丁伟 / Ding Wei

丁伟 / Ding Wei

Huaibei, Anhui, China

Posts by Collection

notes

Teaching experience 1

Published:

This is a description of a teaching experience. You can use markdown like any other post.

portfolio

publications

Dynamic evolutionary model based on a multi-sampling inherited HAPFNN for an aluminium electrolysis manufacturing system

Published in Applied Soft Computing, 2021

文章简介：针对铝电解制造系统具有多参数、动态时变、过程数据非高斯分布等复杂特性，构建了一种基于多采样继承的混合退火粒子滤波神经网络MSI-HAPFNN动态自适应模型。

Recommended citation: Ding W, Yao L*, Li Y, et al. (2021). "Dynamic evolutionary model based on a multi-sampling inherited HAPFNN for an aluminium electrolysis manufacturing system." Applied Soft Computing. 99: 106925.
Download Paper | Download Slides

Incremental learning model based on an improved CKS-PFNN for aluminium electrolysis manufacturing

Published in Neural Computing and Applications, 2021

文章简介：针对滤波神经网络易受到非高斯噪声的影响，而导致滤波精度低的问题，提出了一种将改进聚类核函数平滑技术与粒子滤波神经网络相结合的新型ICKS-PFNN模型构建算法。

Recommended citation: Ding W, Yao L*, Li Y, et al. (2021). "Incremental learning model based on an improved CKS-PFNN for aluminium electrolysis manufacturing." Neural Computing and Applications. 34(3): 2083-2102.
Download Paper | Download Slides

A multiobjective prediction model with incremental learning ability by developing a multi-source filter neural network for the electrolytic aluminium process

Published in Applied Intelligence, 2022

文章简介：为提高电解铝工艺过程中电流效率和降低能耗，提出了一种基于多源滤波神经网络MSFNN的多目标增量学习框架，并适用于复杂的噪声环境。

Recommended citation: Yao L, Ding W*, He T, et al. (2022). "A multiobjective prediction model with incremental learning ability by developing a multi-source filter neural network for the electrolytic aluminium process." Applied Intelligence. 52: 17387–17409.
Download Paper | Download Slides

基于多层次LSTM网络的多智能体攻防效能动态预测模型

Published in 兵工学报, 2022

文章简介：本文针对多智能体攻防体系作战效能预测过程中动态性差、准确性低和可解释性弱的问题，构建了一种基于多层次长短时记忆LSTM神经网络的多智能体攻防效能动态预测模型。

Recommended citation: 丁伟, 明振军*, 王国新, 等. (2023). "基于多层次LSTM网络的多智能体攻防效能动态预测模型." 兵工学报. 44(01): 176-192.
Download Paper | Download Slides | Download Bibtex

基于正向解析式和多目标博弈优化算法的复杂装备体系优化设计方法

Published in 兵工学报, 2023

文章简介：针对时空众包的动态复杂性而导致的收敛性差、动态响应慢、动作稀疏等问题，提出了一种基于无效动作掩蔽的改进近端策略优化IAM-IPPO算法，用于时空众包体系的智能设计，实现端到端的模型训练和动态方案输出。

Recommended citation: 丁伟, 明振军*, 王国新, 等. (2024). "基于正向解析式和多目标博弈优化算法的复杂装备体系优化设计方法." 兵工学报. 45(06): 1974-1990.
Download Paper | Download Slides | Download Bibtex

System-of-systems approach to spatio-temporal crowdsourcing design using improved PPO algorithm based on an invalid action

Published in Knowledge-Based Systems, 2024

文章简介：针对时空众包的动态复杂性而导致的收敛性差、动态响应慢、动作稀疏等问题，提出了一种基于无效动作掩蔽的改进近端策略优化IAM-IPPO算法，用于时空众包体系的智能设计，实现端到端的模型训练和动态方案输出。

Recommended citation: Ding W, Ming Z*, Wang G, Yan Y. (2024). "System-of-systems approach to spatio-temporal crowdsourcing design using improved PPO algorithm based on an invalid action." Knowledge-Based Systems. 285: 111381.
Download Paper | Download Slides | Download Bibtex

Maritime unmanned rescue system-of-systems design based on Attention Transformer

Published in 2024 IEEE International Conference on Unmanned Systems (ICUS), 2025

文章简介：在海上无人救援体系设计过程中，由于多层级耦合、出现不规律等特点，常常面临机理无法解释、建模不准确等问题，提出了一种基于注意力转换器的海上无人救援体系设计方法。

Recommended citation: Ding W, Ming Z*, Wang G, et al. (2025). "A multiobjective prediction model with incremental learning ability by developing a multi-source filter neural network for the electrolytic aluminium process." 2024 IEEE International Conference on Unmanned Systems (ICUS). Nanjing, China, pp. 732-737.
Download Paper

talks

teaching

Teaching experience 1

Undergraduate course, University 1, Department, 2014

This is a description of a teaching experience. You can use markdown like any other post.

Teaching experience 2

Workshop, University 1, Department, 2015

This is a description of a teaching experience. You can use markdown like any other post.