Effective fault detection techniques can help flotation plant reduce reagents consumption,increase mineral recovery,and reduce labor intensity.Traditional,online fault detection methods during flotation processes have...Effective fault detection techniques can help flotation plant reduce reagents consumption,increase mineral recovery,and reduce labor intensity.Traditional,online fault detection methods during flotation processes have concentrated on extracting a specific froth feature for segmentation,like color,shape,size and texture,always leading to undesirable accuracy and efficiency since the same segmentation algorithm could not be applied to every case.In this work,a new integrated method based on convolution neural network(CNN)combined with transfer learning approach and support vector machine(SVM)is proposed to automatically recognize the flotation condition.To be more specific,CNN function as a trainable feature extractor to process the froth images and SVM is used as a recognizer to implement fault detection.As compared with the existed recognition methods,it turns out that the CNN-SVM model can automatically retrieve features from the raw froth images and perform fault detection with high accuracy.Hence,a CNN-SVM based,real-time flotation monitoring system is proposed for application in an antimony flotation plant in China.展开更多
图嵌入降维算法由于其有效性被广泛应用。传统图嵌入算法构造K-Nearest Neighbors(K-NN)图的计算复杂度至少为O(n^(2)d),其中n为样本数,d为样本维度。在数据量大的情况下,构造K-NN图将非常耗时,因为其计算复杂度与样本数的平方成正比,...图嵌入降维算法由于其有效性被广泛应用。传统图嵌入算法构造K-Nearest Neighbors(K-NN)图的计算复杂度至少为O(n^(2)d),其中n为样本数,d为样本维度。在数据量大的情况下,构造K-NN图将非常耗时,因为其计算复杂度与样本数的平方成正比,这将限制图嵌入算法在大规模数据集上的应用。为降低构图过程的计算复杂度,提出一种基于锚点的快速无监督图嵌入算法(Fast Unsupervised Graph Embedding Based on Anchors,FUGE)。该算法首先从数据集中选取锚点(代表点),然后构造数据点-锚点相似度图,最后执行图嵌入分析。由于锚点数量远小于数据量,所提方法能有效地降低构图过程的计算复杂度;不同于使用核函数来构造相似度图,该算法直接通过数据点的近邻信息来学习数据点-锚点的相似度图,这进一步加快了构图过程。整个算法的计算复杂度为O(nd^(2)+nmd),其中m为锚点数。在基准数据集上的大量实验证明了所提算法的有效性和高效性。展开更多
基金Projects(61621062,61563015)supported by the National Natural Science Foundation of ChinaProject(2016zzts056)supported by the Central South University Graduate Independent Exploration Innovation Program,China
文摘Effective fault detection techniques can help flotation plant reduce reagents consumption,increase mineral recovery,and reduce labor intensity.Traditional,online fault detection methods during flotation processes have concentrated on extracting a specific froth feature for segmentation,like color,shape,size and texture,always leading to undesirable accuracy and efficiency since the same segmentation algorithm could not be applied to every case.In this work,a new integrated method based on convolution neural network(CNN)combined with transfer learning approach and support vector machine(SVM)is proposed to automatically recognize the flotation condition.To be more specific,CNN function as a trainable feature extractor to process the froth images and SVM is used as a recognizer to implement fault detection.As compared with the existed recognition methods,it turns out that the CNN-SVM model can automatically retrieve features from the raw froth images and perform fault detection with high accuracy.Hence,a CNN-SVM based,real-time flotation monitoring system is proposed for application in an antimony flotation plant in China.
文摘图嵌入降维算法由于其有效性被广泛应用。传统图嵌入算法构造K-Nearest Neighbors(K-NN)图的计算复杂度至少为O(n^(2)d),其中n为样本数,d为样本维度。在数据量大的情况下,构造K-NN图将非常耗时,因为其计算复杂度与样本数的平方成正比,这将限制图嵌入算法在大规模数据集上的应用。为降低构图过程的计算复杂度,提出一种基于锚点的快速无监督图嵌入算法(Fast Unsupervised Graph Embedding Based on Anchors,FUGE)。该算法首先从数据集中选取锚点(代表点),然后构造数据点-锚点相似度图,最后执行图嵌入分析。由于锚点数量远小于数据量,所提方法能有效地降低构图过程的计算复杂度;不同于使用核函数来构造相似度图,该算法直接通过数据点的近邻信息来学习数据点-锚点的相似度图,这进一步加快了构图过程。整个算法的计算复杂度为O(nd^(2)+nmd),其中m为锚点数。在基准数据集上的大量实验证明了所提算法的有效性和高效性。
