Interpretable Recognition of Fused Magnesium Furnace Working Conditions with Deep Convolutional Stochastic Configuration Networks

TL;DR

This paper tackles the challenge of generalization and interpretability in recognizing fused magnesium furnace working conditions. It introduces an interpretable recognition framework based on deep convolutional stochastic configuration networks (DCSCNs) that generate Gaussian differential convolution kernels under supervision, build the network incrementally, and employ CAM with a channel-independence interpretability metric. An RL-based adaptive pruning mechanism using a joint reward balances accuracy, interpretability, and model size, ensuring a compact, high-performing network. Experimental results on factory data show strong test accuracy ($92.57\%$) and superior interpretability with reduced parameter counts compared to baselines, demonstrating practical potential for real-time fault detection in industrial furnaces.

Abstract

To address the issues of a weak generalization capability and interpretability in working condition recognition model of a fused magnesium furnace, this paper proposes an interpretable working condition recognition method based on deep convolutional stochastic configuration networks (DCSCNs). Firstly, a supervised learning mechanism is employed to generate physically meaningful Gaussian differential convolution kernels. An incremental method is utilized to construct a DCSCNs model, ensuring the convergence of recognition errors in a hierarchical manner and avoiding the iterative optimization process of convolutional kernel parameters using the widely used backpropagation algorithm. The independent coefficient of channel feature maps is defined to obtain the visualization results of feature class activation maps for the fused magnesium furnace. A joint reward function is constructed based on the recognition accuracy, the interpretable trustworthiness evaluation metrics, and the model parameter quantity. Reinforcement learning (RL) is applied to adaptively prune the convolutional kernels of the DCSCNs model, aiming to build a compact, highly performed and interpretable network. The experimental results demonstrate that the proposed method outperforms the other deep learning approaches in terms of recognition accuracy and interpretability.

Figures (16)

• Figure 1: Structure of interpretable fused magnesium furnace working condition recognition model based on deep convolutional stochastic configuration networks.
• Figure 2: Deep convolutional stochastic configuration network structure diagram.
• Figure 3: Schematic diagram of the class activation mapping based on feature map independence scores.
• Figure 4: Structure of convolutional kernel adaptive pruning based on feature map independence.
• Figure 5: Results after image data enhancement for normal working conditions.