시간적, 공간적 특성을 활용하는 딥러닝기반 고무의 레오미터 품질 적합성 검사 모델
Deep Learning-based Rheometer Quality Inspection Model Using Temporal and Spatial Characteristics
1
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
고무생산업체에서 생산된 고무는 레오미터 측정을 통해 품질 적합성 검사가 이루어진 후, 자동차 부품을 위한 2차 가공으로 이어진다. 그러나 레오미터 검사는 인간에 의해 진행되고 있으며, 숙련된 작업자에게 매우 의존적이라는 단점이 존재한다. 이러한 문제점을 해결하기 위해 본 논문에서는 딥러닝 기반 레오미터 품질 검사 시스템을 제안한다. 제안된 시스템은 레오미터의 시간적, 공간적 특성을 활용하기 위해 LSTM과 CNN을 조합하였고, 각 고무의 배합재료를 보조(Auxiliary) 데이터 입력으로 사용해 하나의 모델에서 다양한 고무 제품의 품질 적합성 검사가 가능하도록 구현하였다. 제안된 기법은 30,000개의 데이터셋으로 그 성능을 학습 및 검사하였으며, 평균 f1-점수를 0.9942 달성하여 그 우수성을 증명하였다.
Abstract
Rubber produced by rubber companies is subjected to quality suitability inspection through rheometer test, followed by secondary processing for automobile parts. However, rheometer test is being conducted by humans and has the disadvantage of being very dependent on experts. In order to solve this problem, this paper proposes a deep learning-based rheometer quality inspection system. The proposed system combines LSTM(Long Short-Term Memory) and CNN(Convolutional Neural Network) to take advantage of temporal and spatial characteristics from the rheometer. Next, combination materials of each rubber was used as an auxiliary input to enable quality conformity inspection of various rubber products in one model. The proposed method examined its performance with 30,000 validation datasets. As a result, an F1-score of 0.9940 was achieved on average, and its excellence was proved.
참고문헌 (23)
- "Smart Factory Market Size To Hit USD 321.98 Billion By 2032"[URL]
- Mohammed Mabkhot, "Requirements of the Smart Factory System: A Survey and Perspective", Machines, 6(2), pp.23~ (2018), MDPI AG[DOI]
- Hyun-Lim Yang, "Exploring the Research Trend of Smart Factory with Topic Modeling", Sustainability, 10(8), pp.2779~ (2018), MDPI AG[DOI]
- Navid Shariatzadeh, "Integration of Digital Factory with Smart Factory Based on Internet of Things", Procedia CIRP, 50, pp.512~517 (2016), Elsevier BV[DOI]
- Baotong Chen, "Smart Factory of Industry 4.0: Key Technologies, Application Case, and Challenges", IEEE Access, 6, pp.6505~6519 (2017), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- Armir Bujari, "Standards, Security and Business Models: Key Challenges for the IoT Scenario", Mobile Networks and Applications, 23(1), pp.147~154 (2017), Springer Science and Business Media LLC[DOI]
- R. Ozdemir, "A quality control application on a smart factory prototype using deep learning methods", 2019 IEEE 14th international conference on computer sciences and information technologies (CSIT), pp.46~49 (2019)
- HT. Nguyen, "Defective product classification system for smart factory based on deep learning", The 9th International Conference on Smart Media and Applications, pp.80~85 (2020)
- Jiafu Wan, "A Blockchain-Based Solution for Enhancing Security and Privacy in Smart Factory", IEEE Transactions on Industrial Informatics, 15(6), pp.3652~3660 (2019), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- Yanjun Zuo, "Making smart manufacturing smarter – a survey on blockchain technology in Industry 4.0", Enterprise Information Systems, 15(10), pp.1323~1353 (2020), Informa UK Limited[DOI]
- Jeong Yeon Won, "Smart factory adoption in small and medium-sized enterprises: Empirical evidence of manufacturing industry in Korea", Technological Forecasting and Social Change, 157, pp.120117~ (2020), Elsevier BV[DOI]
- G. Milani, "Rubber blends: kinetic numerical model by rheometer experimental characterization", Journal of Mathematical Chemistry, 56(6), pp.1520~1542 (2018), Springer Science and Business Media LLC[DOI]
- C. Sample, "An overview of anomaly detection", IT Professional, 15(1), pp.8~11 (2013)[DOI]
- B. Maschler, "Towards deep industrial transfer learning for anomaly detection on time series data", 2021 26th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA), pp.1~8 (2021)
- H. Liu, "Semi-supervised Sentiment Classification Based on Auxiliary Task Learning", Natural Language Processing and Chinese Computing: 7th CCF International Conference, pp.372~382 (2018)
- Huy Toan Nguyen, "Defective Product Classification System for Smart Factory Based on Deep Learning", Electronics, 10(7), pp.826~ (2021), MDPI AG[DOI]
- J. Song, "Deep generative model with time series-image encoding for manufacturing fault detection in die casting process", Journal of Intelligent Manufacturing, 34(7), pp.3001~3014 (2022)[DOI]
- PC. Ngo, "Fence GAN: Towards better anomaly detection", 2019 IEEE 31St International Conference on tools with artificial intelligence (ICTAI), pp.141~148 (2020)
- Weijun Xie, "Recognition of Defective Carrots Based on Deep Learning and Transfer Learning", Food and Bioprocess Technology, 14(7), pp.1361~1374 (2021), Springer Science and Business Media LLC[DOI]
- B. Koonce, "Convolutional Neural Networks with Swift for Tensorflow: Image Recognition and Dataset Categorization", pp.63~72 (2021)
- Amin Khorram, "End-to-end CNN + LSTM deep learning approach for bearing fault diagnosis", Applied Intelligence, 51(2), pp.736~751 (2020), Springer Science and Business Media LLC[DOI]
- Christos Spandonidis, "Evaluation of deep learning approaches for oil & gas pipeline leak detection using wireless sensor networks", Engineering Applications of Artificial Intelligence, 113, pp.104890~ (2022), Elsevier BV[DOI]
- Zulfiqar Khan, "Towards Efficient Electricity Forecasting in Residential and Commercial Buildings: A Novel Hybrid CNN with a LSTM-AE based Framework", Sensors, 20(5), pp.1399~ (2020), MDPI AG[DOI]