© 2009 Chevron Oronite Companies. All rights reserved. Cummins ISM Reference Data Review for Cummins Surveillance Panel August 26, 2009 Jim Rutherford.

Slides:



Advertisements
Similar presentations
United Nations Statistics Division
Advertisements

IIIG LTMS V2 Review. LTMS V2 Review Data Summary: – Includes 285 Chartable reference oil results from all test laboratories – Most recent chartable reference.
Penguin Parade. Quantitative description [A] – The linear equation is y = x – On average, the number of penguins marching is decreasing.
Science – High School 2nd grade 1st Term
Tips for Writing Free Response Questions on the AP Statistics Exam Laura Trojan Cannon School.
Mathematics SL Internal Assessment
Pensions and Benefits Date : March How to vote 1 You need to check your handset is set to the correct channel. Press this arrow and if the display.
Student Consensus on RateMyProfessors.com April Bleske-Rechek, Amber Fritsch, and Brittany Henn University of Wisconsin Eau Claire Background Method Discussion.
Chapter 4: Image Enhancement
Example 2.11 Comparison of Male and Female Movie Stars’ Salaries Exploring Data with Pivot Tables.
Mr Barton’s Maths Notes
1 Psych 5500/6500 The t Test for a Single Group Mean (Part 5): Outliers Fall, 2008.
Sampling Distributions
8-2 Basics of Hypothesis Testing
Build a Thermometer Screen Design and Technology – Thermometer Screen Project Name___________ Date ___________.
Exponents Scientific Notation
Design and Technology – Anemometer Project
Lesson 4: Percentage of Amounts.
Variance and Standard Deviation. Variance: a measure of how data points differ from the mean Data Set 1: 3, 5, 7, 10, 10 Data Set 2: 7, 7, 7, 7, 7 What.
Page 1 Mobile Quote & Payment Request Usability Test Results | January 2015 Quote and Payment Requests Mobile (iPhone) Usability Test Results Conducted.
Mixed-level English classrooms What my paper is about: Basically my paper is about confirming with my research that the use of technology in the classroom.
Lecture Slides Elementary Statistics Twelfth Edition
Psy B07 Chapter 8Slide 1 POWER. Psy B07 Chapter 8Slide 2 Chapter 4 flashback  Type I error is the probability of rejecting the null hypothesis when it.
Oregon Presented by: Office of Economic Analysis Date: September 22, 2009 Corrections Population Forecasting Advisory Committee.
WHEN, WHY, AND HOW SCIENCE RESEARCH IS REPORTED IMRAD.
Short Division.
Analysis of the ISM Matrix Draft 3 November 5, 2004.
The Story of Oil Bonds – By Prof. Simply Simple The most talked about subject these days is whether petrol prices will rise even further or not and if.
Copyright © 2014, 2011 Pearson Education, Inc. 1 Chapter 22 Regression Diagnostics.
Basic Statistics Concepts Marketing Logistics. Basic Statistics Concepts Including: histograms, means, normal distributions, standard deviations.
Primes and Tests for Divisibility Chapter 5 Section 1 By: Tiffany Fey.
Formulae For each severity adjustment entity, X i = i th test result in original units in end-of-test order T i = i th test result in appropriate units.
Brian Macpherson Ph.D, Professor of Statistics, University of Manitoba Tom Bingham Statistician, The Boeing Company.
By Ava Mason. The first question, do you eat healthily has the options yes and always. Yes and always are the same so, to improve I will use a small.
Copyright © 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley Chapter 8 Linear Regression.
Mack T-12 Precision Matrix Preliminary Analyses Presented to T-12 Task Force October 11, 2005 Jim Rutherford (510)
Slide Slide 1 Copyright © 2007 Pearson Education, Inc Publishing as Pearson Addison-Wesley. Lecture Slides Elementary Statistics Tenth Edition and the.
1 The Second Addition of LTMS (Theoretical Sneak Peak for the VG) VG SP: May 2010.
Revised ISM IAS Merit Calculation Proposal June 22, 2010 Pat Fetterman Steve Kennedy (discussed with Shawn Whitacre & Philpe Saad 6/21/10)
Lubricant Test Monitoring System (LTMS) Quick Deck Draft 3 March 2, 2012.
Final Major Project Survey Results from Surveymonkey and Analysis.
1 © 2012 Chevron Oronite Company LLC. All rights reserved. Filter Settings - CHART: ( Y)
The Commutative Property Using Tiles © Math As A Second Language All Rights Reserved next #4 Taking the Fear out of Math.
Mack T-12 Pre-Matrix Data Analyses Version 3 Presented to T-12 Task Force March 17, 2005 Jim Rutherford (510)
Writing Skills Writing a comment.
Copyright © 2007 Pearson Education, Inc. Publishing as Pearson Addison-Wesley Slide 8- 1.
JACTest Monitoring Center Test Monitoring Center Report to the Mack Test Surveillance Panel June 17, 2002 Montreal.
© 2009 Chevron Oronite Companies. All rights reserved. New Liner and Ring Batch Effects in the Mack T-12 Presented to Mack Surveillance Panel Conference.
ISM Test Development Task Force Report June 21, 2004.
Copyright © 2011 Pearson Education, Inc. Regression Diagnostics Chapter 22.
LTMS Task Force Statistics Subgroup Report to Joint LTMS Open Forum San Antonio, TX May 11, 2010.
D OES PLAYING SPORTS AFFECT SCHOOL MARKS ? Arun Jha and Sagar Badve Year 10 Perth Modern School.
C13 LTMS discussion Follow-up to San Antonio O&H meeting Elisa Santos November 29 th, 2005.
JACTest Monitoring Center T-10 PB Ad Hoc Task Force Report to the Mack Test Surveillance Panel September 10, 2004 Richmond, VA.
© 2011 Chevron Oronite Companies. All rights reserved. ISB Data Review Presented to Cummins Surveillance Panel Addendum 3 Cam/Tappet Interactions Jim Rutherford.
1 IP Routing table compaction and sampling schemes to enhance TCAM cache performance Author: Ruirui Guo, Jose G. Delgado-Frias Publisher: Journal of Systems.
Research Assessment Task
ADD PRESENTATION TITLE HERE (GO TO: VIEW / MASTER / SLIDE MASTER TO AMEND) ADD PRESENTER’S NAME HERE / ADD DATE HERE © Copyright EDF Energy. All rights.
© 2011 Chevron Oronite Companies. All rights reserved. ISB Data Review Presented to Cummins Surveillance Panel Jim Rutherford March 16, 2011.
LTMS Task Force Statistics Subgroup Report to Joint LTMS Open Forum San Antonio, TX May 11, 2010.
FIN 30220: Macroeconomic Analysis
Cummins ISM Reference Data Review Merit Addendum for Cummins Surveillance Panel August 26, 2009 Jim Rutherford.
Caterpillar C13 Matrix Data Analysis
LTMS Task Force Statistics Subgroup Report to Joint LTMS Open Forum
Caterpillar C13 Test Matrix Update
Do Pitchers Try Harder for Their 20th Win?
Control chart (Ex 5-3) Subgroup No. Measurement Average Range Date
Alignment of Part 4B with ISAE 3000
Presentation transcript:

