Rishant Dutt

About Rishant Dutt

Posts by Rishant Dutt:

May 23 2023

Where to begin with SPC

Figuring out where to begin

Given how important initial impressions are, care must be taken with any SPC initiative with regards to which problems to address first. In a previous post we went over why we recommend a results-oriented small-scale approach to starting with SPC, in this post we will go over tools and techniques that detail how to go about actually doing it.

Start with these …

CHECK SHEET

PARETO ANALYSIS

Check sheets can be used as a standalone tool or be used to construct Pareto charts (though they’re not necessary to create Pareto charts).

Also known as the 80/20 rule. It is based on the fundamental assumption that approximately 80% problems arise from roughly 20% of the possible causes.

They include a list of nonconformities and a tally of the number of each nonconformity.

The take home message being that most significant improvements will be seen by addressing the few vital problems, while solving the other problems will only produce incremental results.

Check sheets usually also include the name of the project, for which the data is being collected, the shift when the items were produced, the names of the people collecting the data, dates when the data was collected, and the location of data collection.

The analysis process includes Pareto charts, which serve as a graphical tool that can convey the importance of problems, compared to each other.

CHECK SHEET

Check sheets can be used as a standalone tool or be used to construct Pareto charts (though they’re not necessary to create Pareto charts).

They include a list of nonconformities and a tally of the number of each nonconformity.

Check sheets usually also include the name of the project, for which the data is being collected, the shift when the items were produced, the names of the people collecting the data, dates when the data was collected, and the location of data collection.

PARETO ANALYSIS

Also known as the 80/20 rule. It is based on the fundamental assumption that approximately 80% problems arise from roughly 20% of the possible causes.

The take home message being that most significant improvements will be seen by addressing the few vital problems, while solving the other problems will only produce incremental results.

The analysis process includes Pareto charts, which serve as a graphical tool that can convey the importance of problems, compared to each other.

More on Check Sheets

When creating a list of nonconformities it is important to standardize it. This is for three reasons,

REASON 1

You’ll find a lot of people don’t agree on the major categories of nonconformities. A good way around this is to have a brainstorming session with everyone involved, like production personnel, management, QC personnel, and your customers.

REASON 2

Most of the times people do not agree on what precisely constitutes a nonconformity and perhaps even a nonconforming item. That is to say, how bad does an item have to be to get thrown in the scrap or rework pile.

REASON 3

Finally, people from different backgrounds, and sometimes even people within the same department, might put a defective item in a different category. Without standard terminology and definitions, it is very difficult to conduct a Pareto Analysis.

More on Pareto analysis

The keys to good pareto analysis are as follows,

KEY 1

Using check sheets is always advisable when performing pareto analysis. Check sheets offers standardization, which can help you avoid a lot of conflicts.

KEY 2

The frequency of nonconformities is not the only factor that needs to be taken into account. The cost associated with each non conformity needs to be factored in as well.

KEY 3

The cost associated with a nonconformity depends on the cost of each, scrap and rework. Not only the cost but also the percentage of scrap and rework for each nonconformity needs to be accounted for when calculating the costs associated with them.

July 7 2022

Attributes Control Charts in SPC

SPC

Attributes

Control

Charts

Provide verification for the impact of any change made and help ensure that the process remains stable over time. Without the use of controls charts, there’s a greater chance of wasting time and resources chasing false alarms, while being unsure of the impact of any change that’re made to the process and the process’ sustainability.

Attributes Control Charts

Variables Control Charts

Attributes Control Charts

When it isn’t possible to measure things, you are limited to counting / tallying the results, e.g. whenever there’s an all or none inspection like go / no-go, acceptable / unacceptable, etc., this is where attributes control charts become important.

In a factory environment the common situations where attributes are the only choice are when yes/no decisions need to be made, for example,

Evaluating packaging appearance
Checking the accuracy of package labeling
Checking label locations on packages
Making sure that packaging is free of grease marks and forklift tracks

Another great use for attributes control charts is to analyze historical data. Many companies already collect inspection data before they ever start using SPC. This data is almost always attribute data such as number of defects detected in a unit / sample / batch, etc.

Variables Control Charts

Variables data provides more detailed and helpful information for troubleshooting and process improvements, therefore it is favored wherever it’s feasible to collect variables data. For example, a go / no-go gauge only tells you whether a part passed inspection or not, it doesn’t tell you whether it was over the upper tolerance value or lower than the lower tolerance value and by how much. This information can be critical when trying to troubleshoot or improve a process.

Another key advantage of using variables data to construct control charts is that they require significantly less data to construct. Sample sizes for attributes data are not only lager but also the amount of data required increases inversely with the rate of nonconformities, that is to say, the lower the rate of nonconformities the larger the sample size for a attributes control chart must be. For example, if the rate of nonconformity is 1 in 100 but you take a sample of size 10. Then the chances of coming across an out-of-spec part are very low. This means that the chart will indicate that there were 0 out-of-spec parts, it will be a flat horizontal line at 0, which is not very helpful.

* This especially troublesome because companies usually want to spend as little time collecting samples as possible.

