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

EVA AI Visual Inspection Equipment

EVA AI visual inspection equipment targets ethylene vinyl acetate foam, performing inline inspection of chipped corners, bubbles, indentations, color differences, surface roughness, poor adhesion and other defects, with OK/NG output and production line interlocking.

Materials Overview

Closed-cell resilient surface: bubbles and indentations are the focus

Quick answers

EVA AI visual inspection equipment images ethylene-vinyl acetate foam; the algorithm identifies defects such as missing corners, bubbles, indentations, color difference, rough surface and poor adhesion, outputs OK/NG results and interlocks with the production line.

EVA (ethylene-vinyl acetate copolymer) foam is closed-cell and resilient, with a surface that is more uniform and finer than open-cell sponge, and is commonly used in footwear materials, sports mats, packaging and electronic cushioning. Its difficulty lies in the "bubbles" and "indentations" on the closed-cell surface — both appear as local bulges or depressions, and normal process variation must be distinguished from defects.

Defects specific to EVA include bubbles (abnormal bulging of closed cells), missing corners (cutting / transport damage), indentations (crushing), color difference, rough surface and poor bonding (multi-layer EVA or multi-material lamination). Poor bonding is the hidden risk in multi-layer structures.

Inspection uses AI to build a model of the normal closed-cell surface and judges abnormal bulges, collapse and rupture as defects; changing color and hardness mainly means adjusting illumination and recipes.

Applicable Type

EVA Foamed Sheet

Closed-cell; the focus is on bubbles and indentations

EVA midsole

For footwear material, the focus is on missing corners and color difference

Laminated EVA

Multilayer lamination, the focus is on poor adhesion

EVA Cut Pieces

Already cut, inspected piece by piece with defect locating

EVA Roll Stock

Continuous material feed, line-scan full-width inspection

Common defect

Defect TypesTypical ManifestationsInspection Focus Points
BubblesAbnormal closed-cell bulgingDistinguished from normal surface
Missing cornerIncomplete OutlineRequires Positioned Measurement
indentationCrush CollapseLow-angle light forms a clear image
color difference Inconsistency Within BatchStable Color Reference
Rough SurfaceLocal RoughnessGrayscale Statistics
Poor BondingInterlayer SeparationFocus on the Edges
Stain / Foreign MatterOil Stains, ParticlesDistinguish From Surface
crack Surface CrackingLow-Angle Light

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 EVA loading / roll unwinding or cut-piece infeed
  • 02 Flattening and tension control
  • 03 Triggered Imaging
  • 04 Closed-cell surface modeling
  • 05 Anomaly region segmentation
  • 06 Defect classification and grading
  • 07 Dimension / contour judgement (optional)
  • 08 Synthesized OK / NG
  • 09 Marking / rejection and image archiving

AI Inspection Principles

AI Visual Inspection Principles

The core of EVA inspection is "finding anomalies on a closed-cell, resilient surface". The algorithm builds a model of the normal surface and classifies bubbles, indentations, chipped corners and cracks as defects. The difficulty is that both bubbles and indentations appear as local bulges / depressions, so normal process features must be distinguished from defects.

For illumination, diffuse light provides uniform lighting and reveals color difference and stains; low-angle light exposes indentations, bubbles and cracks. Stains on dark EVA and indentations on light EVA require separate lighting setups, with recipes grouped by color.

For judgement, we recommend setting missing corners and cracks as high priority, and grading bubbles and indentations by degree. The specific thresholds must be confirmed by measured testing with OK / NG samples.

Applicable Industry

Applicable equipment

Common Question

How are bubbles and indentations in EVA distinguished?
Bubbles are abnormal bulges of closed cells and are fairly round in shape; indentations are crushing collapse and appear strip-like or sheet-like. Sample training is needed to distinguish them, confirmed by measurement on OK / NG samples.
Can interlayer problems in laminated EVA be detected?
Visible surface separation and edge bulging can be inspected; internal interlayer problems that have not formed a clear image are not visible, require other methods, and are outside this equipment's capability.
Is EVA Inspection Very Different from Foam Inspection?
EVA is mostly closed-cell with a more uniform surface, while foam can be open-cell with more visible pores. The model and illumination must be adjusted accordingly; the hardware can be shared.
Do different-colored EVA grades need separate recipes?
Usually yes. Dark colors hide stains and light colors hide indentations, requiring opposite illumination strategies, so light source recipes are generally configured in groups by color.
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 in different colors and different hardness levels (laminated / single layer), the defect acceptance criteria, loading 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 EVA samples in different colors and hardnesses (bonded / single layer), and we will run surface modeling and defect measurements and provide illumination plan and grading 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