Goertek Inc.

Bestee Material (tsingtao) Co., Ltd.

Hisense USA Corporation

Hisense International Co., Ltd.

Hisense Co., Ltd.

Bioex Therapeutics Inc.

Shandong University

China University of Petroleum

Qingdao Haier Washing Machine Co., Ltd.

Hisense Electric Co., Ltd.

Haier Group Corporation

Qingdao University of Science and Technology

Sinotech Academy of Textile (qingdao) Co., Ltd.

Qingdao Hisense Laser Display Co., Ltd.

Livzon Mabpharm Inc.

Jie Liu

Sheng Xu

Peishi Lv

John Walter Schnell

Edward A Pomeroy

Yifan Zhang

Essam Namouz

Henry Johnson

Xiaohua Huang

Li Zhen

Yu Liu

Jifeng Tian

Xiaoqian Huang

Fuli Xie

Shunran Di

Yanming Liu

Xiaolong Huang

Jun Yao

Xin Wang

Yongfei Yang

Wenchao Zhang

Chuansheng Wang

Liang Zhang

Yuling Chen

Hailing Lin

Jinlin Zhou

Xinghong Li

Liguo Ma

Chen Liu

Ke Wang

Weihua Mu

Ziqiang Cao

Xiaojie Pi

Qiang Cai

Shichao Wang

Huiguang Bian

Yongmei Ma

Yunliang Liu

Jinghe Chen

Mengqi Hu

Ruichun Dong

Libin Du

Yifan Ke

Shuo Wei

Mingchen Lei

Chengbin Ma

Rui Zhao

Yongke Zhang

Yingwen Li

Wenjie Zhang

Zhihui Liu

Haiyuan Yang

Qianfei Lv

Ning Wu

Liu Tao

Xinze Li

Pengfei Liu

Hao Wu

Mingsheng Wu

Zhuobing Zhang

Jikuan Shan

Wei Suo

Li Ma

Hong Zhang

Tong Shi

Xiaoben Liu

Zhao Honglin

Chengqi Liu

Xiaoxian Huang

A chitin-containing polyester filament and a preparation method of the chitin-containing polyester filament are provided. The method includes preparing a modified chitin; preparing a chitin-containing functional modifier based on the modified chitin; preparing polyester (PET) functional particles based on the chitin-containing functional modifier and PET pellets; preparing a mixed spinning solution based on the polyester functional particles, where a weight percentage of the polyester functional particles is in a range of approximately 2%-4% based on a total weight of the mixed spinning solution; and performing a spinning molding of the mixed spinning solution to form the chitin-containing polyester filament.

Chitin-containing polyester filament and preparation method thereof

A long-endurance self-powered ocean buoy includes a buoy body, a power generation device and a gas bag base; the power generation device is mounted at a lower end of the gas bag base and includes a housing, a first power generation assembly, a second power generation assembly and a storage battery; the first power generation assembly includes a plurality of mutually-communicated gas chambers, hydraulic bags and control integration units. The lowest gas chamber is filled with a volatile working medium which can generate gas pressure by volatilization to drive power generation fans in turbines on a vent pipe communicating adjacent gas chambers for power generation. The second power generation assembly includes a plurality of temperature difference energy modules with one end surrounded by a phase change material and the other end in contact with the housing, so as to increase the power generation efficiency.

Long-endurance self-powered ocean buoy

A computer vision-based anomaly detection method and device and an electronic apparatus are disclosed. The method comprises: dividing a target picture into at least two feature regions according to different region features of the target picture, and forming training sets respectively using the feature regions corresponding to each target picture; selecting generative adversarial networks GAN as network models to be used, and training GAN network models with the training sets of different feature regions to obtain GAN network models corresponding to different feature regions; and when performing anomaly detection, performing same feature region division on a target picture to be detected, inputting different feature regions of the target picture to be detected into corresponding GAN network models to obtain a generated picture, and performing pixel value-based difference detection on the generated picture and the target picture to be detected.

