+ All Categories
Home > Technology > Predictive Analytics in Manufacturing

Predictive Analytics in Manufacturing

Date post: 12-Apr-2017
Category:
Upload: data-science-thailand
View: 1,244 times
Download: 7 times
Share this document with a friend
23
Kittiphan Pomoung
Transcript
Page 1: Predictive Analytics in Manufacturing

Kittiphan Pomoung

Page 2: Predictive Analytics in Manufacturing

About Me

• Mr Kittiphan Pomoung

• Education : Master degree in Recording Technology @ KMITL

• Experiences :

– 21 years working experience in Hard Disk Drive companies

– 9 months in Data Mining Project Collaboration with IBM

• Email Address : [email protected]

Page 3: Predictive Analytics in Manufacturing

Topics

• Industry Revolusion (Trend) .

• Power of prediction: assess results in advance, identify

key challenges and how to overcome them.

• A taste of success: simple data modeling applied to a

real case in manufacturing process with a satisfactory

result.

Page 4: Predictive Analytics in Manufacturing

Special Thanks

• Eakasit Pacharawongsakda, PhD.

• Aimamorn Suvichakorn, PhD.

• Kosit Bunsri, M. Eng.

Page 5: Predictive Analytics in Manufacturing

Industry 4.0

• Water and

Steam Power

• First Power

Loom- 1784

• Electric Energy

• Assembly belt ,

1870

• Electronics and

information

• Programmable

Logic Control –

PLC, 1969

• Cyber-Physical

System

• All tools will

communicate and

Data will be

shared to each

other .

• Product and

Machine talk

together

• Build Per Order,(flexible with RFID)

2nd

Revolution1st

Revolution

3rd

Revolution

4th

Revolution

Page 6: Predictive Analytics in Manufacturing

Prediction in Manufactory

• Market and Demand Forecast

• Machine Utilization

• Preventive Maintenance

• Quality Improvement

Page 7: Predictive Analytics in Manufacturing

Challenges

• High expectation in prediction accuracy

• Unknown factors and variables– Oli Price

– Market’s demand

• Inadequate resources – Knowledgeable staffs

– Tools

• Limited data and understanding.

Page 8: Predictive Analytics in Manufacturing

Part 2

Page 9: Predictive Analytics in Manufacturing

Reliability Prediction

• Reliability test can take very long time (>1000 hrs),

sometimes with temperature variation.

– Tyre, chair, motor and HDD.

• What if, we can predict the result earlier, “before the

test starts”.– Traditional Method

– Advance / Numerical Predictive Method

Page 10: Predictive Analytics in Manufacturing

10

Components in an HDD

• Can be more than 17 components

• One component possibly comes from 2 suppliers

• At least 34 variables in total! , Many data stored

Page 11: Predictive Analytics in Manufacturing

Reliability Prediction : Background

Electrical

TestAssembly

Components

> 16 parts

Reliability

TestDone

• Data : > 200 parameters (attributes and variables). 1mil data entries per week.

• Duration:

• Some components manufacturing process > 60-90 days

• Reliability test 700-1200 hrs

• Worst case total processing time is 4 months

• What if, the predictive model can predict the result earlier

Basic Hard disk Process

Page 12: Predictive Analytics in Manufacturing

Basic Hard Disk Drive Reliability Test Process• Test under stress condition

• 700-1200 hrs test time

• Limited samples for training

• 200-300 drives per batch

• Only 1-2 failed units per batch

• Some failures occurred at late test hours (worn-out).

Reliability Prediction : Background

Page 13: Predictive Analytics in Manufacturing

• Objective : To predict the Reliability test result for new

material qualification in term of failure rate.

• Benefit : Time saving ($$) and Quality Improvement.

• Background :

– New material qualification usually takes 3 months.

– Failure could occur at the last minute of Reliability test, at the last

test station.

– If happens, to re-design and re-qualification again.

• Challenges :

– Limited failed samples to form the correlation

– Reliability test is more stressed than usual electrical tests

Reliability Prediction : Project

Page 14: Predictive Analytics in Manufacturing

Data Preparation

Classification

Test

Train

Deployment

Validation

Predictive Model

Feature Selection • To improve efficiency and accuracy

• 200 parameters down to ~ 20 attributes

Classification :• Rule Base Moderate

• *Decision Tree Good

• Fusion (Naive Bayes + Decision Tree) Best In Class

Techniques : Limited failed drives• *Over sampling / Boosting

• Under Sampling

• Result ~ 65-70% accuracy when implemented.

• The classification model is continuingly optimized by

training with new samples.

Reliability Prediction : Workflow

Page 15: Predictive Analytics in Manufacturing

• Different products require different modelling techniques.

• Classification method could be constrained when

implementing

• Rule Base --> Moderate

• Decision Tree Good results, easy for implementation

• Fusion (Naive Bayes + Decision Tree) Best In Class

• Future Works

• Defined key parameters input variables (KPIV)

• Establish KPIV/KPOV that correlating to component level .

• Establish Predictive model at component level (prior to HDD

assembly)

Reliability Prediction : Lessons

Page 16: Predictive Analytics in Manufacturing

Part 3

Page 17: Predictive Analytics in Manufacturing

Process/Model(Transfer Function)

Inputs

Parameters

Output

Defect/Pareto

Performance

/Distribution

Factors(Power/ Temp)

Performance Prediction : Objective• Objectives :

– Product Boundary or Product Capability

– Relationship / transfer Function

– Know it earlier , as fast as it possible

– What is the effect if input change (optimization)

Page 18: Predictive Analytics in Manufacturing

Performance Prediction : Process-1

• Average and Stdev of Input Population

• Buy off Distribution Type of output Population

Page 19: Predictive Analytics in Manufacturing

Performance Prediction : Process-2

Outp

ut

Input

• Transfer function

– Output= 15.328527 + 7.012858*Input- 1.5895329*(Input-3.2)^2

Trails -2 -1 CT +1 +2

Input (Avg) 2.7 3.0 3.2 3.4 3.6

Output (Avg) 34 36 37.7 39.3 40.7

• Calculate (simulate ) the Average of output distribution

Page 20: Predictive Analytics in Manufacturing

Performance Prediction : Process-3• Generate (pseudo) output distribution with Random Technique

– Excel/JMP : Random Normal (Output’s Avg, sigma)

– SS = 1000*

• Iterations and Sample size are able to improve accuracy

Trails -2 -1 CT +1 +2

Input (Avg) 2.7 3.0 3.2 3.4 3.6

Output (Avg) 34 36 37.7 39.3 40.7

Page 21: Predictive Analytics in Manufacturing

2.48 2.72 2.96 3.2 3.44 3.68 3.922.48 2.72 2.96 3.2 3.44 3.68 3.92

Output

Input

Failure Rate (CDF Plot)

Spec/Limit

(LCL)Good

• 3.4 is minimum

requirement to meet

product capability

Performance Prediction : Result

Output

Input

• Product Performance(Output) vs Incoming Performance (Input)

Page 22: Predictive Analytics in Manufacturing

• Linear Regression and Monte Carlo Techniques

– Simple

– Decent and Fair Result

• Iterations and Sample size

– More is Good, better accuracy

– Sample size > 50k , 5 times per each input.

– Averaged the result for each run .

Performance Prediction : Lessons

Page 23: Predictive Analytics in Manufacturing

End


Recommended