Xueping Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Xueping Liu has a total of 23 co-authors. Here are the top co-authors by number of shared publications:
- Peihao Tang
Division of Advanced Manufacturing, Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen 518055, China
4 shared publications - Peng Mou
Department of Mechanical Engineering, Tsinghua University, Beijing 100084, China
4 shared publications - Xuanlin Wang
Division of Advanced Manufacturing, Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen 518055, China
4 shared publications - Zhen Li
Division of Advanced Manufacturing, Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen 518055, China
3 shared publications - Long Zeng
Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China
2 shared publications - Cong Tai
Department of Advanced Manufacturing, Shenzhen International Graduate School, Tsinghua University, Shenzhen, China
1 shared publication
Latest Publications
- Open Access
- 15 August 2025
- Published by MDPI AG in Journal of Manufacturing and Materials Processing
- Vol. 9 (8) , 281
A Real-Time Anomaly Detection Model of Nomex Honeycomb Composites Disc Tool
Nomex honeycomb composites (NHCs) are highly sensitive to the abnormal wear state of disc tools during cutting, leading to poor product quality. This paper proposes a real-time anomaly detection method combining a novel CNN–GRU–Attention (CGA) deep learning model with an Exponentially Weighted Moving Average (EWMA) control chart to monitor sensor data from the disc tool. The CGA model integrates an improved CNN layer to extract multidimensional local features, a GRU layer to capture long-term temporal dependencies, and a multi-head attention mechanism to highlight key information and reduce error accumulation. Trained solely on normal operation data to address the scarcity of abnormal samples, the model predicts cutting force time series with an RMSE of 0.5012, MAE of 0.3942, and R2 of 0.9128, outperforming mainstream time series data prediction models. The EWMA control chart applied to the prediction residuals detects abnormal tool wear trends promptly and accurately. Experiments on real NHC cutting datasets demonstrate that the proposed method effectively identifies abnormal machining conditions, enabling timely tool replacement and significantly enhancing product quality assurance.
- 15 August 2025
- Published by MDPI AG in Journal of Manufacturing and Materials Processing
- Vol. 9 (8) , 281
Open AccessA Real-Time Anomaly Detection Model of Nomex Honeycomb Composites Disc Tool
Nomex honeycomb composites (NHCs) are highly sensitive to the abnormal wear state of disc tools during cutting, leading to poor product quality. This paper proposes a real-time anomaly detection method combining a novel CNN–GRU–Attention (CGA) deep learning model with an Exponentially Weighted Moving Average (EWMA) control chart to monitor sensor data from the disc tool. The CGA model integrates an improved CNN layer to extract multidimensional local features, a GRU layer to capture long-term temporal dependencies, and a multi-head attention mechanism to highlight key information and reduce error accumulation. Trained solely on normal operation data to address the scarcity of abnormal samples, the model predicts cutting force time series with an RMSE of 0.5012, MAE of 0.3942, and R2 of 0.9128, outperforming mainstream time series data prediction models. The EWMA control chart applied to the prediction residuals detects abnormal tool wear trends promptly and accurately. Experiments on real NHC cutting datasets demonstrate that the proposed method effectively identifies abnormal machining conditions, enabling timely tool replacement and significantly enhancing product quality assurance.
- Open Access
- 6 February 2025
- Published by MDPI AG in Sustainability
- Vol. 17 (3) , 1321
PCF-RWKV: Large Language Model for Product Carbon Footprint Estimation
As global climate change intensifies, assessing product carbon footprints serves as a foundational step for quantifying greenhouse gas emissions throughout a product’s lifecycle, forming the basis for achieving sustainability and emission reduction goals. Traditional lifecycle assessment methods face challenges such as subjective boundary definitions and time-consuming inventory construction. This study introduces PCF-RWKV, a novel model based on the RWKV architecture with task-specialized low-rank adaptations (LoRAs). Trained on carbon footprint datasets, the model minimizes memory use and data interference, enabling efficient deployment on consumer-grade GPUs without relying on cloud computing. By integrating multi-agent technology, PCF-RWKV automates the creation of lifecycle inventories and aligns production processes with emission factors to calculate carbon footprints. This approach significantly improves the efficiency and security of corporate carbon footprint assessments, providing a potential alternative to traditional methods.