Computer vision-based anomaly detection method, device and electronic apparatus

A modified polypropylene spunbond non-woven fabric and a preparation method of the modified polypropylene spunbond non-woven fabric are provided. The modified polypropylene spunbond non-woven fabric contains a modified nanocomposite material including an organic compound, the organic compound including one of tea polyphenol, naringin, and emodin. The organic compound is in a weight percentage range of approximately 0.1%-5% based on a total weight of the modified polypropylene spunbond non-woven fabric.

Modified polypropylene spunbond non-woven fabric and preparation method thereof

A method and device for small sample defect classification and a computing equipment are disclosed. The method comprises: separating a target to be tested into parts, and segmenting an original image of the target to be tested into at least two sub-images containing different parts according to the separated parts; establishing small sample classification models with respect to each sub-image and the original image respectively, and obtaining a classification result of each sub-image and a classification result of the original image by using corresponding classification models, wherein the classification result includes a defect category and a corresponding category probability; and determining and outputting a defect category of the target to be tested according to classification results of all the sub-images and the original image.

Method and device for small sample defect classification and computing equipment

A product defect detection method, device and system are disclosed. The product defect detection method comprises: constructing a defect detection framework including a classification network, a localization and detection network, and a judgment network, and setting a quantity of the localization and detection network and judgment rules of the judgment network according to classification results of the classification network, wherein each localization and detection network is associated with a classification result, and each judgment rule is associated with a detection result of the localization and detection network; when performing product defect detection, inputting a product image acquired into the defect detection framework, using the classification network to classify defect types in the product image, detecting defects of the product image according to a localization and detection network associated with a classification result, then judging whether the product has a defect, and detecting a defect type and a defect position.

Product defect detection method, device and system

A plant-based functional polypropylene spunbond non-woven fabric and a preparation method of the plant-based functional polypropylene spunbond non-woven fabric are provided. The plant-based functional polypropylene spunbond non-woven fabric contains a plant herb water-soluble extract in a weight percentage range of approximately 0.2%-1.5%. The plant-based functional polypropylene spunbond non-woven fabric has moisture regain in a range of approximately 0.2%-3%, a longitudinal breaking strength of approximately &#x2265;18.5 N/5 cm, a transverse breaking strength of approximately &#x2264;9.5 N/5 cm, a thickness in a range of approximately 0.2 mm-0.5 mm, a weight per unit area in a range of approximately 20 g/m2-40 g/m2, and a fiber diameter in a range of approximately 10 &#x3bc;m-30 &#x3bc;m.

Plant-based functional polypropylene spunbond non-woven fabric and preparation method thereof

The present disclosure discloses a method and device for optimizing an object-class model based on a neural network. The method includes: establishing the object-class model based on the neural network, training the object-class model, and realizing classification of target images by using the object-class model that has been trained; and when a new target image is generated, and the new target image is an image corresponding to a new condition of a target and is capable of still being classified into an original classification system, judging a result of identification of the object-class model to the new target image, and if the object-class model is not capable of correctly classifying the new target image, according to the new target image, selecting some of parameters, adjusting the some of parameters, and training to obtain an object-class model that is capable of correctly classifying the new target image.

Method and device for optimizing object-class model based on neural network

A product defect detection method, device and system are disclosed. The product defect detection method comprises: constructing a defect detection framework including a classification network, a locating detection network and a judgment network; training the classification network by using a sample image of a product containing different defect types to obtain a classification network capable of classifying the defect types existing in the sample image; training the locating detection network by using a sample image of a product containing different defect types to obtain a locating detection network capable of locating a position of each type of defect in the sample image; inputting an acquired product image into the defect detection framework, inputting a classification result and a detection result obtained into the judgment network to judge whether the product has a defect, and detecting a defect type and a defect position when the product has a defect.

A product defect detection method, device and system are disclosed. The method comprises: acquiring a sample image of a product, extracting candidate image blocks probably including a product defect from the sample image, and extracting preset shape features corresponding to the candidate image blocks and texture features corresponding to the candidate image blocks; training a first-level classifier using the preset shape features to obtain a first-level classifier that can further screen out target image blocks probably including a product defect from the candidate image blocks; training a second-level classifier using the texture features to obtain a second-level classifier that can correctly identify a product defect; and when performing product defect detection, inputting preset shape features of candidate image blocks extracted from a product image into the first-level classifier, and then inputting texture features of obtained target image blocks into the second-level classifier to detect a defect in the product.

