-
公开(公告)号：US20240378712A1
公开(公告)日：2024-11-14
申请号：US18610339
申请日：2024-03-20
Applicant: DOOSAN ENERBILITY CO, LTD.
Inventor： June Sung SEO , Jung Min LEE
IPC: G06T7/00 , G06T3/4046 , G06T9/00 , G06V10/82
Abstract: A device and method for analyzing a defect in ultrasonic testing using a three-dimensional deep learning model is proposed. The method includes preparing three-dimensional raw data by collecting a plurality of two-dimensional inspection images obtained by ultrasonic testing of an inspection object and stacking the plurality of two-dimensional inspection images; generating input data for a deep learning model by processing the three-dimensional raw data; deriving representation data, which is an inferenced three-dimensional image representing the defect of the inspection object, through a first feature transformation by applying first weights in a trained state to the input data within a generation network of the deep learning model; and determining a defect type of the inspection object by inputting the representation data to a detecting network of the deep learning model.
-
公开(公告)号：US20240144685A1
公开(公告)日：2024-05-02
申请号：US18468705
申请日：2023-09-16
Applicant: DOOSAN ENERBILITY CO., LTD.
Inventor： Jun Sang YU , Jung Min LEE
IPC: G06V20/50 , G06T7/00 , G06V10/75 , G06V10/762 , G06V10/77 , G06V10/774 , G06V10/776
CPC classification number: G06V20/50 , G06T7/001 , G06V10/751 , G06V10/762 , G06V10/7715 , G06V10/774 , G06V10/776 , G06T2207/20021 , G06T2207/20081 , G06T2207/30108
Abstract: Disclosed is a degradation prediction device predicting a lifetime of a target material, including: at least one processor, and the at least one processor is configured to train a degradation index prediction model based on the representative value of a degradation index of a material by environmental conditions and the environmental information of a material subjected to a destructive testing, train a LMP (Larson-Miller Parameter) value prediction model based on the representative value of a degradation index of a material by environmental conditions and a theoretical value of LMP at a destructive testing, predict a degradation index for a target material using the degradation index prediction model for which training is completed based on environmental information of the target material and predict a LMP value of the target material using the LMP value prediction model for which training is completed based on the predicted degradation index.
-
Patent Agency Ranking
公开(公告)号：US20240233420A9
公开(公告)日：2024-07-11
申请号：US18468710
申请日：2023-09-17
Applicant: DOOSAN ENERBILITY CO., LTD.
Inventor： Jun Sang Yu , Jung Min LEE
Abstract: Disclosed is an annotation device including at least one processor. The at least one processor generates a plurality of superpixels in an annotation target image based on a predetermined non-parametric segmentation method, recommends segmentation regions based on outlines of the plurality of superpixels, respectively, and performs labeling for each of the recommended segmentation regions based on a user input for labeling.
-
公开(公告)号：US20240201682A1
公开(公告)日：2024-06-20
申请号：US18518483
申请日：2023-11-23
Applicant: Doosan Enerbility Co., Ltd.
Inventor： Jung Min LEE , Jun Sang YU
IPC: G05B23/02
CPC classification number: G05B23/0283 , G05B23/024 , G05B23/0254
Abstract: Disclosed is a device for determining the operational status of a sensor configured to: determine initial parameters of a Bayesian model and a degree of a polynomial regression model based on historical data of a target sensor and a reference sensor; infer a posterior distribution of a regression coefficient and an error term of a regression curve using the polynomial regression model and the Bayesian model; set a credible interval based on the posterior distribution of the regression coefficient and the error term of the regression curve, and set control lines of data of the target sensor using the credible interval; determine an accuracy of the target sensor based on current data of the target sensor and the set control line; and control an operational status of the target sensor based on the accuracy.
-
公开(公告)号：US20240362504A1
公开(公告)日：2024-10-31
申请号：US18610365
申请日：2024-03-20
Applicant: DOOSAN ENERBILITY CO., LTD.
Inventor： June Sung SEO , Jung Min LEE , Gung Hul PARK , Hyun Su KANG
Abstract: A device and method for predicting exhaust emissions on the basis of data analysis is proposed. The method includes collecting, by a collection unit, raw data in real time from a power generation facility comprising a gas turbine, extracting, by a prediction unit, analysis data from the raw data, and predicting, by the prediction unit, the exhaust emissions to be emitted from the power generation facility a pre-derived delay time after the collecting of the raw data by analyzing the analysis data using a prediction model trained by learning.
-
公开(公告)号：US20240169683A1
公开(公告)日：2024-05-23
申请号：US18496798
申请日：2023-10-27
Applicant: DOOSAN ENERBILITY CO., LTD.
Inventor： June Sung SEO , Gung Hul PARK , Seong Sik KO , Jung Min LEE
CPC classification number: G06V10/25 , G06V10/46 , G06V20/64 , G06V2201/07
Abstract: A method of detecting a radiographic object is proposed. The method includes receiving, by a feature processing module, an input of radiographic image obtained by irradiating a region containing a plurality of tubes including at least one target tube as a radiographic object and at least one untargeted tube that is not a radiographic object, extracting, by the feature processing module, feature values of extremal points from the radiographic image to detect feature vectors, and analyzing, by a detection module, the feature vectors using a training model to detect a region in the radiographic image where the at least one target tube as a radiographic object exists.
-
公开(公告)号：US20240135738A1
公开(公告)日：2024-04-25
申请号：US18468710
申请日：2023-09-16
Applicant: DOOSAN ENERBILITY CO., LTD.
Inventor： Jun Sang Yu , Jung Min LEE
Abstract: Disclosed is an annotation device including at least one processor. The at least one processor generates a plurality of superpixels in an annotation target image based on a predetermined non-parametric segmentation method, recommends segmentation regions based on outlines of the plurality of superpixels, respectively, and performs labeling for each of the recommended segmentation regions based on a user input for labeling.
-
-
-
-
-
-
Search Results
7
records
(took 0.012 seconds)
