Author name cluster

Yongfang Xie

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

9 papers

2 author rows

EAAI Journal 2026 Journal Article

Exploring semantic dependency for reasoning over temporal knowledge graph

Hong Yu
Meiqi Chen
Ronghua Tian
Yongfang Xie

Temporal knowledge graph reasoning aims to predict future facts based on given historical ones. When two entities that have had no historical interaction interact with each other, we call a new event occurs. Most existing methods suffer from limitations in predicting new events, as they only focus on direct historical interaction. To this end, we propose a temporal knowledge graph reasoning method by exploring semantic dependencies, abbreviated as SdTKG. It enriches the characterization of entities by capturing and representing potential semantic dependencies between entities with limited historical interactions. First, a potential semantic dependency graph and its encoder are constructed based on temporal path analysis to capture potential dependencies beyond direct historical interactions. Second, the entities with the similar stance to the target entity, which are mined by the potential semantic dependency graph, are used as positive samples; and then, self-supervised negative-free contrastive learning is employed on the positive samples to enhance the representation of potential semantic dependencies. Extensive experiments fully demonstrate that SdTKG is more competitive than ten state-of-the-art models. The mean reciprocal rank (MRR) values of SdTKG for relation prediction and new event prediction exceed those of the best baseline method 6. 47% and 5. 46% on average, respectively. The code is available at: https: //github. com/yuhongcqupt/SdTKG.

Details DOI

AAAI Conference 2026 Conference Paper

MDMLP-EIA: Multi-domain Dynamic MLPs with Energy Invariant Attention for Time Series Forecasting

Hu Zhang
Zhien Dai
Zhaohui Tang
Yongfang Xie

Time series forecasting is essential across diverse domains. While MLP-based methods have gained attention for achieving Transformer-comparable performance with fewer parameters and better robustness, they face critical limitations including loss of weak seasonal signals, capacity constraints in weight-sharing MLPs, and insufficient channel fusion in channel-independent strategies. To address these challenges, we propose MDMLP-EIA (Multi-domain Dynamic MLPs with Energy Invariant Attention) with three key innovations. First, we develop an adaptive fused dual-domain seasonal MLP that categorizes seasonal signals into strong and weak components. It employs an adaptive zero-initialized channel fusion strategy to minimize noise interference while effectively integrating predictions. Second, we introduce an energy invariant attention mechanism that adaptively focuses on different feature channels within trend and seasonal predictions across time steps. This mechanism maintains constant total signal energy to align with the decomposition-prediction-reconstruction framework and enhance robustness against disturbances. Third, we propose a dynamic capacity adjustment mechanism for channel-independent MLPs. This mechanism scales neuron count with the square root of channel count, ensuring sufficient capacity as channels increase. Extensive experiments across nine benchmark datasets demonstrate that MDMLP-EIA achieves state-of-the-art performance in both prediction accuracy and computational efficiency.

PDF Details DOI

IROS Conference 2025 Conference Paper

Hierarchical Decision-Making for Autonomous Navigation: Integrating Deep Reinforcement Learning and Fuzzy Logic in Four-Wheel Independent Steering and Driving Systems

Yizhi Wang
Degang Xu
Yongfang Xie
Shuzhong Tan
Xianan Zhou
Peng Chen

This paper presents a hierarchical decision-making framework for autonomous navigation in four-wheel independent steering and driving (4WISD) systems. The proposed approach integrates deep reinforcement learning (DRL) for high-level navigation with fuzzy logic for low-level control to ensure both task performance and physical feasibility. The DRL agent generates global motion commands, while the fuzzy logic controller enforces kinematic constraints to prevent mechanical strain and wheel slippage. Simulation experiments demonstrate that the proposed framework outperforms traditional navigation methods, offering enhanced training efficiency and stability and mitigating erratic behaviors compared to purely DRL-based solutions. Real-world validations further confirm the framework’s ability to navigate safely and effectively in dynamic industrial settings. Overall, this work provides a scalable and reliable solution for deploying 4WISD mobile robots in complex, real-world scenarios.

