118 th Metalcasting Congress April 8-11, 2014 – Schaumburg, IL USA Identify Energy Savings Opportunities at Foundries through Energy-Use Monitoring & Analysis* ♦ Principal Investigator – James (Jamie) Wiczer, PhD ♦ Sensor Synergy, Inc. – Barrington, IL - 847-353- 8200 ♦ Co-Investigator – Brad Tidd, Senior Kaizen Manager ♦ North Vernon Industry Corporation, North Vernon, IN • Case studies described in this presentation were funded by the American Foundry Society under R&D project #12-13#03 and by the Collaborating Foundries including NVIC & CA Lawton
71
Embed
Energy Savings in Foundries - AFS R&D Project Summary
Identify Energy Savings Opportunities at Foundries through Energy-Use Monitoring & Analysis. Energy savings case studies from American Foundry Society R&D project based on remote monitoring.
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
118th Metalcasting Congress April 8-11, 2014 – Schaumburg, IL USA
Identify Energy Savings Opportunities at Foundries through Energy-Use
Monitoring & Analysis*
♦ Principal Investigator – James (Jamie) Wiczer, PhD ♦
Sensor Synergy, Inc. – Barrington, IL - 847-353-8200
♦ Co-Investigator – Brad Tidd, Senior Kaizen Manager ♦ North Vernon Industry Corporation, North Vernon, IN
• Case studies described in this presentation were funded by the American Foundry Society under R&D project #12-13#03 and by the Collaborating Foundries including NVIC & CA Lawton
118th Metalcasting Congress April 8-11, 2014 – Schaumburg, IL USA
Knowledge is PowerSir Francis Bacon -- 1597
118th Metalcasting Congress April 8-11, 2014 – Schaumburg, IL USA
Knowledge is Power SavingSensor Synergy Staff -- 2014
$
$
$$
$ $
118th Metalcasting Congress April 8-11, 2014 – Schaumburg, IL USA
"If you can not measure it, you can not improve it.".
- - Lord Kelvin 1883
118th Metalcasting Congress April 8-11, 2014 – Schaumburg, IL USA
Overview
• Program Goals (JW)
• 3 Projects within Main Program – V-Process Vacuum Pumps (JW / BT)
– Shakeout Table & Dust Collector (JW)
– Induction Furnaces (JW/BT)
• Overall Conclusions (JW/BT)
118th Metalcasting Congress April 8-11, 2014 – Schaumburg, IL USA
Project #1 - Vacuum Pumps for V-Process Molds – Energy Saving Opportunities?
• Up to 4 Large Electric Motors Driving Vacuum Pumps to Supply Vacuum to the Pouring Floor and Shakeout area– Motors Include 250hp, 250hp, 250hp & 200hp
• Monitor Power Used by Motors and Vacuum Pressure Measured at Pouring Floor and Shakeout Floor
Lawanda
Brad Tidd slide.1 3 ea 250 HP 1ea 200 HP Vacuum Pump Motors2. Pouring Floor and Shake Out
118th Metalcasting Congress April 8-11, 2014 – Schaumburg, IL USA
Simultaneous Measurements of Electric Power Consumed and Vacuum Pressure
• Monitoring in Plant and Across the Internet Enabled Off-Site Review and Analysis of Data During Measurements
• Primary Goal: Observe correlation of Vacuum Pressure Changes with Power Consumption Changes.
• Secondary Goal: Identify Opportunities for Saving Power by Monitoring Pump Turn- On / Turn-Off Time
Lawanda
Brad slide1. Cloud Monitoring of the Vacuum Pump MotorsIdentified a Vacuum Pump Motor FailureAdditional Findings that we had additional capacity2. Primary Goal to corrolate Vacuum Pressure changes with power consumption3. Secondary Goal Identify Opportunities for savings. Turn on / Turn Off Time.
118th Metalcasting Congress April 8-11, 2014 – Schaumburg, IL USA
Electric Power Consumption by 3 Connected Motors – 250hp, 250hp & 200hp.
