Browsing by Author "Sun, Xianfang"

Now showing 1 - 3 of 3
  • Thumbnail Image
    ItemOpen Access
    Deep fusion for energy consumption prediction in additive manufacturing
    (Elsevier, 2021-11-26) Hu, Fu; Qin, Jian; Li, Yixin; Liu, Ying; Sun, Xianfang
    Owing to the increasing trend of additive manufacturing (AM) technologies being employed in the manufacturing industry, the issue of AM energy consumption attracts attention in both industry and academia. The energy consumption of AM systems is affected by various factors. These factors involve features with different dimensions and structures which are hard to tackle in the analysis. In this work, a data fusion approach is proposed for energy consumption prediction based on CNN-LSTM (convolutional neural network and long short-term memory) model. A case study was conducted on an SLS system by using the proposed methodology, achieving the RMSE of 8.143 Wh/g in prediction.
  • Thumbnail Image
    ItemOpen Access
    Feature-level data fusion for energy consumption analytics in additive manufacturing
    (IEEE, 2020-10-08) Hu, Fu; Liu, Ying; Qin, Jian; Sun, Xianfang; Witherell, Paul
    The issue of Additive Manufacturing (AM) energy consumption is attracting attention in both industry and academia, particularly with the trending adoption of AM technologies in the manufacturing industry. It is crucial to analyze, understand, and manage the energy consumption of AM for better efficiency and sustainability. The energy consumption of AM systems is related to various correlated attributes in different phases of an AM process. Existing studies focus mainly on analyzing the impacts of different processing and material attributes, while factors related to design and working environment have not received the same amount of attention. Such factors involve features with various dimensions and nested structures that are difficult to handle in the analysis. To tackle these issues, a feature-level data fusion approach is proposed to integrate heterogeneous data to build an AM energy consumption model to uncover energy-relevant information and knowledge. A case study using real-world data collected from a selective laser sintering (SLS) system is presented to validate the proposed approach, and the results indicate that the fusion strategy achieves better performances on energy consumption prediction than the individual ones. Based on the analysis of feature importance, the design-relevant features are found to have significant impacts on AM energy consumption.
  • Thumbnail Image
    ItemOpen Access
    Task-driven data fusion for additive manufacturing: framework, approaches, and case studies
    (Elsevier, 2023-07-01) Hu, Fu; Liu, Ying; Li, Yixin; Ma, Shuai; Qin, Jian; Song, Jun; Sun, Xianfang; Tang, Qian
    Additive manufacturing (AM) has been envisioned as a critical technology for the next industrial revolution. Due to the advances in data sensing and collection technologies, a large amount of data, generated from multiple sources in AM production, becomes available for relevant analytics to improve process reliability, repeatability, and part quality. However, AM processes occur over a wide range of spatial and temporal scales where the data generally involves different types, dimensions and structures, leading to difficulties when integrating and then analysing. Hence, in what way and how to integrate the heterogeneous data or merge the spatial and temporal information lead to significant challenges in data analytics for AM systems. This paper proposed a task-driven data fusion framework that enables the integration of heterogeneous data from different sources and modalities based on tasks to support decision-making activities. In this framework, the data analytics activities involved in the task are identified in the first place. Then, the data required for the task is identified, collected, and characterised. Finally, data fusion techniques are employed and applied based on the characteristics of the data for integration to support data analytics. The fusion techniques that best fit the task requirements are selected as the final fusion approach. Case studies on different research directions of AM, including AM energy consumption prediction, mechanical properties prediction of additively manufactured lattice structures, and investigation of remelting process on part density, were carried out to demonstrate the feasibility and effectiveness of the proposed framework and approaches.