- 6 February 2025
- Published by MDPI AG in Sustainability
- Vol. 17 (3) , 1321
Open AccessPCF-RWKV: Large Language Model for Product Carbon Footprint Estimation
As global climate change intensifies, assessing product carbon footprints serves as a foundational step for quantifying greenhouse gas emissions throughout a product’s lifecycle, forming the basis for achieving sustainability and emission reduction goals. Traditional lifecycle assessment methods face challenges such as subjective boundary definitions and time-consuming inventory construction. This study introduces PCF-RWKV, a novel model based on the RWKV architecture with task-specialized low-rank adaptations (LoRAs). Trained on carbon footprint datasets, the model minimizes memory use and data interference, enabling efficient deployment on consumer-grade GPUs without relying on cloud computing. By integrating multi-agent technology, PCF-RWKV automates the creation of lifecycle inventories and aligns production processes with emission factors to calculate carbon footprints. This approach significantly improves the efficiency and security of corporate carbon footprint assessments, providing a potential alternative to traditional methods.
- Open Access
Time Series Data Augmentation for Energy Consumption Data Based on Improved TimeGAN
Predicting the time series energy consumption data of manufacturing processes can optimize energy management efficiency and reduce maintenance costs for enterprises. Using deep learning algorithms to establish prediction models for sensor data is an effective approach; however, the performance of these models is significantly influenced by the quantity and quality of the training data. In real production environments, the amount of time series data that can be collected during the manufacturing process is limited, which can lead to a decline in model performance. In this paper, we use an improved TimeGAN model for the augmentation of energy consumption data, which incorporates a multi-head self-attention mechanism layer into the recovery model to enhance prediction accuracy. A hybrid CNN-GRU model is used to predict the energy consumption data from the operational processes of manufacturing equipment. After data augmentation, the prediction model exhibits significant reductions in RMSE and MAE along with an increase in the R2 value. The prediction accuracy of the model is maximized when the amount of generated synthetic data is approximately twice that of the original data.
Open AccessTime Series Data Augmentation for Energy Consumption Data Based on Improved TimeGAN
Predicting the time series energy consumption data of manufacturing processes can optimize energy management efficiency and reduce maintenance costs for enterprises. Using deep learning algorithms to establish prediction models for sensor data is an effective approach; however, the performance of these models is significantly influenced by the quantity and quality of the training data. In real production environments, the amount of time series data that can be collected during the manufacturing process is limited, which can lead to a decline in model performance. In this paper, we use an improved TimeGAN model for the augmentation of energy consumption data, which incorporates a multi-head self-attention mechanism layer into the recovery model to enhance prediction accuracy. A hybrid CNN-GRU model is used to predict the energy consumption data from the operational processes of manufacturing equipment. After data augmentation, the prediction model exhibits significant reductions in RMSE and MAE along with an increase in the R2 value. The prediction accuracy of the model is maximized when the amount of generated synthetic data is approximately twice that of the original data.
- Open Access
- 19 December 2024
- Published by MDPI AG in Preprints.org
PCF-RWKV: Product Carbon Footprint Estimation System Based on Large Language Model
As global climate change intensifies, assessing product carbon footprints has become essential for measuring greenhouse gas emissions throughout a product’s lifecycle, a key factor in achieving sustainable development and emission reduction goals. Traditional lifecycle assessment methods encounter challenges such as subjective product boundary determination and lengthy lifecycle inventory construction. Recent advancements in large language models offer new opportunities for rapid, knowledge-based content generation, yet these models often lack domain-specific training, face data security concerns, and have complex deployment requirements. This study introduces the PCF-RWKV model, which utilizes the RWKV architecture with multiple stacked residual blocks and three task-specialized Low-Rank Adaptations (LoRAs). Trained on a carbon footprint assessment-specific dataset using low-rank adaptive techniques, the model minimizes data interference and memory waste, enabling efficient deployment on consumer-grade single GPUs without relying on cloud storage.By integrating Multi-Agents technology, PCF-RWKV automates the construction of LCI for production processes, aligns production processes with emission factors to calculate carbon footprints, thereby enhancing the efficiency and security of enterprise carbon footprint evaluations and addressing the limitations of traditional methods.