A plant-based functional polyester filament and a preparation method of the plant-based functional polyester filament are provided. The plant-based functional polyester filament includes polyester, and plant extract in a weight percentage range of approximately 0.1%-1.5%. The plant extract includes one or more of a peppermint extract, a valerian extract, a lavender extract, a wormwood extract, a chitin extract and a seaweed extract. The method includes preparing a plant-based functional polyester masterbatch, including: heating polyethylene terephthalate (PET) chips to a molten state, adding an antioxidant and a dispersant to the molten PET, stirring the molten PET, adding a protective agent and a plant extract to the molten PET, stirring the molten PET at a high speed, adding a modifier to the molten PET, obtaining a mixture by uniformly mixing the molten PET, and performing an extrusion granulation process on the mixture.

Method of preparing plant-based functional polyester filament

The present invention discloses an algae modified pp spunbond non-woven fabric, which contains 0.1-2% of alginate. The algae modified pp spunbond non-woven fabric has a moisture regain of 0.2-3.5%, and an antibacterial rate &#x2265;98%. The algae modified pp spunbond non-woven fabric prepared in the invention contains modified alginic acid, and also has hydrophilic functional groups, such as hydroxyl and amido groups, and hydrophobic functional groups such as branched alkyl groups. After spinning with pp into non-woven fabrics, protons can be both generated and received, so that when liquid is encountered on the surface of non-woven fabrics, the surface tension of liquid can be significantly reduced; additionally, there are a large number of gaps in the dense interpenetrating network structure formed by the modified alginic acid, which forms a structure like sponge having good hygroscopicity; moreover, the algae modified pp spunbond non-woven fabric absorbs water rapidly, the surface remains dry after absorbing water, and it can absorb many times its mass of water, so it has an excellent hydrophilicity.

Algae modified pp spunbond non-woven fabric

A product defect detection method, device and system are disclosed. The method comprises: constructing a defect detection framework including segmentation networks, a concatenating network and a classification network, and setting a quantity of the segmentation network according to product defect types, wherein each segmentation network corresponds to a defect type; concatenating the sample image with the mask image output by each segmentation network by using the concatenating network to obtain a concatenated image; training the classification network by using the concatenated images to obtain a classification network capable of correctly identifying a product defect and a defect type; and when performing product defect detection, inputting a product image acquired into the defect detection framework, and detecting a product defect and a defect type existing in the product by using the segmentation networks, the concatenating network and the classification network.

A method and system for determining contact angles of porous media, including: in a displacement simulation experiment, injecting a displacement fluid into a actual core sample, and performing computed tomography scanning on the core to determine three-dimensional images at different oil displacing time points; segmenting different phases of the three-dimensional images to obtain segmented three-dimensional images; marking a contact line between different phases according to the segmented three-dimensional images, where the phases are underground fluids or displacement fluids and a rock matrix in the displacement simulation experiment; and determining a contact angle of the porous media at different 3D positions at different time points according to the contact line. The method and system provided can obtain the dynamic changing process of the contact angle at different 3D positions in the core at different displacement time points, reflect the wettability of the real reservoir environment more accurately.

Method and system for determining contact angle of porous media

A gas-assisted rubber wet mixing preparation apparatus is disclosed, including a rack, a reactor is fixedly mounted below the rack; a mixing chamber in an ellipsoidal shape is provided inside the reactor; the reactor is provided with a plurality of feed ports, the feed ports are provided at an included angle with respect to the horizontal plane; spray guns cooperating with the feed ports are fixedly mounted on an outer wall of the reactor, a material storage tank and a gas supply device are connected to the spray gun; the spray guns and the material storage tanks are in one-to-one correspondence, and the spray guns are connected to the corresponding material storage tanks respectively; a discharge port is further provided below the reactor, and a receiver tray is provided below the discharge port.

Gas-assisted rubber wet mixing preparation apparatus

Growing community of inventors

Qingdao, China

Jie Liu