基于3D卷积神经网络的膏体屈服应力预测
TD853; 膏体流变性能是膏体充填技术重要指标,是金属矿膏体充填工艺流程的重要工程参数.本文提出一种基于 3D卷积神经网络的膏体屈服应力预测方法,通过制定图像采集标准并研发图像采集装置采集图像数据集.经Sobel算子实现膏体边缘检测、全图缩小等预处理,得到膏体图像数据集.采用十折交叉验证方法划分数据集,避免因单次随机划分造成的偶然误差.以膏体图像-屈服应力数据集为基础,利用 3D卷积神经网络模型提取膏体纹理特征和时序信息等,又通过引入直方图均衡化算法的图像增强策略减少环境因素干扰,提高模型稳健性.利用预处理后的数据集在 3D卷积神经网络模型上做训练和测试,得到模型损失值曲线图和混淆矩阵.将屈...
Saved in:
| Published in | 工程科学学报 Vol. 46; no. 8; pp. 1337 - 1348 |
|---|---|
| Main Authors | , , , , , , , |
| Format | Journal Article |
| Language | Chinese |
| Published |
昆明理工大学国土资源工程学院,昆明 650093%云南驰宏锌锗股份有限公司会泽矿业公司,曲靖 654211%中铝集团玉溪矿业有限公司,玉溪 653100
01.07.2024
|
| Subjects | |
| Online Access | Get full text |
| ISSN | 2095-9389 |
| DOI | 10.13374/j.issn2095-9389.2023.10.11.005 |
Cover
| Abstract | TD853; 膏体流变性能是膏体充填技术重要指标,是金属矿膏体充填工艺流程的重要工程参数.本文提出一种基于 3D卷积神经网络的膏体屈服应力预测方法,通过制定图像采集标准并研发图像采集装置采集图像数据集.经Sobel算子实现膏体边缘检测、全图缩小等预处理,得到膏体图像数据集.采用十折交叉验证方法划分数据集,避免因单次随机划分造成的偶然误差.以膏体图像-屈服应力数据集为基础,利用 3D卷积神经网络模型提取膏体纹理特征和时序信息等,又通过引入直方图均衡化算法的图像增强策略减少环境因素干扰,提高模型稳健性.利用预处理后的数据集在 3D卷积神经网络模型上做训练和测试,得到模型损失值曲线图和混淆矩阵.将屈服应力模型预测结果进行分析,又引入卷积注意力机制嵌入到卷积神经网络实现模型优化,并对模型参数进行调整,模型预测平均准确率从 93.26%提升至 98.19%,论证了基于 3D卷积神经网络的膏体屈服应力预测方法可行性.经图像增强处理的数据集应用到各模型中,模型预测平均准确率均提升 3%以上.相比传统膏体流变测量方式,解决了传统膏体屈服应力测量操作复杂、外部因素扰动大、工程现场难以开展等问题. |
|---|---|
| AbstractList | TD853; 膏体流变性能是膏体充填技术重要指标,是金属矿膏体充填工艺流程的重要工程参数.本文提出一种基于 3D卷积神经网络的膏体屈服应力预测方法,通过制定图像采集标准并研发图像采集装置采集图像数据集.经Sobel算子实现膏体边缘检测、全图缩小等预处理,得到膏体图像数据集.采用十折交叉验证方法划分数据集,避免因单次随机划分造成的偶然误差.以膏体图像-屈服应力数据集为基础,利用 3D卷积神经网络模型提取膏体纹理特征和时序信息等,又通过引入直方图均衡化算法的图像增强策略减少环境因素干扰,提高模型稳健性.利用预处理后的数据集在 3D卷积神经网络模型上做训练和测试,得到模型损失值曲线图和混淆矩阵.将屈服应力模型预测结果进行分析,又引入卷积注意力机制嵌入到卷积神经网络实现模型优化,并对模型参数进行调整,模型预测平均准确率从 93.26%提升至 98.19%,论证了基于 3D卷积神经网络的膏体屈服应力预测方法可行性.经图像增强处理的数据集应用到各模型中,模型预测平均准确率均提升 3%以上.相比传统膏体流变测量方式,解决了传统膏体屈服应力测量操作复杂、外部因素扰动大、工程现场难以开展等问题. |
| Abstract_FL | The rheological properties of paste are the foundation of the paste-filling process in metal mines,and paste yield stress is an important evaluation index for paste-filling technology.The change in ratio and concentration has a significant impact on the texture and appearance of paste slurry.Herein,a method for predicting the paste yield stress using three-dimensional convolutional neural networks(3D CNNs)is proposed through the development of image acquisition standards and an image acquisition device to collect image data sets based on a paste image data set.The Sobel operator is used to realize the pretreatment of paste edge detection and full size shrinking,and the paste image data set is obtained.The ten-fold cross-validation method is used to divide the data set to avoid accidental errors caused by a single random division.Based on the paste image-yield stress data set,the 3D CNNs model is used to extract the depth features and timing information on the