- 19 December 2024
- Published by MDPI AG in Preprints.org
Open AccessPCF-RWKV: Product Carbon Footprint Estimation System Based on Large Language Model
As global climate change intensifies, assessing product carbon footprints has become essential for measuring greenhouse gas emissions throughout a product’s lifecycle, a key factor in achieving sustainable development and emission reduction goals. Traditional lifecycle assessment methods encounter challenges such as subjective product boundary determination and lengthy lifecycle inventory construction. Recent advancements in large language models offer new opportunities for rapid, knowledge-based content generation, yet these models often lack domain-specific training, face data security concerns, and have complex deployment requirements. This study introduces the PCF-RWKV model, which utilizes the RWKV architecture with multiple stacked residual blocks and three task-specialized Low-Rank Adaptations (LoRAs). Trained on a carbon footprint assessment-specific dataset using low-rank adaptive techniques, the model minimizes data interference and memory waste, enabling efficient deployment on consumer-grade single GPUs without relying on cloud storage.By integrating Multi-Agents technology, PCF-RWKV automates the construction of LCI for production processes, aligns production processes with emission factors to calculate carbon footprints, thereby enhancing the efficiency and security of enterprise carbon footprint evaluations and addressing the limitations of traditional methods.
- Open Access
- 22 October 2024
- Published by Springer Nature in Heritage Science
- Vol. 12 (1) , 1-20
An algorithm based on multi-branch feature cross fusion for archaeological illustration of murals
Archaeological illustration is a graphic recording technique that delineates the shape, structure, and ornamentation of cultural artifacts using lines, serving as vital material in archaeological work and scholarly research. Aiming at the problems of low line accuracy in the results of current mainstream image generation algorithms and interference caused by severe mural damage, this paper proposes a mural archaeological illustration generation algorithm based on multi-branch feature cross fusion (U2FGAN). The algorithm optimizes skip connections in U2Net through a channel attention mechanism, constructing a multi-branch generator consisting of a line extractor and an edge detector, which separately identify line features and edge information in artifact images before fusing them to generate accurate, high-resolution illustrations. Additionally, a multi-scale conditional discriminator is incorporated to guide the generator in outputting high-quality illustrations with clear details and intact structures. Experiments conducted on the Dunhuang mural illustration datasets demonstrate that compared to mainstream counterparts, U2FGAN reduced the Mean Absolute Error (MAE) by 10.8% to 26.2%, while also showing substantial improvements in Precision (by 9.8% to 32.3%), Fβ-Score (by 5.1% to 32%), and PSNR (by 0.4 to 2.2 dB). The experimental results show that the proposed method outperforms other mainstream algorithms in archaeological illustration generation.
- 22 October 2024
- Published by Springer Nature in Heritage Science
- Vol. 12 (1) , 1-20
Open AccessAn algorithm based on multi-branch feature cross fusion for archaeological illustration of murals
Archaeological illustration is a graphic recording technique that delineates the shape, structure, and ornamentation of cultural artifacts using lines, serving as vital material in archaeological work and scholarly research. Aiming at the problems of low line accuracy in the results of current mainstream image generation algorithms and interference caused by severe mural damage, this paper proposes a mural archaeological illustration generation algorithm based on multi-branch feature cross fusion (U2FGAN). The algorithm optimizes skip connections in U2Net through a channel attention mechanism, constructing a multi-branch generator consisting of a line extractor and an edge detector, which separately identify line features and edge information in artifact images before fusing them to generate accurate, high-resolution illustrations. Additionally, a multi-scale conditional discriminator is incorporated to guide the generator in outputting high-quality illustrations with clear details and intact structures. Experiments conducted on the Dunhuang mural illustration datasets demonstrate that compared to mainstream counterparts, U2FGAN reduced the Mean Absolute Error (MAE) by 10.8% to 26.2%, while also showing substantial improvements in Precision (by 9.8% to 32.3%), Fβ-Score (by 5.1% to 32%), and PSNR (by 0.4 to 2.2 dB). The experimental results show that the proposed method outperforms other mainstream algorithms in archaeological illustration generation.