Sensor Synergy Staff
JW Slide
118th Metalcasting Congress April 8-11, 2014 – Schaumburg, IL USA
Shake-Out Area Vacuum Pressure Monitor
Sensor Synergy Staff
JW Slide
118th Metalcasting Congress April 8-11, 2014 – Schaumburg, IL USA
Pouring Floor Vacuum Pressure Monitor
Sensor Synergy Staff
JW Slide
118th Metalcasting Congress April 8-11, 2014 – Schaumburg, IL USA
Unexpected Motor Failure During Measurements Revealed Excess Capacity
Sensor Synergy Staff
JW Slide
118th Metalcasting Congress April 8-11, 2014 – Schaumburg, IL USA
Vacuum System Energy Savings Opportunities
DatesHours “On” Past
Ideal Turn Off time
Approx. Extra kW-hr usage
Potential Savings if turn-
off time optimum
Total Potential Savings from 6 weekends
10,280 kW-hr $1028
Total Potential Savings from
1 year (50 wks) if these 6 weekends are
typical
85,570 kW-hr $8,570
Potential Savings by Reducing
Extra Vacuum
Capacity
No Capital Expenditure
Expenditures per
Building ($12,000)
Estimated Annual Failure Costs Due to
Reduced BackUp Vacuum Capacity
Measured in Bldg. 2 $80,000 $100,000 to
$130,000 $0 / $7,500
Estimated Total for both Bldg. 1 & 2
$160,000 $200,000 to $260,000 $0 / $15,000
Sensor Synergy Staff
JW Slide
118th Metalcasting Congress April 8-11, 2014 – Schaumburg, IL USA
Results from Vacuum Pump Monitoring
• Excess Capacity for “Design Margin” Can Be Costly in the long term
• Identified $50,000/Yr to $90,000/Yr at Each Facility Extra Capacity Energy Costs
• Effort Needed to Identify Extra Capacity (if any) and to Achieve Savings
• Cost vs. Savings Trade-Off
Sensor Synergy Staff
JW Slide
118th Metalcasting Congress April 8-11, 2014 – Schaumburg, IL USA
Additional Conclusions from Vacuum Pump Study
• Measurements of Vacuum Pressure During Vacuum Pump Failure Highlighted Extra Capacity in System
• Weekly Measurements Highlighted “Turn-Off” Time Inconsistencies
• 24/7 Vacuum Pressure Measurements Indicate Low Fluctuations Due to Pump System Extra Capacity
Lawanda
Brad Tidd Slide1. Vacuum Pump Failure2 Turn On / Turn Off Times3 Extra Capacity in the Syastem
118th Metalcasting Congress April 8-11, 2014 – Schaumburg, IL USA
Project #2 – Monitor Dust Collector and Shakeout Table
• Monitor the Synchronization of the Shakeout Table and a Dedicated Dust Collector
• Opportunities for Savings with Better Synchronization
• Use 2-second Measurements to Monitor Operations of these two Power Hogs
Sensor Synergy Staff
JW Slide
118th Metalcasting Congress April 8-11, 2014 – Schaumburg, IL USA
Sensor Synergy Staff
JW Slide
118th Metalcasting Congress April 8-11, 2014 – Schaumburg, IL USA
Total Hours of Operation
Power Consumed On / Off Cycles
Electricity Costs for Operations @$ 0.1/kW-Hr
Overlap Hours of Operation
Shake Out Table
17.9 hrs 513 kW-Hr 77 On-Off $51.3 17.9 hrs
North Dust Collector
40.43 hrs 6808.1 kW-Hr 8 On-Off $681.81 17.9 hrs
Potential Savings by Turning Off Dust Collector
22.5 hrs
Excess Operational Time
3788.4 kW-Hr
Excess Electrical Power Consumed
$ 378.84
Excess Costs for Operations while Dust Collector is OFF
(No Overlap 22.5 hrs)
Results from 2-Day Power-Use Study of North Dust Collector and Shake-Out Table
Sensor Synergy Staff
JW Slide
118th Metalcasting Congress April 8-11, 2014 – Schaumburg, IL USA
Project #2 Conclusions
• Improved Synchronization of Shakeout Table and Dedicated Dust Collector Drive Motor can Save– $38,000/year in Electricity
Sensor Synergy Staff
JW Slide
118th Metalcasting Congress April 8-11, 2014 – Schaumburg, IL USA
Project #3 – Induction Furnaces #4 & #5 @ NVIC
• Install Power-Use Measurement Equipment on 2, 4MW induction furnaces ---- #4 and #5
• Make 1-Measurement/second, 24/7 for the duration of the project
• Send Data to Cloud Server to Share Data with all Interested Stake-Holders
• Correlate Power-Use Measurements with Activities at Foundry
Lawanda
Brad1.Worked with Furnace Manufacturer to install Power Monitoring Equipment.2. 1 measurement / Second 24/73. Data sent to the cloud4. Correlate Power use to process
118th Metalcasting Congress April 8-11, 2014 – Schaumburg, IL USA
Key Features of Induction Furnace Monitoring Project
• Over 16 Million Power Measurements during the first 3-months on 2 Furnaces
• Correlated Weight of Metal Heated During Each Furnace Heat with the Amount of Electricity Used for a Portion of the 3-month Study Period
• Correlated Run Sheet “Time of Day” Information with Power Measurements Time of Day Data
Lawanda
Brad1. Over 16 million power measurements2. Correlate Heat weight to Electricity used. Variation for operator to operator3. Correlated Run Sheet with power measurements. Variation from operator to operator.
