MACE sools for Problem Sony, aoe Ng And for Deep Analysis MARUTI CENTER FOR EXCELLENCE ven knetrapal: 9813801111, yasheimerat.c.n: Usst Modifed 12% api! 2022 Introducing all Rus => Your name, company name => Your responsibility and department => Expectation from this program (optional) Please be respectful to others and do not use your mobile phone in the training room (No texting, mailing or surfing please).MACE Goal of an organization? To make profit Next goal? Next goal How? Products & services must be preferable to customers over competi rs. Organizations must continuously meet Needs & Expectations of the customers i.e. Delight of the customers is called QUALITY Inspn, QC and Quality AssuratAc japesion (aay Conwead Ty ATR Th lf Oo dey loss | Th le GA rome ice resiauaipaeds | Aromen eden pceae, Fide &iniving ses of [EB ad way ‘ty eles egy &_| paraerner am ste esuomem m atcoteners | isesiment tasteLook for the problems All ts well? Impossible. ‘There must be a problem that you've overlooked... ACE What is a problem? ‘A “problem” the gap between the present situation and the expected situation or objective (ideal situation or objective ) A Good a a a 6 E |Gap Problem = (ideal situation or objective) -| (present level) Present LevelProblem defined Deviation from the expectation : + In achieving the desired standard. * Standard has been achieved but a higher standard is required now. + Inconsistency in achieving the standards. ‘An opportunity for improvement ACE Uniformity around a target value is called quality + TotYACE ‘The required steps of problem solving ares aia Cen edi acht clones eh iegieceae Sefer anetarate enenomthecr bused evant develop souemennres and plement thar Scasasysasenl yeas tal Suu the pect of con en Uta the rele dormers Heroes Sheet WL EMEA Sheet 5 tha he pcblem arm : MACE What are the 7 QC Tools ? 7 essential tools to identify, analyze and solve the problems. These tools are very powerful and help to identify the causes of work related problems and to find solutions for the same in a systematic manner.The7QC Tools ACE togram hd Itis a graphic summary of variation of one specific variable (dimension, weight etc) in a process. Random samples are taken from an already processed lot and the frequency distribution of that variable is plotted in the bar form to: * Analyze quickly whether this lot can meet customer's requirements. * Predict quickly, future performance of the process. * When you want a quick check whether a change has been introduced in the process. We find out the above through the Three Indicators from the graph : Location of its center, Spread from the target, and Shape.Histogram ..... * The etymology of the word histogram is uncertain. Sometimes it is said to be derived from the Greek word histos (anything set upright : as the mast of a ship, the bar of a loom, or the vertical bars of a histogram) and gramma : (drawing, record, writing) It is also said that Karl Pearson who introduced the term in 1891, derived the name from “historical diagram” * This tool represents process centering, spread and shape (density and frequency distribution of one particular dimension or any other one variable). 5 MACE About the inventor + Itis believed that this was invented by Karl Pearson (1857-1936) a follower of Sir Francis Galton + He developed the concept of Mathematical Statistics + First to start the Department of Statistics in a university at LondonHistogram — steps MACE Obtain set of 0 ~ 100 observations as shown below (exmp : 100 east) ‘orig sop nants 40 mm rod to be ct ino Bans of 209 gms +20 gms 100 pes Were picked from the blank cutang shop on random basis ond the resis ae as unde. What should the Shop fn-charge do now? zz_| am | var | nas | ax2 [aus | aie | 0s [on | nue | 208 | 204 203_| 20a | 218 | 216 | 210 | 237 | 225 noa_|ama_| ae | 200 | axe | air [ons | 205 | 20s | 227 [aso | aze | aan | aur | xz | azz [21a | 200 | 207 | 22s an_| a2 is 203 | 200 | 225 | 203 | 205 | 247 | 227 218 | 209 | 230 | 205 | 210 | 207 | 219 | as | 21¢ | a7 aa_| 210 | 206 | 220 | 214 | a5 | ars | ze | 201 | 210 203_| 208 | 218 | a3 | 209 | a3 zr_| a7 | 200 zos_| ar | a6 | 207 | 2m | 228 zaa_| 215 | 201 | 208 | a9 | 225 eee 203 | 2s | 207 Range and no of classes’ 1, Range = Max value ~ Min value (Range : Largest Measurement-Smallest Measurement) R: 230-200 = 30 2. Determine the number of classes (use thumb rule): Number of data (N) Number of Classes(k) (Min) 50 5-7 - 100 6 - 10 + 250 10 - 16 Over 250 16 - 20 (The value of k is the App Square Root of the N; a general thumb rule)[ACE Class Width and Class bound} 3. Class Width = Range/No of Classes= 20/10-3 ¢ Use the smallest measurement as the 1* Class Interval. In this case 200 e Add the Class Width (3 to the above) eg 200 +3 = 203 and go on adding.... * Ensure that all measurements are suitably placed in their classes. Construct a Frequency Tale = [lasses ass Boundary | Frequency Freq Count 0 2 vn 8 af aDraw the Histogram On the X Axis, draw the classes On the Y Axis, draw the freq count. MACE Histogram through Excel HistogramNormal Distribution Curve 59.7% of the data are within standard deviation ofthe mess 5% thin 2etandard deviatione ex within eanderd ‘éevation woe ete ett MACE MACE Diff Between Control limit and Spec Limit ontrol Limits Ispocification Limits oie of the process Woice of the customer alulated from Dats etna by the customer ude for process actions {separate good tems from bad alte process is doing natwe want the process todohe. Ls. MACE + Dark blue is one standard deviation on either side of the mean. For the normal distribution, this accounts for 68.27 percent of the set; while two standard deviations from the mean (medium and dark blue) account for 95.45 percent; three standard deviations (light, medium, and dark blue) account for 99.73 percent; Svat NNN aa oF acceptance 4 Std Deva ~90:998% [Link] Dem 9.990049 6 Std Devo 99.9000007% 7'8td Devn 99.s809900008% ‘Theoretically, Itis not possible to achieve perfection. However, Unless we chase perfection, we can not catch excellence 12MACE Histogram for grade wise distribution in Maths class No, of students MACE a =—_ > 16. | a San a. ae peaerbena aeeneenees » /(0!: com | Jno [titogram Ineraceation | bow ous umber of pots on eer eo te mean ie nara However, are 1 hema faut ne etn for thor prceres nich ave a atl it on one ie wil lneyrmetical Natur! fis pee GALES on one He Th peaks vans ae eee fener is possible to tave arma atrovten because xe. Puy 28 a, purty of Me sauing gs, reamed Nols, boache sos, surce aah honedlapaed pus | comes oftwo procter wth deren usr are combined nage 4 poobepeax Pacomes i might he cle 3 idl srbson Several proces wih nema o- istribution are combined, > ne Petepnerbepetng eave aspr el arm mat oh Prams pee its te borrou BOYS epee mae cones wo Bes fond brea Curt tors Rael Its ores bre beg oped the proces means msg. MACE Histogram Process + Get the data in Excel + Ensure that the Analysis Tool Pack is activated (File> Options>Add- Ins>Analysis Tao! Pack>OK) ‘+ Take the data for which a histogram is to be made. + Find the min value =min{table range) + Find the max value = max(table range) + Get the difference + Determine the number of classes (square root of number of values) + Give input range (all data values) + Give bin range (incremental values of bins : 200, 203, 206, ....230) + Among radio buttons, select New Worksheet Ply + Select Chart Output + Glick ox 14Scatter Diagram ey diegcam) CE ‘To study and identify the possible relationship between the changes observed in two different sets of variables (eg temperature and hardness, stress and strain etc). ‘This diagram shows pairs of numerical data, one variable on