Thursday, December 27, 2012

Calculating Sample Probabilities From a Finite Population

Ref : Design for Six Sigma Statistics (3.1.4.2)

Suppose "n" items selected randomly from a finite population of "N" items
If "D" = defective items in a population
Then, Non-defective items in the population = N-D

What is the probabilities samples will contain exactly "x" defective items and (n-x) non-defective items ?

Example
Suppose a box contain 50 parts
Based on historical data, average defective part found per box = 4% (2 defective part per box)

If each assembly required 5 part pick up randomly from the box, what would be the probability of assembly containing 1 or more defective part ?

This is a finite population sampling problem, where the population = 50pcs (including 2 defective parts)

There are 2 possible outcome from this case
1. assembly containing 1 defective part
2. assembly containing 2 defective part

Since these are mutually exclusive events, the probabilities add.

Solution as below


Alternatively, I calculate the probability this way

Monday, December 24, 2012

A Review Of My 6 Sigma Journey of 2012

How fast time flies by and you don’t even realize, it is coming to the end of year 2012! During the festive season, I would spend some time to review through the status of Thinking 6 Sigma + Lean program in the OP BE before the closing of year 2012.

2012 is the second year of Thinking 6 Sigma + Lean program being deploy in Infineon Melaka. Over the past 2 years, we conducted 4 Wave of Green Belt training that covered Melaka, Wuxi & Singapore site. Total 101 engineers being trained in Thinking 6 Sigma + Lean problem solving approach, 34 of them (3 from Wuxi, 29 from Melaka & 2 from Kulim) successfully fulfill the Infineon Green Belt certification criteria and awarded as certified Green Belt from IFAG. As today, there are 37 Green Belt project closed that contribute to about one million euro saving from the improvement solution implemented. There are 64 Green Belt project in the pipe line, projected to contribute about 1.5 million euro saving in FY2013.

Besides Green Belt training, there is also Black Belt training being organized in year 2012 in Munich, involving colleagues from Melaka & Wuxi site, as well as colleagues from Front End site such as Kulim, Regensburg and Business Unit. The main objective of Black Belt training is to further develop existing Green Belt  to handle more advance Thinking 6 Sigma + Lean tools, so that they are capable enough to support the local management in program deployment and supporting Green Belts in applying Thinking 6 Sigma + Lean problem solving approach to achieve breakthrough improvement.

23 November 2012, we are celebrating the Green Belt Graduation ceremony for Green Belts participate in the Wave II training, this is the second graduation ceremony since last year, total 20 Green Belt of Infineon Melaka and 1 from Wuxi participate the training program successfully fulfill the stringent certification criteria and awarded Green Belt certification from IFAG QM SI. At the same time, we officially announce Khirullah was certified as Thinking 6 Sigma + Lean trainer after going through assessment by our program partner from the HQ. With Khirullah, we further strengthen our local trainer team to face the new challenging year of 2013.



Experience and the sustainable result gained in the past two year proven Thinking 6 Sigma + Lean is a practical problem solving approach, it is a reliable strategy that drive us toward a High Performance company.

2013 will be a very challenging year ahead, overwhelming demand for Thinking 6 Sigma + Lean program support and Green Belt training shows the strong interest of management in this program. We appreciate your involvement and we welcome you as part of our team, as strong management support and involvement is the key success factor of this program. Let’s team up and make Thinking 6 Sigma + Lean systematic problem solving approach as an important driver to the OP BE toward a High Performance organization.

Last but not least, I would like to take the opportunity to wish all colleagues Merry Christmas & Happy New Year.

Saturday, November 17, 2012

My First GB Training In Singapore

Holding a GB training in Singapore for the first time. I was a bit uneasy when getting an instruction from my boss to conduct training for the Singapore colleague. My main concern mainly on my self-confident, I m worry I m not able to meet the high expectation standard set by the Singaporean.

Anyway, like or don’t like, I have to deliver as this is a management target. Yes, I management to deliver my first Block of training without major negative feedback. I m glad my colleagues appreciate the problem solving methodology and will recommend this training to other colleagues as well.

In general, this is my first experience in Singapore, and I feel that communication and level of understanding is easier compare to other location. 

