Patents by Inventor Huafeng Yu
Huafeng Yu has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 11568597Abstract: A method and apparatus for performing automated supervision and inspection of an assembly process. The method is implemented using a computer system. Sensor data is generated at an assembly site using a sensor system positioned relative to the assembly site. A three-dimensional global map for the assembly site and an assembly being built at the assembly site is generated using the sensor data. A current stage of an assembly process for building an assembly at the assembly site is identified using the three-dimensional global map. A context for the current stage is identified. A quality report for the assembly is generated based on the three-dimensional global map and the context for the current stage.Type: GrantFiled: July 26, 2019Date of Patent: January 31, 2023Assignee: The Boeing CompanyInventors: Daniel S. ReMine, Huafeng Yu
-
Patent number: 11555480Abstract: The present invention discloses a prestressed-bolted dry-assembled segmental precast hybrid tower with grouting-free, comprising a top steel tower tube, a reverse self-balancing steal-concrete transition section, and a prestressed-bolted dry-assembled segmental precast concrete tower with grouting-free dry fast splicing and a gear reinforced wind turbine foundation; the steel tower tube, the steel-concrete transition section, the concrete tower tube and the hollow wind turbine foundation are integrally connected from top to bottom through a prestressed steel strand system to improve the overall bending resistance of the tower; the upper end of the prestressed steel strands is anchored to the steel-concrete transition section, and the lower end is anchored to the bottom face of the wind turbine foundation corbel; the concrete tower tube is composed of a number of segmental tapered precast concrete tower segments, which are grouting free spliced vertically, and the vertical splicing utilizes positioning pins toType: GrantFiled: December 21, 2020Date of Patent: January 17, 2023Assignee: POWERCHINA HUADONG ENGINEERING CORPORATION LIMITEDInventors: Chunlin Huang, Dongliang Zhang, Qunyi Tang, Xingjian Sun, Jinjun Chen, Weijiang Feng, Huafeng Yu, Kun Fu, Tianhao Li, Fei Wang, Junzhong Xue, Ziteng Peng, Zhongshuai Yuan
-
Patent number: 11442438Abstract: A method and apparatus for performing automated supervision and inspection of an assembly process. The method is implemented using a computer system. Sensor data is generated at an assembly site using a sensor system positioned relative to the assembly site. A current stage of an assembly process for building an assembly at the assembly site is identified using the sensor data. A context for the current stage is identified. A quality report for the assembly is generated based on the sensor data and the context for the current stage.Type: GrantFiled: July 26, 2019Date of Patent: September 13, 2022Assignee: The Boeing CompanyInventors: Huafeng Yu, Daniel S. ReMine, Tyler Charles Staudinger
-
Publication number: 20220188646Abstract: A classifier is executed including an unsupervised artificial intelligence model and a supervised artificial intelligence model. The classifier is configured to receive run-time input data, and process the run-time input data using the unsupervised artificial intelligence model and an outlier detection algorithm to determine whether the run-time input data is an outlier as compared to training input data. Responsive to determining that the run-time input data is not an outlier, the classifier determines a predicted response label for the run-time input based on the run-time input data processed using the supervised artificial intelligence model. Responsive to determining that the run-time input data is an outlier, the classifier refrains from determining the predicted response label for the run-time input based on the run-time input data processed using the supervised artificial intelligence model, and instead outputs a prompt for user input of a user-curated response label for the run-time input.Type: ApplicationFiled: November 5, 2021Publication date: June 16, 2022Inventors: Anapathur Viswanathan Ramesh, Michael Thomas Swayne, Huafeng Yu
-
Publication number: 20220056884Abstract: The present invention discloses a prestressed-bolted dry-assembled segmental precast hybrid tower with grouting-free, comprising a top steel tower tube, a reverse self-balancing steal-concrete transition section, and a prestressed-bolted dry-assembled segmental precast concrete tower with grouting-free dry fast splicing and a gear reinforced wind turbine foundation; the steel tower tube, the steel-concrete transition section, the concrete tower tube and the hollow wind turbine foundation are integrally connected from top to bottom through a prestressed steel strand system to improve the overall bending resistance of the tower; the upper end of the prestressed steel strands is anchored to the steel-concrete transition section, and the lower end is anchored to the bottom face of the wind turbine foundation corbel; the concrete tower tube is composed of a number of segmental tapered precast concrete tower segments, which are grouting free spliced vertically, and the vertical splicing utilizes positioning pins toType: ApplicationFiled: December 21, 2020Publication date: February 24, 2022Inventors: Chunlin HUANG, Dongliang ZHANG, Qunyi TANG, Xingjian SUN, Jinjun CHEN, Weijiang FENG, Huafeng YU, Kun FU, Tianhao LI, Fei WANG, Junzhong XUE, Ziteng PENG, Zhongshuai YUAN