each axis to look for a relationship between them. Ifthe variables are correlated, the points will fall along a line or curve. Stronger the correlation, closer the points will be to the line. This diagram is particularly useful, after making a fishbone diagram to objectively determine whether an effect and its cause are related or not. This diagram was first used by Sir Francis Galton in 1888 to know correlation between the height of people and their forearm lengths. For this, he collected data of 348 adult men, MACE About Scatter Diagram + Also known as x y Chart + Invented by Sir Francis Galton (1822-1911), a British citizen, cousin of Charles Darwin. + AMathematician, Anthropologist, Eugenicist, Explorer, Geographer, Inventor, Proto-geneticist, Psychometrician, Statistician + Knighted in 1909. 15‘Temp Vs Bend Height Trend in Automotive Glass Mfg woe smc smc HOC SHE mC SMC OC GG eC aE THe o ‘ Positive Correlation _ Negative Correlation n=30 n=30 16Positive Correlation May Be Present Negative Correlation May, 2 No Correlation n=30 apf feo > on ee fe Pe as a a 17Correlation * The measure of the strength of the linear association in a correlation analysis is “R” the correlation coefficient. © Properties of R :- * R > O indicates a positive linear relationship © R pictorial form The most commonly used graphs are: * Bar Graph © Pie Graph © Radar Graph * Line Graph Purpose of Graph: A picture is worth more than thousand words 43Bar Graph : Best for indicating the difference in numeric quantities Dent Analysis 2 '§No of Dents Rr Ctr Fit. Roof Ft Rr Bk Body Pilar Panel Door Door Door o Pie Chart : Best for showing the percentage break up] Others ‘Spot Dent 9 20% Gun Touch Dents 25% AREA OMNI W/B, PERIOD 05/01/2001 [Link] 150 44‘SYSTEM AUDIT REPORT Paasianamtin om 2 i nner cy 3 coe Cuneo oy eaaionsavanra een sony oo 7 sepeowa 7 a cnet anna aoa TT Toe reece POS 79% .Opestmneanses 10% 7 Gherareatapewin sane 710% "2h three ever ‘om 13. Gusy epee pent oe 1 Gere erecta natin ee 15, Cone repecon enim om, 7 Fenian oars HEE TI 7a, 1 cacao eniomeg pia 7 12 Spe oe ee 2 ery manpeeT Aa 7 2x inpenanatontrepecen 7% the gaps in performance (expected vs actual). Radar Graph tar cn: Tomenare he peemae fobs acs NAACE (ase 45LINE GRAPH : A graph to show the changes in quantum wart change in conditions. Effect and Causes diagram * Invented by Prof Dr. Kaoru Ishikawa (1915- 1985) + President Musashi Institute of Technology + Member of Union of Japanese Scientists and Engineers (JUSE) MACE 46Effect & Causes diagran + Shows the relationship between a problem and its possible or probable causes. + Also known as : Fishbone diagram; Ishikawa diagram + Asystematic arrangement of all possible causes which have given rise to the effect are made. The causes are first divided into major sources (6Ms) i.e., Man, Machine, Method, Material, Mother Nature, and Measurement. + Then each source is divided into sub-sources and so on. It helps to find out root causes of the problem Methodology : How to find root causes of AACE problem Step 1 : Make fish bone diagram and write all possible causes in 6 (M's after brainstorming session, Step 2 : Find out suspect causes from the possible causes. Highlight them. Step 3 : Validate all the suspect causes and write the judgment. All the validated judgments are the valid causes of the problem Step 4 : Do the why why analysis for the each valid cause and through these, find out the root causes of the problem, 47MACE METHODOLOGY : Possbie/Probabie cayses ‘Suspect causes Validation | \Valid_causes nalysis. ‘Why Why | Root _causes (ACE Effect and Causes diagram - Major and cuvsiaar GAG Material Methods Environment \eormn _— ae soe ve x ~via a an PP fw rom socom Men Machine Measurement 48MACE Effect and Causes Diagram METHOD MATERIAL process: PUMP PRESSURE. QgACE Effect and Causes Diagram Morte Mangoner eos 49The QC Problem-Solving Approach by Maruti Center for Excellence (MACE) inva Problem Perception ———_ <—~tearae. vague, Complicated prniem) 7 - Clarify the Problem The Real” Probie Grasp the Situation Poss Cause Valercause Cause 5 Why ?