Manufactures & Factories
❯
Product improvement
❯Information extraction from hand-marked industrial inspection sheets
AI solution to quickly identify defects during quality assurance process on wind turbine blades
For:
Manufacturer
Scope:
Detecting defects in products by inspecting non-destructive testing scanning
data.
Goal:
Other
AI decryption of magnetograms
For:
Manufacturer
Scope:
Oil and gas transportation. AI solution to quickly identify defects during the
quality assurance process on a field pipeline.
Goal:
Improve Operation Efficiency
Leveraging AI to enhance adhesive quality
For:
Manufacturing industries; suppliers and buyers; environment
Scope:
Batch/continuous/discrete manufacturing (Deployed in 75+ manufacturing lines
in 10+ countries; specifically identify the contributors to quality; predict
potential quality failures).
Goal:
Other
Improvement of productivity of semiconductor manufacturing
For:
Executives of semiconductor manufacturing companies
Scope:
Analysis of data taken from production equipment and improvement of productivity based on the analysis.
Goal:
Other
Generative design of mechanical parts
For:
Organizations, designers, customers, end users
Scope:
Help mechanical engineers design lighter, strong, and better parts.
Automatic classification tool for full size core
For:
Manufacturer, geologist
Scope:
Oil and Gas exploration, classification of rock types, oil saturation, carbonate and
fracture according to core images
Goal:
Other
Information extraction from hand-marked industrial inspection sheets
For:
Manufacturing companies, machine inspectors, engineers
Scope:
Localization and mapping of machine zones, arrows and text, to extract
information from manually tagged inspection sheets.
Optimization of ferroalloy consumption for a steel production company
For:
Steelmaking, steel industry
Scope:
Recommendation for the optimal consumption of ferroalloys by the ladle furnace
treatment during secondary steelmaking.
Goal:
Other
New machine-learning simulations reduce energy need for N95 mask fabrics
For:
Manufacturing companies of high density mask fabrics, in this project 3M specifically.
Goal:
Improved Product Development / R&D
AI solution to calculate amount of contained material from mass spectrometry measurement data
Scope:
Calculating the amount of contained material from mass spectrometry
measurement data using chromatography.
Goal:
Reduce costs
Information extraction from hand-marked industrial inspection sheets
For:
Manufacturing companies, machine inspectors, engineersProblem addressed
To create a pipeline to build an information extraction system for machine
inspection sheets, by mapping the machine zones to the handwritten code using
state-of-the-art deep learning and computer vision techniques.
Scope of use case
Localization and mapping of machine zones, arrows and text, to extract
information from manually tagged inspection sheets.
Description
In order to effectively detect faults and maintain heavy
machines, a standard practice in several organizations is to
conduct regular manual inspections. The procedure for
conducting such inspections requires marking of the
damaged components on a standardized inspection sheet,
which is then camera-scanned. These sheets are marked for
different faults in corresponding machine zones using hand-
drawn arrows and text. As a result, the reading environment
is highly unstructured and requires a domain expert while
extracting the manually marked information.
We have proposed a novel pipeline to build an information
extraction system for such machine inspection sheets,
utilizing state-of-the-art deep learning and computer vision
techniques. The pipeline proceeds in the following stages:
(1) localization of different zones of the machine, arrows and
text using a combination of template matching, deep learning
and connected components, and (2) mapping the machine
zone to the corresponding arrow head and the text segment
to the arrow tail, followed by pairing them to get the correct
damage code for each zone.
The proposed method yields an accuracy of 83,2 % at the end
of the pipeline. The organization has two million such sheets
that are manually processed. This project would enable
considerable savings in terms of time and manpower as it
takes roughly 5 min per sheet for the manual process. The AI
system would process a sheet in 20 s and can be parallelized
for further speed-up.