118th Metalcasting Congress April 8-11, 2014 – Schaumburg, IL USA
Additional Factoids about this Project
• A short 3-Day period was selected for intense detailed analysis.– This Case Study Focused on 3 days Sept. 4 – Sept. 6,
2013
• Whatever Issues or Problems that Operators Noted on Run Sheets were also Noted in our study to correlate “real in-foundry” events with measured data for the corresponding heat
Lawanda
Brad1. 3 day period for detail analysis. minimal downtime2. Used operator data to correlate measured data for each heat. Operator data was not always reported correctly
118th Metalcasting Congress April 8-11, 2014 – Schaumburg, IL USA
Equipment Installation
Sensor Synergy Staff
JW Slide
118th Metalcasting Congress April 8-11, 2014 – Schaumburg, IL USA
Induction Furnace Power Supply
Remote, Real-Time AC Power Usage Monitor
Internet-based Cloud ServerCollects Data from Sensor Computer
at Foundry and Provides Data to Web Browsers for Authorized
Stake-Holders
Wireless Router
Data Acquisition Unit Converts Analog AC
Power Sensor Signals to Digital Info for
Network
Notebook Computer at FoundryFactory Loaded with All
Monitoring/Logging & Display Software
Web Browser Data Viewer – Anywhere, Anytime - Requires
Internet Connection
mini-LAN for SensorsWireless data
signals within foundry to deliver power-use data
to staff desktop
118th Metalcasting Congress April 8-11, 2014 – Schaumburg, IL USA
PC Data Viewer located in Foundry
Sensor Synergy Staff
JW Slide
Web Browser Data Viewer on the Internet
Sensor Synergy Staff
JW Slide
118th Metalcasting Congress April 8-11, 2014 – Schaumburg, IL USA
Sample of Raw Data
30 Row sample of the 150,000 Rows for #4 Furnace Used During 3-Day Analysis Period !
Sensor Synergy Staff
JW Slide
118th Metalcasting Congress April 8-11, 2014 – Schaumburg, IL USA
Finally …. Data!• First - How Much Electricity is
Used by All 4 Induction Furnaces at Foundry based on 8 weeks of Detailed Measurements
Approx. $3.0 - $4.0 Million/yr
Sensor Synergy Staff
JW Slide
118th Metalcasting Congress April 8-11, 2014 – Schaumburg, IL USA
Important to be able to Support Data
– Power Measurements from July 21, 2013 to Sept. 14, 2013 – Data Measured Every Second on Each Furnace
– Furn. #4 + Furn. #5 Used 3.4 million kW-Hrs during 8 weeks
– At this rate, annually All 4 Furnaces use 42.4 Million kw-Hr during a 50 week year
– If Costs at $0.10/kW-Hr = $4.240 M/year for Electricity
Sensor Synergy Staff
JW Slide
118th Metalcasting Congress April 8-11, 2014 – Schaumburg, IL USA
Power measurements for the same time duration during normal operations and during problem operations
Red area shows when
furnace is using
electrical power
White area shows when
furnace is not using electrical
power
Furnace Electrical Power
Usage is as expected – Start at ½ power then go to full power and finally off while tapping
Furnace Electrical Power Usage Profile is
unexpected – Long periods of “Off Time” while
equipment is repaired and other issues.
Lawanda
bradNormal furnace operation 50% - 100%Upper graph would recognize close to normal operation.Lower graph indicates process variation due to equipment downtime.