Sunday, September 30, 2012

Toyota A3 Reporting Format

Since last year I started the Lean Manufacturing System training, I notice the weakness of the training module I set up. With the initial management objective is to organize an introduction of Lean Manufacturing System to the Industrial Engineers. Because this is just an “Introduction” session, therefore I prepare a set of training material which is very much focus on the Lean Manufacturing Concept, but not much in the practical.
I conducted 3 classes in year 2012, according to the feedback from participant, I can sense that, they appreciate the concept and believe it is applicable in their work place, but how to start? This is the common question post to me at the end of the session. They need a systematic Lean project management guide to guide them through. Well, in fact, I also know the weakness and this is the topic I need to fix in the coming year.
So, after few consideration of DMAIC & Toyota A3 reporting format, I choose the A3 format for my future Lean training program, this is to avoid unnecessary argument between the die hearth supporters of Six Sigma & Lean. Anyway, it is not so important to me whether it is more Six Sigma bias or Lean bias, it is just a tool to guide us solving our problem in a systematic way, and I see a lot of similarity between Six Sigma and Lean in term of this reporting format. Ok, I will talk about it in my next posting.
Below is the A3 format I prepare.

Tuesday, September 4, 2012

VSM Tool - Microsoft Office Visio

Microsoft Office Visio – This software was appearing on my start button since long time ago, but I never know that it is also a tool for VSM construction. It draw my attention after I launch the software by accident and I spot the VSM feature on the desktop. By then, I try to explore, trying to find the way to automate the VSM tool with my data based in Excel format. Hmm… after 3 days of trial and error, look, this is the outcome of my 1st VSM from Microsoft Office Visio. I would say, it is quite a useful tool for VSM construction.

Tuesday, August 14, 2012

The Story Of Process Variation - 2

I mentioned about variation within member of management could be a key contributor to Six Sigma program failure, I dare to make such statement because I personally seen this happen in my past experience. A well running Six Sigma program, could just turn into red just because a small group of people in the key management team having different opinion about the program.
We have to admit there is no perfect program set up that fulfill everybody’s expectation, therefore the variation come in. We can’t eliminate variation, what we can do is trying to minimize it.
When such variations exist within the management team, it triggers a political issue. Peoples that do not align with the big direction will start to build up barrier to isolate themselves or even their organization within their control to get involve.
Sometime, I feel pity to the peoples who spend lot of effort to drive the program successfully for the sake of company benefit, but their effort was just end up destroy like that by the key guys who have different opinion in their mind without giving a good reason.
I face a similar problem recently ( in fact, this the second time face such issue ), a successful Six Sigma program, running well in the past two years and now facing some challenge due to such kind of variation. I don’t know the reason behind a new management shows such a negative attitude toward the program, but for sure, motivational level of a group of Six Sigma practitioners within the organization were badly deteriorated. I foresee, sooner or later the people will just give up the good practice and go back to the old way due to lack of management support , for those who would like to continue the practice, most probably, they will just take away the knowledge and continue their career at the competitor site.

Saturday, August 4, 2012

The Story Of Process Variation - 1

When we talk about Six Sigma process, it refer to a process variation that at least 6x smaller than the gap of process center to its specification limit. In short, maintaining a small process variation is the key success factor of a process to achieve Six Sigma level.
A “Process”, is a series of activity arranged in sequence to from a product or service. Therefore, every single task we do in the shop floor could be part of the process, don’t forget, we introduce variation to the task we did. A small variation may not be critical to the process, but a big variation that we introduce, could be serious enough to result a process failure.
In fact, managing the Six Sigma program also involving a complicated process, especially in a multi-national company, where various peoples with different background, different culture, different interest and different leadership style meet together to form a so call “Management Team”. The process of bringing them together and get them align to a common Six Sigma Program direction is always complicated. From my previous experience, the variation within the management team members is anytime higher ( much higher ) than any process variation in the shop floor. A often I see Six Sigma program fail main due to one or two management team member who have different perception to the program.
 Therefore, as program leader, while staying focus in minimizing the process variation in the shop floor to delivery great saving, you shouldn’t forget the variation introduce by the group of funny peoples who determine the overall program performance.
Ok… I will continue my story in the coming post… stay tune…

Thursday, July 26, 2012

A Tear Down Of GR&R Template For Continuous Data

When I m free, this is one of the thing I like to do.

I try to understand the template sometime ago, but I couldn't get it right and I find it too complecated to follow.

