Abstract: Disclosed is an AI-based product surface inspecting apparatus. The AI-based apparatus includes: a sensor unit photographing a product to generate image data and measures a color, a saturation, a brightness, a transparency, and/or a reflectance of the product; a detection unit detecting a defect on the product by inputting the image data to a convolutional neural network (CNN) trained to detect a defect on a product surface; and a preprocessor converting the image data based the color, the saturation, the brightness, the transparency, and/or the reflectance of the product to input the converted data to the detection unit. The number of convolution layers of the convolutional neural network is determined based on a defect detection difficulty determined according to at least one of the color, the saturation, the brightness, the transparency, and the reflectance of the product and a defect type.

Abstract: Disclosed is an AI-based apparatus for detecting a defect of a product. The AI-based apparatus includes: a sensor unit which photographs a product to generate image data and measures at least one of a color, a saturation, a brightness, a transparency, and a reflectance of the product; and a detection unit which detects a defect on the product by inputting the image data to a convolutional neural network (CNN) trained to detect a defect on a product surface. The number of convolution layers of the convolutional neural network is determined based on a defect detection difficulty determined according to at least one of the color, the saturation, the brightness, the transparency, and the reflectance of the product and a defect type.

Abstract: Disclosed is an AI-based product surface inspecting apparatus for adjusting a number of convolution layers. The AI-based apparatus includes: a sensor unit which photographs a product to generate image data and measures at least one of a color, a saturation, a brightness, a transparency, and a reflectance of the product; and a detection unit which detects a defect on the product by inputting the image data to a convolutional neural network (CNN) trained to detect a defect on a product surface, wherein a number of convolution layers of the convolutional neural network is determined based on a defect detection difficulty determined according to at least one of the color, the saturation, the brightness, the transparency, and the reflectance of the product and a defect type.

Abstract: Disclosed is an AI-based product surface inspecting apparatus for adjusting a number of convolution layers. The AI-based apparatus includes: a sensor unit which photographs a product to generate image data and measures at least one of a color, a saturation, a brightness, a transparency, and a reflectance of the product; and a detection unit which detects a defect on the product by inputting the image data to a convolutional neural network (CNN) trained to detect a defect on a product surface. The number of convolution layers of the convolutional neural network is determined based on a defect detection difficulty determined according to at least one of the color, the saturation, the brightness, the transparency, and the reflectance of the product and a defect type.

Abstract: Disclosed is an AI-based apparatus for detecting a defect of a product. The AI-based apparatus includes: a sensor unit which photographs a product to generate image data and measures at least one of a color, a saturation, a brightness, a transparency, and a reflectance of the product; and a detection unit which detects a defect on the product by inputting the image data to a convolutional neural network (CNN) trained to detect a defect on a product surface. Also, the number of convolution layers of the convolutional neural network is determined based on a defect detection difficulty determined according to at least one of the color, the saturation, the brightness, the transparency, and the reflectance of the product and a defect type.

Abstract: Disclosed is an AI-based product surface inspecting apparatus. The AI-based apparatus includes: a sensor unit which photographs a product to generate image data and measures a color, a saturation, a brightness, a transparency, and/or a reflectance of the product; a detection unit which detects a defect on the product by inputting the image data to a convolutional neural network (CNN) trained to detect a defect on a product surface; and a preprocessor which converts the image data based on the color, the saturation, the brightness, the transparency, and/or the reflectance of the product to input the converted data to the detection unit. The number of convolution layers of the convolutional neural network is determined based on a defect detection difficulty determined according to at least one of the color, the saturation, the brightness, the transparency, and the reflectance of the product and a defect type.

Abstract: Disclosed is an AI-based product surface inspecting apparatus. The AI-based apparatus includes: a sensor unit which photographs a product to generate image data and measures a color, a saturation, a brightness, a transparency, and/or a reflectance of the product; a detection unit which detects a defect on the product by inputting the image data to a convolutional neural network (CNN) trained to detect a defect on a product surface; and a preprocessor which converts the image data based on the color, the saturation, the brightness, the transparency, and/or the reflectance of the product to input the converted data to the detection unit. The number of convolution layers of the convolutional neural network is determined based on a defect detection difficulty determined according to at least one of the color, the saturation, the brightness, the transparency, and the reflectance of the product and a defect type.

Abstract: Provided are a catalyst for olefin polymerization including a hybrid catalyst composition and an olefin-based polymer prepared therefrom. The hybrid metallocene catalyst allows preparation of an olefin polymer having a broad molecular weight distribution and excellent high-speed processability. In addition, an olefin-based polymer prepared in the presence of the hybrid catalyst has a broad molecular weight distribution and excellent high-speed processability.

Abstract: Provided are a method for preparing an olefin-based polymer and an olefin-based polymer produced using the same. The method for preparing an olefin-based polymer according to an exemplary embodiment may adjust processability of the olefin-based polymer produced using the method by a polymerization temperature. In addition, the method for preparing an olefin-based polymer according to the exemplary embodiment may adjust drop impact strength of a finally obtained film by a polymerization temperature.

