Abstract: The present application relates to the field of power equipment detection devices, and in particular to a power transformer fault detection device, which includes a detection component for detecting the oil composition of the transformer, and also includes a rotating part comprising multiple groups of oil pools that are evenly spaced around the rotating axis of the rotating part. The multiple groups of oil pools are connected to oil outlets at different heights on the transformer, and a light-transmitting window is provided on the oil pool. A detection component is installed on the rotating part, and can detect the composition of the liquid in the oil pool through the light-transmitting window. The present application has the effect of allowing staff to monitor the working status of the transformer in a timely manner and reducing the labor burden of the staff.

Abstract: A vision-based enhanced omni-directional defect detection method is provided. The method includes: performing posture adjustment on equipment, changing an equipment angle and a transmission speed, acquiring a multi-angle detection picture, and performing information fusion and classification. By means of the method, the influence of natural and human factors is solved, the problem of missing detection is solved by adoption of defect feature enhancement, and the part detection accuracy is improved.

Abstract: A method and a system for detecting a scene text are provided. The method includes: acquiring a scene text picture in a preset manner, pre-processing the acquired scene text picture, detecting the pre-processed scene text picture with a training model for scene text detection, and acquiring a detection result. Accordingly, the method and the system have an original PSENet (Progressive Scale Expansion Network) backbone network ResNet (Deep Residual Network) is replaced with a rich feature structure network (i.e. Res2NeXt (Combination of Res2Net and ResNeXt)) to improve a network feature extraction capability, thereby increasing a text detection precision of the network; mixed pooling is added at an appropriate location in the backbone network to acquire useful context information by performing pooling operations of different kernel shapes and capture long and short distance dependency relationships between different locations, thereby further increasing the text detection precision of the network.

Abstract: A making method of meal replacement bread is provided, which is based on hypoglycemic function of black fungus polysaccharide and yam polysaccharide, and uses ?-amylase inhibition rate as a measurement index. Five single-factor experiments are designed with an addition of composite polysaccharide, buckwheat flour, butter, cream cheese and milk respectively, to screen out the best addition of each nutrient and provide a making recipe of the hypoglycemic meal replacement bread with high nutrition.

Abstract: A method and a system for detecting a scene text are provided. The method includes: acquiring a scene text picture in a preset manner, pre-processing the acquired scene text picture, detecting the pre-processed scene text picture with a training model for scene text detection, and acquiring a detection result. Accordingly, the method and the system have an original PSENet (Progressive Scale Expansion Network) backbone network ResNet (Deep Residual Network) is replaced with a rich feature structure network (i.e. Res2NeXt (Combination of Res2Net and ResNeXt)) to improve a network feature extraction capability, thereby increasing a text detection precision of the network; mixed pooling is added at an appropriate location in the backbone network to acquire useful context information by performing pooling operations of different kernel shapes and capture long and short distance dependency relationships between different locations, thereby further increasing the text detection precision of the network.