Super-Resolved in-Operando Observation of SOFC Pattern Electrodes

Abstract

Nickel (Ni) is widely used for solid oxide fuel cell (SOFC) anodes due to high catalytic activity and electron conductivity. However, Ni coarsening and depletion are the major causes of electrode degradation during long time operation. In order to investigate the microstructural changes of Ni under actual operating environment, in-operando observations of Ni-pattern electrodes were carried using confocal laser microscope [1,2]. However, low resolution and shallow depth of field limit detailed investigation of the microstructure. On the other hand, high resolution images can be obtained by scanning electron microscope (SEM) or environmental SEM (ESEM), but the sample must be kept inside a vacuum chamber, which makes it extremely difficult to operate the sample cell with electrochemical reaction. Therefore, an automatic method to super-resolve the confocal laser scanning image is desired, which will be a great help to understand the Ni degradation phenomena under operation.Recently, deep learning is applied to image processing in many applications. Convolutional neural network (CNN) is widely used for various vision tasks including image classification and object detection. In particular, an application of generative adversarial network (GAN) [3] based on CNN has been successfully incorporated in image synthesis. The GAN consists of two networks, i.e. the generator to fabricate images and the discriminator to identify the output image as real or fake. Implementation of GAN such as image to image translation (pix2pix) [4] is highly expected in SOFC research.In the present study, two machine learning algorithms for improving the laser microscope image quality are investigated. The algorithms are applied to the Ni pattern electrodes deposited on mirror-polished yttrium stabilized zirconia (YSZ) substrate. Sets of low resolution (LR) laser scanning microscope images and high resolution (HR) SEM images of identical positions were collected for the training data.Firstly, the semantic segmentation proxy is proposed for the automatic material detection from the LR laser microscope images. The incorporated algorithms are based on CNN deep neural network. U-net [5] with encoder-decoder network is also conducted for comparison. In addition to visual assessment, phase fractions and triple phase boundary (TPB) density are calculated. The automatically segmented LR laser microscope images showed good agreement with the manually segmented HR SEM images. The estimated TPB density was close to the real value. The images segmented with U-net were better than those with encoder-decoder CNN in fine details, which indicates that U-net is superior in transferring local information.Secondly, a new method for synthesizing SEM-quality image from laser image is proposed. The super-resolution network incorporates pix2pix GAN architecture [4] which enables image to image translation. Figure 1A shows LR laser microscope image, which is an input for the pix2pix GAN. High resolution image generated by GAN is shown in Fig. 1B. Real HR SEM image is presented in Fig. 1C for comparison. Realistic HR images can be synthesized from LR laser image, which reveals that the proposed method is effective for super-resolving patterned electrode microstructures. The semantic segmentation proxy and super-resolution algorithms will enable quantitative evaluation of dynamic changes of SOFC electrodes under in-operando observation by a laser microscope.[1] Z. Jiao and N. Shikazono, J. Power Sources, 396, pp. 119–123 (2018).[2] Y. Suzuki et al., 14th European SOFC and SOE Forum, B1513 (2020).[3] I. Goodfellow et al., Advances in neural information processing systems, 27, pp. 2672-2680 (2014).[4] P. Isola et al., Proceeding of the IEEE on CVPR, pp. 1125-1134 (2017).[5] O. Ronneberger et al., MICCAI, pp. 234-241 (2015). Figure 1