Machine Vision System / AIDC - PumasAutomation & Robotics Pte Ltd

Automated Vision Inspection for Automotive QA

webadmin — Thu, 13 Apr 2023 00:51:24 +0000

Automated Vision Inspection for Automotive QA

SSCN Number : SSCN-0009
Project Number : FASKL-1711-224
Solution : Automated Vision Inspection
Industries : Automotive-Plastic

Problem Statement

– In QC process an operator visual check the part and some time misjudged the defective part. This caused a lot rework job needed when quality issue feedback from end-user.

Solutions

– Using the 5 Mega camera to detect the burr and stain defects

– Two combinations of the light to handle the different type of the defects

Results

– Our Vision Solution successfully implemented in Malaysia’s Automotive Industry.

– Door Plastic Panel Inspection.

– We have provided and supported our customer with our High-Resolution vision system for their production line automation project – Inspection process of car interior panels.

The post Automated Vision Inspection for Automotive QA first appeared on PumasAutomation & Robotics Pte Ltd.

Inspection System for Filter Positioning

webadmin — Thu, 13 Apr 2023 00:48:37 +0000

Solutions

Inspection System for Filter Positioning

Industry: Semiconductors / Electronics
Brands: Cognex Insight Camera
Case Number: TH-0018
Solution: Vision Inspection

Problem Statement

Customer has a problem on filter positioning not installed properly. So, they need to inspect the gap between filter and media. Gap > 100mm is good part and gap < 100mm will be rejected.

Solution

Cognex 7000 Series Vision System is used to address the issue.

Customer’s Feedback

With our Vision Inspection System, it can reduce the cost of 2 operators and also do 100% real-time inspection without error.
Also increase productivity around 10 times, inspection time reduced from 10 seconds to 1 second.

The post Inspection System for Filter Positioning first appeared on PumasAutomation & Robotics Pte Ltd.

Precision Pick & Place Unit for Circuit Board Assembly

webadmin — Thu, 30 Mar 2023 09:12:51 +0000

Solutions

Precision Pick & Place Unit for Circuit Board Assembly

Industry: Automotive
Brands: Epson & Cognex
Case Number: CN-0016
Solution: Robotics and Vision Inspection

Problem Statement

Refer to the work flow, the project is splitted into following sub-projects：
1.Epoxy dispensing.
2.Air bubble check after dispensing.
3.Circuit board casing.
4.Label checking.
5.Temp cycle test after casing.
6.Mounting Assembly.

Solution

By using Epson Robot and Cognex Vision System. With precision pick and place by the Epson robot, plus accurate positioning and inspection of the Cognex vision system.

Result & Benefit

With the Epson robot, there is a reduction of the generation of bubbles and no leaking, resulting in uniform coating and speed is improved. Most importantly, the robot achieve efficiency and a higher inspection pass rate.

The post Precision Pick & Place Unit for Circuit Board Assembly first appeared on PumasAutomation & Robotics Pte Ltd.

Deep Learning-based Approach to OCR

webadmin — Tue, 28 Mar 2023 01:00:10 +0000

Solutions

Deep Learning-based Approach to OCR

SSCN Number : SSCN-0029
Project Number : FASKL_VKL2011127
Industry : Others
Solution : Machine Vision System/AIDC
Brands : Cognex

Problem Statement

The graphite electrode is labeled with a unique code for monitoring and tracking purpose. This unique code contains alphanumeric character that is stamped onto a graphite electrode. Poorly stamped characters, confusing background and unwanted noise make it difficult for a machine vision system with traditional rules-based approach to recognize the characters.

Solutions

With In-Sight ViDi, a powerful deep learning software platform, the In-Sight D900 vision system is able to read characters under challenging situations such as noisy backgrounds and poorly stamped characters. In the training phase, images under different conditions were collected and labeled for training and validation purposes. During training & validation phase, re-labelling of the incorrect characters or missed characters is done until the software’s model is able to correctly identifies all characters. When deployed, the In-Sight ViDi Read tool operates on input images and produces results based on the validated training data.

Benefits

Good reading rate for low quality ID stamped characters. With deep learning-based OCR, reading rate improves by at least 20% as compared to traditional rules-based algorithm.

The post Deep Learning-based Approach to OCR first appeared on PumasAutomation & Robotics Pte Ltd.