Accurate grade prediction is conducive to proper flotation operation or control. Different from grade monitoring, grade prediction needs to obtain the target grade in advance. However, there is usually a time delay between the flotation cell and the predicted grade in froth flotation. This time delay makes it difficult to match the features of the observed flotation cell with the predicted grade. To solve this problem, this article studies the method of zinc tailings grade prediction using encoder-decoder models. The proposed model considers the feature time series of the first rougher and the previously measured tailings grades. First, according to the sample ratio between froth video and X-ray fluorescence (XRF) analyser, the feature time series of the first rougher can be automatically extracted by finding the nearest available feature vectors. Next, the feature time series of the first rougher is fed into the encoder to generate a context vector, and then the context vector and previously measured grades are sent into the decoder to predict the current tailings grade. The proposed model effectively captures the dynamic consistency between the feature time series and previously measured grades. The effectiveness of the proposed model in the froth flotation has been verified by experiments. Compared with the traditional recurrent neural network (RNN)-based models, the root mean squared error (RMSE) and mean absolute percentage error (MAPE) of the proposed model decrease by about 17.8% and 1.9%. respectively, and the R-squared (R²) score of the proposed model increases by about 13.8%.

准确的品位预测有利于正确的浮选操作或控制。与品位监测不同，品位预测需要提前获得目标品位。然而，浮选槽与泡沫浮选预测品位之间通常存在时间延迟。这种时间延迟使得很难将观察到的浮选槽的特征与预测的品位相匹配。为了解决这个问题，本文研究了使用编​​码器-解码器模型进行锌尾矿品位预测的方法。所提出的模型考虑了第一粗矿和先前测量的尾矿品位的特征时间序列。首先，根据泡沫视频和X射线荧光（XRF）分析仪之间的样本比例，通过寻找最近的可用特征向量来自动提取第一个粗糙的特征时间序列。接下来，将第一个粗矿的特征时间序列输入编码器生成上下文向量，然后将上下文向量和先前测量的品位发送到解码器中以预测当前尾矿品位。所提出的模型有效地捕获了特征时间序列与先前测量的等级之间的动态一致性。实验验证了该模型在泡沫浮选中的有效性。与传统的基于循环神经网络（RNN）的模型相比，所提出模型的均方根误差（RMSE）和平均绝对百分比误差（MAPE）分别降低了约17.8%和1.9%。和 R 平方 (R 然后将上下文向量和先前测量的品位发送到解码器中以预测当前的尾矿品位。所提出的模型有效地捕获了特征时间序列与先前测量的等级之间的动态一致性。实验验证了该模型在泡沫浮选中的有效性。与传统的基于循环神经网络（RNN）的模型相比，所提出模型的均方根误差（RMSE）和平均绝对百分比误差（MAPE）分别降低了约17.8%和1.9%。和 R 平方 (R 然后将上下文向量和先前测量的品位发送到解码器中以预测当前的尾矿品位。所提出的模型有效地捕获了特征时间序列与先前测量的等级之间的动态一致性。实验验证了该模型在泡沫浮选中的有效性。与传统的基于循环神经网络（RNN）的模型相比，所提出模型的均方根误差（RMSE）和平均绝对百分比误差（MAPE）分别降低了约17.8%和1.9%。和 R 平方 (R 实验验证了该模型在泡沫浮选中的有效性。与传统的基于循环神经网络（RNN）的模型相比，所提出模型的均方根误差（RMSE）和平均绝对百分比误差（MAPE）分别降低了约17.8%和1.9%。和 R 平方 (R 实验验证了该模型在泡沫浮选中的有效性。与传统的基于循环神经网络 (RNN) 的模型相比，所提出模型的均方根误差 (RMSE) 和平均绝对百分比误差 (MAPE) 分别降低了约 17.8% 和 1.9%。和 R 平方 (R²）所提出模型的得分提高了约13.8%。