118th Metalcasting Congress April 8-11, 2014 – Schaumburg, IL USA
Electricity Costs/Heat – Tap to Tap
12:00 AM 4:48 AM 9:36 AM 2:24 PM 7:12 PM 12:00 AM 4:48 AM$0
$50
$100
$150
$200
$250
$300
$350
$400
Electricity Costs/Heat ---- Costs Measured from Tap to Tap duration (with electric cost
@ $.1/kW-h)
Cost @ $.1/k...
Electricity Cost per HeatAverage $240.33Std. Dev $52.51Coefficient of Variation 0.219
In this Data, there is No correction for the amount of metal added to the furnace after the previous furnace tap. Power Measurement showed a wide spread in the amount of electricity used per heat during our 3-day measurement period.
Average Cost/Heat
$240.33without correction
for weight
Lawanda
Brad SlideTap to Tap Electrical cost Average $240.33Wide range identifies need for training
118th Metalcasting Congress April 8-11, 2014 – Schaumburg, IL USA
Cost of Electricity/Heat per Ton
12:00 AM 4:48 AM 9:36 AM 2:24 PM 7:12 PM 12:00 AM 4:48 AM0
20
40
60
80
100
120
140
160
Electricity Costs/Heat per 2,000 LB --- Costs Measured for Duration from Tap to Tap time)
Cost per 2,000 LB
Electricity Cost per Ton per HeatAverage $53.15Std. Dev $19.29Coefficient of Variation 0.363
Associating the amount of electricity used (costs) for a single heat with the amount of metal heated does not result in a strong correlation. In fact the Coefficient of Variation is Greater when we tried to compensate for the different amount of metal being heated during each furnace run.
Average Cost/Ton
$53.15
Lawanda
Brad SlideAbility to look at cost per ton Avg $53.15.Variation due to operator and equipment issues
118th Metalcasting Congress April 8-11, 2014 – Schaumburg, IL USA
Range of Costs for Different Heats Measured During 3–day Tests
$0/T
on -
$10/
Ton
$10/
Ton -
$20/
Ton
$20/
Ton -
$30/
Ton
$30/
Ton -
$40/
Ton
$40/
Ton -
$50/
Ton
$50/
Ton -
$60/
Ton
$60/
Ton -
$70/
Ton
$70/
Ton -
$80/
Ton
$80/
Ton -
$90/
Ton
$90/
Ton -
$100
/Ton
>$100
/Ton
Elec
tricit
y0
5
10
15
20
25Electricity Costs $/Ton per Heat
Electricity Costs $/Ton
# Heats in Cost Range
Lawanda
bradWide range of heat cost per ton.Throw out the High and the lowTrain to achieve the middle
118th Metalcasting Congress April 8-11, 2014 – Schaumburg, IL USA
Tap-to-Ready Duration vs Weight
0.00
10.00
20.00
30.00
40.00
50.00
60.00
70.00
80.00
90.00
100.00
0 2000 4000 6000 8000 10000 12000
Len
gth
of
Tim
e T
ap t
o R
ead
y (m
inu
tes)
Weight of Metal Added for Melt
Tap to Ready Duration (min)
Tap to Ready …
Associating the amount of time required to complete a single heat with the amount of metal heated also does not result in a strong correlation.
Average Time Required from Tap-to-Ready 46.44 minutes
Expected Relationship
between Required Heat
Time and Weight of Heat
Lawanda
bradAverage tap to ready time was with-in desired specified time.Based on heat weight we did not recognize a reduced time.Based on the other measurements taken actual tap time was over the desired time. Slagging of Furnace or furnace hold time.
118th Metalcasting Congress April 8-11, 2014 – Schaumburg, IL USA
Monitoring Can Provide Operational InsightsHow Much Power Is Used During Cold-Start?
Date Time Function Total Cold-Start Power
8/11/2013 8:45 PM Begin Cold-Start 8/12/2013 12:55 AM End Cold-Start 2155 kW-Hr
8/18/2013 8:37 PM Begin Cold-Start 8/19/2013 12:43 AM End Cold-Start 2200 kW-Hr
8/25/2013 8:45 PM Begin Cold-Start 8/26/2013 12:57 AM End Cold-Start 2330 kW-Hr
9/8/13 8:45 PM Begin Cold-Start 9/9/2013 12:42 AM End Cold-Start 2100 kW-Hr
9/22/13 8:55 PM Begin Cold-Start 9/23/13 12:55 AM End Cold-Start 2050 kW-Hr
Average Power Used 2,167 kW-Hrfor Both Furnaces #4 & #5 on Sunday Night during Start-Up
Lawanda
brad & jwRecognized that our start-up power for cold start vs holding the furnace overnight.Trade off was the ability to run production quicker while holding the furnace.