paste.An image enhancement strategy for the histogram equalization algorithm is introduced to reduce the interference of environmental factors.The preprocessed data set is used for training and testing the 3D CNNs network model.In addition,the prediction accuracy of the yield stress model is analyzed:the convolutional attention block module is embedded into the CNN to optimize the model,and the introduction of channel attention and spatial attention enhances the ability of the model to perceive important areas in the image,which helps improve its ability to capture important information in the image and adjust the model parameters.The prediction accuracy of the model is increased from 93.26%to 98.19%,and the sample prediction error is within 20%,demonstrating the feasibility of paste yield stress prediction based on 3D CNNs.The image enhancement strategy using the histogram equalization algorithm can significantly improve the prediction accuracy of paste yield stress.The image enhancement strategy is applied to each model experiment,and the model prediction accuracy is improved by more than 3 percentage points.The developed image acquisition device and image acquisition standard can reduce the disturbance of environmental factors on image recognition and ensure the accuracy of paste yield stress prediction.Compared with the traditional paste rheological measurement method,the proposed method solves the problems of complex operation of traditional paste yield stress measurement,strong interference of external factors,and the difficulties associated with engineering sites. |
| Author | 李在利 吴顺川 姜关照 程海勇 刘泽民 孙伟 刘伟铧 毛明发 |
| AuthorAffiliation | 昆明理工大学国土资源工程学院,昆明 650093%云南驰宏锌锗股份有限公司会泽矿业公司,曲靖 654211%中铝集团玉溪矿业有限公司,玉溪 653100 |
| AuthorAffiliation_xml | – name: 昆明理工大学国土资源工程学院,昆明 650093%云南驰宏锌锗股份有限公司会泽矿业公司,曲靖 654211%中铝集团玉溪矿业有限公司,玉溪 653100 |
| Author_FL | LI Zaili LIU Weihua WU Shunchuan JIANG Guanzhao CHENG Haiyong LIU Zemin SUN Wei MAO Mingfa |
| Author_FL_xml | – sequence: 1 fullname: LIU Zemin – sequence: 2 fullname: CHENG Haiyong – sequence: 3 fullname: MAO Mingfa – sequence: 4 fullname: LI Zaili – sequence: 5 fullname: WU Shunchuan – sequence: 6 fullname: JIANG Guanzhao – sequence: 7 fullname: SUN Wei – sequence: 8 fullname: LIU Weihua |
| Author_xml | – sequence: 1 fullname: 刘泽民 – sequence: 2 fullname: 程海勇 – sequence: 3 fullname: 毛明发 – sequence: 4 fullname: 李在利 – sequence: 5 fullname: 吴顺川 – sequence: 6 fullname: 姜关照 – sequence: 7 fullname: 孙伟 – sequence: 8 fullname: 刘伟铧 |
| BookMark | eNo9j89Kw0AYxPdQwVr7HOIh8dv9spvsUepfKHjRc8lmE2mULbiIfYAiotQietKiIIhH8SBCSt-m6epb2KJ4moHfMMMskYrpmJSQFQo-RQyDtdxvW2sYSO5JjKTPgKE_p9QH4BVS_UeLpG5tWwGnGFLJoEp4-VRMimvcKPuf7vXNvTy60cCNb9xo6O57X-eDyfi2fL-YDvtlcVdePnw_96YfV8tkIYuPbVr_0xo52Nrcb-x4zb3t3cZ607MUAuplIuUoYhaxUCYq0VEyNzFVjGlFFcRIeZai0lSkMmQQKdQcZ0EutGAiwBpZ_e09i00Wm8NW3jk9MbPFlsqPct3tqtnXACIAij9j8V86 |