Types of Attributes Control Charts

p charts: Reflect the ratio of nonconforming units in a sample to the conforming units in the sample. Given that it’s a fraction the actual sample size may vary.
np charts: Like ‘p charts‘ but instead of the ratio, np charts show the number of nonconforming units in a sample, because it charts the number of nonconforming samples, the sample size must remain constant.
u charts: Reflect the ratio of nonconformities per unit in a given sample, because it’s a ratio, the sample size may vary.
c charts: Like ‘u charts‘ but instead of a ratio, c charts show the number of nonconformities for all the units in a sample, therefore the sample size must stay the same.

Collecting Data

* Like variables control charts, attributes control charts are graphs that display the value of a process variable over time. Therefore, the order of production matters even though, it’s not always tracked while collecting attributes data which is not meant to be used for constructing control charts.

A good place to start collecting attributes data is while conducting experiments, but extra care must be taken to record the order of production as well, which isn’t always the case because of the randomized nature of experiments.

Historical data is often a good source of attributes data as well, because most companies tend to keep a record of inspections that’ve occurred in the past.

Inspections, of all sorts, are also a good place to collect attributes data. Especially, when the attribute being evaluated has no objective unit of measurement.

Also, any situation where a binary decision needs to be made like acceptable / unacceptable or go / no-go, etc. is good place to collect attributes data for control charts.

* FSWorks, by Factory Systems, offers an intuitive data collection solution for attributes data along with automatic and real-time attributes control chart generation for all types of attributes control charts such as p-charts, np-charts, u-charts, and c-charts.

If you want to leverage the powerful, yet easy-to-use, suite of tools offered by FSWorks in order to gain a deeper understanding from the data being collected in your factory or the historical data you’ve collected in the past, please click here.

Analyzing Data

Data analysis for attributes control charts is simpler than that for variables control charts.

We need to keep a track of the number of nonconformities (for np and c charts) or the fraction of nonconformities (for p and u charts), for each sample (in p and np charts) or each inspection unit (in c and u charts).

Constructing Control Charts

I. Centerline

The centerlines for attributes control charts are per sample/unit averages of total number/fraction of nonconformities, usually denoted by p-bar, c-bar, and u-bar.

II. Control Limits

‘p‘ and ‘np‘ control charts are known to follow a Binomial Distribution, and from statistical theory we know that the standard deviation of a binomial variable is,

therefore the upper and lower control limits for p and np control charts are as follows,

where p-bar and np-bar are the estimate of the long-term process mean established during control-chart setup.

u and c charts are known to follow a Poisson distribution, and from statistical theory we know that the standard deviation for a poisson variable is,

Therefore the upper and lower control limits for c and u control charts are as follows,

where c-bar and u-bar are the estimate of the long-term process mean established during control-chart setup.

Analyzing Attributes Control Charts

In analyzing the attributes control charts, our primary interest is process stability and consistency. With that in mind, if there’s only evidence of inherent variability, then the process can be thought of being in-control / stable. However, if there is evidence of assignable-cause variability, then the process can be thought of as being out-of-control / unstable, in which case you must take action to return stability to the process before proceeding further.

Some of the trends in attributes control charts that indicate if a process is out-of-control are,

Any point outside of the control limits.
9 points in a row above or below centerline.
6 points in a row steadily increasing or decreasing.
14 points in a row alternating up and down.

Conclusion

Attributes control charts help you ensure that the process remains stable and predictable, when collecting variable measurements is either infeasible or impossible. That being said, variables data is always preferred and should be used wherever possible. Also, control charts, of either kind, don’t help you decide when to be satisfied with the current state of the process, they only tell you if it’s stable and provide you with the value that the process is centered on and the amount of variability in the process.

Want to learn more?

Factory System’s FSWorks is a world-class data acquisition and quality management software

Still not sold?

Try our 30-day trial and witness the transformational ability of FSWorks for yourself

July 5 2022

Control charts in SPC

SPC

Variables

Control

Charts

What is a control chart, really?

At a very rudimentary level, a control chart is a chart which has points, a centerline, and control limits. In SPC, there is a need to monitor the accuracy (centering) and precision (variability) of a process. In order to do so we need to two control charts, one for each purpose. These charts are,

X-bar chart (centering)

Here the points represent the average value of individual measurements in a sample, as it plots these sample averages over time.

The centerline is the running average of the aforementioned sample averages referred to as x bar-bar.

The control limits are horizontal lines known as upper control limit and lower control limit, these will be discussed further later in the article.

R bar / s bar chart (spread)

Here the points represent the range of values in a sample for an R chart or the standard deviation from mean for an s chart.

The centerline is the running average of all range values, for each sample, or all standard deviations, for each sample.

The control limits are horizontal lines known as upper control limit and lower control limit, these will be discussed further later in the article.

Overview of the statistics involved and key definitions

Sample: When dealing with large numbers, like in production, it’s rarely feasible to audit each member. We instead try to find a representative few and extrapolate our findings to the whole. Though it inevitably biases our results, if done properly it allows us to draw powerful conclusions about a population.

Average (aka ‘mean’): It provides a sense of the center value of a group of data. It can be calculated by simply adding the values for each member of the group and dividing by the number of values in the group.

