JYJinghui Yang

Jinghui Yang

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Jinghui Yang has a total of 8 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • A Multiphase Dual Attention-Based LSTM Neural Network for Industrial Product Quality Prediction

    by Zhengyang Dong, Yifeng Pan, Jinghui Yang, Jun Xie, Jianzhong Fu, Peng Zhao

    Quality prediction plays an essential role in industrial process monitoring and optimization. However, the existed methods lack of the ability to extract features in multiphase and nonlinear time series data. To improve the quality prediction accuracy and simultaneously provide some suggestion of the process mechanism, this article proposes a phased dual-attention long short-term memory (PDA-LSTM) neural network, which consists of a phase segmentation module and a prediction module. The whole series data are first divided into phases in the phase segmentation module, and individual models are subsequently constructed for each phase in the prediction module to capture distinct patterns. The LSTM network with input and temporal attention mechanism is utilized to select the most relevant variables and time steps throughout the time sequence. The proposed method is verified with a numerical example and a real injection molding process. Compared with the existed methods, the PDA-LSTM method has the advantages of higher prediction accuracy and the ability to interpret the key input variable and time points of the process data.


  • Open Access

    Research on the Fused Deposition Modeling of Polyether Ether Ketone

    by Ruoxiang Gao, Jun Xie, Jinghui Yang, Chaojie Zhuo, Jianzhong Fu, Peng Zhao

    As a special engineering polymer, polyether ether ketone (PEEK) has been used widely due to its excellent mechanical properties, high thermal stability, and chemical resistance. Fused deposition modeling (FDM) is a promising process for fabricating PEEK parts. However, due to the semi-crystalline property and high melting point of PEEK, determining appropriate process parameters is important to reduce warpage deformation and improve the mechanical properties of PEEK. In this article, the influence of raster angle and infill density was determined by single factor experiment, which are the two most important parameters. The results showed that samples with 0°/90° raster angle and 50% infill density had the best comprehensive properties in terms of warpage deformation, tensile strength, and specific strength. Subsequently, based on the results above, the effects of printing speed, nozzle temperature, platform temperature, raster width, and layer thickness were analyzed by orthogonal experiment. The results indicated that platform temperature had the greatest impact on warpage deformation while printing speed and nozzle temperature were significant parameters on tensile strength. Through optimization, warpage deformation of the samples could be reduced to almost 0 and tensile strength could increase by 19.6% (from 40.56 to 48.50 MPa). This will support the development of FDM for PEEK.