Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Zhifu Lin has a total of 4 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Physics-Embedded Deep Learning to Predict Real-Time Flow Parameters in Complex Thermodynamic Machinery

    by Zhifu Lin, Dasheng Xiao, Hong Xiao

    Flow through complex thermodynamic machinery is intricate, incorporating turbulence, compressibility effects, combustion, and solid–fluid interactions, posing a challenge to classical physics. For example, it is not currently possible to simulate a three-dimensional full-field gas flow through the propulsion of an aircraft. In this study, a new approach is presented for predicting the real-time fluid properties of complex flow. This perspective is obtained from deep learning, but it is significant in that the physical context is embedded within the deep learning architecture. Cases of excessive working states are analyzed to validate the effectiveness of the given architecture, and the results align with the experimental data. This study introduces a new and appealing method for predicting real-time fluid properties using complex thermomechanical systems.


  • Open Access

    Thrust Prediction of Aircraft Engine Enabled by Fusing Domain Knowledge and Neural Network Model

    by Zhifu Lin, Hong Xiao, Xiaobo Zhang, Zhanxue Wang

    Accurate prediction of aircraft engine thrust is crucial for engine health management (EHM), which seeks to improve the safety and reliability of aircraft propulsion. Thrust prediction is implemented using an on-board adaptive model for EHM. However, the conventional methods for building such a model are often tedious or overly data-dependent. To improve the accuracy of thrust prediction, domain knowledge can be leveraged. Hence, this study presents a strategy for building an on-board adaptive model that can predict aircraft engine thrust in real-time. The strategy combines engine knowledge and neural network architecture to construct a prediction model. The whole-model architecture is divided into separate modules that are mapped in a one-to-one form using a domain decomposition approach. The engine domain knowledge is used to guide feature selection and the neural network architecture design in the method. Furthermore, this study explains the relationships between aircraft engine features and how the model can predict engine thrust in flight condition. To demonstrate the effectiveness and robustness of the architecture, four different testing datasets were used for validation. The results show that the thrust prediction model created by the given architecture has maximum relative deviations below 4.0% and average relative deviations below 2.0% on all testing datasets. In comparison to the performance of the models created by conventional neural network architecture on the four testing datasets, the model created by the presented architecture proves more suitable for aircraft propulsion.