Range: It is one of the most common measure of variation in a group of data. It is calculated by simply subtracting the minimum value from the maximum value. Though range is easier to calculate and understand, however it is less accurate because it only uses two data points from a sample.

Standard Deviation: It provides a better measure of variation because it uses all the sample data, however it is more complicated to calculate. In SPC, traditionally table values are used to estimate the standard deviation for a given range.

* Statistical theory shows that the standard deviation of small samples taken from a population is biased, i.e., it tends to be less than the true value. Thus it is better to inflate the value a bit by dividing by ‘n-1’ rather than ‘n’.

Normal Distribution: It is one of the most prevalent distribution in nature and specially in the field of statistics. It is often identified by the recognizable bell shape of the distribution, therefore it is sometimes called a bell curve.

* Even if a population isn’t distributed normally (eg. age), the mean of samples from a population tend to follow a normal distribution reasonably well.

Creating Control Charts

i. Collecting Data

Why not collect everything? Why not measure everything?

Well, if it were convenient in terms of time and money then we would! But there are always constraints on both those factors. This creates a need for a more efficient way of collecting data, in SPC it is usually called “Rational subgrouping“.

Our approach needs to minimize variation within a sample but maximize variation between samples, because substantial variation within sample makes it harder to detect variation between samples if there is inherent variation within the process, it the process is stable then the there would be little no inherent variability in the process thus rendering the difference in time between readings inconsequential.

In SPC the process of collecting data is generally as follows,

Collect a small sample (3-10 units) in rapid succession
Wait for some amount of time before collecting another sample

* NOTE: Make sure to collect data in the order they’re produced because control charts are meant to be a time-series chart

ii. Construction Control Limits

X-bar chart

Here, we’re monitoring the averages of samples not the individual measurements. Therefore, control limits cannot simply be based on estimate of standard deviation of the individual measurements, because they do not accurately reflect the variability of the averages is much less than the variability of individual measurements. This relationship is given by the standard deviation of samples being root of number of samples times less than the standard deviation of individual measurements.

Also, there is a well established relationship between the standard deviation of a normal distributed process and the range of a normal distributed sample, also given that we’ve already calculated the overall range of the samples given by R-bar, therefore the estimate of standard deviation of a process is given by,

therefore,

Upon condensing the constant parts into a single value we get,

R chart

Now we need the control limits for the R chart (which is more common than the s chart). The centerline for this chart is going to be the overall average range, R-bar, we used previously. The upper and lower limits control limits depend on the sample size, defined as,

where, D₃ and D₄ are constants defined in the table below.

Figure. X-bar and R chart in FSWorks by Factory Systems

Mathematical Constants

Sample size (n)	d₂	A₂	D₄
2	1.128	1.880	3.267
3	1.693	1.023	2.574
4	2.059	0.729	2.282
5	2.326	0.577	2.114
6	2.534	0.483	2.004

Sample size (n)	d₂	A₂	D₄
2	1.128	1.880	3.267
3	1.693	1.023	2.574
4	2.059	0.729	2.282
5	2.326	0.577	2.114
6	2.534	0.483	2.004

* Trend analysis is a highly time sensitive process. If you wait to draw the control charts and perform trend analysis on them there will be always a lag between the process going out-of-control and you detecting it. If the trend analysis shows that the process has gone out-of-control then you just spent time making defective parts and without proper traceability it will be very difficult to find and separate those parts for rework or for scrapping.

With FSWorks we aim to offer many features to our customers but probably none more important. FSWorks offers continuous evaluation of trends with an instant alarm system, which alerts you to your process going out-of-control as soon as possible, while also offering comprehensive tracking for all the parts being produced on a line.

Figure. Customizable alarms based on continuous trend analysis in FSWorks by Factory Systems

Trend Analysis

The primary purpose of control charts is to determine if the variation in a process is due to some assignable cause or is it inherent to the process. There are many ways to interpret a control chart in order to come to that determination, a simple approach may be to simply react to any points that fall outside of the control limits, but another popular approach is known as the Western Electric Rules, because it was developed by Western Electric Company, and is as follows,

A control chart indicates an out-of-control process if any of the following rules are met,

Rule 1: Any point outside of the control limits

Rule 2: 2 or 3 consecutive points beyond two standard deviations

Rule 3: 4 or 5 consecutive points beyond one standard deviation, on the same side of centerline

Rule 4: 7 consecutive points above or below centerline

Rule 5: 5 consecutive steps upward or downward

These rules can be adopted whole-cloth or be bent according to your specific requirements, depending on how strict you want your quality control to be.

* X-bar chart is based on the value of overall average range, R-bar, so if the R chart indicates an out-of-control process then our estimate of the range isn’t reliable and therefore we can’t be confident in the limits of the X-bar chart either.

Future Steps

When a process is determined to be out-of-control, the team needs to go looking for problems, once a problem is found, it needs to be fixed and the sample that indicated the existence of the problem needs to be excluded and the control limits recalculated and redrawn, these limits are called test limits.