118th Metalcasting Congress April 8-11, 2014 – Schaumburg, IL USA
How Much Power Is Used During Cold-Start?Average Power Used 2,167 kW-Hr for Both Furnaces #4 & #5 on Sunday Night
Hold Power /Furnace about 100 KW. Calculations indicate both furnaces consume about 4,800 kW-Hr during Sunday before production begins again.
Measurements show 6,106 kW-Hr used during Sunday day for both furnaces.
Lawanda
JW and/or BradMeasurements show that more power was consumed than should have been required to hold both furnaces.
118th Metalcasting Congress April 8-11, 2014 – Schaumburg, IL USA
Observations from Project #3
• Power Data is a High Resolution Indicator of Induction Furnace Activity
• Knowing the Costs of “Issues” may help a foundry determine which ones to Remedy – Equipment in need of Frequent Repair– Shift Change Issues– Hold Power Usage
• Power Setting During Hold Times• What Events Cause a Shift to Hold Power• Total Energy Expenditures after Ready Time
Lawanda
bradPower measurements are indicative of our furnace operation.Power measurements allow management to ask real time questions. Placing a dollar figure to our shortcomings.Allow management to prioritze training for proper furnace operations.
118th Metalcasting Congress April 8-11, 2014 – Schaumburg, IL USA
Using Data & Observations Explore the Up-Side --
Do Some What If Analyses• “What If” observations can indicate what
savings might be achieved
• For example, “What If” some of the worst case heats could be eliminated from a typical week.– From the Measurements Perspective, this is NOT about Making
Recommendations to Change the Details of a Process – Those Changes are the Foundry’s Expertise!
– This IS about, IF some process related Issues can be Improved, what would be the Benefit.
– Now the Foundry Staff Needs to Explore what it costs to make these changes
Sensor Synergy Staff
JW Slide
118th Metalcasting Congress April 8-11, 2014 – Schaumburg, IL USA
What IF ?• Can You Get Rid of Your Worst 25%
Performing Heating– What if the most expensive 25% of the
induction furnace heats could be eliminated and replaced with a heat that performed the same function but used an amount of electricity and time similar to the lower 75% of these measurements?
Sensor Synergy Staff
JW Slide
118th Metalcasting Congress April 8-11, 2014 – Schaumburg, IL USA
Costs with Worst 25%
9/4/13 12:00 AM 9/4/13 12:00 PM 9/5/13 12:00 AM 9/5/13 12:00 PM 9/6/13 12:00 AM 9/6/13 12:00 PM 9/7/13 12:00 AM 9/7/13 12:00 PM$0.00
$50.00
$100.00
$150.00
$200.00
$250.00
$300.00
$350.00
$400.00
Tap to Tap Costs/Heat ($'s) for 3 Day Sample / Orange - Lower 75% / Lt. Blue = Upper 25%
Tap to Tap CostsUpper 25% of Tap to Tap Costs
Date and Time of Day
Tap
-to
-Tap
Co
sts
($'s
)
Average Costs
including Lt. Blue Values
Average Costs Excluding Lt. Blue Values
Sensor Synergy Staff
JW Slide
118th Metalcasting Congress April 8-11, 2014 – Schaumburg, IL USA
If we could do this, then ….
• The average electricity costs/heat for operating the induction furnaces would decrease from
•$200.18 … to … $178.11
• This would create and Annual Electricity Savings of …
•$466,400
Sensor Synergy Staff
JW Slide
118th Metalcasting Congress April 8-11, 2014 – Schaumburg, IL USA
Other What If
• What if the Electricity Expenses after the Induction Furnace is Ready to Tap could be Eliminated ?– 6.1% of the Electricity Cost/Heat Could be
Eliminated– for an Annual Savings of …
•$254,400/year
Sensor Synergy Staff
JW Slide
118th Metalcasting Congress April 8-11, 2014 – Schaumburg, IL USA
And ….
