The 7 Quality Control (QC) Tools Explained with an Example!

CQE Academy
21 Jul 202116:04

Summary

TLDRIn this video, Andy from CQE Academy discusses the Seven QC Tools essential for quality management and problem-solving. He covers each tool, including flow charts, check sheets, Pareto charts, cause-and-effect diagrams, scatter diagrams, histograms, and control charts. Using a practical example involving toaster defects, Andy demonstrates how to apply these tools to identify and address quality issues, ultimately reducing defects by controlling variables like humidity. The video is valuable for those preparing for Green Belt, Black Belt, or CQE exams, as well as professionals seeking to enhance their quality improvement skills.

Takeaways

  • πŸ› οΈ The video covers the seven QC tools essential for quality improvement and problem-solving.
  • πŸ“ The tools discussed include flow charts, check sheets, Pareto charts, cause and effect diagrams, scatter diagrams, histograms, and control charts.
  • πŸ“ˆ Flow charts visually depict the sequence of a process, promoting a common understanding and simplifying complex processes.
  • πŸ“Š Check sheets are vital for collecting, organizing, and analyzing data, ensuring decisions are based on accurate information.
  • πŸ“‰ Pareto charts help identify the most significant issues by applying the 80/20 rule, focusing on the vital few causes of problems.
  • 🐟 Cause and effect diagrams, also known as fishbone diagrams, are used to identify potential root causes of problems through structured brainstorming.
  • πŸ” Scatter diagrams illustrate relationships between two variables, helping to determine potential correlations without assuming causation.
  • πŸ“… Histograms display the frequency of data over time, helping to understand process variation and distribution patterns.
  • πŸ”¬ Control charts monitor and confirm that processes remain in control by showing data within control limits and detecting any significant changes.
  • πŸ“‰ Practical example: The video uses a toaster defect problem to demonstrate the application of these tools, highlighting how controlling humidity can reduce defects.

Q & A

  • What are the seven QC tools discussed in the video?

    -The seven QC tools are the flow chart, check sheet, Pareto chart, cause and effect diagram, scatter diagram, histogram, and control charts.

  • Why are these seven QC tools important according to the video?

    -These tools are considered incredibly powerful for solving problems and making improvements, with the claim that 95% of quality problems can be solved with these fundamental tools.

  • What is the purpose of a flow chart in the QC tools?

    -A flow chart is a visual tool that helps depict the flow or sequence of a process, making complex processes simple and promoting a common understanding of the process.

  • What is a check sheet and how is it used?

    -A check sheet is a simple tool for collecting, organizing, and analyzing data. It ensures that decisions are based on data and should include metadata such as who, when, and where the data was collected.

  • What is the Pareto principle and how does it relate to the Pareto chart?

    -The Pareto principle, or the 80/20 rule, states that 80% of problems are often due to 20% of causes. A Pareto chart helps identify these 'vital few' causes so that efforts can be focused on the most significant issues.

  • What is a cause and effect diagram and what is its purpose?

    -A cause and effect diagram, also known as a fishbone diagram or Ishikawa diagram, is used to systematically identify potential causes of a problem and understand the relationship between them.

  • How can a scatter diagram be used in QC processes?

    -A scatter diagram plots pairs of data to identify and analyze the relationship between two variables, helping to understand if and how one variable affects another.

  • What does a histogram show and why is it useful?

    -A histogram is a bar chart that graphs the frequency of occurrence of continuous data, showing the distribution and variation within a process, which helps in understanding process behavior and capability.

  • How does a control chart help in maintaining process control?

    -A control chart monitors the stability of a process over time, ensuring that it remains within control limits and only experiences normal variation, confirming the effectiveness of implemented changes.

  • What was the specific example used in the video to demonstrate the use of the seven QC tools?

    -The example used was reducing the number of defects in a toaster manufacturing process, where the tools were applied to identify and control for high humidity during assembly as a root cause of defects.

