SolVisionCase Study

Petrochemicals, Plastics, and Rubber

Inspecting Rubber Injection Molded Parts Using AI

Case

Factors and Defects in Rubber Injection Molding

The rubber injection molding process is influenced by various factors including the quality of raw materials, machine specifications, mold parts, and injection parameters. Defects can occur, spanning from minor aesthetic issues like stains and scratches to significant structural damage resulting from inadequate material or mishandling during ejection.

Interface of SolVision AI Vision system software Inspecting rubber injection molded parts

Challenge

Limitations of Conventional Vision Systems

Conventional rule-based vision systems, reliant on extensive data for training, have struggled with the dynamic nature and varying locations of defects in injection molded parts, leading to low accuracy rates. Manual inspection, hampered by the lack of standardized defects, has proven too slow and inconsistent for effective quality control.

Solution

Precise Injection Molded Parts Inspection Using AI

SolVision employs AI deep learning to inspect injection molded parts by analyzing sample images to learn the distinct characteristics of various defects, enabling precise detection and identification. As the database is enriched with additional images, the AI model strengthens, enhancing the system’s accuracy in defect recognition.

Defect Detection

Uneven incisions defects on a rubber injection molding part

Uneven Incisions

Missing material defects on a rubber injection molding part

Missing Material

Mold crush defects on a rubber injection molding part

Mold Crush

Stain defects on a rubber injection molding part

Stain

Outcome

Streamlined the quality control process
Enabled precise detection of various defects
Constantly improved detection recognition through deep learning
Related Posts
  • Central Processor Of A Computer

    Inspecting Semiconductor Packaging Processes

    SolVision enables visual inspection through AI image analysis, strengthening the reliability of displacement and angle information to recognize defective products and errors in the die bonding process.
    SolVisionCase StudiesDefect DetectionSemiconductors
  • a group of square objects

    Automating Semiconductor Wafer Inspections

    Faulty wafers also usually have subtle defects randomly scattered on the surface, and this prevents AOI systems from setting rules for efficient inspections.
    SolVisionCase StudiesDefect DetectionQuality/Safety InspectionSemiconductors
  • a group of square objects

    Detecting Chipping Defects in Wafer Dicing

    The location, size and shape of cracks vary each time, and traditional optical inspection cannot accurately identify such unpredictable defects.
    SolVisionCase StudiesDefect DetectionQuality/Safety InspectionSemiconductors

  • Egg Quality Inspection Using AI

    SolVision recognizes defects and categorizes eggs, enabling automated AI inspection on a fast moving production line for better food safety and quality control.
    SolVisionCase StudiesClassificationDefect DetectionFood and Beverage