Author name cluster

Wenli Du

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

AAAI Conference 2026 Conference Paper

From Text to Simulation: A Multi-Agent LLM Workflow for Automated Chemical Process Design

Xufei Tian
Wenli Du
Shaoyi Yang
Han Hu
Hui Xin
Shifeng Qu
Ke Ye

Process simulation is a critical cornerstone of chemical engineering design. Current automated chemical design methodologies focus mainly on various representations of process flow diagrams. However, transforming these diagrams into executable simulation flowsheets remains a time-consuming and labor-intensive endeavor, requiring extensive manual parameter configuration within simulation software. In this work, we propose a novel multi-agent workflow that leverages the semantic understanding capabilities of large language models(LLMs) and enables iterative interactions with chemical process simulation software, achieving end-to-end automated simulation from textual process specifications to computationally validated software configurations for design enhancement. Our approach integrates four specialized agents responsible for task understanding, topology generation, parameter configuration, and evaluation analysis, respectively, coupled with Enhanced Monte Carlo Tree Search to accurately interpret semantics and robustly generate configurations. Evaluated on Simona, a large-scale process description dataset, our method achieves a 31. 1% improvement in the simulation convergence rate compared to state-of-the-art baselines and reduces the design time by 89. 0% compared to the expert manual design. This work demonstrates the potential of AI-assisted chemical process design, which bridges the gap between conceptual design and practical implementation. Our workflow is applicable to diverse process-oriented industries, including pharmaceuticals, petrochemicals, food processing, and manufacturing, offering a generalizable solution for automated process design.

PDF Details DOI

EAAI Journal 2025 Journal Article

A high-accuracy deep learning framework for digital twin model development of actual chemical processes

Yue Li
Zhongmei Li
Jingzheng Ren
Wenli Du
Weifeng Shen

The development of intelligent chemical industry urgently calls for high-accuracy digital twin modeling methods of actual chemical processes. However, although intelligent technologies such as deep learning are utilized, digital twin modeling is challenged by the complexity and nonlinearity of actual chemical processes, leading to unexpected deviations and poor generalization. To provide a valuable modeling methodology in this field, a novel deep learning framework based on chemical process mechanisms is developed. According to the properties of different neural networks, the framework is designed in a hierarchical way to learn the underlying process mechanisms and deal with the nonlinearity of actual chemical processes. Thus, a digital twin model of the actual chemical process can be developed, which is high-accuracy and good-generalization. Based on the sensor data from the distributed control system of an actual industrial distillation process, the proposed deep learning digital twin modeling framework is verified by thoroughgoing and careful analyses, including the modeling test, ablation experiment and residue distribution analysis of model results. Compared with wide-spread baseline models, the new framework decreases the predicting mean absolute error by 45. 6 % and increases the coefficient of determination by 13. 8 % on average. This intelligent framework reveals desirable application potentials that it can create a high-fidelity digital twin of actual chemical processes. Such digital representation acts as a basic model, which can support advanced manufacturing tasks such as real-time optimization by detailed digital inference. This work provides an intelligent digital twin modeling methodology in chemical engineering and facilitates the development of intelligent chemical industry.

Details DOI

EAAI Journal 2024 Journal Article

A truncated Gaussian distribution based multi-scale segment-wise fusion transformer model for multi-step commodity price forecasting