Outlines

00:00

πŸ“ˆ Introduction to the Seven QC Tools

Andy from CQE Academy introduces the seven quality control (QC) tools, emphasizing their importance in work efficiency, problem-solving, and preparation for exams like the Green Belt, Black Belt, and CQE. The video will cover an overview of the tools, their role in the problem-solving process, and a practical application to reduce defects in toasters. The quote from Kaoru Ishikawa highlights the power of these tools in solving up to 95% of quality problems. The session will also explain the Plan-Do-Check-Act (PDCA) cycle and the Define, Analyze, Improve, Control (DMAIC) methodology.

05:01

πŸ› οΈ Utilizing the Flow Chart and Check Sheet

The first tool discussed is the flow chart, a visual representation of process steps that simplifies complexity and fosters a common understanding. The speaker uses a toaster example to demonstrate creating a flow chart, emphasizing the importance of boundaries and team collaboration. The second tool, the check sheet, is introduced for data collection with a focus on including metadata for data integrity. The team uses the check sheet to identify the most frequent defects during final testing, setting a goal to reduce defects by 25% based on collected data.

10:02

πŸ“Š Analyzing Defects with the Pareto Chart

The Pareto chart is introduced as a tool to apply the 80/20 rule, identifying the most significant issues affecting quality. The video explains the historical background of the Pareto principle and its application in focusing on key defects. Using the check sheet data, the Pareto chart reveals that 'control PCB issues' account for 40% of defects, indicating the primary area to target for improvement. The speaker also discusses the importance of teamwork and structured analysis in identifying root causes.

15:02

πŸ“š Cause and Effect Diagram and Scatter Diagram

The cause and effect diagram, also known as the fishbone diagram or Ishikawa diagram, is detailed as a method for root cause analysis. The process involves a well-defined problem statement and structured thinking across different categories like the 8Ms (Man, Machine, Material, etc.). The video also introduces the scatter diagram for understanding the relationship between two variables, using the example of how humidity affects defect rates. The speaker cautions against assuming causality from correlation alone.

πŸ“ˆ Histogram and Control Chart for Process Analysis

The histogram is explained as a tool for analyzing the pattern of process variation, allowing engineers to understand the behavior of a process and its capability when compared to specification limits. The control chart is introduced as a method to confirm process stability, ensuring that only normal variation is occurring. The video concludes with an example of how controlling humidity reduced defects in the toaster process, demonstrating the effectiveness of the QC tools in achieving the improvement target.

πŸŽ“ Conclusion and Resources for Quality Engineering

The video concludes with a summary of the QC tools' effectiveness in reducing defects by controlling humidity in the toaster example. The speaker invites viewers to engage with the content, offering a free course for those interested in becoming a Certified Quality Engineer (CQE). The course is available at CQE Academy's website and includes practice exams to assist in exam preparation.

Mindmap

Keywords

πŸ’‘Seven QC Tools

The Seven QC (Quality Control) Tools are fundamental instruments used in quality management to analyze and improve processes. They include the flow chart, check sheet, Pareto chart, cause and effect diagram, scatter diagram, histogram, and control charts. These tools are emphasized in the video as essential for solving quality problems and improving processes in various contexts, including preparation for certification exams like the Green Belt, Black Belt, and CQE.

πŸ’‘Flow Chart

A flow chart is a visual tool used to depict the sequence of steps in a process. It helps simplify complex processes and promotes a common understanding among team members. In the video, the flow chart is presented as the first QC tool, used to outline the process of reducing defects in a toaster production scenario, highlighting its importance in the planning phase of problem-solving.

πŸ’‘Check Sheet

A check sheet is a structured form for collecting and analyzing data. It ensures that data is gathered systematically, facilitating accurate decision-making. The video demonstrates the use of a check sheet in the toaster example to collect defect data, emphasizing the need for metadata (like who, when, and where) to maintain data integrity and quality.

