Provided is a system and method for visual inspection. The system may be used in a quality assurance station at a manufacturing facility or site. The system may evaluate and determine the quality of manufactured or fabricated articles. The system may include a mechanical subsystem for capturing images of the article. The system may include a sensor such as a camera for capturing data, such as images. The system may include an artificial intelligence system to determine if the article suffers from an impermissible defect.

A system and method are disclosed for enhancing pit detection and sizing in a test object. Response signatures are created and stored in a signature library to characterize various sensor responses (liftoff, orientation) and pit properties (e.g., depth, width), possibly with or without additional considerations (e.g., edges, cracks). A sensor is placed on and scanned across a surface of interest on the test object. During scanning the sensor is measured repeatedly at regular intervals. An encoder may be used to record the sensor position for each measurement. The measurement results are then correlated with one or more signatures in the signature library. A threshold is used to determine if the correlation is indicative of the detection of a pit. If so additional processing may be performed to estimate pit properties.

The present invention discloses a boom monitoring method and engineering machinery comprising a boom monitoring system. The method comprises obtaining a boom damage signal monitored in boom operation by a piezoelectric sensing network formed by a plurality of piezoelectric sensors arranged at different points on a boom, and determining a damage position of the boom and a corresponding first boom damage value such that when the first boom damage value reaches a preset starting value of an optical fiber sensing network formed by a plurality of optical fiber sensors arranged at the different monitoring points on the boom, optical wave values of the corresponding monitoring points are obtained and a boom crack signal is determined. A second boom damage value is calculated according to the boom crack signal, which comprises a crack change factor and a crack length. According to the present invention, the boom is monitored with improved efficiency.

An inspection device includes a scanning device, a first recognition unit, and a second recognition unit. The scanning device includes a laser sensor that emits laser slit light for measuring a two-dimensional shape, and a movement mechanism that moves the laser sensor in a predetermined direction. The first recognition unit obtains three-dimensional shape data of an inspection object and a workpiece by associating a plurality of two-dimensional shape data obtained by the laser sensor with position data of the laser sensor at the time of measuring the two-dimensional shape. The second recognition unit derives a three-dimensional shape of the workpiece by obtaining a difference between first three-dimensional shape data indicating a three-dimensional shape before the workpiece is laminated on the mold and second three-dimensional shape data indicating a three-dimensional shape after the workpiece is laminated on the mold.

A surface defect inspection assembly that includes translation means configured to move a part in an advance direction in a first axis. The assembly also includes a structure that supports at least one mobile inspection head that is used for inspecting the surface of the part. The mobile inspection head including a light emitter configured to emit at least one light profile on the part and means for receiving the light reflected by the part. The assembly also includes a control unit that is configured to process the reflected light and to determine if a detect exists in the surface of the part. The control unit is additionally configured to activate one or more motors to move the mobile inspection head in response to the light reflected by the part while the translation means is moved in the advance direction, orienting the light profile towards the part.

A method, system and devices for optical structural health monitoring that implements digital image correlation (DIC) by applying an invisible pattern comprising a random dot pattern and/or codes, which is applied using a coating containing a dye or substance that is not visible during the normal lighting conditions. The structure is imaged at different time intervals by capturing images of the pattern and codes using a camera and suitable light source. The captured images of the pattern and codes are stored in a CAD file that represents the structure or part to which the pattern and codes are applied, and includes the locations of the pattern and codes. Comparative measurements of the pattern and codes (e.g., using DIC) determine one or more structural health parameters, such as strain, deformation, and other stresses or averse conditions that may be detected from one interval to another (e.g., between measurements).

An imaging system is for recording images of a bearing raceway and includes a platform having a surface sized to receive the bearing ring and an optical imager having a lens. A positioner secures the optical imager or a reflector oriented to reflect light to the optical imager lens and locates the optical imager lens or the reflector axially between first and second axial ends of the raceway and facing generally toward the raceway. A motor rotates the platform or the positioner relative to the other one of the platform and the positioner. A processor operates the optical imager and the motor such that the optical imager takes a series of images about the entire perimeter of the bearing raceway. The processor also indexes each image to a separate one of a plurality of arcuate segments of the raceway and constructs a panoramic image of the raceway.

A self-calibrating inspection system includes an inspection device adapted to visually inspect or measure an article placed on a carrier, and a motion actuator moving the inspection device along a predetermined motion trajectory relative to the carrier and the article placed thereon. A correction member of the system is fixedly positioned with respect to the carrier. A distance sensor is fixedly positioned relative to the inspection device and adapted to sense a first spacing between the distance sensor and the correction member during the movement of the inspection device by the motion actuator. A controller communicates with the motion actuator and the distance sensor for determining a deviation between an actual motion trajectory of the inspection device moved by the motion actuator and the predetermined motion trajectory based on the first spacing, and to control the motion actuator based on the deviation to move the inspection device along a path substantially consistent with the predetermined motion trajectory.

An artificial neural network-based method for detecting a surface type of an object includes: receiving a plurality of object images, wherein a plurality of spectra of the plurality of object images are different from one another and each of the object images has one of the spectra; transforming each object image into a matrix, wherein the matrix has a channel value that represents the spectrum of the corresponding object image; and executing a deep learning program by using the matrices to build a predictive model for identifying a target surface type of the object. Accordingly, the speed of identifying the target surface type of the object is increased, further improving the product yield of the object.

Provided are a structure inspection method and a structure inspection system capable of efficiently inspecting structure and predicting deterioration with high accuracy. The structure inspection method includes: acquiring information on a location having internal damage within an inspection target region; and imaging the inspection target region with a visible light camera a plurality of times while shifting an imaging location, wherein a location except for the location having the internal damage is imaged with first pixel resolution and the location having internal damage is imaged with second pixel resolution higher than the first pixel resolution. Damage appearing on a surface of the structure is detected on the basis of a visible light image captured by the visible light camera. Information on the location having internal damage within the inspection target region is acquired by capturing an image that visualizes an internal state of the inspection target region.