Author name cluster

Qiqiang Li

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.

3 papers

1 author row

EAAI Journal 2025 Journal Article

A novel local enhanced channel self-attention based on Transformer for industrial remaining useful life prediction

Zhizheng Zhang
Wen Song
Qiong Wu
Wenxu Sun
Qiqiang Li
Lei Jia

Remaining useful life (RUL) prediction is a foundational technique for predictive maintenance (PdM) and is critical to ensuring the reliability and safety of complex industrial machines. Recently, while advanced deep learning architectures like recurrent neural network (RNN), convolutional neural network (CNN) and self-attention (SA) have been widely used for RUL prediction, existing methods still face difficulties in simultaneously processing global long-term dependencies and local contextual information of sequence units as well as the spatial correlations of industrial multi-sensors. In this article, we propose local enhanced channel self-attention based on Transformer (LECformer), a novel deep RUL prediction method to overcome these issues. LECformer can more effectively capture the long-term dependencies by Transformer architecture compared with RNN/CNN-based methods. Moreover, LECformer proposes a novel local enhanced channel self-attention (LECSA) mechanism to replace the traditional SA of vanilla Transformer, which can adaptively extract both long-term dependencies and local contextual information, while dynamically weighting the importance of different channels to improve predictive performance. Two widely used turbofan engine datasets and a bearing dataset are applied to validate the effectiveness of the proposed method. Experimental results show that the LECformer significantly outperforms the state-of-the-art RUL prediction methods.

Details DOI

EAAI Journal 2023 Journal Article

Container stacking optimization based on Deep Reinforcement Learning

Xin Jin
Zhentang Duan
Wen Song
Qiqiang Li

Cargo storage is one of the key aspects of the maritime transportation. As the prior site planning, container stacking has a critical influence on the operation efficiency of the storage yard. To store a group of containers in a certain number of stacks with capacity constraints in order, we propose a self-attention based Deep Reinforcement Learning (DRL) method, which can learn high-quality policy to solve the container stacking problem. We design a Markov Decision Process (MDP) model to simulate the container stacking process and enable the DRL agent to learn to minimize the number of blockages when retrieving the containers. In the proposed DRL model, a novel feature extraction network based on self-attention is utilized to effectively capture the interrelationships between stacks and represent the state of all stacks. Additionally, the size-agnostic policy network enables the agent to have the ability to handle problems of different scales. Through extensive experimental verification, our method significantly outperforms general stacking rules, heuristic-search algorithm and mathematical programming in medium-scale and large-scale problems. Specifically, the proposed DRL method outperforms the optimal existing method by 54% and 80% for medium and large-scale problems, respectively. Moreover, the learned policies exhibit outstanding generalization performance on unseen scenarios with different scales and settings.

Details DOI

EAAI Journal 2023 Journal Article

Instance-specific algorithm configuration via unsupervised deep graph clustering

Wen Song
Yi Liu
Zhiguang Cao
Yaoxin Wu
Qiqiang Li

Instance-specific Algorithm Configuration (AC) methods are effective in automatically generating high-quality algorithm parameters for heterogeneous NP-hard problems from multiple sources. However, existing works rely on manually designed features to describe training instances, which are simple numerical attributes and cannot fully capture structural differences. Targeting at Mixed-Integer Programming (MIP) solvers, this paper proposes a novel instances-specific AC method based on end-to-end deep graph clustering. By representing an MIP instance as a bipartite graph, a random walk algorithm is designed to extract raw features with both numerical and structural information from the instance graph. Then an auto-encoder is designed to learn dense instance embeddings unsupervisedly, which facilitates clustering heterogeneous instances into homogeneous clusters for training instance-specific configurations. Experimental results on multiple benchmarks show that the proposed method can improve the solving efficiency of CPLEX on highly heterogeneous instances, and outperform existing instance specific AC methods.

Details DOI