πŸ’‘Pareto Chart

A Pareto chart is a bar graph that prioritizes issues based on their frequency or impact, helping to identify the 'vital few' causes that contribute most to a problem. The video uses a Pareto chart to analyze defects in toaster production, illustrating the 80/20 rule where 80% of problems are often due to 20% of the causes, thus guiding where to focus improvement efforts.

πŸ’‘Cause and Effect Diagram

Also known as a fishbone diagram or Ishikawa diagram, this tool helps identify, explore, and display the possible causes of a specific problem. It categorizes potential causes to facilitate thorough analysis. In the video, it's used to examine the root causes of PCB failures in the toaster example, employing the 8Ms (categories like materials, methods, and machines) for a structured approach.

πŸ’‘Scatter Diagram

A scatter diagram plots pairs of numerical data to investigate potential relationships between two variables. It helps in understanding correlations. The video uses a scatter diagram to analyze the relationship between humidity and defects in toaster production, warning viewers not to confuse correlation with causation.

πŸ’‘Histogram

A histogram is a type of bar chart that represents the frequency distribution of continuous data. It helps visualize the pattern of variation in a process. The video demonstrates how a histogram can be used to analyze relative humidity data over time in the toaster example, providing insights into process behavior and variation.

πŸ’‘Control Chart

A control chart monitors process performance over time, distinguishing between common cause variation (normal) and special cause variation (abnormal). It is essential for ensuring a process remains in control after changes are made. In the video, control charts are used to track defect rates in toaster production before and after controlling humidity, showing their role in maintaining improvements.

πŸ’‘Plan-Do-Check-Act (PDCA) Cycle

The PDCA cycle is a continuous loop of planning, doing, checking (studying), and acting, used to achieve continuous improvement in processes. The video mentions PDCA as a framework for applying the QC tools to solve the toaster defect problem, illustrating its iterative nature in process improvement.

πŸ’‘Defects

Defects refer to imperfections or faults in a product or process that reduce its quality. The video uses the example of defects in toaster production to explain how the Seven QC Tools can be applied to identify, analyze, and reduce these defects, thereby improving product quality and process efficiency.

Highlights

Introduction to the seven QC tools: Flow Chart, Check Sheet, Pareto Chart, Cause and Effect Diagram, Scatter Diagram, Histogram, and Control Charts.

Flow Chart: A visual tool that simplifies complex processes and promotes a common understanding.

Quote from Dr. Deming: 'If you can't describe what you're doing as a process, you don't know what you're doing.'

Check Sheet: A powerful tool for collecting, organizing, and analyzing data with an emphasis on including metadata for data integrity.

Pareto Chart: Helps identify the vital few issues that account for most problems, using the 80/20 rule popularized by Joseph Juran.

Cause and Effect Diagram (Fishbone/Ishikawa Diagram): Used to identify potential root causes and contributing factors of a problem.

Scatter Diagram: Illustrates the relationship between two variables, highlighting the importance of distinguishing correlation from causation.

Pearson Correlation Coefficient: Quantifies the relationship between variables, ranging from -1 (perfect negative correlation) to 1 (perfect positive correlation).

Histogram: A bar chart that displays the frequency of occurrence of continuous data, useful for understanding process variation and capability.

Control Chart: Monitors and controls processes to ensure changes are effective over time, distinguishing normal variation from special cause variation.

Application of the seven QC tools in a practical example to reduce defects in a toaster manufacturing process by 25%.

Ishikawa's quote on QC tools: 'As much as 95% of quality problems can be solved with seven fundamental tools.'

Importance of team-based activities in quality improvement processes.

Use of Plan-Do-Check-Act (PDCA) or DMAIC cycle in problem-solving with QC tools.

Encouragement to use brainstorming and cross-functional teamwork to identify potential root causes in the cause and effect diagram.