• The average duration for a complete Tap –to – Tap Cycle Would be Reduced from
•61.26 minutes …to… 53.49 minutes
• Annually, this 12.7% reduction in Induction Furnace Operations Time Would Save …
•874 Hours/Year of Induction Furnace Operations
Sensor Synergy Staff
JW and/or Brad Slide
118th Metalcasting Congress April 8-11, 2014 – Schaumburg, IL USA
Enhanced Operator Training Can Remedy Many Issues
• Energy Measurements Identify Operational Issues that, in some cases, Can be Remedied with Additional Operator Training
• Specific Examples ----
Lawanda
bradPower measurements offer Training Oportunities by identifying operational short comings.Charging the furnaceFlux and tap temperatureShut down procedures (Elephants foot)
118th Metalcasting Congress April 8-11, 2014 – Schaumburg, IL USA
Other Conclusions
• Real-Time Power-Use Monitoring Can Support Process Improvement Studies to Reduce Energy Consumption and Reduce Induction Furnace Operations Time
• The Addition of Real-Time Text Message Alerts Can Help Make Improvements and Identify Issues Using Automation - independent of staff actions/communications.
Lawanda
bradReal time power use monitoring Supports process improvementsAdditional real time text message alerts can help make improvements and identify operational issues using automation.
118th Metalcasting Congress April 8-11, 2014 – Schaumburg, IL USA
4 Metrics for Induction Furnace Energy Efficiency
• 1) Measure the Fraction of Time and Energy Spent on
OFF / HOLD / MEDIUM / FULL Power
• 2) Measure & Continuously Monitor the Energy Cost/Ton for Charge to Tap Energy Input
Sensor Synergy Staff
JW Slide
118th Metalcasting Congress April 8-11, 2014 – Schaumburg, IL USA
More -- 4 Metrics for Induction Furnace Efficiency
• 3) Measure & Track the Tap-to-Tap Cycle Tap for Different Alloys
• 4) Measure & Compare Your Energy Cost/Ton to Industry “standard” values.
Sensor Synergy Staff
JW Slide
118th Metalcasting Congress April 8-11, 2014 – Schaumburg, IL USA
Continuous Function of Power Levels During Prior Week Furnace Operations
1/kW
Sensor Synergy Staff
JW Slide
Sensor Synergy Staff
JW Slide
118th Metalcasting Congress April 8-11, 2014 – Schaumburg, IL USA
Aggregate Weekly OperationsPercent of Week at 4 Power Levels
Percent of Time During Week Week Furnace # Off Mode Hold Mode Medium Power Full Power Total Time (Hrs)
Average Percent Power 0.09% 15.71% 14.58% 69.62% 33,272.85
Sensor Synergy Staff
JW Slide
118th Metalcasting Congress April 8-11, 2014 – Schaumburg, IL USA
Sensor Synergy Staff
JW Slide
118th Metalcasting Congress April 8-11, 2014 – Schaumburg, IL USA
Sensor Synergy Staff
JW Slide
118th Metalcasting Congress April 8-11, 2014 – Schaumburg, IL USA
Finally… Program Conclusions
• Time Resolved, Energy-Use Measurements Can Provide Unique Insights about the Operations of Power-Intense Equipment – Including Pump Motors, Dust Collectors, Air
Compressors, & Induction Furnaces
• Energy Savings Can Often Be Achieved with Simple Administrative Solutions
• Energy Savings Should Pay NOT Cost• Energy Savings Are Often Accompanied by
Productivity Gains• Energy Measurements Are Necessary to Identify
“Engineering Margin” Energy Costs
Sensor Synergy Staff
JW Slide
118th Metalcasting Congress April 8-11, 2014 – Schaumburg, IL USA
Putting the Data to Use
• Real Time Monitoring• Operator Training• Downtime Notification• Equipment Design• Peace of Mind
Lawanda
Brad Slidereal time monitoringOperator TrainingDowntime notificationEquipment designPeace of mind
118th Metalcasting Congress April 8-11, 2014 – Schaumburg, IL USA
For additional information:
James (Jamie) Wiczer, PhD Sensor Synergy, Inc. – Barrington, IL
Brad Tidd, Senior Kaizen Manager North Vernon Industry Corporation, North Vernon, IN
Brad.Tidd@NVIC-CWT / 1-812-346-8772 x 1288
118th Metalcasting Congress April 8-11, 2014 – Schaumburg, IL USA
Extra MaterialPreview of Thursday’s
Presentation
• More complete descriptions of this work can be found at the Metalcasting Congress
Panel: Computerization in the Foundry Industry
• Thursday 3:45 PM. 14-132
118th Metalcasting Congress April 8-11, 2014 – Schaumburg, IL USA
Data Analysis Tools
• Build tools to study data specifically for foundry applications
• Goal: Extract the best information for those most knowledgeable about the operations & demands of a particular foundry– Experts + data can learn the most about
improving their operations
118th Metalcasting Congress April 8-11, 2014 – Schaumburg, IL USA
Generating Furnace Operation Logs
• Let’s focus on one example of a data analysis tool we’re working on– Problem inspired by this project with
NVIC• In this project, we focused on
correlating energy with operations.– This required accurate logging that is
difficult to achieve over extended periods of time
118th Metalcasting Congress April 8-11, 2014 – Schaumburg, IL USA
Generating Furnace Operation Logs (cont.)
