Journal of Internet Computing and Services (인터넷정보학회논문지)

Korean Society for Internet Information (한국인터넷정보학회)
권호 표지
DOI QR코드

DOI QR Code

An Artificial Neural Network Based Phrase Network Construction Method for Structuring Facility Error Types

설비 오류 유형 구조화를 위한 인공신경망 기반 구절 네트워크 구축 방법

  • Roh, Younghoon (Industrial and Management Engineering, Kyonggi University) ;
  • Choi, Eunyoung (Industrial and Management Engineering, Kyonggi University) ;
  • Choi, Yerim (Industrial and Management Engineering, Kyonggi University)
  • Received : 2018.08.08
  • Accepted : 2018.10.30
  • Published : 2018.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

In the era of the 4-th industrial revolution, the concept of smart factory is emerging. There are efforts to predict the occurrences of facility errors which have negative effects on the utilization and productivity by using data analysis. Data composed of the situation of a facility error and the type of the error, called the facility error log, is required for the prediction. However, in many manufacturing companies, the types of facility error are not precisely defined and categorized. The worker who operates the facilities writes the type of facility error in the form with unstructured text based on his or her empirical judgement. That makes it impossible to analyze data. Therefore, this paper proposes a framework for constructing a phrase network to support the identification and classification of facility error types by using facility error logs written by operators. Specifically, phrase indicating the types are extracted from text data by using dictionary which classifies terms by their usage. Then, a phrase network is constructed by calculating the similarity between the extracted phrase. The performance of the proposed method was evaluated by using real-world facility error logs. It is expected that the proposed method will contribute to the accurate identification of error types and to the prediction of facility errors.

4차 산업혁명 시대의 도래와 함께 스마트 팩토리의 개념이 대두되면서 설비가동률과 생산성에 악영향을 미치는 설비 오류의 발생을 데이터 분석 기법을 통해 예측하고자 하는 노력이 이루어지고 있다. 데이터 분석 기법을 활용하여 설비 오류를 예측하기 위해서는 설비 오류가 발생한 상황과 설비 오류 유형을 명시한 데이터인 설비 오류 이력이 필요하다. 하지만 많은 제조 현장에서는 설비 오류 유형이 정확하게 정의/분류가 되지 않아 설비를 운영하는 작업자가 자신의 경험적 판단에 의거하여 정형화되지 않은 텍스트의 형태로 설비 오류 유형을 작성하고, 이에 따라 데이터 분석 기법의 적용이 어렵다. 따라서 본 논문에서는 수기로 작성된 설비 오류 이력을 활용하여 설비 오류 유형을 파악하고 구조화하기 위한 구절 네트워크 구축 방법을 제안하고자 한다. 구체적으로, 단어를 쓰임새에 따라 분류한 용도 딕셔너리를 활용하여 비정형의 텍스트 데이터로부터 설비 오류 유형을 의미하는 구절을 추출하고, 추출된 구절 간의 유사도를 계산하여 네트워크를 구축한다. 제안하는 방법의 성능을 실제 제조 기업의 설비 오류 이력 데이터를 활용하여 검증하였으며, 본 연구의 결과는 텍스트 데이터에 기반한 설비 오류 유형 구조화와 나아가서는 설비 오류 발생 예측에 이용할 수 있을 것을 기대한다.

Keywords

OTJBCD_2018_v19n6_21_f0001.png 이미지

(그림 1) 제안 방법 도식 (Figure 1) Framework of the proposed method

OTJBCD_2018_v19n6_21_f0002.png 이미지

(그림 2) CBOW 모델 도식 (Figure 2) Concept of CBOW model

OTJBCD_2018_v19n6_21_f0003.png 이미지

(그림 3) 유사도 지표에 따른 구절 네트워크 시각화 결과 (Figure 3) Comparison of the phrase networks using two similarity measures, (a) cosine and (b) Pearson.

(표 1) 수집된 설비 오류 이력 데이터 예시 (Table 1) Example of the collected facility error logs

OTJBCD_2018_v19n6_21_t0001.png 이미지

(표 2) 설비 오류 이력 텍스트로부터 추출된 구절 (Table 2) Example of the extracted phrases from facility error logs

