Working condition recogition of fused magnesium furnace based on stochastic configuration networks and reinforcement learning

Abstract

Abstract Automatic and accurate detection of abnormal working conditions of fused magnesia furnace is of great significance to the safe and reliable production of fused magnesia. Aiming at the defects of manual judgment of abnormal working conditions in the production process of fused magnesium furnace and the existing recogition method of abnormal working conditions based on machine learning. This paper proposes a working condition recogition model of fused magnesium furnace based on stochastic configuration networks and reinforcement learning. Firstly, a hybrid data augmentation method of generative and non-generative is used to obtain high-quality sample data with salient features. Secondly, based on ResNeXt, multi-scale local features are extracted under the condition of limited parameter quantity by controlling the cardinality. Combining the mixed attention and weighted bidirectional feature pyramid mechanism, the extracted local feature maps of different scales are cross-scale fused and focused, and more differentiated detailed feature information of the region of interest is retained. Thirdly, based on Transformer, the multi-modal working condition recognition network of fused magnesium furnace is constructed, and the global correlation between adjacent local features is improved in the spatial dimension. Send the fused complete features to the SCNs to establish a classification criterion for abnormal working conditions of the fused magnesium furnace with generalization ability and global approximation ability. Finally, reinforcement learning is used to evaluate the credibility of uncertain recognition results of samples in real time, and a self-optimizing adjustment action strategy at the Transformer encoding layer is defined. Build a Transformer model library with different encoding layer to adapt to the completely different feature extraction requirements of multi-modal 1 working samples. The experimental results show that the method in this paper has better recognition accuracy and generalization ability than other algorithms.