• Challenges to getting accurate operations logs / run sheets:1. Manual logging is time-consuming
• Inaccuracies may result from the many tasks performed by furnace operators at tap time
2. Additional instrumentation for electronic detection of melt start/end times is often complex and costly
118th Metalcasting Congress April 8-11, 2014 – Schaumburg, IL USA
• Use the power data we collect to guess when operation events (e.g. tap time, melt ready time, etc) occur
• But first…
Furnace Operation Logs – A Third Option
118th Metalcasting Congress April 8-11, 2014 – Schaumburg, IL USA
Some preparation for a little bit of computer talk
• Algorithm: A calculation or procedure a computer program uses
• Parse: Splitting up data into pieces• Score: The algorithm’s evaluation of
some data.• Sigma (σ): Standard deviation. The
“spread” of some data.
118th Metalcasting Congress April 8-11, 2014 – Schaumburg, IL USA
Software identification of melt start & stop events
• Computer prediction can sacrifice some accuracy in favor of ease-of-implementation– Algorithmic approach– Get lots of data and treat them
statistically– Enable operators to focus on core
duties
118th Metalcasting Congress April 8-11, 2014 – Schaumburg, IL USA
How the algorithm works• Manually log times during
“training” period– We used 3 days & 82 melts for this
example• Learning based on Principle
Component Analysis (PCA)– Most notably used in face
recognition algorithm “eigenfaces”– Think of a 15 min window around
each event as a “face”(Photo: AT&T Labs Cambridge)
118th Metalcasting Congress April 8-11, 2014 – Schaumburg, IL USA
Sliding windowPower measurements
Prediction score
Window (prediction input)
Evaluate a window and predict how likely start of tap event is at the center.
15 Minutes
118th Metalcasting Congress April 8-11, 2014 – Schaumburg, IL USA
Sliding window scoresPower measurements
Prediction score
The power curve gets a corresponding curve for likelihood of tap start.
118th Metalcasting Congress April 8-11, 2014 – Schaumburg, IL USA
Algorithm processes scores and generates melt start times
Power measurements
Predicted event times
Take the highest scores in a neighborhood and get discrete tap time predictions.
118th Metalcasting Congress April 8-11, 2014 – Schaumburg, IL USA
Repeat for melt ready times
Apply the same algorithm to melt ready times and combine the results.
Power measurements
Predicted start times
Predicted ready times
118th Metalcasting Congress April 8-11, 2014 – Schaumburg, IL USA
Exploratory Analysis
Tap to Ready Time (min)
Ave
rage
Pow
er (
KW
)
118th Metalcasting Congress April 8-11, 2014 – Schaumburg, IL USA
Exploratory Analysis
Tap to Ready Time (min)
Ene
rgy
Con
sum
ed (
KW
Hr)
118th Metalcasting Congress April 8-11, 2014 – Schaumburg, IL USA
Improved Metrics
Mean = 42.1 minσ = 12.4 min
Mean 11.7 minσ = 4.3 min
118th Metalcasting Congress April 8-11, 2014 – Schaumburg, IL USA
Improved Metrics
• Analyze furnace usage from “Ready time” to “End-of-Tap time”:– Average energy: 24 KW Hr– % of Tap-to-Tap energy: 2.4%– Average time: 11.8 min– % of Tap-to-Tap time: 23.7%