| ClassificationCodes | TD853 |
| ContentType | Journal Article |
| Copyright | Copyright © Wanfang Data Co. Ltd. All Rights Reserved. |
| Copyright_xml | – notice: Copyright © Wanfang Data Co. Ltd. All Rights Reserved. |
| DBID | 2B. 4A8 92I 93N PSX TCJ |
| DOI | 10.13374/j.issn2095-9389.2023.10.11.005 |
| DatabaseName | Wanfang Data Journals - Hong Kong WANFANG Data Centre Wanfang Data Journals 万方数据期刊 - 香港版 China Online Journals (COJ) China Online Journals (COJ) |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| DocumentTitle_FL | Prediction of paste yield stress based on three-dimensional convolutional neural networks |
| EndPage | 1348 |
| ExternalDocumentID | bjkjdxxb202408001 |
| GrantInformation_xml | – fundername: (国家自然科学基金); (云南省重大科技项目); (云南省基础研究计划项目) funderid: (国家自然科学基金); (云南省重大科技项目); (云南省基础研究计划项目) |
| GroupedDBID | -0C -SC -S~ 2B. 2RA 4A8 5VR 92I 92M 93N 9D9 9DC AAITT AFUIB ALMA_UNASSIGNED_HOLDINGS CAJEC CQIGP FA0 GROUPED_DOAJ JUIAU PB1 PB6 PSX Q-- Q-2 R-C RT3 T8S TCJ U1F U5C |
| ID | FETCH-LOGICAL-s1041-f6e536a28279cbcd8c279ca1b22db1b0a315fe3bd16e97208b3d53bcd56d62643 |
| ISSN | 2095-9389 |
| IngestDate | Thu May 29 04:07:32 EDT 2025 |
| IsPeerReviewed | false |
| IsScholarly | true |
| Issue | 8 |
| Keywords | paste backfill 膏体充填 rheology 3D convolutional neural networks 预测 yield stress prediction 流变性能 屈服应力 3D卷积神经网络 |
| Language | Chinese |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-s1041-f6e536a28279cbcd8c279ca1b22db1b0a315fe3bd16e97208b3d53bcd56d62643 |
| PageCount | 12 |
| ParticipantIDs | wanfang_journals_bjkjdxxb202408001 |
| PublicationCentury | 2000 |
| PublicationDate | 2024-07-01 |
| PublicationDateYYYYMMDD | 2024-07-01 |
| PublicationDate_xml | – month: 07 year: 2024 text: 2024-07-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationTitle | 工程科学学报 |
| PublicationTitle_FL | Chinese Journal of Engineering |
| PublicationYear | 2024 |
| Publisher | 昆明理工大学国土资源工程学院,昆明 650093%云南驰宏锌锗股份有限公司会泽矿业公司,曲靖 654211%中铝集团玉溪矿业有限公司,玉溪 653100 |
| Publisher_xml | – name: 昆明理工大学国土资源工程学院,昆明 650093%云南驰宏锌锗股份有限公司会泽矿业公司,曲靖 654211%中铝集团玉溪矿业有限公司,玉溪 653100 |
| SSID | ssib051371920 ssib023167159 ssj0003313525 ssib022319478 ssib041261352 ssib036435564 |
| Score | 2.3961344 |
| Snippet | TD853; 膏体流变性能是膏体充填技术重要指标,是金属矿膏体充填工艺流程的重要工程参数.本文提出一种基于 3D卷积神经网络的膏体屈服应力预测方法,通过制定图像采集标准并研... |
| SourceID | wanfang |
| SourceType | Aggregation Database |
| StartPage | 1337 |
| Title | 基于3D卷积神经网络的膏体屈服应力预测 |
| URI | https://d.wanfangdata.com.cn/periodical/bjkjdxxb202408001 |