If the new limits still indicate that the process is not in control then the above procedure needs to be repeated. However, if the process is now in-control, then extra attention needs to be paid to this process over the next several days, probably with an increased sampling frequency, and longer the process stays stable, the more confident you can be in its stability.

* If the R chart indicates an out-of-control process, because the points are above upper control limit, but the X-bar chart is in control, this indicates variability of the process has increased.

Else if the R chart indicates that the process is in control but the data points on the X-bar chart are trending downward or outside lower control limit, it indicates that the process’ average/center has decreased significantly.

If both charts indicate that the process is out-of-control, then there may be several issues to explore and address.

Want to learn more?

Factory System’s FSWorks is a world-class data acquisition and quality management software

Still not sold?

Try our 30-day trial and witness the transformational ability of FSWorks for yourself

June 20 2022

Designing experiments for SPC

SPC

Design of

Experiments

in SPC

Design of Experiments (DOE) is used a catch-all term to describe a set of statistical methods and tools that ensure effective and efficient conduct of experiments. The steps that constitute DOE include designing and conducting the experiment, data analysis, and interpretation of the results.

* People often conflate design of experiments (DOE) with designing an experiment, which are two separate concepts. DOE incorporates the designing of an experiment as an important step in the process but it also includes other steps that are just as vital.

Traditional approach (w/o DOE and statistics)

In an attempt to save time and money, while creating the least amount of disruption and causing the minimum hassle, most companies tend to approach the experimentation part of the process with the goal of performing a few all encompassing large-scale experiments.

This approach treats all factors discovered during the process of creating the cause-and-effect diagram as being relevant and try to develop operating procedures to monitor all of them. This quickly becomes time consuming, costly and inefficient. It also create frustration amongst the equipment operator as they are asked to collect data, that in most cases is never studied or followed up on in any manner.

This often coupled with relying on experience and expertise of employees who often try tweaking the process at several different places, often lacking proper coordination or knowledge of all the changes being instituted by other departments.

Another common trait of this approach is the reliance on a small number of results, done in an effort to save time and money. As a whole such an experiment, a large-scale attempt to monitor several factors, while tweaking the process independent of it, using a small number of results, leads to hard to interpret results.

Even if the results came out as hoped, how can it inspire any confidence that the results will be the same over time when the changes are made permanent. Such large unstructured experiments also make it really hard to perform any statistical analysis on the results, which further invalidates any confidence that could be gained from the results.

* It is perfectly reasonable for the reader to assume, from the above passage, that the best approach would be to perform multiple smaller experiments where all factors are tested individually but it is not so.

When you test factors one-at-a-time it becomes impossible to ascertain how factors interact with one another, which might the the root cause of the problem rather than the the factors themselves.

Challenges in setting up experiments:

When in an industrial setting, even the simplest of experiments can be difficult to setup, execute and analyze the results for. This complexity contributes to the high costs associated with experiments, both in terms of time and money, especially if the sample are analyzed destructively.

Because of the aforementioned factors, using statistically designed, conducted, and analyzed experiments become imperative. With proper design of experiments (DOE) you will get the most value for your investment.

How can

Design of Experiments

(DOE) help?

DOE, and the statistics associated with it, help answer some of the most pertinent questions when a company is looking to conduct experiments in search of the root cause of a problem:

Which variable or combination of variables affected the results?
Are the results significant (i.e., likely to be the same if the experiments were conducted again)?

Steps in Design of Experiments (DOE)

Step 1: Objectives

At the beginning of the experiment two questions need to be answered,

Why are we conducting the experiment?
What does the company hope to learn from it?

Step 2: Determine the ‘Response variables’

Response variables are the determined by the outcomes of interest of any experiment. They must be selected carefully, it serves to keep in mind that response variables must match the problem that is needed to be solved.

Next, a way of measuring these variables needs to be established, this includes how, when and where in the process they will be measured.

Step 3: Determine the ‘Process variables/factors’

It can be hard to know which factors to control and which ones to vary, especially on the first attempt. A common strategy is to rely on the experience of your employees and iteration.

This step also involves deciding the correct granularity for process variables of the experiment. Once the granularity is decided, methods for measuring each continuous factor and labeling scheme for discrete factor also needed to be decided upon.

* Granularity can be a tricky concept to deal with, especially for continuous factors. You must ask yourself how much coverage do you want? For example, assume a factory making cast iron skillets gets iron ranging from 80%-95% purity, what percentages of iron should you study? Levels should be realistic but with enough range, so that, if the factor is indeed important, then, real differences are likely to occur.

Step 4: Number of replicates

Based on the process variables, there are a bunch of combinations of factors that need to be tested. This raises the question, how many samples do you plan to collect for each combination of factors? There are statistical formulae that provide guidance on the number of replicates needed, depending on the variability of the measure of interest.

The number of replicates needed are also determined by the level of difference you want to be able to detect and your desired certainty in the outcome.

* Usually, the ability to detect significant results increases with the number of replicates. However, If experience has shown that a factor is consistent, has low variability, fewer samples may be needed and if the factor has high variability in the results, a larger sample will be needed to detect significant differences.