- 4 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 9 (5) , 4099-4105
FusedNet: End-to-End Mobile Robot Relocalization in Dynamic Large-Scale Scene
To improve robot relocalization accuracy in both static and dynamic environments, we introduce a novel network, FusedNet, which incorporates a cross-attention to fuse global and local image features for end-to-end relocalization. This approach relies solely on a monocular camera sensor that is fixed on the mobile robot, and directly predicts the absolute pose from the input RGB image. Additionally, we have collected a mobile robot relocalization dataset, termed moBotReloc, consisting of dynamic large-scale scenes, using the Unity 3D simulation platform and a real mobile robot. Through extensive experiments on 7Scenes and moBotReloc, we demonstrate that FusedNet achieves significant accuracy in 6-DoF camera relocalization in static scenes, and exhibits superior relocalization performance in dynamic large-scale scenes for mobile robot applications, outperforming existing end-to-end methods that rely solely on a single global or local feature.
- 4 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 9 (5) , 4099-4105
FusedNet: End-to-End Mobile Robot Relocalization in Dynamic Large-Scale Scene
To improve robot relocalization accuracy in both static and dynamic environments, we introduce a novel network, FusedNet, which incorporates a cross-attention to fuse global and local image features for end-to-end relocalization. This approach relies solely on a monocular camera sensor that is fixed on the mobile robot, and directly predicts the absolute pose from the input RGB image. Additionally, we have collected a mobile robot relocalization dataset, termed moBotReloc, consisting of dynamic large-scale scenes, using the Unity 3D simulation platform and a real mobile robot. Through extensive experiments on 7Scenes and moBotReloc, we demonstrate that FusedNet achieves significant accuracy in 6-DoF camera relocalization in static scenes, and exhibits superior relocalization performance in dynamic large-scale scenes for mobile robot applications, outperforming existing end-to-end methods that rely solely on a single global or local feature.
- Open Access
- 1 September 2021
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 2029 (1) , 012001
A flexible control system for reconfigurable assembly lines
With the rising demand for customized and frequently updated products, the current assembly systems require a higher level of reconfigurability and flexibility. Thus we proposed a scheme of reconfigurable assembly line and hierarchical control system. To increase the flexibility of control systems, a communication method and control strategy is presented in this paper. This approach will endow the reconfigurable assembly system with flexibility by encapsulating the ladder diagram program and providing an external interface for the control software to call. This approach is validated with one assembly unit assembling shuttle valve, which takes 40s during the process. The control system can not only monitor the assembling process, but also control the action of the actuator via control panel or control commands.
- 1 September 2021
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 2029 (1) , 012001
Open AccessA flexible control system for reconfigurable assembly lines
With the rising demand for customized and frequently updated products, the current assembly systems require a higher level of reconfigurability and flexibility. Thus we proposed a scheme of reconfigurable assembly line and hierarchical control system. To increase the flexibility of control systems, a communication method and control strategy is presented in this paper. This approach will endow the reconfigurable assembly system with flexibility by encapsulating the ladder diagram program and providing an external interface for the control software to call. This approach is validated with one assembly unit assembling shuttle valve, which takes 40s during the process. The control system can not only monitor the assembling process, but also control the action of the actuator via control panel or control commands.
- 25 November 2015
- Published by Springer Nature in Journal of Applied Phycology
- Vol. 28 (3) , 1579-1588
Selection of optimal flocculant for effective harvesting of the fucoxanthin-rich marine microalga Isochrysis galbana
- 25 November 2015
- Published by Springer Nature in Journal of Applied Phycology
- Vol. 28 (3) , 1579-1588
Selection of optimal flocculant for effective harvesting of the fucoxanthin-rich marine microalga Isochrysis galbana