A general super-resolution reconstruction strategy was proposed for turbulent velocity fields using a generative adversarial network-based artificial intelligence framework. Two advanced neural networks, i.e., super-resolution generative adversarial network (SRGAN) and enhanced-SRGAN (ESRGAN), were first applied in fluid mechanics to augment the spatial resolution of turbulent flow. As a validation, the flow around a single-cylinder and a more complicated wake flow behind two side-by-side cylinders were experimentally measured using particle image velocimetry. The spatial resolution of the coarse flow field can be successfully augmented by 42 and 82 times with remarkable accuracy. The reconstruction performances of SRGAN and ESRGAN were comprehensively investigated and compared, including an analysis of the recovered instantaneous flow field, statistical flow quantities, and spatial correlations. The results convincingly demonstrated that both models can reconstruct the high-spatial-resolution flow field accurately even in an intricate flow configuration, and ESRGAN can provide a better reconstruction result than SRGAN in the mean and fluctuation flow field.

The outbreak and continuation of the COVID-19 pandemic has challenged the implementation of physical education theory (PET) curriculums among global colleges and universities. This study aimed to describe the design and students’ evaluation of a blended “Sports Multimedia Courseware Design” course among Chinese university students during the COVID-19 pandemic. Using information communication technologies, a 4-month blended course was developed, which consisted of 36 credits (18-credit online self-learning + 18-credit offline group-learning). A total of 1300 Chinese university students who majored in physical education, completed the blended course from Mar to Jun 2020, among which 238 (69.75% males; 21 ± 1.2 years) were randomly recruited to evaluate the course in terms of three aspects: (1) online self-learning, (2) offline group-learning, and (3) overall learning outcomes. A descriptive analysis was conducted using the IBM SPSS 27.0. Students’ overall positive evaluation supported a successful development and implementation of the blended course. Over 90% of students fulfilled the learning tasks and satisfied with the online learning resources. About 83% of students indicated high levels of autonomous motivation and engagement in online self-learning. Approximately 88% of students showed positive attitudes to the offline group-learning content, while the participation rate (60%) was relatively lower than of the online self-learning. Over 50% of the students indicated self-improvements in diverse aspects after attending the blended course. Blended online and offline pedagogy shows apparent promise in delivering the PET course among Chinese university students during the COVID-19 pandemic. Further application and comprehensive evaluation are warranted in the future.

This paper focuses on the time-resolved turbulent flow reconstruction from discrete point measurements and non-time-resolved (non-TR) particle image velocimetry (PIV) measurements using an artificial intelligence framework based on long short-term memory (LSTM). To this end, an LSTM-based proper orthogonal decomposition (POD) model is proposed to establish the relationship between velocity signals and time-varying POD coefficients obtained from non-TR-PIV measurements. An inverted flag flow at Re = 6200 was experimentally measured using TR-PIV at a sampling rate of 2000 Hz for the construction of training and testing datasets and for validation. Two different time-step configurations were employed to investigate the robustness and learning ability of the LSTM-based POD model: a single-time-step structure and a multi-time-step structure. The results demonstrate that the LSTM-based POD model has great potential for time-series reconstruction since it can successfully recover the temporal revolution of POD coefficients with remarkable accuracy, even in high-order POD modes. The time-resolved flow fields can be reconstructed well using coefficients obtained from the proposed model. In addition, a relative error reconstruction analysis was conducted to compare the performance of different time-step configurations further, and the results demonstrated that the POD model with multi-time-step structure provided better reconstruction of the flow fields.