Non-contact and full-field online monitoring of curing temperature during the in-situ heating process based on deep learning

Abstract

Online monitoring of the curing temperature field is essential to improving the quality and efficiency of the manufacturing process of composite parts. Traditional embedded sensor-based technologies have difficulty monitoring the full temperature field or have to introduce heterogeneous items that could have an undesired impact on the part. In this paper, a non-contact, full-field monitoring method based on deep learning that predicts the internal temperature field of composite parts in real time using surface temperature measurements of auxiliary materials is proposed. Using the proposed method, an average temperature monitoring accuracy of 97% is achieved in various heating patterns. In addition, this method also demonstrates satisfying feasibility when a stronger thermal barrier covers the part. This method was experimentally validated during the self-resistance electric heating process, in which the monitoring accuracy reached 93.1%. This method can potentially be applied to automated manufacturing and process control in the composites industry.

Keywords

Online monitoring / Curing temperature field / Deep learning (DL) / In-situ heating

References

[1.] Kim M, Sung DH, Kong K, et al. Characterization of resistive heating and thermoelectric behavior of discontinuous carbon fiber-epoxy composites. Compos B-Eng, 2016, 90: 37-44.

[2.] Joseph C, Viney C. Electrical resistance curing of carbon-fibre/epoxy composites. Compos Sci Technol, 2000, 60: 315-319.

[3.] Xia T, Zeng D, Li Z, et al. Electrically conductive GNP/epoxy composites for out-of-autoclave thermoset curing through Joule heating. Compos Sci Technol, 2018, 164: 304-312.

[4.] Liu S, Li Y, Shen Y, et al. Mechanical performance of carbon fiber/epoxy composites cured by self-resistance electric heating method. Int J Adv Manuf Tech, 2019, 103: 3479-3493.

[5.] Zhou J, Li Y, Zhu Z et al (2022) Microwave heating and curing of metal-like CFRP laminates through ultrathin and flexible resonance structures. Compos Sci Technol 218:109200. https://doi.org/10.1016/j.compscitech.2021.109200

[6.] Naik TP, Singh I, Sharma AK (2022) Processing of polymer matrix composites using microwave energy: a review. Compos Part A-Appl S 156:106870. https://doi.org/10.1016/j.compositesa.2022.106870

[7.] Li N, Li Y, Jelonnek J, et al. A new process control method for microwave curing of carbon fibre reinforced composites in aerospace applications. Compos B- Eng, 2017, 122: 61-70.

[8.] Chen J, Wang Y, Liu F, et al. Laser-induced graphene paper heaters with multimodally patternable electrothermal performance for low-energy manufacturing of composites. ACS Appl Mater Inter, 2020, 12: 23284-23297.

[9.] Tu R, Liu T, Steinke K et al (2022) Laser induced graphene-based out-of-autoclave curing of fiberglass reinforced polymer matrix composites. Compos Sci Technol 226:109529. https://doi.org/10.1016/j.compscitech.2022.109529

[10.] Shen Y, Lu Y, Liu S, et al. Temperature distribution analysis of carbon fiber reinforced polymer composites during self-resistance electric heating process. J Reinf Plast Comp, 2022, 41(19/20): 805-821.

[11.] Zobeiry N, Park J, Poursartip A. An infrared thermography-based method for the evaluation of the thermal response of tooling for composites manufacturing. J Compos Mater, 2019, 53: 1277-1290.

[12.] Dolkun D, Wang H, Wang H, et al. Influence of large framed mold placement in autoclave on heating performance. Appl Compos Mater, 2020, 27: 811-837.

[13.] Zhou J, Li Y, Li N, et al. A multi-pattern compensation method to ensure even temperature in composite materials during microwave curing process. Compos Part A-Appl S, 2018, 107: 10-20.

[14.] Shen Y, Lu Y, Liu S, et al. Self-resistance electric heating of shaped CFRP laminates: temperature distribution optimization and validation. Int J Adv Manuf Technol, 2022, 121: 1755-1768.

