Research and development of thick plate shape prediction system based on industrial big data
Thick plate shape is one of the important indicators to measure the quality of thick plate products.The timely prediction of the final plate shape in production is of great significance for adjusting the operation and control of thick plate production.In actual industrial production, thick plate dat...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
China InfoCom Media Group
2021-09-01
|
| Series: | 物联网学报 |
| Subjects: | |
| Online Access: | http://www.wlwxb.com.cn/zh/article/doi/10.11959/j.issn.2096-3750.2021.00239/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841531206673367040 |
|---|---|
| author | Yufei MA Changxin LIU Wei KONG Jinliang DING |
| author_facet | Yufei MA Changxin LIU Wei KONG Jinliang DING |
| author_sort | Yufei MA |
| collection | DOAJ |
| description | Thick plate shape is one of the important indicators to measure the quality of thick plate products.The timely prediction of the final plate shape in production is of great significance for adjusting the operation and control of thick plate production.In actual industrial production, thick plate data has many characteristics, such as multiple coupling information, large amount of redundant information, and multi-source heterogeneity of data.Combining the needs of thick plate shape prediction, a thick plate shape prediction system was designed and developed.The data dump function was used to filter and preprocess the industrial big data to remove the coupling information and redundant variables in the data.LSTM neural network, convolutional neural network and 3D convolutional neural network were used to extract data features from data of different dimensions, and the features were fused based on the maximum mutual information coefficient to establish an integrated learning prediction model, which effectively solved the modeling difficulties caused by multi-source heterogeneous data.The actual industrial data of a domestic thick plate production line was used for verification, and the results showed the effectiveness of the developed system. |
| format | Article |
| id | doaj-art-dbbcaded761846d39e4a82d1cdbbc4d9 |
| institution | Kabale University |
| issn | 2096-3750 |
| language | zho |
| publishDate | 2021-09-01 |
| publisher | China InfoCom Media Group |
| record_format | Article |
| series | 物联网学报 |
| spelling | doaj-art-dbbcaded761846d39e4a82d1cdbbc4d92025-01-15T02:53:14ZzhoChina InfoCom Media Group物联网学报2096-37502021-09-015394859648021Research and development of thick plate shape prediction system based on industrial big dataYufei MAChangxin LIUWei KONGJinliang DINGThick plate shape is one of the important indicators to measure the quality of thick plate products.The timely prediction of the final plate shape in production is of great significance for adjusting the operation and control of thick plate production.In actual industrial production, thick plate data has many characteristics, such as multiple coupling information, large amount of redundant information, and multi-source heterogeneity of data.Combining the needs of thick plate shape prediction, a thick plate shape prediction system was designed and developed.The data dump function was used to filter and preprocess the industrial big data to remove the coupling information and redundant variables in the data.LSTM neural network, convolutional neural network and 3D convolutional neural network were used to extract data features from data of different dimensions, and the features were fused based on the maximum mutual information coefficient to establish an integrated learning prediction model, which effectively solved the modeling difficulties caused by multi-source heterogeneous data.The actual industrial data of a domestic thick plate production line was used for verification, and the results showed the effectiveness of the developed system.http://www.wlwxb.com.cn/zh/article/doi/10.11959/j.issn.2096-3750.2021.00239/thick plate shapeprediction modelmulti-source heterogeneous datasystem development |
| spellingShingle | Yufei MA Changxin LIU Wei KONG Jinliang DING Research and development of thick plate shape prediction system based on industrial big data 物联网学报 thick plate shape prediction model multi-source heterogeneous data system development |
| title | Research and development of thick plate shape prediction system based on industrial big data |
| title_full | Research and development of thick plate shape prediction system based on industrial big data |
| title_fullStr | Research and development of thick plate shape prediction system based on industrial big data |
| title_full_unstemmed | Research and development of thick plate shape prediction system based on industrial big data |
| title_short | Research and development of thick plate shape prediction system based on industrial big data |
| title_sort | research and development of thick plate shape prediction system based on industrial big data |
| topic | thick plate shape prediction model multi-source heterogeneous data system development |
| url | http://www.wlwxb.com.cn/zh/article/doi/10.11959/j.issn.2096-3750.2021.00239/ |
| work_keys_str_mv | AT yufeima researchanddevelopmentofthickplateshapepredictionsystembasedonindustrialbigdata AT changxinliu researchanddevelopmentofthickplateshapepredictionsystembasedonindustrialbigdata AT weikong researchanddevelopmentofthickplateshapepredictionsystembasedonindustrialbigdata AT jinliangding researchanddevelopmentofthickplateshapepredictionsystembasedonindustrialbigdata |