Transcripts

play00:00

hey guys andy here with cqe academy and

play00:02

in today's video i want to talk about a

play00:04

really important topic

play00:05

which is the seven qc tools now whether

play00:08

you just want to get better at work and

play00:09

use these tools in your everyday job

play00:11

or you're preparing for something like

play00:13

the green belt exam or the black belt

play00:14

exam or the cqe exam

play00:16

today's lecture is for you all right

play00:18

let's head over to the computer get

play00:19

started

play00:20

all right let's go ahead and jump in

play00:22

right into the agenda so we're gonna

play00:23

start with a brief

play00:24

intro of the seven qc tools kind of talk

play00:26

about all of them and how they fit into

play00:28

the

play00:28

problem solving process or the the

play00:30

improvement process and then we're gonna

play00:31

go through each one we're gonna start

play00:32

the flow chart

play00:33

the check sheet the pareto chart the

play00:35

cause and effect diagram

play00:37

scatter diagram histogram and then the

play00:38

control charts and then

play00:40

along the way as we go through this

play00:42

we're actually gonna work a problem

play00:44

using all seven tools and we're gonna

play00:46

reduce the number of defects

play00:48

associated with our toaster all right

play00:49

let's go and get started so the seven qc

play00:51

tools

play00:52

i love this quote from kerou ishikawa

play00:54

who said

play00:55

as much as 95 of quality problems can be

play00:58

solved with seven fundamental tools and

play01:01

i

play01:01

absolutely agree with that i think these

play01:03

tools are probably

play01:04

the seven most powerful tools whether

play01:08

you're talking about

play01:08

green belt or black belt or quality

play01:10

engineering it doesn't matter

play01:12

these seven tools are incredibly

play01:14

powerful for

play01:15

solving problems and making improvements

play01:18

and and this is a really important topic

play01:19

by the way as we go through this i'll

play01:21

make sure to talk about

play01:22

where we're at in something like the

play01:24

plan do check act or the domain cycle

play01:26

we're gonna solve a problem with our

play01:28

toaster and we'll we'll use either the

play01:30

domain or the plan do check out process

play01:32

to do it

play01:33

all right let's get into it all right so

play01:34

the very first tool is the flow chart

play01:37

and what a flowchart does is say it's a

play01:39

visual tool

play01:40

that helps you depict the flow or the

play01:42

sequence of a process

play01:44

this could be things like the flow of

play01:45

information or the flow of tasks or

play01:47

material or people or decisions

play01:49

it doesn't matter the reason that a

play01:51

flowchart is so incredibly valuable is

play01:53

it makes a

play01:54

really complex process simple and

play01:57

it promotes a common understanding of a

play01:59

process anytime you get more than one

play02:01

person in a room to talk about a process

play02:04

there's likely going to be disagreement

play02:05

about how the process works

play02:07

and i love using this analogy often

play02:10

times when when we sit down to

play02:11

analyze a process there's what

play02:13

management thinks is happening

play02:14

there's what the procedure says is

play02:16

happening there's what's actually

play02:18

happening on the production floor

play02:19

and then there's what could be happening

play02:21

and the beauty of a flow chart is it it

play02:23

does just that it gets everyone on the

play02:25

same page

play02:26

about what's actually happening and i

play02:28

love this quote

play02:29

from dr deming who said if you can't

play02:31

describe what you're doing as a process

play02:34

you don't know what you're doing and the

play02:36

best way

play02:37

to describe what you're doing is to use

play02:39

a flowchart

play02:40

and that's why this tool is so powerful

play02:41

if you're in the planning phase of the

play02:43

define phase

play02:44

it's really good to use a flow chart

play02:46

define your process

play02:48

and then use that flow chart to plan out

play02:50

your experiment and plan out how you're

play02:51

going to make an improvement

play02:53

so let's do just that let's say we're

play02:55

talking about our toaster

play02:56

and we want to make an improvement right

play02:59