OTJBCD_2018_v19n6_21_t0002.png 이미지

(표 3) 코사인 유사도 기반 오류 유형 (Table 3) The type of error based on cosine similarity

OTJBCD_2018_v19n6_21_t0003.png 이미지

(표 4) 피어슨 유사도 기반 오류 유형 (Table 4) The type of error based on Pearson similarity

OTJBCD_2018_v19n6_21_t0004.png 이미지

References

  1. Seifi M, Salem A, Beuth J, Harrysson O, and Lewandowski J. J, "Overview of Materials Qualification Needs for Metal Additive Manufacturing." The Journal of The Minerals, Metals & Materials Society, Vol. 68, No. 3, pp. 747-764, 2016. https://doi.org/10.1007/s11837-015-1810-0
  2. Seong Jun Kim, Byung Hak Choe, and Woo sik Kim, "Prognostics for Industry 4.0 and Its Application to Fitness-for-Service Assessment of Corroded Gas Pipelines." Journal of the Korean Society for Quality Management, Vol. 45, No. 4, pp. 649-664, 2017. https://doi.org/10.7469/JKSQM.2017.45.4.649.
  3. Gee Wook Song, Woo Sung Choi, Wanjae Kim, and Nam Gun Jung, "Damage Analysis for Last-Stage Blade of Low-Pressure Turbine." Transactions of the Korean Society of Mechanical Engineers B, Vol. 37, No. 12, pp. 1153-1157, 2013. http://dx.doi.org/10.3795/KSME-B.2013.37.12.1153
  4. Wang, Chen, Hoang Tam Vo, and Peng Ni, "An IoT Application for Fault Diagnosis and Prediction." In Proceedings of the IEEE International Conference on Data Science and Data Intensive Systems, pp. 726-731, 2015. https://doi.org/10.1109/DSDIS.2015.97
  5. Ju Seop Park, Soon Goo Hong, and Na Rang Kim, "A Development Plan for Co-creation-based Smart City through the Trend Analysis of Internet of Things." Journal of the Korea Industrial Information Systems Research, Vol. 21, No. 4, pp. 67-78, 2016. http://dx.doi.org./10.9723/jksiis.2016.21.4.067
  6. Bok Hee Lee, Kang Hee Lee, Tae Ki Kim, Han Soo Kim, "A Study on the Present State and Consistent use of Terminologies Concerning Grounding." Journal of the Korean Institute of Illuminating and Electrical Installation Engineers, Vol. 27, No. 4, pp. 81-87, 2013. https://doi.org/10.5207/JIEIE.2013.27.4.081
  7. Ur-Rahman, Nadeem, and Jennifer A. Harding, "Textual Data Mining for Industrial Knowledge Management and Text Classification: a Business Oriented Approach." Expert Systems with Applications, Vol. 39, No. 5, pp. 4729-4739, 2012. https://doi.org/10.1016/j.eswa.2011.09.124
  8. Dino Isa, Lam Hong Lee, V.P. Kallimani, and R. Rajkumar, "Text Document Preprocessing With the Bayes Formula for Classification Using the Support Vector Machine." IEEE Transactions on Knowledge and Data engineering, Vol. 20, No. 9, p.1264-1272, 2008. https://doi.org/10.1109/TKDE.2008.76
  9. Rossant C, Goodman D. F, Platkiewicz J, and Brette R, "Automatic Fitting of Spiking Neuron Models to Electrophysiological Recordings." Frontiers in Neuroinformatics, Vol. 4, No. 2, pp. 1-10, 2010. https://doi.org/10.3389/neuro.11.002.2010
  10. Dhillon, Inderjit S, and Dharmendra S. Modha., "Concept Decompositions for Large Sparse Text Data using Clustering." Machine Learning, Vol. 42, No. 1-2, pp. 143-175, 2001. https://doi.org/10.1023/A:1007612920971
  11. Nam gyu Kim, Dong hoon Lee, Ho chang Choi, and Wong William Xiu Shun, "Investigations on Techniques and Applications of Text Analytics." The Journal of Korean Institute of Communications and Information Sciences, Vol. 42, No. 2, pp. 471-492, 2017. https://doi.org/10.7840/kics.2017.42.2.471
  12. Yung Shen Lin, Jung Yi Jiang, and Shie Jue Lee, "A Similarity Measure for Text Classification and Clustering." IEEE Transactions on Knowledge and Data Engineering, Vol. 26, No. 7, pp. 1575-1590, 2014. https://doi.org/10.1109/TKDE.2013.19
  13. Monedero I, Biscarri F, Leon C, Guerrero J. I, Biscarri J, and Millan R, "Detection of Frauds and Other Non-Technical Losses in a Power Utility using Pearson Coefficient, Bayesian Networks and Decision Trees." International Journal of Electrical Power & Energy Systems, Vol. 34, No. 1, pp. 90-98, 2012. https://doi.org/10.1016/j.ijepes.2011.09.009
  14. 우진공업, http://www.ngkntk.co.kr
  15. Gephi, https://gephi.org
  16. Blondel V. D, Guillaume J. L, Lambiotte R, and febvre E, "Fast Unfolding of Communities in Large Networks." Journal of Statistical Mechanics: Theory and Experiment, Vol. 2008, No. 10, pp. 10008, 2008. https://doi.org/10.1088/1742-5468/2008/10/P10008
  17. Yoo sin Kim, Sung Gwan Hong, Hee Joo Kang, and Seung Ryul Jeong, "Electronic-Composit Consumer Sentiment Index(CCSI) development by Social Bigdata Analysis." Journal of Internet Computing and Services, Vol. 18, No. 4, pp. 121-131, 2017. https://doi.org/10.7472/jksii.2017.18.4.121
  18. Tae Soo Park and Ok Ran Jeong, "Event Detection System Using Twitter Data." Journal of Internet Computing and Services, Vol. 17, No. 6, pp. 153-158, 2016. https://doi.org/10.7472/jksii.2016.17.6.153.
  19. Yong Woong Lee, Se Han Kim, Kyo Hun Son, In Hwan Lee, and Chang Sun Shin, "Implementation of Failure-Diagnostic Context-awareness Middleware for Support Highly Reliable USN Application Service." Journal of Internet Computing and Services, Vol. 12, No. 3, pp. 1-16, 2011. https://doi.org/10.7472/jksii.2015.16.4.71
  20. Wei Ji and Lihui Wang, "Big Data Analytics Based Fault Prediction for Shop Floor Scheduling." Journal of Manufacturing Systems, Vol. 43, No. 1, pp. 187-194, 2017. https://doi.org/10.1016/j.jmsy.2017.03.008
  21. Huma Lodhi, Craig Saunders, John Shawe- Taylor, Nello Cristianini, and Chris Watkins, "Text Classification Using String Kernels." Journal of Machine Learning Research, Vol. 2, pp. 419-444, 2002. https://doi.org/10.1162/153244302760200687