Yesterday when cleaning up my folder, I found the template again and I ask myself a second chance. I printed the whole template out in big A3 paper and try to link up the relationship of each single working step. Finally, I think I understandit it better.

Monday, July 23, 2012

A Chance To Share In Wuxi

There are many first time for this round of business trip to the Mainland China.

First time I touch down on Shanghai and Wuxi
First time I given a chance to conduct training in Wuxi
First time the GBs sitting in front of me are manager level
First time I have to conduct the training in 50% in English and 50% in Mandarin.



Yes, it is a totally new experience to me.

In the past, the GB training I involve, most of the time GBs attending my training are junior or senior engineers nominated by their functional manager, and most of the time, their managers as their project sponsor has limited knowledge about the Six Sigma program and problem solving methodology and even limited knowledge about the improvement project the GBs identify for their GB training.

But for this round, it is the first time the company organize a GB training program, not for their engineers, but for the functional managers. The whole idea is, all the functional managers ( at least in the operation ) should be GB certified, so that they can guide their subordinate to handle improvement activities through Six Sigma DMAIC methodology.

Yes, this should be the right way to go if a company serious about the program. I believe everybody know that management support and commitment is the key success factor of Six Sigma deployment, getting the functional managers trained as GB can be an effective way to spread the Six Sigma culture throughout the company.

The Wuxi plant is another focus of me after Melaka. It will be more challenging to me as I have to work with a team and in an environment that totally new to me. I do hope I can create another success story in the Mainland China.

Thursday, June 21, 2012

Lean Game - Lucky Face Assembly

 

The Lucky Face Assembly is a Lean Manufacturing Game that I suppose to tailor it for Lean Manufacturing System training. Unfortunately, I don’t have the chance to test the effectiveness until the Black Belt training in Munich.

As the counterpart request me to take care the Lean Manufacturing topic, I decided to take a risk to trial run the game in Munich. Fortunately, it runs well in the first round though there are some minor hip up, I manage to handle it anyway.

In fact, I learnt the Game from You Tube ( just do a search of “Mr Happy”, you should able to get it ). But I did some changes so that overall flow and handling procedure is matching the business nature of my company.

I m happy to see the participants are able to make use of the Lean Tools I introduce and manage to make significant improvement to meet the unpredictable customer demand. They learnt how to construct a VSM through the game as well.

Monday, May 28, 2012

A Chance To Share In Munich

Manage to earn a chance to share my knowledge in Six Sigma & Lean with my counter part in Munich.

This is the first Black Belt training ever I participate, involving Green Belt candidate from Malaysia, Germany & China, it is quite an exciting experience to work with a group of counter part from different country, where we are facing some language problem, yet we manage to over come it and work together to achieve our objective.

In prepare some practical game to make the training fun, fortunately it works well despite facing some time constraint, in general, I m happy with the outcome for this round.

Together with me, there are three trainer from Germany and one from Malaysia.


BB Training - Munich 21 - 27 May 2012

Wednesday, May 9, 2012

How Minitab draws the line and determines significant effects on the normal plot of the effects

In the last knowledge sharing session, I share about 2k factorial DOE with Minitab. Somebody ask how actually Minitab define the red line in the Pareto Chart of Effect, and what is Lenth's PSE


Answer given to the audiance during the knowledge session was : sorry, I don't know.
Anyway, I try to find out the asnwer yesterday and here the answer I get.

Reference document

I try to work out the number with the example I shared, fortunately, I manage to workout the answer manually.

Just follow the step below, I believe you guy can get the answer as well

Step 1 : Stat > DOE > Analyse Factorial Design
Check Storage & Effect as shown in the picture below


Copy the value of EFFE1 and paste it into Excel for manual calculation
Table as shown in the picture below. You should able to get Lenth's PSE of 11.4375

In Minitab, the Red Line of Pareto chart is named as Margin Error (ME).
ME = t x Lenth's PSE

Where t can be find from t distribution.
Cal > Probability Distribution > t
Refer to Ref Document above.



Finally, I got the answer.




Thursday, April 12, 2012

Box-Cox Transformation

Minitab procedure
Stat  >  Control Chart > Box-Cox Transformation

The Box-Cox transformation is used to transform non-normal data or when within subgroup variation is unstable that cause the data non-normal. The Box-Cox procedure was developed to determine an optimal transformation from the collection of the form







The optimal value of Lambda is then used as a guide for data transformation. It is not necessary to use precisely define Lambda. For example, use Lambda = 0.5 instead of Lambda = 0.48339.