-
Patent number: 11113864Abstract: A set of 3D user-designed images is used to create a high volume of realistic scenes or images which can be used for training and testing deep learning machines. The system creates a high volume of scenes having a wide variety of environmental, weather-related factors as well as scenes that take into account camera noise, distortion, angle of view, and the like. A generative modeling process is used to vary objects contained in an image so that more images, each one distinct, can be used to train the deep learning model without the inefficiencies of creating videos of actual, real life scenes. Object label data can be generated for each distinct image. This and other methods can be used to artificially create new scenes that do not have to be recorded in real-life conditions and that do not require costly and time-consuming, manual labelling or tagging of objects.Type: GrantFiled: May 4, 2020Date of Patent: September 7, 2021Assignee: The Boeing CompanyInventors: Huafeng Yu, Tyler C. Staudinger
-
Patent number: 11058971Abstract: Disclosed is an oil-water separator for offshore wind farms. The separator is arranged between an oil drain pipe and an accident oil tank, and has a cylindrical structure, and includes an oil storage compartment, a water storage compartment and a partition plate between them. The disclosure can ensure that the accident oil tank is empty under normal operating conditions so that a platform weight is reduced; and an insulation and an electric heating treatments are only performed at the oil-water separator to save insulation project quantity and energy consumption for heating; and a two-stage oil-water separation is achieved in the oil-water separator to avoid mixing oil droplets into water discharged from a water outlet.Type: GrantFiled: August 31, 2018Date of Patent: July 13, 2021Assignee: PowerChina Huadong Engineering Corporation LimitedInventors: Huafeng Yu, Haifeng Qi, Chunlin Huang, Shengxiao Zhao, Qunyi Tang, Zhenzhou Sun, Dongliang Zhang, Jianping Yuan, Xianlin Jia, Wei Lou, Baofeng Zhang
-
Patent number: 11035091Abstract: A transportation device for an offshore platform, including a vessel and a floating structure which are fixedly connected. The floating structure is placed on a sea surface and is configured to assist the vessel to sail. The floating structure is provided with an adjustment mechanism which is configured to adjust the floating structure to rise and fall relative to the sea surface. A rail is arranged on the vessel and is in sliding connection with the topside module, so that the topside module slides onto the vessel from land. During the transportation of the topside module, the buoyancy of the floating structure is adjusted through the adjustment mechanism, so that the floating structure provides sufficient anti-rolling moments beside the vessel, thereby reducing the vibration of the topside module caused by the winds and waves during the sailing and reducing the potential damage to the topside module.Type: GrantFiled: August 13, 2020Date of Patent: June 15, 2021Assignee: PowerChina Huadong Engineering Corporation LimitedInventors: Haifeng Qi, Chunlin Huang, Huafeng Yu, Baofeng Zhang, Guoer Lv, Zhenzhou Sun, Xianlin Jia, Gen Xiong, Gangjie Yu, Shanshan Huang, Guangming Xu, Ning Liang, Tianhao Li, Jiefeng Chen
-
Publication number: 20200265630Abstract: A set of 3D user-designed images is used to create a high volume of realistic scenes or images which can be used for training and testing deep learning machines. The system creates a high volume of scenes having a wide variety of environmental, weather-related factors as well as scenes that take into account camera noise, distortion, angle of view, and the like. A generative modeling process is used to vary objects contained in an image so that more images, each one distinct, can be used to train the deep learning model without the inefficiencies of creating videos of actual, real life scenes. Object label data is known by virtue of a designer selecting an object from an image database and placing it in the scene. This and other methods care used to artificially create new scenes that do not have to be recorded in real-life conditions and that do not require costly and time-consuming, manual labelling or tagging of objects.Type: ApplicationFiled: May 4, 2020Publication date: August 20, 2020Applicant: The Boeing CompanyInventors: Huafeng Yu, Tyler C. Staudinger, Zachary D. Jorgensen, Jan Wei Pan
-