[15.] Zhang B, Li Y, Liu S, et al. Layered self-resistance electric heating to cure thick carbon fiber reinforced epoxy laminates. Polym Compos, 2021, 42: 2469-2483.

[16.] Eriksen A, Osinski D, Hjelme DR. Evaluation of thermal imaging system and thermal radiation detector for real-time condition monitoring of high power frequency converters. Adv Manuf, 2014, 2: 88-94.

[17.] Huang XK, Tian XY, Zhong Q, et al. Real-time process control of powder bed fusion by monitoring dynamic temperature field. Adv Manuf, 2020, 8: 380-391.

[18.] Li F, Yu ZH, Li H, et al. Real-time monitoring of raster temperature distribution and width anomalies in fused filament fabrication process. Adv Manuf, 2022, 10: 571-582.

[19.] Konstantopoulos S, Tonejc M, Maier A, et al. Exploiting temperature measurements for cure monitoring of FRP composites—applications with thermocouples and infrared thermography. J Reinf Plast Comp, 2015, 34: 1015-1026.

[20.] Ito Y, Minakuchi S, Mizutani T, et al. Cure monitoring of carbon–epoxy composites by optical fiber-based distributed strain–temperature sensing system. Adv Compos Mater, 2012, 21: 259-271.

[21.] Hübner M, Lang W (2017) Online monitoring of composites with a miniaturized flexible combined dielectric and temperature sensor. In: Multidisciplinary digital publishing institute proceedings, Paris, France, 2017, 1, p 627. https://doi.org/10.3390/proceedings1040627

[22.] Ramakrishnan M, Rajan G, Semenova Y, et al. Overview of fiber optic sensor technologies for strain/temperature sensing applications in composite materials. Sensors, 2016, 16: 99.

[23.] Bagavathiappan S, Lahiri BB, Saravanan T, et al. Infrared thermography for condition monitoring—a review. Infrared Phys Techn, 2013, 60: 35-55.

[24.] Nash C, Karve P, Adams D et al (2020) Real-time cure monitoring of fiber-reinforced polymer composites using infrared thermography and recursive Bayesian filtering. Compos B-Eng 198:108241. https://doi.org/10.1016/j.compositesb.2020.108241

[25.] Zobeiry N, Humfeld KD (2021) A physics-informed machine learning approach for solving heat transfer equation in advanced manufacturing and engineering applications. Eng Appl Artif Intel 101:104232. https://doi.org/10.1016/j.engappai.2021.104232

[26.] Humfeld KD, Gu D, Butler GA et al (2021) A machine learning framework for real-time inverse modeling and multi-objective process optimization of composites for active manufacturing control. Compos B-Eng 223:109150. https://doi.org/10.1016/j.compositesb.2021.109150

[27.] Wang M, Hu W, Jiang Y, et al. Internal temperature prediction of ternary polymer lithium-ion battery pack based on CNN and virtual thermal sensor technology. Int J Energy Res, 2021, 45: 13681-13691.

[28.] Ma H, Hu X, Zhang Y et al (2020) A combined data-driven and physics-driven method for steady heat conduction prediction using deep convolutional neural networks. arXiv preprint arXiv:2005.08119. https://doi.org/10.48550/arXiv.2005.08119

[29.] Amini NS, Haghighat E, Campbell T et al (2021) Physics-informed neural network for modelling the thermochemical curing process of composite-tool systems during manufacture. Comput Method Appl M 384:113959. https://doi.org/10.1016/j.cma.2021.113959

[30.] Szegedy C, Liu W, Jia Y et al (2015) Going deeper with convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, Boston, MA, USA, 2015, pp 1–9. https://doi.org/10.1109/CVPR.2015.7298594

[31.] Alvarez-Ramirez J, Rodriguez E, Carlos Echeverría J. Detrending fluctuation analysis based on moving average filtering. Physica A, 2005, 354: 199-219.

[32.] Shorten C, Khoshgoftaar TM. A survey on image data augmentation for deep learning. J Big Data-Ger, 2019, 6: 60.

Funding

National Natural Science Foundation of China http://dx.doi.org/10.13039/501100001809(51875288)