Siemens Energy, Inc.

Kevin P Bailey

Ziyan Wu

Jan Ernst

Terrence Chen

Rameswar Panda

Birgi Tamersoy

Randy Edward Whitener

Neil Leslie Kilpatrick

Kalyan Kannan

A method of determining the risk of a stator failure is provided. The stator includes multiple stator coil windings. Each of the windings includes multiple conductive metal strands. The number of strand failures is determined from an image captured by a radiography. A risk analysis is assessed from the determined number of strand failures.

Method of assessing the risk of a stator failure

Method and system for detecting defects on surface of object are presented. An imaging device captures images of surface of object under ambient and dark field illumination conditions. The images are processed with a plurality of image operations to detect area of potential defect at location on surface of object based on predictable pattern consisting of bright and shadow regions. Kernels are defined corresponding to configurations of dark field illumination sources to enhance detecting potential defect. Areas of potential defect are cut from processed images to sub images. Sub images are stitched together to generate hypothesis of potential defect at location on surface of object. The hypothesis is classified with a classifier to determine whether the potential defect is true defect. The classifier is trained with training data having characteristics of true defect. The method provides efficient automated detection of micro defects on surface of object.

Method and system for detecting defects on surface of object

Method and system for detecting line defects on surface of object are presented. An imaging device captures images of surface of object under ambient and dark field illumination conditions. The images are processed with a plurality of image operations to detect areas of potential defects based on predictable pattern consisting of bright and shadow regions. Areas of potential defect are cut from processed images to sub images. Sub images are stitched together to generate hypotheses of potential defects at locations on surface of object. The hypotheses are classified to determine whether the potential defects are true defects at the locations. Line defect is detected by refining line segments detected on the processed image based on criteria. The criteria include distance from the true defects to the line segments and slops between the true defects and the line segments are less than threshold values.

Method and system for detecting line defects on surface of object

A method for inspecting an object to assist in determining whether the object has a surface defect. The method includes moving the object in a first direction and illuminating the object under ambient lighting conditions. The method also includes capturing at least one image of the object under the ambient lighting conditions while the object moves in the first direction. In addition, the object is illuminated under object lighting conditions and at least one image of the object under the object lighting conditions is captured while the object moves in the first direction to provide at least one object image. Further, the method includes selecting at least one object image having at least one indication of a possible defect to provide images having defect candidates and comparing the defect candidates with previously defined characteristics associated with the defect to facilitate determination of whether a defect exists.

System and method for enhancing visual inspection of an object

A method for verifying a lighting setup used for inspecting a micro defect. The method includes simulating a scene including a micro defect, light source and imaging device. A position of the light source and imaging device is then optimized to form an optimized simulated setup for viewing micro defect. A shadow calibration reference (SCR) having a simulated shadow field is then rendered in a location. Next, a physical imaging device and light source are positioned based on information from the optimized simulated setup to form an optimized physical setup. A physical SCR based on information from the SCR rendering is fabricated. Next, an image is captured of a physical SCR in a corresponding location associated with each SCR rendering. The optimized physical setup is verified if at least one shadow parameter from the SCR rendering is substantially similar to a corresponding shadow parameter in a corresponding image.

Method and apparatus for verifying lighting setup used for visual inspection

Eddy current non-destructive examination and evaluation of physical properties of a component, such as a generator retaining ring, after experiencing potentially degrading thermal exposure during any stage of manufacture, assembly and service use, is performed to determine whether it is acceptable for service use, requires further modification (e.g., additional heat treatment processing) or whether is permanently unsuitable for service. Eddy current test measurements are correlated with component temperature exposure (e.g., absolute temperature and/or cumulative time-temperature heat absorption) and cumulative alteration of the component physical properties, such as, among others, material yield strength (YS), toughness, and tensile ductility. Using the eddy current test measurements and reference data correlating electrical conductivity with ring material thermal exposure, the component's physical properties are evaluated to determine its serviceability. The testing can be performed in situ in the field, such as for evaluation of generator rings within field serviced generators.

Growing community of inventors

Chuluota, FL, United States of America

Kevin P Bailey