Patent number: 10643368Abstract: A set of 3D user-designed images is used to create a high volume of realistic scenes or images which can be used for training and testing deep learning machines. The system creates a high volume of scenes having a wide variety of environmental, weather-related factors as well as scenes that take into account camera noise, distortion, angle of view, and the like. A generative modeling process is used to vary objects contained in an image so that more images, each one distinct, can be used to train the deep learning model without the inefficiencies of creating videos of actual, real life scenes. Object label data is known by virtue of a designer selecting an object from an image database and placing it in the scene. This and other methods care used to artificially create new scenes that do not have to be recorded in real-life conditions and that do not require costly and time-consuming, manual labelling or tagging of objects.Type: GrantFiled: June 27, 2017Date of Patent: May 5, 2020Assignee: The Boeing CompanyInventors: Huafeng Yu, Tyler C. Staudinger, Zachary D. Jorgensen, Jan Wei Pan
-
Publication number: 20200057432Abstract: A method and apparatus for performing automated supervision and inspection of an assembly process. The method is implemented using a computer system. Sensor data is generated at an assembly site using a sensor system positioned relative to the assembly site. A current stage of an assembly process for building an assembly at the assembly site is identified using the sensor data. A context for the current stage is identified. A quality report for the assembly is generated based on the sensor data and the context for the current stage.Type: ApplicationFiled: July 26, 2019Publication date: February 20, 2020Inventors: Huafeng Yu, Daniel S. ReMine, Tyler Charles Staudinger
-
Publication number: 20200058161Abstract: A method and apparatus for performing automated supervision and inspection of an assembly process. The method is implemented using a computer system. Sensor data is generated at an assembly site using a sensor system positioned relative to the assembly site. A three-dimensional global map for the assembly site and an assembly being built at the assembly site is generated using the sensor data. A current stage of an assembly process for building an assembly at the assembly site is identified using the three-dimensional global map. A context for the current stage is identified. A quality report for the assembly is generated based on the three-dimensional global map and the context for the current stage.Type: ApplicationFiled: July 26, 2019Publication date: February 20, 2020Inventors: Daniel S. ReMine, Huafeng Yu
-
Publication number: 20190366238Abstract: Disclosed is an oil-water separator for offshore wind farms. The separator is arranged between an oil drain pipe and an accident oil tank, and has a cylindrical structure, and includes an oil storage compartment, a water storage compartment and a partition plate between them. The disclosure can ensure that the accident oil tank is empty under normal operating conditions so that a platform weight is reduced; and an insulation and an electric heating treatments are only performed at the oil-water separator to save insulation project quantity and energy consumption for heating; and a two-stage oil-water separation is achieved in the oil-water separator to avoid mixing oil droplets into water discharged from a water outlet.Type: ApplicationFiled: August 31, 2018Publication date: December 5, 2019Inventors: Huafeng YU, Haifeng QI, Chunlin HUANG, Shengxiao ZHAO, Qunyi TANG, Zhenzhou SUN, Dongliang ZHANG, Jianping YUAN, Xianlin JIA, Wei LOU, Baofeng ZHANG
-
Publication number: 20180374253Abstract: A set of 3D user-designed images is used to create a high volume of realistic scenes or images which can be used for training and testing deep learning machines. The system creates a high volume of scenes having a wide variety of environmental, weather-related factors as well as scenes that take into account camera noise, distortion, angle of view, and the like. A generative modeling process is used to vary objects contained in an image so that more images, each one distinct, can be used to train the deep learning model without the inefficiencies of creating videos of actual, real life scenes. Object label data is known by virtue of a designer selecting an object from an image database and placing it in the scene. This and other methods care used to artificially create new scenes that do not have to be recorded in real-life conditions and that do not require costly and time-consuming, manual labelling or tagging of objects.Type: ApplicationFiled: June 27, 2017Publication date: December 27, 2018Applicant: The Boeing CompanyInventors: Huafeng Yu, Tyler C. Staudinger, Zachary D. Jorgensen, Jan Wei Pan
-
Patent number: 10124779Abstract: The disclosure includes implementations for supervising a data load for a vehicle. The method may include receiving report data that may describe a data load for the supervised component. The method may include retrieving specification data for the supervised component that describes a threshold for the data load. The method may include performing an analysis of the data load to determine whether the data load exceeds the threshold. The method may include providing graphical data to an electronic display panel to cause the electronic display panel to display a message responsive to the analysis indicating that the data load exceeds the threshold. The method may include providing an accommodation to the supervised component so that the data load does not exceed the threshold, where the accommodation includes stopping an operation of a device of the vehicle.Type: GrantFiled: May 20, 2016Date of Patent: November 13, 2018Inventors: Chung-Wei Lin, Huafeng Yu, Bowen Zheng
