Recently, a research team led by Dr. Xue Dong, Associate Professor of China-UK Low Carbon College of Shanghai Jiao Tong University, published a paper called "100 kHz CH2O imaging realized by lower speed planar laser induced fluorescence and deep learning" in Optics Express. The first author is Wei Zhang, a PhD student at LCC, and the corresponding author is Dr. Xue Dong. The work is a product of research collaborations between Shanghai Jiao Tong University, University of Adelaide in Australia, Southern University of Science and Technology in China, and Lund University in Sweden.
Recent development of laser diagnostic techniques enables the visualization of combustion products with high spatio-temporal resolution. For example, Planar laser-induced fluorescence (PLIF) adopting the burst-mode laser with prolonged sequence, has been reported to be successful in capturing the distribution of CH2O with various ultra-high frequencies. Previous works have demonstrated the advantages of PLIF in non-instructive, high spatio-temporal resolution and high precision. But to achieve a consecutive high-speed PLIF diagnostic, a complicated laser imaging system is always needed. Its delicate operation and high experimental cost constrain the implementation of this high-speed imaging technique. Moreover, the frequency of laser imaging system has been another limitation of PLIF application.
This paper reports an approach to interpolate PLIF images of CH2O between consecutive experimental data by means of computational imaging realized with convolutional neural network (CNN). Such a deep learning based method can achieve a higher temporal resolution for 2D visualization of intermediate species in combustion based on high-speed experimental images. The capability of the model was tested for generating 100 kHz PLIF images by interpolating single and multiple PLIF frames into the sequences of experimental images of lower frequencies (50, 33, 25 and 20 kHz). Results show that the prediction indices, including intersection over union (IoU), peak signal to noise ratio (PSNR), structural similarity index (SSIM), and time averaged correlation coefficient at various axial positions could achieve acceptable accuracy. This work sheds light on the utilization of CNN-based models to achieve optical flow computation and image sequence interpolation, also providing an efficient off-line model as an alternative pathway to overcome the experimental challenges of the state-of-the-art ultra-high speed PLIF techniques, e.g., to further increase repetition rate and save data transfer time.
About the Authors
Wei Zhang, PhD student, China-UK Low Carbon College of Shanghai Jiao Tong University. Research interests: deep learning, image processing, laser imaging
Xue Dong, Associate Professor, China-UK Low Carbon College of Shanghai Jiao Tong University. Research interests: turbulent flow combustion diagnosis; laser imaging and image processing, sensor fusion, etc.