Xin Peng
Zhengxiang Chen
Jiale Zhang
Zhi Li
Wenli Du

Accurately forecasting commodity price trends is crucial for producers, market participants, and related enterprises to make informed decisions regarding production planning and scheduling. However, achieving high accuracy in multi-step forecasting poses significant challenges due to the unique financial characteristics inherent in commodities. Thus, this paper proposes a novel truncated Gaussian distribution based multi-scale segment-wise fusion Transformer for multi-step commodity price forecasting. First, a multi-scale segment-wise fusion module, which capture the time dependencies from different time granularity, is designed to describe the time-varying trend characteristics of commodity prices. Second, considering the characteristics of price range fluctuation and truncation, a truncated Gaussian distribution is introduced to describe price uncertainty. Last, to evaluate the proposed method’s effectiveness, extensive experiments are conducted using real data on energy chemical product prices. The experimental results demonstrate that the proposed method accurately captures price change trends and effectively estimates price uncertainty. Compared to the widely adopted Autoformer, our approach achieves approximately 30% reductions in both root mean square error (RMSE) and mean absolute error (MAE) metrics. Additionally, it exhibits certain advantages over the current state-of-the-art (SOTA). In the 20-step and 60-step multi-step prediction tasks, the proposed method achieves RMSE values of 91. 18 and 142. 94, respectively, surpassing the current SOTA. The introduced research framework provides valuable insights for decision-makers engaged in analyzing and forecasting commodity markets. The code is available on https: //github. com/dean-ob/TGD-MSSF.

Details DOI

ICML Conference 2024 Conference Paper

Differentiable Distributionally Robust Optimization Layers

Xutao Ma
Chao Ning 0002
Wenli Du

In recent years, there has been a growing research interest in decision-focused learning, which embeds optimization problems as a layer in learning pipelines and demonstrates a superior performance than the prediction-focused approach. However, for distributionally robust optimization (DRO), a popular paradigm for decision-making under uncertainty, it is still unknown how to embed it as a layer, i. e. , how to differentiate decisions with respect to an ambiguity set. In this paper, we develop such differentiable DRO layers for generic mixed-integer DRO problems with parameterized second-order conic ambiguity sets and discuss its extension to Wasserstein ambiguity sets. To differentiate the mixed-integer decisions, we propose a novel dual-view methodology by handling continuous and discrete parts of decisions via different principles. Specifically, we construct a differentiable energy-based surrogate to implement the dual-view methodology and use importance sampling to estimate its gradient. We further prove that such a surrogate enjoys the asymptotic convergency under regularization. As an application of the proposed differentiable DRO layers, we develop a novel decision-focused learning pipeline for contextual distributionally robust decision-making tasks and compare it with the prediction-focused approach in experiments

Details

EAAI Journal 2023 Journal Article

DFSGAN: Introducing editable and representative attributes for few-shot image generation

Mengping Yang
Saisai Niu
Zhe Wang
Dongdong Li
Wenli Du

Training generative adversarial networks (GANs) usually requires large-scale data and massive computation resources. The performance of GANs plummets when given limited data due to the discriminator overfitting, thus providing meaningless feedback to the generator during the adversarial training. Existing few-shot GANs are primarily concerned with transferring knowledge from models that have been pre-trained on large-scale datasets or using data augmentation to expand the training sets. However, previous methods consistently take latent codes sampled from a single distribution as the generator’s input. We contend that more complicated latent codes can provide the generator with more editable attributes. In this paper, we propose DFSGAN for few-shot image generation, which takes dynamic Gaussian mixture (DGM) latent codes as the generator’s input. Our DFSGAN can select the Gaussian components of the latent codes quantitatively. We also design two techniques to strengthen the representative ability of intermediate features of the generating process to improve the fidelity and maintain the content and layout information of the synthesized images. Our DGM and intermediate representation enhancement techniques complement each other and improve synthesis quality. We conduct extensive experiments on 15 few-shot datasets with different resolutions spanning from art paintings to realistic photos. Qualitative and quantitative results demonstrate the superiority and effectiveness of our model.

Details DOI

IS Journal 2022 Journal Article

Heterogeneous Federated Meta-Learning With Mutually Constrained Propagation

Ziqiu Chi
Zhe Wang
Wenli Du

Federated learning is a popular framework that guarantees privacy security. Thereinto, heterogeneity is a challenging barrier. We propose a meta-based federated method with mutually constrained propagation (2MFed) method to cope with this. First, 2MFed gives each client the right to choose the most appropriate model from server-side parallel models as its local model, which tolerates hardware heterogeneity. Second, the server mutually exchanges the information of parallel models under the consistency and disparity constraints to improve robustness, thus eliminating data heterogeneity. Third, we use the power of the meta-based label propagation algorithm to treat the federated training as the federated few-shot problem, which removes the model heterogeneity. Finally, extensive experiments confirm the effectiveness of the proposed method. In addition, we evaluate the proposed method on few-shot tasks and demonstrate its excellent performance further.