and so the first thing we're going to do

play03:00

is we're going to start with the

play03:01

boundaries we want to analyze a process

play03:03

but we want to start with our boundaries

play03:04

first

play03:05

so we're going to go from receiving a

play03:06

work order to completing a workload

play03:07

that's the boundaries of our flow chart

play03:09

now i've got the team here because all

play03:11

of these activities all these tools are

play03:13

all team based so imagine you're sitting

play03:14

down with your team

play03:15

and the first thing you're going to do

play03:16

is brainstorm all of the steps in the

play03:19

process right

play03:20

talk to the experts how does the process

play03:22

work use post-it notes right don't try

play03:24

to do this in some software

play03:26

use post-it notes write down all the

play03:27

activities and then once you're done

play03:29

brainstorming

play03:30

organize those thoughts into that

play03:32

logical flow

play03:33

that logical sequence of activities for

play03:35

your process

play03:37

and now that we have our process here

play03:38

we're in that planning phase and we want

play03:40

to create a target right

play03:41

what sort of improvement are we going to

play03:42

make and we want to reduce defects by 25

play03:46

now we can't make an improvement and we

play03:48

can't solve a problem without data

play03:50

and we know that most of our defects

play03:52

happen during final testing

play03:54

so now we need to collect a little bit

play03:55

of data and this is where the check

play03:57

sheet comes into play

play03:58

so the check sheet is a very simple tool

play04:01

for collecting

play04:02

organizing and analyzing data every

play04:05

problem you solve or every improvement

play04:06

you make

play04:07

should be based on data and the check

play04:09

sheet is probably the most powerful tool

play04:11

for collecting data

play04:12

now there's something wrong with the

play04:14

check sheet that i'm showing you here on

play04:15

the screen

play04:16

and that problem is is it doesn't have

play04:17

any metadata

play04:19

if you're collecting data and you want

play04:20

to make a high quality decision

play04:22

using that data you also need metadata

play04:24

so when you're creating your check sheet

play04:26

don't forget to include things like who

play04:28

and when and where

play04:30

all those key elements of data integrity

play04:33

and data accuracy

play04:34

are really important for making high

play04:36

quality decisions

play04:37

okay so we've got the team together and

play04:39

again we did a little bit more

play04:40

brainstorming we said

play04:41

okay at final testing we have eight

play04:43

defects that we want to collect some

play04:44

data on so we create this check sheet

play04:46

we've got our metadata here

play04:47

we hand this off to the team and they

play04:49

come back to us a week later

play04:51

with a bunch of data now this is

play04:53

fantastic we finally have some data

play04:55

that we can analyze and the question is

play04:57

which defect

play04:58

do we focus on i want to improve our

play05:01

target so we originally said

play05:02

we want to reduce defects by 25 percent

play05:05

well now that we have a little bit of

play05:06

data we can actually create a target

play05:08

so we have 145 defects across a whole

play05:10

week that's seven days

play05:12

that means we're averaging about 20 to

play05:14

21 defects

play05:16

per day now if we can reduce that by 25

play05:19

percent

play05:20

we will eliminate five defects per day

play05:23

now we obviously can't focus on all

play05:25

these defects so the real question is

play05:27

how do we know

play05:28

what to focus on and that's where the

play05:30

pareto chart comes into play

play05:32

so the pareto chart is another qc tool

play05:34

that allows you to

play05:36

analyze your data in search of the

play05:38

pareto principle

play05:39

so what it what is the pareto rule what

play05:41

is this 80 20 rule

play05:42

so this this is a a natural phenomenon

play05:45

that was discovered by a guy named

play05:46

vilfredo paredo

play05:48

he's an italian researcher who was

play05:50

studying

play05:51

land ownership and wealth distribution

play05:53

in italy

play05:54

and in europe and what he found is that

play05:56

80 percent of the land

play05:57

was owned by 20 percent of the people