If the variability is extensive, then it might make more sense to improve the stability of the process before conducting an experiment.

Step 5: Detailed experimental plan

Create a plan that details, step-by-step. Who will do what, when, and where they’ll do it? Specify the materials, procedures, operators, measurement tools, testing date and time, etc. It is also important to consider how you will analyze the data, and how you will interpret and use the results. Make sure to analyze in a way that answers critical questions. Perform ‘Dry run’ to figure out what might go wrong, how things are going to move, special fixtures required, and try to analyze the preliminary data.

* Establish a budget and set deadlines at this step. Experience would suggest that no more than 1/4^th of the full budget should be spent on the first experiment. Many times, a first trial will reveal more questions and provide suggestions for what to study next.

Step 6: Decide what factors to be held constant

In step 3, factors that were to be varied intentionally were identified, however, other factors that are held constant still need to be taken into account. Besides the potential causes that are being studied, every other cause in the cause-and-effect diagram should be held constant. The goal is to eliminate, as much as possible, all other factors that may be the cause of variability, thus providing assurance that any differences in results are due to the selected experimental factors.

Step 7: Post-Experiment Plans

This step consists of finding answers to the following questions, How will you use the results? If the results suggest a potential solution, how, by whom, and when will it be implemented? Will you conduct confirmation trials? How will you monitor the process to be sure that the changes remain in place and continue to effectively reduce the problem? If the tests are not successful, what course of action will you take next?

Conclusion

Often at the end of an experiment there is a good chance that there will be no definite solutions but rather recommendations that need to be implemented and followed up on. Still there is great value in designing experiments using DOE and statistical techniques because they can help you ensure you maximize the return on your investment, especially given the high costs and general complexity of conducting experiments in an industrial environment.

Want to learn more?

Factory System’s FSWorks is a world-class data acquisition and quality management software

Still not sold?

Try our 30-day trial and witness the transformational ability of FSWorks for yourself

June 17 2022

Bang-for-Buck SPC

SPC

ARE YOU GETTING

THE MOST OUT OF

SPC?

SPC programs can offer great value to a business but if done poorly they can be a big resource sink. In the following sections we will discuss some tools and concepts that one must understand and adhere to, in order to ensure they avoid the most common, often costly, pitfalls when creating their SPC programs.

Why implementing SPC can be daunting?

And result in an expensive failure if proper care isn’t taken.

The idea of adopting SPC, and other statistical quality improvement programs, represents a major shift from the pre-established quality programs. These traditional approaches to quality management rely on detecting defects in products. SPC on the other hand is a process oriented approach, which aims to improve the processes involved in production, thus resulting in defect prevention.

Implementing an effective SPC program requires significant effort from all levels of an organization. The quality department can’t succeed in such an endeavor without organizational support and commitment.

Not only will it require an in-depth examination of the processes being employed, this will include a thorough analysis at both macro and micro levels through the use of flow charts and Pareto charts. Participation from production personnel is also key, as they are the ones who’ll be responsible for monitoring and taking proactive corrective measures.

* Moreover, if the push to adopt SPC isn’t directed in a particular direction, in order to achieve a particular result, and instead becomes an all-encompassing behemoth set of quality improvement activities and programs, then the resulting inefficacy and costs can lead to frustration and eventual disenfranchisement throughout the organization, making any future attempts even harder.

What
to
do?

What to do?

We recommend a small-scale targeted approach, focusing on the primary issue as determined by customer feedback and pareto analysis.

This should be a results-oriented effort, with a time horizon of a few months, not years.

But Why ?

Reason 1: Overcoming Resistance

By only introducing SPC where it’s needed the most, there is a much greater probability that everyone involved in that process is going to be excited for and be accepting of the new changes.

Reason 2: Best bang-for-buck

By targeting the most frequent and costly defect first, there is a lot potential value that can be added to the organization. This can set a powerful precedent.

Reason 3: Promotes incremental success

Focusing on one problem at a time makes it easier to succeed at achieving the desired result. This approach can then be extended to other problem areas.

Reason 4: Allows for trial-and-error

It’s easier to identify and correct mistakes at a small-scale without causing a significant monetary loss. Eventually it’ll give you a better idea of what works and what doesn’t.

Reason 5: Helps develop experience

With sustained successes comes a wealth of experience and confidence. Once you’ve produced tangible results, SPC will be more readily welcomed by everyone in the organization.

Want to learn more?

Factory System’s FSWorks is a world-class data acquisition and quality management software

Still not sold?

Try our 30-day trial and witness the transformational ability of FSWorks for yourself

May 23 2022

Identifying sources of defects

SPC

alexey-turenkov-NEwe0UGsTfY-unsplash (1) (1)

Identifying

Sources of

Defects!

Defects or nonconformities are often a result of multiple aspects of the manufacturing process not working as intended. There is however, a “root” cause which is primarily responsible for the defect/nonconformity.

In this post we will discuss the two main techniques that are commonly deployed for identifying the cause for a defect/nonconformity. These techniques work in conjunction with one another, though they can be employed separately.

