Common challenges in manufacturing:

100% assurance in cognitive quality control not sampling
  • In high volume production lines, visual inspection becomes the bottleneck process. Conflict between speed and QC

  • Quality control usually done in batches – wasteful loss on batch reject, risk of batchlevel approvals.

Traditional machine vision has not worked
  • Most existing machine vision solutions detect anomalies and not defects.

  • They are not equipped to handle drift in manufacturing process, causing high cost of repurposing

Calibration of economic and quality levers
  • In high volume production lines, visual inspection becomes the bottleneck process. Conflict between speed and QC

  • Quality control usually done in batches – wasteful loss on batch reject, risk of batchlevel approvals.

Reliance on individuals - Expensive and shortage of expertise
  • Unavailability of trained Subject Matter Experts (SME). Loss of community knowledge when SME quits

  • Manual Inspection is highly subjective. Results in inconsistent output. Human accuracy rarely exceeds 85%, usually due to employee fatigue. Leads to excess false positives, wasteful rejection

Quality control in manufacturing

Traditional QC
  • Manual inspection of basic defects that an eye can see (cognitive and measurable) – at a batch level/QC by sampling

  • Lower accuracy levels, defect leakage and bottlenecks in production line

Evolved QC
  • Using machine vision (cameras) to detect anomalies (anything that doesnt look like a perfect model)

  • Only able to detect defects at a basic level.

  • Image to image comparisons result in high false positives.

Next Generation QC
  • AI powered Automated Cognitive Quality Control Solution

  • Using AI to understand defects and its types and make intelligent decisions that ensure high quality products – just like a good subject matter expert would

  • Fully automated, high accuracy, high speed and consistency.

Our Solutions
Incoming, In-process and final Inspection

elasticity.png
Surface defect - object detection

​Designed to look for specifically defined objects -  can be trained and added to defect library

genetics.png
Anomaly detection

​Anomaly Detection aims to identify anomalies - Anything that doesnt look like the original is a defect

teamwork.png
Assembly verification - classification

Designed to look for low no of defects in specific areas

headphones.png
Audio defect

​Designed to look for variations in decible levels and vibrations

label.png
Identification services

Designed to look for anomalies on printed material - labels, barcodes and QR Codes

Industries we work with

Automotive

  • Fine blanking and forging part - surface defects - dents, damages, scratches, cracks,rust/colour difference

  • Assembly and casting parts - process/part missing, product sorting, Counting in
    packaging and assemblies, Wet leak test

  • Ground and machine parts - Counting in packages and assemblies

  • Radiography - defects on Xray - porosity, shrinkage

  • Print quality - colour, offsets, misprints, smudges. Content error

  • Noise-based inspection (NVH) - Seatbelt, Car horn

  • All Products - product sorting, dimension measurement

General Manufacturing

  • Packaging and printing - colour, offsets, misprints, smudges. Content error

  • Textiles - holes, gaps, stitch defects, colour differences, etc.

  • Machine tools - parts missing, Wrong sequence in assembly

  • Airconditioning - validating ducts/tubes and final packaging

  • Solar panels - surface defects - dents, damages, scratches, cracks,
    colour difference

  • Electricals - presence/absence

Pharma

  • Vials and cartridges - surface defects on containers, foreign particle presence, bubble detection

  • Tablets and capsules - surface defects, foreign particles

  • Needles - surface defects, dimension measurement

Electronics

  • Printed circuit boards - presence/absence

  • Assemblies (capacitor/resistor) - validation, presence/absence

  • Soldering - Wrong/improper soldering

Food

  • Packaging - colour, offsets, misprints, smudges. Content error

  • damages - crushed, broken, discoloured food products

  • assembly - parts missing, Wrong sequence in assembly, counting

  • Product inspection - presence/absence

Equipment Manufacturers

  • Accuracy certificate with consignment - surface defects - dents, damages, scratches, cracks, rust/colour difference

In-machine Realtime Inspection 

  • Authentication process (automated) - surface defects, dimension measurement
    Parts missine, colour, offsets, misprints, smudges. Content error. Wrong sequence in assembly, Wrong /improper soldering

Cutting Edge Analytics identifying process drifts

Step 1. Training data to AI 

QC Baseline (50 samples) 

CEAIP.png

Step 2. AI in production

Raw image with AI inference

CEAIP 2.png
  • Labels indicates data collected

  • Captures “community knowledge”, which acts as benchmark

  • Matches shop floor information with reality

Step 3. Outcome from Heatmap Production trend 

Month 1 in production: 514 instances

CEAIP 3.png

Month 2 in production: 429 instances

CEAIP 4.png
  • Month 1 closely reflecting trained data 

  • Month 2 – process drift identified ! Major occurrences of defect changed orientation

  • Visual summary of occurrence trend for each type of defect by location

  • Critical input for Preventive Action and continuous improvement

Cutting Edge Analytics recognizing and Clustering Defects

CEARCD.png

The Cluster map shows…

  • Pattern in defects will be identified and grouped as clusters

  • Mapping of existing defects

  • Simultaneous mapping of other possible defects/features not trained to AI model

Key Outcomes of the analysis

  • Helps prioritize focus areas

  • Allows to identify clusters and reclassify them as OK or NG

  • Allows for continuous upskilling for new defect identification and improving accuracy of the end product