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

2025-01-06

AI Summary

To address poor generalizability and limited interpretability in molten magnesium furnace operating-condition identification, this paper proposes an interpretable recognition method based on Deep Convolutional Stochastic Configuration Networks (DCSCN). Methodologically, it innovatively introduces a physics-guided, supervised Gaussian derivative convolution kernel generation mechanism; constructs a hierarchical error-convergent, incremental, non-iterative modeling framework; and designs channel-wise feature independence coefficients to enable visualization of condition activation maps. Furthermore, a joint reward function—integrating accuracy, confidence, and parameter count—is formulated to drive reinforcement learning-based adaptive channel-level pruning. Experimental results demonstrate that the proposed approach significantly outperforms mainstream deep learning models in identification accuracy, model compactness, and quantitative interpretability evaluation capability.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Stochastic Optimization
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

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.

Problem

• Magnesium Smelting Furnace
• Model Adaptability
• State Recognition

Innovation

• DCSCNs
• Reinforcement Learning Optimization
• Interpretable Deep Learning