the growing demand for reliable and intelligent electronics, particularly in the context of the Internet-of-Things (IoT) and autonomous vehicles. This paper proposes a cost-effective and time-efficient approach to maintenance planning and monitoring of electronic systems through continuous real-time data analysis. By leveraging machine learning algorithms, the aim is to ensure the safety and reliability of electrical components without the need for permanent data storage. The degradation of solder contacts, caused by cyclic temperature loads, is identified as a primary cause of electronic failures. Finite Element Analysis (FEA) is commonly used for evaluating solder joint reliability but is not suitable for real-time monitoring due to computational resource requirements. Instead, FEA is employed to generate artificial data for training machine learning models. The paper presents a portable solution for online health assessment using a combination of real-world field data from an electric bike's power module and a synthetic database. The focus is on evaluating the Remaining Useful Lifetime (RUL) of solder joints without the need for a large temperature database. The methodology, including field data acquisition and machine learning model training, is described in detail. The results obtained demonstrate the potential of the proposed approach for practical implementation in electronic systems.
References
F. Che and J. H. Pang, "Vibration reliability test and finite element analysis for flip chip solder joints," Microelectronics reliability, vol. 49, no. 7, pp. 754-760, 2009.
L. F. Coffin Jr, "A study of the effects of cyclic thermal stresses on a ductile metal," Transactions of the American Society of Mechanical engineers, vol. 76, no. 6, pp. 931-949, 1954.
I. Goodfellow, Y. Bengio, and A. Courville, Deep learning. MIT press, 2016.
M. Izadi, M. Jabari, N. Izadi, M. Jabari, and A. Ghaffari, "Adaptive Control based on the Lyapunov Reference Model Method of Humanoid Robot Arms using EFK," in 2021 13th Iranian Conference on Electrical Engineering and Computer Science (ICEESC), 2021.
K. He, X. Zhang, S. Ren, and J. Sun, "Delving deep into rectifiers: Surpassing human-level performance on imagenet classification," in Proceedings of the IEEE international conference on computer vision, 2015, pp. 1026-1034.
G. E. Hinton, N. Srivastava, A. Krizhevsky, I. Sutskever, and R. R. Salakhutdinov, "Improving neural networks by preventing co-adaptation of feature detectors," arXiv preprint arXiv:1207.0580, 2012.
D. P. Kingma and J. Ba, "Adam: A method for stochastic optimization," arXiv preprint arXiv:1412.6980, 2014.
A. Krogh and J. Hertz, "A simple weight decay can improve generalization," Advances in neural information processing systems, vol. 4, 1991.
S. K. Kumar, "On weight initialization in deep neural networks," arXiv preprint arXiv:1704.08863, 2017.
R. Metasch et al., "Experimental investigation of the visco-plastic mechanical properties of a Sn-based solder alloy for material modelling in Finite Element calculations of automotive electronics," in 2014 15th International Conference on Thermal, Mechanical and Mulit-Physics Simulation and Experiments in Microelectronics and Microsystems (EuroSimE), 2014: IEEE, pp. 1-8.
M. Reynell, "Advanced thermal analysis of packaged electronic systems using computational fluid dynamics techniques," Computer-aided engineering journal, vol. 7, no. 4, pp. 104-106, 1990.
A. Schubert, R. Dudek, E. Auerswald, A. Gollhardt, B. Michel, and H. Reichl, "Fatigue life models for SnAgCu and SnPb solder joints evaluated by experiments and simulation," in Electronic components and technology conference, 2003: IEEE; 1999, pp. 603-610.
R. Schwerz, M. Roellig, and K.-J. Wolter, "Reliability analysis of encapsulated components in 3D-circuit board integration," in 2018 19th International Conference on Thermal, Mechanical and Multi-Physics Simulation and Experiments in Microelectronics and Microsystems (EuroSimE), 2018: IEEE, pp. 1-12.
S. Izadi, K. Jabari, M. Izadi, B. Khadem Hamedani, and A. Ghaffari, "Identification and Diagnosis of Dynamic and Static Misalignment in Induction Motor Using Unscented Kalman Filter," in 2021 13th Iranian Conference on Electrical Engineering and Computer Science (ICEESC), 2021.
N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov, "Dropout: a simple way to prevent neural networks from overfitting," The Journal of machine learning research, vol. 15, no. 1, pp. 1929-1958, 2014.
A. Syed, "Accumulated creep strain and energy density based thermal fatigue life prediction models for SnAgCu solder joints," in 2004 Proceedings. 54th electronic components and technology conference (IEEE Cat. No. 04CH37546), 2004, vol. 1: IEEE, pp. 737-746.
.
