Welcome to Kunshan EEK Automation Equipment Co., Ltd.
Home/Materials /Carbon Fiber Prepreg AI Visual Inspection Equipment

Carbon Fiber Prepreg AI Visual Inspection Equipment

Carbon fiber prepreg AI visual inspection equipment targets resin-impregnated carbon fiber fabric, performing inline inspection of fiber direction, wrinkles, resin starvation and excess resin, white strands, missing weft, scratches, delamination and other defects, with OK/NG output and production line interlocking.

Materials Overview

Fiber-direction sheen + resin reflection; wrinkles and white filaments are the key focus

Quick answers

Carbon fiber prepreg AI visual inspection equipment images resin-impregnated carbon fiber cloth; the algorithm identifies defects such as fiber orientation deviation, wrinkles, resin starvation and resin-rich areas, white strands, missing weft, scratches, and delamination, outputs OK/NG results, and interlocks with the production line.

Carbon fiber prepreg is a semi-finished product made by impregnating carbon fiber fabric with resin, where fiber orientation and resin content are both critical. Its difficulty lies in the double reflection of "fiber + resin": carbon fiber has directional gloss, so unidirectional and woven fabrics reflect differently; the resin also forms a reflective film on the surface that hides defects such as wrinkles, white strands, and resin-starved areas.

Defects specific to carbon fiber prepreg include fiber orientation deviation (ply misalignment), wrinkles (bending damage), resin starvation / resin-rich areas (uneven resin), white strands (exposed fibers not fully impregnated), missing weft, scratches and delamination. Wrinkles and white strands have a major effect on the strength of the finished part and are key items to intercept.

Inspection uses AI to build a model of the normal fiber texture and gloss, and judges direction deviation, wrinkles and white strands as defects; resin reflection needs stripe / coaxial light suppression. Changing the weave (unidirectional / plain / satin) mainly means adjusting the recipe.

Applicable Type

Unidirectional Prepreg

Aligned fibers, key points: direction and white fibers

Woven Prepreg

Plain weave / satin weave, key points: wrinkles and missing weft

Prepreg Roll Stock

Continuous material feed, line-scan full-width inspection

Prepreg Cut Pieces

Already cut, inspected piece by piece with defect locating

Narrow-width Prepreg

Narrow-width special specification, the focus is on edges

Common defect

Defect TypesTypical ManifestationsInspection Focus Points
Fiber orientation deviationPly placement / weave direction misalignmentOrientation Angle Measurement
wrinkleBending DamageLow-angle light forms a clear image
Resin Starvation / Resin RichUneven ResinSuppress resin reflection
White streaksExposed fibers, incomplete impregnationContrast Against Black Filaments
Missing weftMissing Weft YarnCompare With Weave Pattern
ScratchesSurface DamageRequires Reflection Suppression
DelaminationInterlayer SeparationFocus on the Edges
Foreign Matter / StainParticles, Oil StainsHigh-contrast Features

inspection Workflow

Complete chain from loading to judgment

Visual inspection judgement chainThe complete chain from image acquisition to OK/NG judgement and PLC interlocking.image acquisitiontrigger captureTarget Positioningtemplate matchingfeature recognitionAlgorithm JudgementResult JudgementOK / NGindustrial communicationPLC interlockingRelease OKRejection / NG AlarmEvery step's result retains the image and judgement item, for traceability and review
Inspection Judgement Chain — Acquisition → Positioning → Recognition → Judgment → Communication interlocking; the entire chain runs locally on the machine.
  • 01 Prepreg loading / roll unwinding or cut-piece feeding
  • 02 Flattening and tension control
  • 03 Triggered imaging (resin reflection suppression)
  • 04 Fiber direction angle measurement
  • 05 Weave modeling
  • 06 Defect segmentation and classification
  • 07 Defect Grading
  • 08 Synthesized OK / NG
  • 09 Marking / rejection and image archiving

AI Inspection Principles

AI Visual Inspection Principles

Inspection of carbon fiber prepreg is difficult because of "fiber sheen + resin reflection." The algorithm builds a model of normal fiber texture and orientation and classifies orientation deviation, wrinkles, white strands and resin starvation/resin-rich areas as defects; resin reflection must be suppressed with stripe / coaxial light, otherwise wrinkles and white strands are masked.

For illumination, stripe light / coaxial light is used to suppress specular reflection from the resin and to highlight fibers and wrinkles; low-angle light is used to reveal white strands and bends. Unidirectional and woven fabric reflect light differently, so separate recipes are required.

For judgement, we recommend setting wrinkles and white fiber as high priority (they affect strength), with fiber orientation judged by angular tolerance. Specific thresholds need to be confirmed by measured testing with OK / NG samples.

Applicable Industry

Applicable equipment

Common Question

Does resin reflection on carbon fiber prepreg mask defects?
Yes. Resin forms a reflective film on the surface that masks wrinkles, white strands and resin-starved areas, so stripe / coaxial light is needed to suppress reflection, followed by low-angle light to make them visible. Reflection suppression is subject to measurement on samples.
Can Fiber Orientation Deviation Be Measured?
Yes. The fiber orientation angle is measured to check whether the layup / weave direction is offset; exceeding the tolerance is judged an anomaly, and the angle tolerance is subject to the customer's acceptance criteria.
How Do You Tell White Yarn from Normal Black Yarn?
White fiber is fiber that is exposed and not fully impregnated; it appears as light-colored strands with clear contrast against black carbon fiber, but resin reflections must be suppressed for stable recognition, to be confirmed by measured sample testing.
Can Internal Delamination Be Detected?
Surface vision can detect edge separation and surface anomalies caused by delamination, but internal delamination that does not form a clear image is invisible and requires other methods, which is outside the capability of this equipment.
What is the inspection accuracy?
To be added. Accuracy is determined by the field of view and camera resolution: pixel equivalent = FOV ÷ pixel count. First define the minimum defect size, then work back to the imaging solution and validate it by measurement with samples.
What samples are needed to develop a solution?
Provide OK and NG samples of different types such as unidirectional / woven, the defect acceptance criteria, feeding format and production line cycle time.
Can It Be Integrated Into an Existing Production Line?
Yes. The system exchanges data with the PLC over I/O, TCP, RS485, Modbus, S7, Profinet and others, and outputs OK/NG to trigger rejection; the specific protocol depends on the site.

Submit sample testing

Send us OK and NG samples of different types of carbon fiber prepreg, such as unidirectional and woven, and we will carry out resin reflection suppression and measured fiber orientation testing, then give illumination solution recommendations.

JPG / PNG supported, multiple files allowed
Each file must not exceed 20 MB
    JPG / PNG supported, multiple files allowed
    Each file must not exceed 20 MB
      JPG / PNG supported, multiple files allowed
      Each file must not exceed 20 MB
        A solution engineer will contact you within 1 business day after submission

        Need to assess imaging conditions, defect criteria and cycle time item by item? Go to the Full Requirement Assessment →

        Send Us Your Material and We Will Show You the Measured Results

        Provide several OK and NG samples of the material, and a solution engineer will run actual imaging and judgement tests on the equipment to give a workable inspection configuration recommendation, rather than reading the datasheet alone.

        Online support WhatsApp
        WeChat
        Scan the QR code to add us on WeChat
        Call us Back to top