The first thing we’re going to focus on is ‘Flowcharts‘ which are a symbolic/graphical representation of the actual process that takes place on the factory floor. Next, we are going to discuss ‘Cause-and-effect Diagrams‘ which are used to enumerate and categorize the possible causes for problems, hence making it easier to arrive at the root cause of a problem.

Flowcharts

Initiates discussion between personnel from all departments of the plant. Also, Establishing consensus about what actually happens not what’s supposed to ideally happen.
Can reveal non-value-added activities such as redundant inspection and steps reworks, bottlenecks. With enough detail flowcharts can also reveal unnecessary movement and processing loops.
Promotes clarity with a graphical representation of the steps in creating the product, while elucidating key details about the processes that personnel may be unware of.
Makes everyone question all the steps involved in the process, leading to optimization.
Allows for analysis at multiple levels, via macro, intermediate, and micro flowcharts.
Highlights the quality characteristics that should or need to be monitored.

* From an SPC point-of-view,

Flowcharts help reveal the stages in the process where data may be collected.

Cause-and-Effect Diagrams

Cause-and-effect analysis helps identify main causes for problems and the steps we can take to solve them, once the pervious steps give us an indication as to what the problem is and where it might be occurring in the process.
The best part is often the process not the results, as with any team effort. With representatives from all departments, each member can share their expertise and experience with the problem, they assists clarification of potential causes, and building consensus for causes.
Circumvents the trap of “Pet Theories”, where people assert that they already know the cause of a problem without taking part in a collaborative analysis. If the person is wrong then it leads to a waste of time and resources, even if the theory is correct, it may be only partially correct, i.e., it might address a symptom or secondary cause rather than the root cause.
Cause-and-effect diagram promote sense of ownership over the process and motivates everyone to implement and maintain the solution. Without a team effort, personnel may feel their input to problems is neither needed nor valued.

Flowcharts

Flowcharts are invaluable in initiating discussions during Cause-and-effect analysis. The team effort helps get everyone on the same page, while revealing key details.

Ensure that everyone understands and agrees on the actual processes that really take place on the factory floor, rather than what is supposed to happen.

They also help to find opportunities to optimize the process at various locations and more data collection, while highlighting non-value-added activities.

Steps involved in creating a flowchart

* For future reference note the names of team members, the date, and the purpose for creating the chart should be included.

Step 1: Determine the start and stop points that the chart will cover. The level of detail should be maintained at a consistent level of detail, so it’s imperative to decide on it from the beginning. Macro-level flowcharts show key action steps but no decision boxes, intermediate-level flowcharts show action and decision points, while micro-level flowcharts also include intricate details.

Step 2: Brainstorm amongst all the team members, either allowing anyone to chime in with an idea or going round-about giving everyone the opportunity to contribute. Ask everyone to list all the steps involved between start and stop points of the flowchart, finally, put the steps in order.

Step 3: Draw the flowchart using the standard symbols to signify Inputs/Outputs, Processing, Decision, Storage, Delay, Data Entry, Movement, and Inspection. Each step needs to be labeled. Arrows should be used to indicate the flow of steps. Label branches of decision boxes, e.g., “Yes”, “No”, etc.

Step 4: Test the accuracy and completeness of the resultant flowchart, by making sure,

All symbols are used correctly
Steps are identified correctly and clearly
Process loops are closed (i.e., every path flows to a logical end)
If process box has more than one output arrow, consider a decision diamond
Get external review done

Step 5: Look for opportunities to improve the process by comparing the actual process to the ideal process, in order reduce non-value-added activities and eliminate,

Unnecessary redundancies including bottlenecks, multiple inspection points for the same quality characteristic, etc.
Delays
Many Movements, for example to a staging area, to storage, to holding area, to production, etc.

Suggestions for eliminating non-value-added activities using flowcharts

* Macro flowcharts lack the level of detail required for optimizing the process.

Rearrange sequence of steps

Change work methods

Redesign forms and documents

Improve supervision

Eliminate unnecessary steps

Rearrange physical location of the operator in the system

Change type of equipment used

Improve operator training

Consolidate process steps

Cause–and–Effect Diagrams

Once flowcharts, or through other team activities, have identified points in the process where the problems might occur, as well as where measurements were currently being taken.

To be able to address this problem,

i. identify the root cause

ii. test potential solutions

Types of Cause–and–Effect Diagrams

There are two common formats used for Cause-and-Effect diagrams,

Dispersion Analysis

Focuses more on structuring the diagram according to the major possible causes for nonconformities such as machines, methods, materials, operators, and environments.

Process Classification

This format focusses on enumerating the steps involved during the production process such as incoming inspection, ripping, sanding, moulding, etc.

Steps involved in creating a cause-and-effect diagram

Problem solving using cause and effect or fishbone diagram with keyboard

Step 1: The problem/nonconformity/effect needs to be clearly stated and understood by everyone. There needs to only be one effect that’s being examined at a time.

Step 2: Select one of the two available formats as your format of choice, either dispersion analysis or process classification.

Step 3: Before brainstorming for the possible causes, based on the format. First, draw a blank cause-and-effect diagram, with only the major categories filled in.