© 2009 Chevron Oronite Companies. All rights reserved. Cummins ISM Reference Data Review for Cummins Surveillance Panel August 26, 2009 Jim Rutherford

2 © 2009 Chevron Oronite Companies. All rights reserved. Introduction At the August 13 Cummins Surveillance Panel conference call several questions were raised about ISM severity. Here is an attempt to address the following questions. 1. Are the soot adjustments right? 2. Are the industry correction factors right? 3. Are the cross cylinder σ’s changing? 4. Should we update targets? 5. Should we use severity adjustments?

3 © 2009 Chevron Oronite Companies. All rights reserved. 1. Are the soot adjustments right? Background – According to the ISM Timeline March 22, 2005 marked “COMPLETION OF MINI-MATRIX ANALYSES AND IMPLEMENTATION OF SOOT ADJUSTMENTS FOR WEAR PARAMETERS” To the best of my memory, this mini-matrix consisted of 15 tests from four labs on three oils. Although I can’t find that analysis or notes from the meeting we had in Columbus and each time I have gone back to recreate what we did I get confused about which data are correct, the analyses looked something like this. So although we couldn’t get exactly the same numbers to many decimal places, we rounded to 3 and 1.7 and used the TGA average from of 3.9

4 © 2009 Chevron Oronite Companies. All rights reserved. 1. Are the soot adjustments right? (CWL) For crossheads, there was clearly more slope for the other two oils ( and ISMA) than for

5 © 2009 Chevron Oronite Companies. All rights reserved. 1. Are the soot adjustments right? (CWL) Since the implementation of soot adjustments, slope has maybe increased for CWL on This chart shows industry corrected, outlier screened CWL without soot adjustment versus soot for the original seven tests with and all references since then. The slope before is about 0.5 and for later a bit over 1.

