|
| Prediction Model for Copper Anode Furnace Refining Reduction Endpoint based on GRNN Algorithm |
|
Received:June 26, 2024
Revised:July 15, 2024
Accepted:July 16, 2024
Published Online:November 17, 2024
|
| View Full Text View/Add Comment Download reader |
| DOI：doi：10.3969/j.issn.1007-7545.2024.12.005 |
| KeyWord:copper smelting in anode furnaces; reduction period; GRNN algorithm; image processing; endpoint determination |
| Author | Institution |
| SHU Bo |
楚雄滇中有色金属有限责任公司 |
| WANG Enzhi |
楚雄滇中有色金属有限责任公司 |
| XU Jianxin |
昆明理工大学复杂有色金属资源清洁利用国家重点实验室 |
| CHEN Xitang |
楚雄滇中有色金属有限责任公司 |
| REN Junxiang |
楚雄滇中有色金属有限责任公司 |
| YU Jianming |
楚雄滇中有色金属有限责任公司 |
| GAO Rong |
楚雄滇中有色金属有限责任公司 |
| WANG Hua |
昆明理工大学复杂有色金属资源清洁利用国家重点实验室 |
|
| Hits: 1720 |
| Download times: 886 |
| Abstract: |
| Address to limitations of relying on manual judgment for determining the endpoint of reduction period in copper smelting in anode furnaces, machine learning techniques was utilized to achieve intelligent judgment. Image feature optimization was performed through image deblurring, followed by grayscale difference matrix operation on the images. The extracted feature values from the matrix were used as inputs to a neural network, a novel model for determining the endpoint of the reduction period in copper smelting in anode furnaces was established. Experimental results demonstrate that employing the GRNN algorithm for predicting the reduction endpoint effectively eliminates correlations among different indicators during copper smelting, thereby reducing data redundancy and system errors, leading to an improved prediction accuracy of 96.54% in real production environments. Compared to traditional methods, this new judgment model significantly enhances the accuracy of determining the endpoint of the reduction period in copper smelting in anode furnaces. |
| Close |