Step 4: The team will now brainstorm potential causes that may fall under each category, defined in the previous step. Though, it’s typically done in a rapid-fire manner without regard for which category each cause falls under. Asking questions about the manufacturing process can lead to a healthier discussion.

Step 5: Once all the various potential causes for the effect being studied have been listed, go over the now filled in cause-and-effect diagram in search for the root cause. This will involve a lot of discussion and a healthy debate amongst the team members. At some point everyone will arrive at a natural conclusion, either by exhausting all possibilities or reaching a consensus.

Want to learn more?

Factory System’s FSWorks is a world-class data acquisition and quality management software

Still not sold?

Try our 30-day trial and witness the transformational ability of FSWorks for yourself

May 11 2022

Must Know SPC Tools

SPC

“A man is only as good as his tools“

But it’s not enough to simply have all the tools at your disposal,

You need to understand what each of the tools does, when to use each one of them, and how to be effective with the tool you’re using.

Treat this as an introduction to the most common and useful SPC tools.

A more comprehensive look at each one is warranted and presented in other articles on this site.

Though not comprehensive, this article should serve as a way to familiarize yourself with several SPC tools, thus providing the reader with a good jumping off point for them to dive deeper into each one, without loosing sight of the bigger picture.

1.

Before we make changes to any process, we must attempt to understand the behavior that process exhibits under “normal” conditions. This understanding can be achieved most effectively by generating Histograms. They will help us understand the distribution of the process output and estimate the limits within which the process operates, under “normal” conditions.

2.

While histograms are essential for understanding the distribution of a process and estimating limits, they’re not suitable for continuous monitoring, evaluation and control over the process. This is where Control Charts come in to play, as the name suggests, control charts help us answer the question, “Is the process in statistical control?”. An “in control” process is stable and predictable, in contrast, an “out of control” process is not predictable, as it’s under significant influence from special cause, or assignable, variability.

3.

Now that we have estimated control limits and ensured that our process is stable, it doesn’t imply that we can meet the specifications of the product being manufactured, as our process may be incapable of meeting the requirements even when running as intended. This leads us to Process Capability Analysis to compare process performance to specifications.

4.

If our process is incapable of meeting specifications, or needs to be improved for any other reason, we encounter the next problem, where do we begin? What would be the best use of our time, energy and resources? Pareto Analysis provides the answer. It combines frequency with which each nonconformity (from the specification) occurs with the relative cost to scrap or rework. It essentially tells you what the “biggest bang for the buck” improvement you can make is.

5.

The Pareto Analysis identifies which nonconformity to target, now we need to identify which step or what characteristic of the raw materials are causing the nonconformity. This process starts with Flowcharts, which are meant to be an accurate representation of the manufacturing process, and Cause-Effect Diagrams, which serve to discover all possible causes for variation, narrowing it down to the root cause.

6.

Flowcharts and Cause-Effect Diagrams are essential tools but they do not provide us with the “true cause” for the variation/instability, the next tool we are going to discuss is going to help you with exactly that. This tool is unlike the others in that it is more of a guided process than a mathematical or visual tool. Design of Experiments (DOE) is step-by-step process that helps you construct, conduct and analyze experiments in order to figure the “true/root cause” for nonconformity.

Conclusion

Start your SPC journey with us…

This was a light introduction to some of the tools commonly used in Statistical Process Control (SPC), meant to pique the reader’s curiosity and give them the confidence to foray into the vast and exciting world of SPC. In doing so I hope it gave the reader a general sense of what each of the tools is used for.

In the series of upcoming articles on our website we will delve deeper into each of these one, while introducing new ideas that complement everything discussed here. At the end of this series we hope to be successful in convince the reader of the utility SPC tools in modern manufacturing and its critical role in Industry 4.0 and beyond.

Want to learn more?

Factory System’s FSWorks is a world-class data acquisition and quality management software

Still not sold?

Try our 30-day trial and witness the transformational ability of FSWorks for yourself

May 9 2022

The Philosophy of SPC

SPC

The

Elevator

Pitch!

Traditional Product-oriented Quality Control programs emphasize defect detection, relying heavily on inspection, scrap, and rework. In other words, it pays workers to make defects and then to correct them.

The goal of SPC is defect prevention, through improving the production system.

How deep does

the rabbit hole go?

Most companies start out using SPC with the objective of ensuring that the production process is stable and capable of producing products to the specification. But this is just touching the surface of what is possible with a robust SPC program, and as these initial objectives are met, the program should shift to improving the system.

The usual course of progression for companies trying to implement SPC programs is,

Monitor variation and take necessary preventative measures before more value is added.
Eventually you understand that variation is unavoidable in manufactured products. Further, a distinction is made between common cause and special/assignable cause variations.
For continued growth, companies start creating control process flow charts and Pareto charts. This gives the company a better insight into their manufacturing process, while also identifying the most significant causes of quality problems.
Once the efficacy of SPC has been established in multiple small result-centered programs, SPC is accepted as the standard way of doing things and becomes an expectation for vendors to implement as well.

I’m in, but

How do I

implement SPC

for a project?