6 © 2009 Chevron Oronite Companies. All rights reserved. 1. Are the soot adjustments right? (CWL) This chart shows industry corrected, outlier screened, soot adjusted CWL versus soot for the original seven tests with and all references since then. The negative slope over the soot range could be an indication that the soot adjustment is overcompensating for This could make sense based on original data. But what is it doing for other oils?

7 © 2009 Chevron Oronite Companies. All rights reserved. 2. Are the industry correction factors right? (CWL) This chart shows outlier screened, soot adjusted CWL versus date for all 36 chartable results with and without industry correction. On the average, the correction looks not bad; maybe a little too much for more recent tests. Industry Correction Before After

8 © 2009 Chevron Oronite Companies. All rights reserved. 1. Are the soot adjustments right? (CWL) 2. Are the industry correction factors right? (CWL) This chart shows industry corrected, outlier screened, soot adjusted CWL versus date for all 36 chartable results. Over the life of the test final results for might have increased an average of 0.5 mg. Soot Adjustment Calc Before After Industry Correction Before After

9 © 2009 Chevron Oronite Companies. All rights reserved. 1. Are the soot adjustments right? (IAS) For injector adjusting screws in the original mini- matrix data, and had similar slope. ISMA had greater slope but only two results.

10 © 2009 Chevron Oronite Companies. All rights reserved. 1. Are the soot adjustments right? (IAS) Since the implementation of soot adjustments, slope has apparently decreased for IAS on This chart shows industry corrected, outlier screened ln(IAS) without soot adjustment versus soot for the original seven tests with and all references since then. The slope before is over 1 and for later under 0.

11 © 2009 Chevron Oronite Companies. All rights reserved. 1. Are the soot adjustments right? (IAS) This chart shows industry corrected, outlier screened, soot adjusted IAS versus soot for the original seven tests with and all references since then. The negative slope over the soot range could be an indication that the soot adjustment is overcompensating for This overcompensation contradicts mini-matrix conclusions for But what is it doing for other oils? However, since later tests tend to have higher soot, it would be hard to say whether soot adjustment or industry correction or both contribute to the trend.

12 © 2009 Chevron Oronite Companies. All rights reserved. 2. Are the industry correction factors right? (CWL) This chart shows outlier screened, soot adjusted IAS versus date for all 36 chartable results with and without industry correction. On the average, the correction looks not bad; maybe not enough for more recent tests. Industry Correction Before After

13 © 2009 Chevron Oronite Companies. All rights reserved. 1.Are the soot adjustments right? (IAS) 2. Are the industry correction factors right? (IAS) This chart shows industry corrected, outlier screened, soot adjusted IAS versus date for all 36 chartable results. Over the life of the test final results for might have decreased an average of 4 mg. Soot Adjustment Calc Before After Industry Correction Before After

14 © 2009 Chevron Oronite Companies. All rights reserved. 3. Are the cross cylinder σ’s changing? This chart shows original measurement and outlier screened CWL standard deviations across the six cylinders for exhaust and intake by date. I don’t know what to say about it. No simple trends.

15 © 2009 Chevron Oronite Companies. All rights reserved. 3. Are the cross cylinder σ’s changing? This chart shows original measurement and outlier screened IAS standard deviations across the six cylinders for exhaust and intake by date. Maybe the trend is downward?

16 © 2009 Chevron Oronite Companies. All rights reserved. 4. Should we update targets? This chart shows previous three sets of targets. It seems that they were simple averages of all tests available at each time. A possible update with current tests is shown.

17 © 2009 Chevron Oronite Companies. All rights reserved. OFDP transformed back from ln(OFDP+1) Actual target w/o industry correction Should we update targets?

18 © 2009 Chevron Oronite Companies. All rights reserved. Actual sd w/o industry correction 10.7 Industrty didn’t believe this number. Used 0.20 instead. 4. Should we update targets?

19 © 2009 Chevron Oronite Companies. All rights reserved. 4. Should we update targets? 5. Should we use severity adjustments? My opinion on these last two questions: Yes, we should update targets. But not as shown above. They should be part of the revised LTMS for ISM. Yes, we should allow severity adjustments. As most of you know, we have an LTMS Task Force and an active LTMS TF Statistics Subgroup. Our next LTMS TF SS meeting is September 1. I hope to suggest a new LTMS for ISM for consideration at that meeting based on revised LTMS concepts and framework. The LTMS TF could eventually propose new LTMS to this Surveillance Panel.