Details DOI

JBHI Journal 2021 Journal Article

FLDNet: Frame-Level Distilling Neural Network for EEG Emotion Recognition

Zhe Wang
Tianhao Gu
Yiwen Zhu
Dongdong Li
Hai Yang
Wenli Du

Based on the current research on EEG emotion recognition, there are some limitations, such as hand-engineered features, redundant and meaningless signal frames and the loss of frame-to-frame correlation. In this paper, a novel deep learning framework is proposed, named the frame-level distilling neural network (FLDNet), for learning distilled features from the correlations of different frames. A layer named the frame gate is designed to integrate weighted semantic information on multiple frames to remove redundant and meaningless signal frames. A triple-net structure is introduced to distill the learned features net by net to replace the hand-engineered features with professional knowledge. Specifically, one neural network is normally trained for several epochs. Then, a second network of the same structure will be initialized again to learn the extracted features from the frame gate of the first neural network based on the output of the first net. Similarly, the third net improves the features based on the frame gate of the second network. To utilize the representation ability of the triple neural network, an ensemble layer is conducted to integrate the discriminative ability of the proposed framework for final decisions. Consequently, the proposed FLDNet provides an effective method for capturing the correlation between different frames and automatically learn distilled high-level features for emotion recognition. The experiments are carried out in a subject-independent emotion recognition task on public emotion datasets of DEAP and DREAMER benchmarks, which have demonstrated the effectiveness and robustness of the proposed FLDNet.

Details DOI

EAAI Journal 2021 Journal Article

Unsupervised cycle optimization learning for single-view depth and camera pose with Kalman filter

Tianhao Gu
Zhe Wang
Ziqiu Chi
Yiwen Zhu
Wenli Du

This paper presents a general cycle optimization framework with a Kalman filter (KF) module for single-view depth prediction and camera pose estimation. The framework designs a KF module based on measurement noise estimated from networks without supervision to reduce the noise of pose parameters and optimizes the DepthNet architecture to add a new upconvolutional module and a decoder structure to overcome the gradient locality and adjust the mode of multi-task coupling. All modules are integrated to construct a cycle optimization strategy as the core of this paper for overall performance improvement. Experimental results on the KITTI dataset show that the cycle optimization framework greatly improves the performance of the original framework and is better than other improvements on the same original framework; single-view depth prediction and camera pose estimation achieve state-of-the-art performance compared with existing methods under the same or comparable structure.

Details DOI

EAAI Journal 2020 Journal Article

Multiple Universum Empirical Kernel Learning

Zhe Wang
Sisi Hong
Lijuan Yao
Dongdong Li
Wenli Du
Jing Zhang

This paper proposes a novel framework called Multiple Universum Empirical Kernel Learning (MUEKL) that combines the Universum learning with Multiple Empirical Kernel Learning (MEKL) for the first time to inherit the advantages of both techniques. The proposed MUEKL not only obtained supplementary information of multiple feature spaces through MEKL, but also obtained priori information of samples by Universum learning. MUEKL incorporates a novel method, Imbalanced Modified Universum (IMU), to generate more efficient Universum samples by introducing the imbalanced ratio of data. MUEKL develops the basic multiple kernel learning framework by introducing a regularization of Universum data. The function of the introduced regularization is to adjust the classifier boundary closer to the Universum data to alleviate the influence of the imbalanced data. Moreover, MUEKL performs excellent generalization for both the imbalanced and balanced problems. Extensive experiments verify the effectiveness of the MUEKL and IMU.

Details DOI