Generally, when starting out with implementing SPC, the following course of action is recommended,

Step 1. Target one project for quality improvement

For the biggest “Bang for the buck”, choose the most frequent and costly quality problem. Usually identified through customer claims and a Pareto analysis.

* Too often companies fall into one of the following two traps when trying to implement SPC,

Making SPC the sole responsibility of the quality department

Without the proper understanding of the theory behind SPC, and due to the lack of evidence specific to their company, management and production personnel are often resistant to any changes suggested, thus making a return to old ways inevitable.
Large-scale, activity-centered programs

Some companies commit whole-heartedly to SPC and start enforcing strict guidelines for the various production processes. This is an activity-centric approach which isn’t driven by the positive results that SPC can help produce. These attempts rarely lead to success, but often flounder and die due to lack of results. Leaving the company cynical of all quality improvement techniques.

Step 2. Determine where the problem is and what is causing it

Use flow charts for the manufacturing process, in order to come to a consensus about the actual steps involved in the process, versus the ideal. Once established, use the flow charts to develop a list of possible causes for the problem and determine the root cause using cause-effect-analysis.

Step 3. Determine the current status of the process

Using common SPC tools such as Histograms, control charts, and process capability analysis, find out the following the characteristics of the process,

Where is the process centered?
What is the spread around the center?
Is the process stable and predictable?
What is the defect rate?

Step 4. Take action to solve the problem

Based on the information gathered in the previous steps and a solid understanding of SPC, determine the specific steps to solve the problem.

These steps might involve,

Re-centering the process
Searching for and eliminating sporadic problems
Minimizing operator overcontrol, by instructing them to make adjustments only when a control chart indicates that adjustments are needed
Looking for ways to reduce the natural variability of the process

Once the project is completed, make sure to write a concise final report. This report should state the problem being addressed and its root cause, the status of the process before the project began (including things like defect rate and production efficiency), the actions taken to address the problem, and the status of the project at the end of the project, and finally, it should include an estimate of the monetary impact to the company. Optionally in order to assist with future projects, also try to document the steps taken and whether a step was helpful or not.

Concluding thoughts
…

Where to go from here?

Familiarity is the key value provided by a robust SPC program. Familiarity not only with your own processes but also the capabilities of your suppliers. It brings Objectivity in place of subjective opinions and estimates. Having numbers to quantify results inspires Confidence and establishes a sound basis to Evaluate the most pressing needs, and the Analyze the cost to address those concerns.

At a more primary level SPC programs often lead to a much Deeper Understanding of the manufacturing process, its present Limitations and the Feasibility of the specification its targeting. Before you even gain any meaningful insights, the process of implementing an SPC program should serve as a deterrent to Reckless Spending in pursuits of solutions that won’t work, in order to solve a problem that may not exist.

When done right, targeting Single Projects at a time, it’s easy to integrate and the results-based approach makes the changes more palatable for management and production personnel. It serves as a Safety Net for everyone involved by ensuring that resources are being used optimally and the highest levels of quality are being achieved. Gradually you find that SPC has a positive impact on every aspect of production, with the decrease in defects, a better sense of the process and Sense of Ownership of the product there is marked boost to Employee Morale.

Want to learn more?

Factory System’s FSWorks is a world-class data acquisition and quality management software

Still not sold?

Try our 30-day trial and witness the transformational ability of FSWorks for yourself

Rishant Dutt

About Rishant Dutt

Posts by Rishant Dutt:

Figuring out where to begin

Start with these …

More on Check Sheets

More on Pareto analysis

Attributes

Control

Charts

Attributes Control Charts

Variables Control Charts

Attributes Control Charts

Variables Control Charts

Types of Attributes Control Charts

Collecting Data

Analyzing Data

Constructing Control Charts

I. Centerline

II. Control Limits

Analyzing Attributes Control Charts

Conclusion

Variables

Control

Charts

What is a control chart, really?

Overview of the statistics involved and key definitions

Creating Control Charts

Creating Control Charts

i. Collecting Data

ii. Construction Control Limits

X-bar chart

R chart

Mathematical Constants

Trend Analysis

Future Steps

Design of

Experiments

in SPC

Traditional approach (w/o DOE and statistics)

Challenges in setting up experiments:

How can

Design of Experiments

(DOE) help?

Steps in Design of Experiments (DOE)

Conclusion

Why implementing SPC can be daunting?

And result in an expensive failure if proper care isn’t taken.

Whattodo?

What to do?

But Why ?

Reason 1: Overcoming Resistance

Reason 2: Best bang-for-buck

Reason 3: Promotes incremental success

Reason 4: Allows for trial-and-error

Reason 5: Helps develop experience

Identifying

Sources of

Defects!

Flowcharts

Cause-and-Effect Diagrams

Flowcharts

Steps involved in creating a flowchart

Suggestions for eliminating non-value-added activities using flowcharts

Cause–and–Effect Diagrams

Types of Cause–and–Effect Diagrams

Dispersion Analysis

Process Classification

Steps involved in creating a cause-and-effect diagram

“A man is only as good as his tools“

1.

2.

3.

4.

5.

6.

Conclusion

The

Elevator

Pitch!

What
to
do?

Concluding thoughts
…