The thermography camera is widely used to inspect electrical equipment. The existing defect assessment indicators are mainly the hot spot temperature and the relative temperature difference (RTD), and the analyzing process used to calculate the indicators is usually off-site. A smart thermography camera is designed and its application in the diagnosis of electrical equipment is investigated in this article. For the camera, the regional RTD is calculated automatically based on equipment detection and image registration algorithms, and the defects can be judged according to the existing criteria. Firstly, the regional RTD and its implementation method are proposed to reduce the error when the hot spot is unmeasurable. Then the object detection method based on the convolutional neural network (CNN) is modified dedicated to infrared (IR) images. Over 12 000 historical images and 18 000 labels are used for training and tests. The modified model can identify 16 classes of substation equipment with 86.4% mAP. With low latency, the inference speed of this on-site smart camera reaches 30 frames/s. The test results show that the similarity of diagnosis result between our method and the criteria is 92.2%.

It is essential to develop infrared (IR) thermogram identification technologies to establish automatic diagnosis systems in power substations. The convolutional neural network (CNN) based methods show the highest accuracy in this field. The IR thermograms of electrical equipment are very different from general digital images, which means the present methods need further improvements. For data-driven CNN methods, it is necessary to study the characteristics of the IR data. This paper collected 11817 thermograms from substations and structured the dataset according to equipment types. The statistical features of mean, variance, skewness, kurtosis and contrast are analyzed and compared with other five image datasets. Several tricks are revealed from the analysis and tested on CNN models. Firstly, greycaling the Iron pseudo-color images extracts the temperature information and makes it possible to design models with fewer channels. The test shows it could reduce over 35% computational costs. Secondly, the sparse information of color and edges of thermograms makes it necessary to keep the original aspect ratio. The image preprocessing method of cropping shows better performance than padding and rescaling. Thirdly, the 0–1 normalization can boost the training process for about 100 epochs, which is related to the particular background of thermograms.

The low adhesion of water drops on superhydrophobic surfaces is a prerequisite for their widespread potential industrial applications. The wetting transition between different wetting states significantly influences the dynamic behavior of water drops on solid surfaces. Although some theoretical studies have addressed wetting transitions, the underlying mechanisms by which local micro- and nanostructure parameters on superhydrophobic surfaces affect the wetting transition have not been fully elucidated. This study investigates three-dimensional micropillared and micro/nanopillared superhydrophobic surfaces, deriving thermodynamically the equation for the free energy barrier of wetting transition, which is influenced by the overall roughness of the entire superhydrophobic surface and its local micro/nanostructures. Theoretical calculations are performed to investigate the effects of various micro- and nanostructure parameters on the free energy barrier and wetting transition. Based on the principle of energy minimization and the calculated free energy barrier, the possible wetting states on superhydrophobic surfaces are analyzed and compared with experimental results. This study contributes to the theoretical understanding of wetting transitions and may guide the design of superhydrophobic surfaces for diverse applications.