Journal of the Korea Institute of Information and Communication Engineering (한국정보통신학회논문지)

The Korea Institute of Information and Commucation Engineering (한국정보통신학회)
권호 표지
DOI QR코드

DOI QR Code

The methods to improve the performance of predictive model using machine learning for the quality properties of products

머신러닝을 활용한 제품 특성 예측모델의 성능향상 방법 연구

  • Kim, Jong Hoon (Applied Data Science, Sungkyunkwan University) ;
  • Oh, Hayoung (College of Computing & Informatics, Sungkyunkwan University)
  • Received : 2021.03.06
  • Accepted : 2021.04.21
  • Published : 2021.06.30
Download PDF
⟨ Previous Next ⟩

Abstract

Thanks to PLC and IoT Sensor, huge amounts of data has been accumulated onto the companies' databases. Machine Learning Algorithms for the predictive model with good performance have been widely utilized in the manufacturing process. We present how to improve the performance of machine learning predictive models. To improve the performance of the predictive model, typical techniques such as increasing the sample size, optimizing the hyper parameters for the algorithm, and selecting a proper machine learning algorithm for the predictive model would be shown. We suggest some new ways to make the model performance much better. With the proposed methods, we can build a better predictive model for predicting and controlling product qualities and save incredibly large amount of quality failure cost.

제조 생산공정에는 다양한 센서를 통해 실시간으로 양질의 데이터가 데이터베이스에 축적되고 있다. 이와 함께 통계적으로 접근하기 까다로운 데이터에 대해서 높은 수준의 정확도로 예측모델을 구축할 수 있는 머신러닝이 보급되면서 '4차 산업화 시대'를 맞이하고 있다. 본 논문에서는 이러한 제조업계의 흐름에 따라 업계의 주요 관심사인 제품의 품질특성을 예측하는 머신러닝 모델의 성능을 향상하는 방법을 제시한다. 머신러닝 모델의 성능을 향상하는데 일반적으로 사용되는 샘플 크기의 증가, Hyper-Parameter의 최적화 및 적절한 알고리즘 선택의 효과를 검증한다. 그리고, 새로운 성능향상 방법을 제시하고, 그 효과를 검증해본다. 논문에서 제시한 방법을 통해서 제조업에서는 더욱 향상된 성능의 예측모델을 구축, 품질예측과 관리에 크게 이바지할 수 있을 것이다.

Keywords

References

  1. Machine Learning is the keyword in the manufacturing industry for the next 5 years. Maeil Business News [Internet]. Available: https://www.mk.co.kr/news/economy/view/2021/01/100880/.
  2. The zero percent of the employment rate in the manufacturing industry is coming. Asia Economy [Internet]. Available: https://www.asiae.co.kr/article/2021011106524868927.
  3. The 10 ways to improve the manufacturing industry. AITIMES [Internet]. Available: http://www.aitimes.com/news/articleView.html?idxno=128731.
  4. J. Brownlee. How To Improve Deep Learning Performance. Machine Learning Mastery [Internet]. Available: https://machinelearningmastery.com/improve-deep-learning-performance/.
  5. S. K. Kim, S. Y. Hwang, and J. H. Lee, "Application of Multi-Layer Perceptron and Random Forest Method for Cylinder Plate Forming," Journal of the Society of Naval Architects of Korea, vol. 57, no. 5, pp. 297-304, 2020. https://doi.org/10.3744/SNAK.2020.57.5.297
  6. S. Y. Kim and G. B. Kim, "Classification Performance Analysis of Sillicon Wafer Micro-Cracks Based on SVM," Journal of Korean Society for Precision Engineering, vol. 33, no. 9, pp. 715-721, 2016. https://doi.org/10.7736/KSPE.2016.33.9.715
  7. C. H. Kim, S. H. Choi, W. J. Joo, and G. B. Kim, "Classification of Surface Defect on Steel Strip by KNN Classifier," Journal of Korean Society for Precision Engineering, vol. 23, no. 8, pp. 80-88, 2006.
  8. S. H. Song, "Study on Hot Deformation of Inconel 601 Using DeepNeural Network and Support Vector Regression," Journal of the Korean Society of Mechanical Technology., vol. 21, no. 1, pp. 96-101, 2019. https://doi.org/10.17958/ksmt.21.1.201902.96
  9. S. H. Jeon and Y. S. Son, "Prediction of fine dust PM10 using a deep neuralnetwork model," The Korean Journal of Applied Statistics, vol. 31, no. 2, pp. 265-285, 2018. https://doi.org/10.5351/KJAS.2018.31.2.265
  10. A. B. M. S. Rahman, V. Ragu, M. B. Lee, J. W. Park, Y. Y. Cho, M. H. Lee, and C. S. Shin, "An Analysis Study Based on Linear Regression Model for Changes of Fruit Size over Plum Diseases," Journal of Knowledge Information Technology and Systems, vol. 13, no. 5, pp. 509-519, 2018. https://doi.org/10.34163/jkits.2018.13.5.001
  11. H. Y. Lee, "Research Methodology," 2nd ed. Seoul, Korea: CRbooks, pp. 407-411, 2014.
  12. P. Sarkar. Bagging and Random Forest in Machine Learning. knowledgehut [Internet]. Available: https://www.knowledgehut.com/blog/data-science/bagging-and-random-forest-in-machine-learning.
  13. J. Jordan. Evaluating a machine learning model. Jeremy Jordan [Internet]. Available: https://www.jeremyjordan.me/evaluating-a-machine-learning-model/.