Details

EAAI Journal 2025 Journal Article

Hierarchical multi-scale matched masked autoencoder for industrial multi-rate time series modeling

Changqing Yuan
Yongfang Xie
Shiwen Xie
Jie Wang

In practical industrial processes, due to sensor hardware limitations, the sampling rates of different variables often vary, leading to multi-rate time series (MRTS) data. However, the distribution of multi-scale dynamics in MRTS data typically follows a step-like pattern, with intricate scale transitions from fine to coarse and complex scale-consistent dependencies across rates. Additionally, the inherent characteristics of MRTS data often result in label scarcity. Both factors present significant challenges for MRTS modeling. To address these issues, we propose a novel self-supervised learning strategy, called Hierarchical Multi-Scale Matched Masked Autoencoder (H3MAE). Specifically, we design a scale-matching input fusion mechanism where each layer is hierarchically aligned to a specific scale, with the scale-matching integration from two sources, effectively capturing the multi-scale dynamics and cross-rate scale-consistent dependencies in MRTS data. Besides, we introduce a novel auxiliary task that imputes masked positions in the encoded representation space at each layer, aiming to achieve MRTS representation learning and mitigate label scarcity. Furthermore, we propose a unique encoder-imputer structure in each layer to enable multi-scale self-supervised learning while generating temporally aligned features satisfying the input requirements of the next layer. Experimental results on three benchmark datasets and two industrial multi-rate tasks demonstrate that our framework yields better performance in MRTS modeling. The code is publicly available at https: //github. com/monolithycq/H3MAE.

Details DOI

EAAI Journal 2025 Journal Article

Semi-supervised contrastive learning for flotation process monitoring with uncertainty-aware prototype optimization

Mingxi Ai
Jin Zhang
Peng Li
Jiande Wu
Zhaohui Tang
Yongfang Xie

Froth flotation is a widely employed mineral beneficiation technique, and effective process monitoring is critical for optimizing mineral separation. However, in the industrial process, labeling froth images to create large labeled datasets is both expensive and time-consuming. Semi-supervised deep learning offers a promising solution, but leveraging unlabeled data remains a significant challenge. To this aim, we propose an uncertainty-aware semi-supervised contrastive learning method. Our approach employs a pseudo-labeling module with dropout to generate pseudo labels and estimate uncertainty. Based on the uncertainty scores, the pseudo-labeled data are split into reliable and unreliable sets. A semi-supervised contrastive learning module is developed to exploit pseudo-label information and learn class-aware representations from the reliable set. Additionally, a dynamically weighted consistency learning module is introduced to explore potential classification information in the unreliable data while preventing the model from being misled by low-confidence predictions. Comparison experiments on industrial zinc flotation data show our method achieves 88. 12% classification accuracy, surpassing the best alternative by a margin of 5. 11%. These results demonstrate that our method generalizes well to unseen test data and outperforms state-of-the-art methods.

Details DOI

EAAI Journal 2025 Journal Article

Unknown fault incremental learning based on shapelet prototypical network for streaming industrial signals

Xiaoxue Wan
Lihui Cen
Xiaofang Chen
Yongfang Xie
Zhaohui Zeng

Unknown faults represent faults that have never occurred before, they are constantly emerging due to the changing environments and operations in industrial processes. It is a challenge for existing fault diagnosis methods to continually detect unknown faults and effectively classify known faults in streaming industrial signals. This article proposes an unknown fault incremental learning method for streaming industrial signals. In this work, shapelet prototypical embedding combined with a memory distance matrix is employed to embed streaming industrial signals into a discriminative feature space. Therefore, the category information in the signals can be extracted and is not limited by the size of the sliding window. Besides, a new training paradigm based on meta-learning by sampling simulated-incremental tasks is proposed to obtain generalizable shapelets. Moreover, based on the new training paradigm, the meta-discovery module is proposed to continually detect unknown faults, and the meta-calibrate module can calibrate all prototypes into a distinguishable space. Experiments on the simulated streaming time series, benchmark Tennessee Eastman process, and real-world aluminum electrolysis process illustrate the superiority of the proposed method in terms of accuracy and interpretability. The code is available in https: //github. com/XiaoxueWan/UFIL. git.