- 2 Cause Investigation wo? \ Cause Of Root Cause wn Basic Cause and Effect Investigation iy Why why analysis MACE Problem : Pool of oil on the shop floor . Why? ‘The machine is leaking oil after repairs. Why? Bad gasket was used in maintenance. Why? Because the gaskets were bought in bulk to get the volume discount. Why ? Because the purchase person has to report cost reduction. Why ? Because his grades are judged by the amount of cost reduction. Why ? This is the policy of the company. ey 50MACE ‘This rast must evr be shared with the astomer = fe Fakes fir fect i ane? pean hn feta feet” frome | fates |" ci | fr fn be ot ae jooweseatne | fsb vataMACE Extra reading : How to read Control Charts + Whether a process is in the controlled state or not is judged by the following criteria from the control chart. * Control charts are divided into sigma zones above and below the average line. * Zone C is < 1 sigma from the mean. + Zone B is between 1 sigma and 2 sigma * Zone Ais between 2 sigma and 3 sigma. + Beyond Zone A is > 3 sigma A Process Is in Control If ... a 1. No sample point lies outside limits 2. Most points near process average 3. About equal number of points above and below centerline 4. Points appear randomly distributed The next slides mention Nelson's 8 rules (all are attributed to special causes) 52MACE Control Chart Interpretation : Nelson's 8 Rules Test'1 One point beyond zone A, ucL cu. Let Startup pos/improper set up. ‘Sudden failure of power/cooing/heating/vacuurvsteam system. Machine or tool breakage. New operator introduced, Other spl causes not isted above. 108 ACE Control Chart Interpretation ‘Test: 2 Nine (eight as per some experts) points in a row on one side of center ine. vet cL Let. Improper set up. Excessive tool wearldamaged tool Big change in humiditytemperature New operatorinadequate training/distraction/atigue, New/incoract process parameters. 53MGACE Control Chart Interpretation ‘Test: 3 Sic (seven) in a row steadily increasing or decreesing vol p cL Lot + Operator fatigueldistraction + Excessive wear + Coolantiubricant depletion + Gradual failure of support system (Coolingiheating/compressed air/steam etc) (ACE Control Chart Interpretation Test: 4 Alternating Patterns : Fourteen points in a row alternating upg down vel p cr tet + Intermittent support system failure (cooling, heating, ‘compressed air, vacuum, steam, etc. + Equipment not being warmec up a the shit’ start. + Operator over adjusting the process. 54[ACE Control Chart Interpretation ‘Test: 5 Two out of three points in row in the same zone A or beyond vet cu. Lot + This is also called large shift, due to a major special cause. + Sudden changes In temperature. + 4M change (any one of the 4 Ms) + Operator interrupted or distracted, shift change + Mixed raw materials Control Chart Interpretation ‘Test: 6 Four out of five points in a row in the same zone B and beyond uel poo cL vol4 + Considered a smaller shift + Reasons are same: special causes of omer magnitude 55ACE Control Chart Interpretation ] ‘Test7 Fifteen points in a row in zone C (Above & below canter line) uct. A 8 te ce c 8 A co Let + This called Whitespace Test May be the operator has purposefully truncated the measurements. + May be the limits were wrongly calculated + May be the process has improved significantly due to better tooling et. and now the mits need to be recalculated Control Chart Interpretation Test 8 Eight points in a row on both sides of center ine with none in zone C uct, cL. Let + Mixture (production of various shits, machines, materials mixed) + Teo much over control 12 56