Prediction of Process Quality Performance Using Statistical Analysis and Long Short-Term Memory
In the manufacturing industry, the process capability index (Cpk) measures the level and capability required to improve the processes. However, the Cpk is not enough to represent the process capability and performance of the manufacturing processes. In other words, considering that the smart manufac...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-01-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/2/735 |
| _version_ | 1797496106334027776 |
|---|---|
| author | Tola Pheng Tserenpurev Chuluunsaikhan Ga-Ae Ryu Sung-Hoon Kim Aziz Nasridinov Kwan-Hee Yoo |
| author_facet | Tola Pheng Tserenpurev Chuluunsaikhan Ga-Ae Ryu Sung-Hoon Kim Aziz Nasridinov Kwan-Hee Yoo |
| author_sort | Tola Pheng |
| collection | DOAJ |
| description | In the manufacturing industry, the process capability index (Cpk) measures the level and capability required to improve the processes. However, the Cpk is not enough to represent the process capability and performance of the manufacturing processes. In other words, considering that the smart manufacturing environment can accommodate the big data collected from various facilities, we need to understand the state of the process by comprehensively considering diverse factors contained in the manufacturing. In this paper, a two-stage method is proposed to analyze the process quality performance (PQP) and predict future process quality. First, we propose the PQP as a new measure for representing process capability and performance, which is defined by a composite statistical process analysis of such factors as manufacturing cycle time analysis, process trajectory of abnormal detection, statistical process control analysis, and process capability control analysis. Second, PQP analysis results are used to predict and estimate the stability of the production process using a long short-term memory (LSTM) neural network, which is a deep learning algorithm-based method. The present work compares the LSTM prediction model with the random forest, autoregressive integrated moving average, and artificial neural network models to convincingly demonstrate the effectiveness of our proposed approach. Notably, the LSTM model achieved higher accuracy than the other models. |
| first_indexed | 2024-03-10T01:58:56Z |
| format | Article |
| id | doaj.art-7ea8b4a6ef5c41f19e833b87078139f5 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T01:58:56Z |
| publishDate | 2022-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-7ea8b4a6ef5c41f19e833b87078139f52023-11-23T12:51:51ZengMDPI AGApplied Sciences2076-34172022-01-0112273510.3390/app12020735Prediction of Process Quality Performance Using Statistical Analysis and Long Short-Term MemoryTola Pheng0Tserenpurev Chuluunsaikhan1Ga-Ae Ryu2Sung-Hoon Kim3Aziz Nasridinov4Kwan-Hee Yoo5Techo Startup Center, RUPP’s Compound Russian Federation Blvd., Toul Kork, Phnom Penh 12156, CambodiaDepartment of Computer Science, Chungbuk National University, Chungdae-ro 1, Seowon-Gu, Cheongju 28644, KoreaDepartment of Computer Science, Chungbuk National University, Chungdae-ro 1, Seowon-Gu, Cheongju 28644, KoreaDepartment of Computer Science, Chungbuk National University, Chungdae-ro 1, Seowon-Gu, Cheongju 28644, KoreaDepartment of Computer Science, Chungbuk National University, Chungdae-ro 1, Seowon-Gu, Cheongju 28644, KoreaDepartment of Computer Science, Chungbuk National University, Chungdae-ro 1, Seowon-Gu, Cheongju 28644, KoreaIn the manufacturing industry, the process capability index (Cpk) measures the level and capability required to improve the processes. However, the Cpk is not enough to represent the process capability and performance of the manufacturing processes. In other words, considering that the smart manufacturing environment can accommodate the big data collected from various facilities, we need to understand the state of the process by comprehensively considering diverse factors contained in the manufacturing. In this paper, a two-stage method is proposed to analyze the process quality performance (PQP) and predict future process quality. First, we propose the PQP as a new measure for representing process capability and performance, which is defined by a composite statistical process analysis of such factors as manufacturing cycle time analysis, process trajectory of abnormal detection, statistical process control analysis, and process capability control analysis. Second, PQP analysis results are used to predict and estimate the stability of the production process using a long short-term memory (LSTM) neural network, which is a deep learning algorithm-based method. The present work compares the LSTM prediction model with the random forest, autoregressive integrated moving average, and artificial neural network models to convincingly demonstrate the effectiveness of our proposed approach. Notably, the LSTM model achieved higher accuracy than the other models.https://www.mdpi.com/2076-3417/12/2/735long short-term memorysmart manufacturingstatistical process analysisprocess capability indexprocess quality performance |
| spellingShingle | Tola Pheng Tserenpurev Chuluunsaikhan Ga-Ae Ryu Sung-Hoon Kim Aziz Nasridinov Kwan-Hee Yoo Prediction of Process Quality Performance Using Statistical Analysis and Long Short-Term Memory Applied Sciences long short-term memory smart manufacturing statistical process analysis process capability index process quality performance |
| title | Prediction of Process Quality Performance Using Statistical Analysis and Long Short-Term Memory |
| title_full | Prediction of Process Quality Performance Using Statistical Analysis and Long Short-Term Memory |
| title_fullStr | Prediction of Process Quality Performance Using Statistical Analysis and Long Short-Term Memory |
| title_full_unstemmed | Prediction of Process Quality Performance Using Statistical Analysis and Long Short-Term Memory |
| title_short | Prediction of Process Quality Performance Using Statistical Analysis and Long Short-Term Memory |
| title_sort | prediction of process quality performance using statistical analysis and long short term memory |
| topic | long short-term memory smart manufacturing statistical process analysis process capability index process quality performance |
| url | https://www.mdpi.com/2076-3417/12/2/735 |
| work_keys_str_mv | AT tolapheng predictionofprocessqualityperformanceusingstatisticalanalysisandlongshorttermmemory AT tserenpurevchuluunsaikhan predictionofprocessqualityperformanceusingstatisticalanalysisandlongshorttermmemory AT gaaeryu predictionofprocessqualityperformanceusingstatisticalanalysisandlongshorttermmemory AT sunghoonkim predictionofprocessqualityperformanceusingstatisticalanalysisandlongshorttermmemory AT aziznasridinov predictionofprocessqualityperformanceusingstatisticalanalysisandlongshorttermmemory AT kwanheeyoo predictionofprocessqualityperformanceusingstatisticalanalysisandlongshorttermmemory |