-
Patent number: 10001988Abstract: The disclosure includes a system and method for removing an incompatibility between an adaptive sensor system and an adaptive engine control unit system. The method may include detecting an update to one or more of an adaptive sensor system and an adaptive engine control unit system. The method may include identifying an incompatibility between the adaptive sensor system and the adaptive engine control unit system created by the update. The method may include determining one or more modifications for one or more of the first compatibility module and the second compatibility module. The modifications may be configured to remove the incompatibility. The method may include modifying one or more of the first compatibility module and the second compatibility module so that the incompatibility is removed.Type: GrantFiled: February 18, 2016Date of Patent: June 19, 2018Inventors: Huafeng Yu, Bowen Zheng, Chung-Wei Lin
-
Publication number: 20170339034Abstract: The disclosure includes implementations for supervising a data load for a vehicle. Some implementations of a method may include receiving report data from a communicative coupling shared with a supervised component that includes a report module that transmits a message including the report data. The report data may describe a data load for the supervised component. The method may include retrieving specification data for the supervised component that describes a threshold for the data load. The method may include performing an analysis of the data load to determine whether the data load exceeds the threshold. The method may include providing graphical data to an electronic display panel to cause the electronic display panel to display a message responsive to the analysis indicating that the data load exceeds the threshold. The method may include providing an accommodation to the supervised component so that the data load does not exceed the threshold.Type: ApplicationFiled: May 20, 2016Publication date: November 23, 2017Inventors: Chung-Wei Lin, Huafeng Yu, Bowen Zheng
-
Patent number: 9824509Abstract: The disclosure includes a system and method for providing security or fault tolerance support for an automobile or an element of an automobile. The system may include an automobile component that is communicatively coupled to a processor of an automobile. The automobile component may include a non-transitory memory storing data that is modifiable during a runtime by a middleware component of the automobile to cause the automobile to operate in compliance with one or more of a new security requirement and a new fault tolerance requirement. The data may be configured so that modification of the data affects performance of the automobile component relative to one or more of the new security requirement and the new fault tolerance requirement. The data may be modified by the middleware component at the runtime based on a set of predetermined configurations for the data that was determined at a design time.Type: GrantFiled: February 2, 2016Date of Patent: November 21, 2017Inventors: Huafeng Yu, Bowen Zheng
-
Publication number: 20170242688Abstract: The disclosure includes a system and method for removing an incompatibility between an adaptive sensor system and an adaptive engine control unit system. The method may include detecting an update to one or more of an adaptive sensor system and an adaptive engine control unit system. The method may include identifying an incompatibility between the adaptive sensor system and the adaptive engine control unit system created by the update. The method may include determining one or more modifications for one or more of the first compatibility module and the second compatibility module. The modifications may be configured to remove the incompatibility.Type: ApplicationFiled: February 18, 2016Publication date: August 24, 2017Inventors: Huafeng Yu, Bowen Zheng, Chung-Wei Lin
-
Publication number: 20170221279Abstract: The disclosure includes a system and method for providing security or fault tolerance support for an automobile or an element of an automobile. The system may include an automobile component that is communicatively coupled to a processor of an automobile. The automobile component may include a non-transitory memory storing data that is modifiable during a runtime by a middleware component of the automobile to cause the automobile to operate in compliance with one or more of a new security requirement and a new fault tolerance requirement. The data may be configured so that modification of the data affects performance of the automobile component relative to one or more of the new security requirement and the new fault tolerance requirement. The data may be modified by the middleware component at the runtime based on a set of predetermined configurations for the data that was determined at a design time.Type: ApplicationFiled: February 2, 2016Publication date: August 3, 2017Inventors: Huafeng Yu, Bowen Zheng