Injection molding is the most common method for manufacturing plastic products. However, products made by injection molding often exhibit various molding defects. One major contributing factor to these defects is mold temperature, especially at the cavity section where the resin enters. In our laboratory’s research, the feasibility of measuring the cavity temperature using non-contact thermometers by making simple modifications around the mold cavity area was investigated. It was also examined whether it is possible to distinguish between normal and defective molded products—specifically those with short shots—based on this temperature data. Analyzing data from predefined temperature measurement points raises concerns about significantly increased computation times. For remote monitoring applications, it is necessary to reduce the number of measurement points to decrease data volume. In this paper, an attempt is made to reduce the number of measurement points used in analysis by selecting items with an orthogonal array. As a result, the number of measurement points for analysis was reduced by 55%, thereby decreasing computation time and achieving favorable results for implementing a remote monitoring system equipped with defect detection functionality, which is reported here.

1. [1] National Institute of Population and Social Security Research, “Population projection for Japan 2021–2070.” https://www.ipss.go.jp/pp-zenkoku/e/zenkoku_e2023/pp2023e_Summary.pdf [Accessed September 11, 2025]
2. [2] Cabinet Office of Japan, “Annual report on the ageing society [Summary] FY2024.” https://www8.cao.go.jp/kourei/english/annualreport/2024/pdf/2024.pdf [Accessed September 11, 2025]
3. [3] Y. Murata, T. Abe, Y. Sugano, T. Mizusawa, K. Suzuki, K. Ishikawa, and T. Maruyama, “Investigation on relationship between warpage of injection molded products and temperature distribution in a mold,” J. of the Japan Society of Polymer Processing, Vol.20, No.10, pp. 769-775, 2008 (in Japanese). https://doi.org/10.4325/seikeikakou.20.769
4. [4] N. Kawada, “Study on condition monitoring technology for digital transformation of manufacturing,” Saitama Institute of Technology Advanced Science Research Laboratory Annual Report, Vol.20, pp. 3-14, 2022 (in Japanese).
5. [5] S. Otobe, M. Urano, K. Oizumi, T. Hayashi, A. Ishigami, C. Natthapong, and H. Ito, “Development of ‘expertized AI’ and ‘IoT-based mold’ in mold manufacturing SME,” J. of the Japan Society of Polymer Processing, Vol.31, No.12, pp. 452-455, 2019 (in Japanese). https://doi.org/10.4325/seikeikakou.31.452
6. [6] Y. Murata, “Sensor applicated technology to measure molding phenomenon in polymer injection mold,” J. of the Japan Society of Precision Engineering, Vol.81, No.5, pp. 415-420, 2015 (in Japanese). https://doi.org/10.2493/jjspe.81.415
7. [7] S. Sakakibara, “Reinforcement of manufacturing industry competitiveness by utilizing robotics, IoT and AI,” J. of the Japan Society of Precision Engineering, Vol.83, No.1, pp. 30-35, 2017 (in Japanese). https://doi.org/10.2493/jjspe.83.30
8. [8] Y. Fukushima, T. Suzuki, K. Onda, H. Komatsu, H. Kuroiwa, and T. Kaburagi, “Study on the online monitoring system of barn mark by gas sensor,” Int. J. Automation Technol., Vol.11, No.1, pp. 112-119, 2017. https://doi.org/10.20965/ijat.2017.p0112
9. [9] F. Klocke, S. Kratz, T. Auerbach, S. Gierlings, G. Wirtz, and D. Veselovac, “Process monitoring and control of machining operations,” Int. J. Automation Technol., Vol.5, No.3, pp. 403-411, 2011. https://doi.org/10.20965/ijat.2011.p0403
10. [10] D. Kurihara, Y. Kakinuma, and S. Katsura, “Sensorless cutting force monitoring using parallel disturbance observer,” Int. J. Automation Technol., Vol.3, No.4, pp. 415-421, 2009. https://doi.org/10.20965/ijat.2009.p0415
11. [11] M. Soori, B. Arezoo, and R. Dastres, “Digital twin for smart manufacturing, A review,” Sustainable Manufacturing and Service Economics, Vol.2, Article No.100017, 2023. https://doi.org/10.1016/j.smse.2023.100017
12. [12] A. Yokota, “Shashutsuseikei Kisonokiso,” The Nikkan Kogyo Shimbun, 2007 (in Japanese).
13. [13] S. Sakano, “A study of bills recognition using MTS,” Quality Engineering, Vol.8, No.3, pp. 58-64, 2000 (in Japanese). https://doi.org/10.18890/qes.8.3_58
14. [14] A. M. Yazid, J. K. Rijal, M. S. Awaluddin, and E. Sari, “Pattern recognition on remanufacturing automotive component as support decision making using Mahalanobis-Taguchi System,” Procedia CIRP, Vol.26, pp. 258-263, 2015. https://doi.org/10.1016/j.procir.2014.07.025
15. [15] M. Nagao, M. Yamamoto, K. Suzuki, and A. Ohuchi, “A face identification system based on the Mahalanobis–Taguchi System,” Int. Trans. in Operational Research, Vol.8, No.1, pp. 31-45, 2001. https://doi.org/10.1111/1475-3995.00004
16. [16] K. Honma, M. Ohkubo, S. Eguchi, and Y. Nagata, “Mahalanobis-Taguchi method for anomaly detection and classification,” Total Quality Science, Vol.8, No.1, pp. 1-13, 2022. https://doi.org/10.17929/tqs.8.1
17. [17] J. Shimura, D. Takata, H. Watanabe, I. Shitanda, and M. Itagaki, “Mahalanobis-Taguchi method based anomaly detection for lithium-ion battery,” Electrochimica Acta, Vol.479, Article No.143890, 2024. https://doi.org/10.1016/j.electacta.2024.143890
18. [18] Robust Quality Engineering Society, “Quality Engineering Handbook,” The Nikkan Kogyo Shimbun, 2007 (in Japanese).
19. [19] Y. Fukushima and N. Kawada, “Online monitoring method for mold deformation using Mahalanobis distance,” Int. J. Automation Technol., Vol.15, No.5, pp. 689-695, 2021. https://doi.org/10.20965/ijat.2021.p0689
20. [20] H. Kinjo, Y. Ogawa, Y. Takahashi, N. Kawada, and Y. Fukushima, “Visualization of mold deformation and monitoring system based on Mahalanobis distance,” Quality Engineering, Vol.32, No.2, pp. 32-39, 2024 (in Japanese). https://doi.org/10.18890/qes.32.2_32
21. [21] S. Ishida, T. Tahara, W. Iwasaki, and H. Miyamoto, “Evaluation of wire bonding state by thin AE sensor and Mahalanobis-Taguchi System,” Proc. of the Japan Institute of Electronics Packaging Annual Meeting, Vol.30, pp. 187-190, 2016 (in Japanese). https://doi.org/10.11486/ejisso.30.0_187
22. [22] Y. Fukushima, Z. Zongyang, A. Sakamoto, and N. Kawada, “Condition monitoring method for injection molding process by waveform analysis,” Proc. of the 22nd Int. Conf. on Advances in Materials & Processing Technologies, 2019.
23. [23] K. Hirose and S. Ueda, “Excel de Dekiru Taguchi Mesoddo Kaisekihou nyūmon,” Doyukan, 2003 (in Japanese).
24. [24] K. Tamaura, “Yokuwakaru MT System,” Japanese Standards Association, 2009 (in Japanese).