Abstract: The present invention pertains to a polyolefin having excellent processability. A polyolefin prepared in the presence of a hybrid metallocene catalyst according to an embodiment of the present invention has a broad unimodal molecular weight distribution with a shoulder, and has excellent high-speed processability.

Abstract: A deep learning-based quality inspection system by learning only non-defective manufactured product data may include: an input unit receiving a non-defective manufactured product image data set; a preprocessor preprocessing a model to learn the images with a same size by not applying a cropping task to cut and process only an area at a specific location within each image for each of the plurality of images included in the image data set, but applying a resizing task of adjusting each image to a desired size and a padding task of adjusting the size of the image while maintaining a ratio of each image as it is; and a controller extracting a non-defective manufactured product feature which becomes a non-defective manufactured product criterion from the preprocessed image, and generating a plurality of fake defective manufactured product features by adding a Gaussian noise feature to the extracted non-defective manufactured product feature.

Abstract: Embodiments relate to a deep learning/AI-based product surface quality inspection system which is accurate and reliable in product quality inspection which is a core task in an injection process among various manufacturing fields. The system can provide, to a user, better performance than non-defective/defective manufactured product classification methodology which is an existing commonly used method through a method and a system considering characteristics of a factory environment and an actual product production process for all pipelines of product quality inspection by using only a non-defective manufactured product image unlike most injection process surface inspection AIs developed to date.

Abstract: Disclosed are a product surface inspecting apparatus and method which detect a defect on products having different feature using a previously trained artificial neural network. A product surface inspecting apparatus according to an exemplary embodiment includes a sensor unit which photographs a product to generate image data and measures at least one of a color, a saturation, a brightness, a transparency, and a reflectance of the product; and a detection unit which detects a defect on a product by inputting the image data to a convolutional neural network trained to detect a defect on a product surface, the number of convolution layers of the convolutional neural network may be determined based on at least one of the color, the saturation, the brightness, the transparency, and the reflectance of the product.

Abstract: A thermal image-based hybrid object detection method using a YOLO model and an object tracking technique includes: a) a step of obtaining a plurality of thermal image data by means of a thermal image camera; b) a step of extracting an object region from a thermal image data of the thermal image camera using an installed YOLO model and then creating an object region coordinate data by returning coordinates of the object region by means of an image processor; and c) a step of outputting a first image reflecting an object region coordinate data to each of thermal image data received from the image processor by means of an output device when the output device requests transmission of the first image.

Abstract: A thermal image-based hybrid object detection method using a YOLO model and an object tracking technique includes: a) a step of obtaining a plurality of thermal image data by means of a thermal image camera; b) a step of extracting an object region from a thermal image data of the thermal image camera using an installed YOLO model and then creating an object region coordinate data by returning coordinates of the object region by means of an image processor; and c) a step of outputting a first image reflecting an object region coordinate data to each of thermal image data received from the image processor by means of an output device when the output device requests transmission of the first image.

Abstract: The present invention relates to a semiconductive resin composition for a high voltage power cable. Specifically, the present invention relates to a semiconductive resin composition comprising a base resin in which ethylene butyl acrylates having different melting indices are mixed, carbon black, an antioxidant, and a crosslinking agent. In addition, the present invention relates to a semiconductive resin composition for a high voltage power cable, the composition having excellent scorch stability and processability and low volume resistance even at a high temperature.

Abstract: Disclosed are a product surface inspecting apparatus and method which detect a defect on products having different feature using a previously trained artificial neural network. A product surface inspecting apparatus according to an exemplary embodiment includes a sensor unit which photographs a product to generate image data and measures at least one of a color, a saturation, a brightness, a transparency, and a reflectance of the product; and a detection unit which detects a defect on a product by inputting the image data to a convolutional neural network trained to detect a defect on a product surface, the number of convolution layers of the convolutional neural network may be determined based on at least one of the color, the saturation, the brightness, the transparency, and the reflectance of the product.

Abstract: The present disclosure relates to a composite resin composition for a geocell or a coral cell. A composite resin composition according to one implementation of the present disclosure has high density and excellent mechanical properties such as tensile strength and elongation, and thus a composite resin molded product obtained therefrom can be effectively used in the manufacturing of a geocell or a coral cell.

Abstract: An olefin polymer and a preparation method for manufacturing the olefin polymer are disclosed. The olefin polymer has a high melting point and a high crystallization temperature, thus having excellent heat resistance. Therefore, the olefin polymer may be utilized in spout pouches for high-temperature liquid containers, or the like. The olefin polymer may have a density of 0.9 to 0.95 g/cm3, preferably 0.91 to 0.945 g/cm3, and satisfies the following Equations 1a and 2a: 224.02×d?86.257<Tm, and ??[Equation 1a] 219.64×d?95.767<Tc.

Abstract: A power control device configured for diagnosing an open-circuit fault occurring in a power system of an autonomous vehicle and an open-circuit diagnosis method thereof, may include a power control switch that selectively connects or separates main power output from the first power supply and auxiliary power output from the second power supply, and a processor that determines a possibility of an open-circuit fault of a vehicle power source based on a current flowing through the power control switch and determines whether it is possible to drive an electric load with an output power of the second power supply alone and determine an open-circuit position based on an output of the first power supply when there is the possibility of the open-circuit fault.