Common value for Lambda include


You may use the comman to find the optimal Lambda value and choose to store the transformed data with the command, do not select the Box-Cox option when you make a Control Chart, do ing so will cause double transform of the data.

Example of Box-Cox Plot



Ref : Minitab Stat Guide


Friday, April 6, 2012

Run Test

I learn something new from the past Kulim training.

A Green Belt shared with me how we can apply Run Test to test if the sample series is distributed randomly.
Test procedure as below

Minitab >> Stat >> Nonparametrics >> Run Test

Note : run test is a nonparametris test because we make no assumptions about the distribution of the population being sampled

Session Window

Runs test for C1

Runs above and below K = 10.0000

The observed number of runs = 17
The expected number of runs = 15.7333
17 observations above K, 13 below
P-value = 0.632

P-value > 0.05, the data being test is no significant different evident to proof the data is not in random order.

Saturday, March 24, 2012

Some Lesson Learn From Kulim Green Belt Training Program



I was in Kulim in the past one week, supporting the Green Belt training for the Front End operation. This is their first experience holding Green Belt training, same to me, first time standing in front of a group of colleague that totally new to me. Somehow, thing is not well organize is expected.

Overall, I don’t feel good on this round of training, though I only involve in the second haft of the whole program, I don’t have the feel I achieve my objective. In the discussion with my counterpart, keep on reminding me that Kulim is not Melaka, I shouldn’t measure them based on Melaka’s standard. Ok, noted…

What is the problem then? Why Melaka manage to do it right at the first time, and what is the secret behind? By luck?

Definitely not by luck, I mentioned this in my earlier post
http://www.6sigmaforum.blogspot.com/2011/10/big-project-i-ever-handle.html
Now, let me talk about Kulim, based on what I sense in the four days training.

People attended the training without knowing too much about the program all about, they seem like do not aware the whole training session is break into two block, and what they suppose to deliver in each phase of the training and they under estimate the expectation from the training program. When people notices they are not prepared during training, they start to loss focus, sense of meaningless and de-motivated to continue.
I foresee such issue from my past experience, in Melaka, I used to schedule a briefing session to the potential Green Belt candidate, to make sure they are ready and well prepare before they come to the training. This session also provide a second chance for those who is not ready to commit for project completion to reconsider to sign up for the training.

I believe, this was not done in Kulim before the Block I training.

Project selection could be another problem I see in Kulim, before I come, I hope l can learn something in term of wafer process from the Green Belt through project presentation, unfortunately, non of them ready with some slide to share their problem, or project status. Therefore, we cancel the project presentation session as planned in Melaka. Input given to me from the Green Belt candidate was, they are too busy on other business activities. Who should be blame in this case?

What about Melaka, or the other site in Asia that I handle? I would say, I face the same problem, but not as serious as compare to Kulim. My advice to Kulim is, managers involve in project selection and assigning project, should be smart enough to pick up project that within control of the Green Belt candidate, project can be identify from the engineering activities that Green Belt is currently working on. So that they Green Belt has a project, that within their control and without additional workload.
Training facility, ar……… this is the worst I ever experience. I have to shift from one training room to the other, within the four training day, this is really no fun to me. Such problem can be avoided if somebody paying attention about the training.

Overall, not so bad, at least, I believe somebody is learning something, at least I learn something from the negative point mentioned, so that I m more prepare in the future.

Though this is not at good experience in the first launch, but it is not the end of the world, I do believe they can do better in the next Wave, I do hope I can join them in the next phase, right from the phase of project selection.

Lets see…

Saturday, February 4, 2012

A Recognition From The Head Quater

This is my first Lean Six Sigma project that I do it my own most of the time.
Started from LSS deployment strategy definition
 LSS organization set up
Champion training
GB training material compilation
Wave One GB project selection, training and project coaching
And finally Wave One GB graduation.

In total I spend about 1.5 years to complete the first cycle of LSS deployment phase in the company.
I m happy with the result, all 15 candidate selected to participate the training manage to complete their project on time. Most importantly, majority of the top management impressed with the DMAIC problem solving methodology presented by the GBs during their project checkout.

This year, I decided to pick up the new function, being a full time LSS deployment driver of the company.