刘泽民, 程海勇, 毛明发, 李在利, 吴顺川, 姜关照, 孙伟, 刘伟铧. 基于机器视觉的膏体屈服应力预测研究[J]. 工程科学学报. DOI: 10.13374/j.issn2095-9389.2023.10.11.005
引用本文: 刘泽民, 程海勇, 毛明发, 李在利, 吴顺川, 姜关照, 孙伟, 刘伟铧. 基于机器视觉的膏体屈服应力预测研究[J]. 工程科学学报. DOI: 10.13374/j.issn2095-9389.2023.10.11.005
Prediction of paste yield stress using 3D convolutional neural networks[J]. Chinese Journal of Engineering. DOI: 10.13374/j.issn2095-9389.2023.10.11.005
Citation: Prediction of paste yield stress using 3D convolutional neural networks[J]. Chinese Journal of Engineering. DOI: 10.13374/j.issn2095-9389.2023.10.11.005

基于机器视觉的膏体屈服应力预测研究

Prediction of paste yield stress using 3D convolutional neural networks

  • 摘要: 膏体流变性能是金属矿膏体充填工艺流程的工程需求响应的基础,是膏体充填技术重要指标。本文提出一种基于机器视觉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,以膏体图像数据集为基础,采用3D CNNs网络模型提取膏体深度特征和时序信息,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,将屈服应力数值与图像信息对应标注,利用预处理后的数据集在3D CNNs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。又将3D CNNs网络模型进行优化,模型预测准确率从93.47%提升至98.54%,论证了基于机器视觉的膏体屈服应力预测可行性。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: The rheological property of paste is the foundation of the paste-filling process in metal mines and an important index in paste-filling technology. In this paper, a method of predicting the paste yield stress using machine vision 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 3D convolutional neural networks (3D CNNs) network 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, and the yield stress value corresponds to the image information. The preprocessed data set is used for training and testing the 3D CNNs network model. Additionally, the 3D CNNs network model is optimized, and the prediction accuracy of the model is increased from 93.47% to 98.54%, demonstrating the feasibility of paste yield stress prediction based on machine vision. Compared with the traditional paste rheological measurement method, it solves the problems of complex operation of traditional paste yield stress measurement, strong interference of external factors, and the difficulties associated with engineering sites.

     

/

返回文章
返回