Details DOI

EAAI Journal 2024 Journal Article

Development of data-knowledge-driven predictive model and multi-objective optimization for intelligent optimal control of aluminum electrolysis process

Jie Wang
Yongfang Xie
Shiwen Xie
Xiaofang Chen

Operational optimization of the Hall-Héroult cell is essential for achieving high efficiency and cost-effectiveness in the aluminum electrolysis process. Due to the complicated mechanism and variable working conditions, manual operational decision-making is extensively used in practice. They challenge the reliable and optimal operation of aluminum electrolysis process. In this paper, we develop a data-knowledge-driven decision-making support system (DMSS) to achieve operational optimization for the aluminum electrolysis process. DMSS consists of a prediction model, a multi-objective optimizer, and a knowledge-guided decision-making module. Specifically, we propose a working-conditions-based attention with the exogeneous inputs auto-regressive neural network (WCA-NARX) to construct a data-driven heat balance indicator (HBI) prediction model, where the working condition-related variables serve as covariates to enhance predictability. In addition, the designed structure of introducing working condition information through an attention mechanism can decouple covariates from operational variables and autoregressive variables, facilitating subsequent operational optimization. Then, a novel knowledge-assigned reference vector evolutionary algorithm (KRVEA) is designed to solve the multi-objective optimization problem of the aluminum electrolysis process, in which Pareto front solutions can be solved in the preferred region. Finally, we utilize the knowledge base that stores historical optimization cases to make decisions regarding the selection of a practical-requirement-based control scheme from the Pareto set. Real-world industrial experiments demonstrate that DMSS can effectively enhance control performance and achieve superior results compared to other competitive methods. The source code is available at https: //github. com/wjiecsu/WCA-NARX.

Details DOI

EAAI Journal 2024 Journal Article

Unsupervised heat balance indicator construction based on variational autoencoder and its application to aluminum electrolysis process monitoring

Jie Wang
Shiwen Xie
Yongfang Xie
Xiaofang Chen

Heat balance plays a significant role in reflecting the health state of aluminum electrolysis process (AEP). However, current methods hardly take into consideration the quantitative Heat Balance Indicator (HBI) construction by using the unlabeled data. In addition, it is limited to construct HBI by learning the complex relationship between degraded features and large-scale HBI labels in a supervised manner, because the labeled data are scarce and annotations are expensive in practice. To quantitatively construct HBI by using the unlabeled data, this paper proposes an unsupervised HBI construction method based on variational autoencoder (VAE). Firstly, we propose fuzzy evaluation strategy to estimate the tendency of cell temperature to highlight the trend of heat balance. Rather than simply using the latent features, we extract the feature representation of the heat balance state considering not only the latent features but also the reconstruction error. Finally, HBI is constructed by calculating the distance between the features representation of normal heat balance and degraded state. The applications of heat balance monitoring in a real-world aluminum electrolysis plant are performed to verify its effectiveness. The experimental results demonstrate that our proposed HBI construction method can better represent heat balance state of AEP, the average fault detection rate can achieve 80% for the monitoring electrolytic cells, increasing by more than 3% compared with these traditional monitoring statistics.

Details DOI

EAAI Journal 2023 Journal Article

A dynamic spatial distributed information clustering method for aluminum electrolysis cell

Yubo Sun
Weihua Gui
Xiaofang Chen
Yongfang Xie
Shiwen Xie
Zhong Zou

Distributed anode current (DAC) is a high-dimensional spatial-distributed signal that can be measured online in the industrial aluminum electrolysis process. The difference of physicochemical properties in different spatial regions in an aluminum electrolysis cell can be obtained by spatial clustering analysis of DAC data. In this study, a dynamic spatial distributed information clustering method (DSDIC) for aluminum electrolysis cell is proposed. This method can effectively capture the complex dynamic spatio-temporal correlations in DAC. Firstly, the dynamic graph is identified to capture the complex dynamicity of the DAC. Then, the anode-spatial structure information (ASSI) extends the one-dimensional current signal generated by each carbon anode into a feature matrix to achieve the fusion of data and spatial structure knowledge. Finally, the adjacency matrix of dynamic graph performs low-pass filtering on the feature matrix to obtain low-frequency information that is beneficial to downstream learning tasks. Meanwhile, a fixed graph structure based on process mechanism knowledge is designed to capture the spatial correlation caused by external periodic operations in industrial process. The experimental results on the actual industrial aluminum electrolysis datasets show that our method improves the clustering accuracy by 3. 96% compared with existing clustering methods.

Details DOI