System and method for cyber-physical inspection and monitoring of nonmetallic structures

    公开(公告)号:US11386541B2

    公开(公告)日:2022-07-12

    申请号:US16548509

    申请日:2019-08-22

    Abstract: A technological solution for analyzing a sequence of electromagnetic spectrum image frames of a nonmetallic asset and detecting or predicting an aberration in the asset, including a detected or predicted location of the aberration. The technological solution includes receiving the electromagnetic spectrum image frames by a pair of machine learning systems of different types, applying a machine learning algorithm to the electromagnetic spectrum image frames to stratify the electromagnetic spectrum images into abstraction levels according to an image topology and output first aberration determination information, applying a second machine learning algorithm to the electromagnetic spectrum image frames to detect patterns in electromagnetic spectrum images over time and output second aberration determination information, generating an aberration assessment based on the first and second aberration determination information, and transmitting the aberration assessment to a communicating device, including a prediction and location of an aberration in or on the nonmetallic asset.

    METHOD FOR INSPECTING COMPOSITE STRUCTURES USING QUANTITATIVE INFRA-RED THERMOGRAPHY

    公开(公告)号:US20210208091A1

    公开(公告)日:2021-07-08

    申请号:US17206992

    申请日:2021-03-19

    Abstract: A system and method for inspecting a surface of a structure for defects includes an inspection apparatus having a heating device for heating a section of the surface of the structure, an infrared camera for receiving infrared radiation from the surface in response to heating, a controller configured to generate thermographs from the received infrared radiation, and a communication device. A training system includes an expert system module configured to determine correlations between a set of thermographs generated by a thermal simulation of modeled structural elements with defects, and parameters of the modeled structural elements. A computer system communicatively coupled to the training system and the inspection apparatus, is adapted to receive thermographs received from the inspection apparatus and to detect quantitative parameters of defects in the structure using the correlations obtained from the training system.

    Thermography image processing with neural networks to identify corrosion under insulation (CUI)

    公开(公告)号:US10768094B2

    公开(公告)日:2020-09-08

    申请号:US16711099

    申请日:2019-12-11

    Abstract: A method for identifying corrosion under insulation (CUI) in a structure comprises receiving thermographs from the structure using an infrared camera, applying filters to the thermograph using a first machine learning system, initially determining a CUI classification based on output from the filters, and validating the initial CUI classification by an inspection of the structure. The first machine learning system is trained using results of the validation. Outputs of the first machine learning system and additional structural and environmental data are fed into a second machine learning system that incorporates information from earlier states into current states. The second machine learning system is trained to identify CUI according to changes in the outputs of the first machine learning system and the additional data over time until a second threshold for CUI classification accuracy is reached. CUI is thereafter identified using the first and second machine learning systems in coordination.

    INSPECTION AND FAILURE DETECTION OF CORROSION UNDER FIREPROOFING INSULATION USING A HYBRID SENSORY SYSTEM

    公开(公告)号:US20200072744A1

    公开(公告)日:2020-03-05

    申请号:US16214615

    申请日:2018-12-10

    Abstract: A system for predicting and detecting of corrosion under fireproof insulation (CUF) in an infrastructure asset comprises a first detection apparatus adapted to capture thermal images of the asset, a second detection apparatus adapted to receive THz radiation from the asset, and at least one ambient condition sensor for detecting environmental conditions at a location of the asset, a communication device coupled to the first and second detection apparatus and at least one ambient condition sensor to receive data therefrom and adapted to communicate the received data, and a computing device communicatively coupled to the communication device and configured with instructions for executing a machine learning algorithm taking as inputs the thermal image, THz and ambient condition data received from the communication device, and to output a CUF prediction regarding the asset.

    Thermography image processing with neural networks to identify corrosion under insulation (CUI)

    公开(公告)号:US10551297B2

    公开(公告)日:2020-02-04

    申请号:US15712490

    申请日:2017-09-22

    Abstract: A method for identifying corrosion under insulation (CUI) in a structure comprises receiving thermographs from the structure using an infrared camera, applying filters to the thermograph using a first machine learning system, initially determining a CUI classification based on output from the filters, and validating the initial CUI classification by an inspection of the structure. The first machine learning system is trained using results of the validation. Outputs of the first machine learning system and additional structural and environmental data are fed into a second machine learning system that incorporates information from earlier states into current states. The second machine learning system is trained to identify CUI according to changes in the outputs of the first machine learning system and the additional data over time until a second threshold for CUI classification accuracy is reached. CUI is thereafter identified using the first and second machine learning systems in coordination.

    Field deployable docking station for mobile robots

    公开(公告)号:US10133277B1

    公开(公告)日:2018-11-20

    申请号:US16106407

    申请日:2018-08-21

    Abstract: A deployable docking station for supporting at least one mobile robot is provided. The deployable docking station includes a housing and an anchor connected to the housing. The anchor can engage with a surface to maintain the position of the deployable docking station. The deployable docking station is further configured to couple and decouple with the at least one mobile robot. The deployable docking station can be configured to selectively alternate between a first and second condition. In the first condition, the deployable docking station is coupled with the at least one mobile robot and the at least one mobile robot can transport the deployable docking station to a desired location on the surface. In the second condition, the deployable docking station is de-coupled from the at least one mobile robot.

Patent Agency Ranking