An attention-based long short-term memory prediction model for working conditions of copper electrolytic plates

Abstract

Copper is an important resource of non-ferrous metals. Electrolytic refining is one of the main methods to produce fine copper. In electrolytic process, plate conditions seriously affects the output and quality of copper. Timely and accurate prediction of the working condition of the plate is of great significance to the copper electrolytic refining process. Aiming at the problems of the traditional plate conditions detection algorithm with large lag, poor anti-interference ability and low accuracy, this paper proposes a plate condition prediction model based on LSTM with attention mechanism. The average gray value of the plate in the infrared image is used to characterize the plate working condition. In hidden layer, double layer LSTM network is used to improve the effect of model training. A unique attention mechanism is added to learn the correlation between input and output better and improve the accuracy of model prediction. Experimental results show that the accuracy of the proposed model for plate condition prediction reaches 95.11%. Compared with the commonly used LSTM algorithm, the plate condition prediction model proposed in this paper has stronger prediction ability.

High accuracy key feature extraction approach for the non-stationary signals measurement based on NGO-VMD noise reduction and CNN-LSTM

“…Lei et al [24] designed an end-to-end LSTM-based model to learn key feature information directly from multivariate time series data. However, LSTM is based only on time series; it mainly focuses on the variations and relationships of features in time series and is prone to ignoring other possible spatial features [25].…”