| Volume | 46 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVAON databaseName: DOAJ Directory of Open Access Journals issn: 2095-9389 databaseCode: DOA dateStart: 20230101 customDbUrl: isFulltext: true dateEnd: 99991231 titleUrlDefault: https://www.doaj.org/ omitProxy: true ssIdentifier: ssj0003313525 providerName: Directory of Open Access Journals |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnR1NaxQxdCgVxIsoKn5TxOCh7DpJJjPJcbI7SxH01EJvZbM7o1SoYFsoPRcRpRbRkxYFQTyKBxFa-m-6Xf0XvvcmOzuyRaqwDI_k5X2GyXuzyUsQ3HYFj12sZCNyOmxEKiwaxpluQxQ914X4KA9DPJx8_0E8txDdW1SLU9OHtV1L62uu2ds89lzJ_3gV2sCveEr2HzxbEYUGgMG_8AQPw_NEPmaZYqbDbMqyCJ86k21s021mE5YlLIVfhwBAzBCwlmlqsW1muG8xLQQMEIhYppmOCSciHIkELWdasyxGTE0sgJuJiBcAlmWGpYKGx8xCo60HvYRPMqAkQN962VAAxdI2S-MaECPNVI2mAjHRzBB_K1EoBEJm-BilokvsUXkUgo1XWewBUxhCAVo6I5TOH1Sgp-17QFGgWLJOTf3biIiqfbTlbB5RjGukQbeQWirNQb0Ida4rDNLYtucGfgTTo-1KI6ZI4RjDVcMNM2R00ZoUYBYiYirgpfzMKC0NrjMJ-cqgAZFWRq426Ezd8gDiABXBUk7Drbc5Ot94xqVwGii0vCGtJuQWzqOxpxKaoOVs0tQ1McorAFwEEQch41m84QxXWeVHgtLYJ7EbAeutCwDYANiA1VE4slyaHsf4BAqI1iQpEAX_nhqvmCLEi0dleSfVaHn3X7jL15iurdVcluWGfNzHZVnydSKmALSIggrkUbFownyTTYo5mmGoxuFUtcnVLT9e7m9sOEFlBEM8ZHpKQOwR1j78wKoH8Tk3taJ6AmtT1JIMCTmDqlV0iriAEFxVSYniMuGjK-cw_pQSu3HvdiXs6eDOSJO7f9eDzi6uFN2Vh7Uwe_5ccNbnxzNp-bI7H0xtProQqMHHvcO9V7I92P4x_PJ1-PnDcH9nePB6uL87fLf189nO4cGbwbfnR7vbg723gxfvf33aOvr-8mKw0MnmW3MNf99LY5WDWo0izpWMu0KLxPQcFi1BoMudEH3HXdiVXBW5dH0e5yYRoXayryQgqrgfQ2InLwXTK09W8svBjOGQ-RR5kuTORd3cuD5kcloWicP6nGHvSnDLq7nk3-erSxP-unoSpGvBmfGb53owvfZ0Pb8Becqau0lu_g1f99nn |
| linkProvider | Directory of Open Access Journals |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=%E5%9F%BA%E4%BA%8E3D%E5%8D%B7%E7%A7%AF%E7%A5%9E%E7%BB%8F%E7%BD%91%E7%BB%9C%E7%9A%84%E8%86%8F%E4%BD%93%E5%B1%88%E6%9C%8D%E5%BA%94%E5%8A%9B%E9%A2%84%E6%B5%8B&rft.jtitle=%E5%B7%A5%E7%A8%8B%E7%A7%91%E5%AD%A6%E5%AD%A6%E6%8A%A5&rft.au=%E5%88%98%E6%B3%BD%E6%B0%91&rft.au=%E7%A8%8B%E6%B5%B7%E5%8B%87&rft.au=%E6%AF%9B%E6%98%8E%E5%8F%91&rft.au=%E6%9D%8E%E5%9C%A8%E5%88%A9&rft.date=2024-07-01&rft.pub=%E6%98%86%E6%98%8E%E7%90%86%E5%B7%A5%E5%A4%A7%E5%AD%A6%E5%9B%BD%E5%9C%9F%E8%B5%84%E6%BA%90%E5%B7%A5%E7%A8%8B%E5%AD%A6%E9%99%A2%2C%E6%98%86%E6%98%8E+650093%25%E4%BA%91%E5%8D%97%E9%A9%B0%E5%AE%8F%E9%94%8C%E9%94%97%E8%82%A1%E4%BB%BD%E6%9C%89%E9%99%90%E5%85%AC%E5%8F%B8%E4%BC%9A%E6%B3%BD%E7%9F%BF%E4%B8%9A%E5%85%AC%E5%8F%B8%2C%E6%9B%B2%E9%9D%96+654211%25%E4%B8%AD%E9%93%9D%E9%9B%86%E5%9B%A2%E7%8E%89%E6%BA%AA%E7%9F%BF%E4%B8%9A%E6%9C%89%E9%99%90%E5%85%AC%E5%8F%B8%2C%E7%8E%89%E6%BA%AA+653100&rft.issn=2095-9389&rft.volume=46&rft.issue=8&rft.spage=1337&rft.epage=1348&rft_id=info:doi/10.13374%2Fj.issn2095-9389.2023.10.11.005&rft.externalDocID=bjkjdxxb202408001 |
| thumbnail_s | http://utb.summon.serialssolutions.com/2.0.0/image/custom?url=http%3A%2F%2Fwww.wanfangdata.com.cn%2Fimages%2FPeriodicalImages%2Fbjkjdxxb%2Fbjkjdxxb.jpg |