play06:00

and this 80 20 rule in this 80 20

play06:02

phenomenon

play06:03

was also experienced by a guy named

play06:05

joseph duran

play06:06

now he gave credit for the tool to

play06:09

wilfredo praeto but he was the one who

play06:10

popularized this idea

play06:12

of the 80 20 rule and this idea of the

play06:13

pareto chart and what he told us and

play06:15

what he taught us is that

play06:17

a pareto chart helps you separate the

play06:19

vital few

play06:20

from the trivial many now what did joran

play06:22

mean what he means is when you're

play06:24

solving a problem there's often

play06:25

one or two key issues key root causes or

play06:29

key

play06:30

defects that you need to focus on to

play06:31

have a major impact

play06:33

on that particular situation and that's

play06:35

exactly what you see here

play06:36

when we take our data from the check

play06:38

sheet and we put it into this pareto

play06:39

chart

play06:40

we see that control pcb issues accounts

play06:43

for

play06:44

nearly 40 of our defects you can see if

play06:46

we come across here

play06:48

we've got 40 percent of our defects

play06:49

coming directly from control pcb

play06:52

now there's two things happening on this

play06:53

graph obviously there's the blue bars

play06:54

which are simply just the frequency or

play06:56

the count

play06:57

of defects that occurred throughout the

play06:59

week and then this black bar is actually

play07:01

the cumulative

play07:02

line so this first defect accounts for

play07:04

40 percent and then we go up and up and

play07:05

up all the way to 100

play07:07

now that we have this pareto analysis we

play07:09

know that control pcb

play07:11

is our primary issue it tells us what to

play07:13

focus on now we still don't understand

play07:15

why

play07:16

these issues are happening and this is

play07:17

where something like the cause and

play07:19

effect diagram can be incredibly useful

play07:21

so this is the the fish bone diagram or

play07:23

the ishikawa diagram

play07:24

there's all sorts of different names for

play07:26

it but it is a cause and effect diagram

play07:28

and the way this works is we start with

play07:29

the effect

play07:30

that's over here on the right that's the

play07:31

head of the fish here in orange this is

play07:33

our effect

play07:34

and so step one of the cause-and-effect

play07:36

diagram is to start with a really

play07:39

well-written problem statement

play07:40

so i've put in pcb failures but in

play07:42

reality you want to have a

play07:44

much more descriptive problem statement

play07:46

than this and once you have this effect

play07:48

you can start working through the the

play07:50

fish bone process

play07:52

to analyze all of the potential causes

play07:54

and failures

play07:55

now i'm showing here what's called the

play07:57

8ms and this is the beauty of the

play07:59

fishbone process

play08:00

is that it's a well-structured approach

play08:02

to root cause analysis

play08:04

it forces you to think about all of the

play08:06

potential

play08:08

different categories or scenarios or

play08:10

causes that might be contributing to

play08:12

your problem

play08:13

now along with the cause and effect

play08:15

diagram are a number of tools that you

play08:16

should be using

play08:17

so i would recommend you get out your

play08:19

flow chart look at your process

play08:21

use your flow chart and and ask yourself

play08:23

how might each step in the process fail

play08:26

and contribute to the the effect that

play08:28

we're seeing teamwork is also a must

play08:30

here

play08:30

you're not going to be a subject matter

play08:32

expert in all of those eight m's and you

play08:34

need people from operations and

play08:35

engineering and quality and r d

play08:38

and marketing and maintenance to really

play08:40

do a thorough analysis

play08:42

in each of those areas to truly

play08:43

understand the root cause and then of

play08:45

course brainstorming

play08:46

you know you're going to have to

play08:47

creatively think about and talk about

play08:49

and discuss

play08:50

potential root causes that maybe you're

play08:52

not even aware of

play08:53

and then the five-way analysis i love

play08:54

the five wise it really helps you go

play08:56

from a high-level symptom

play08:58

down to the true root cause and really

play09:00

ask why why why

play09:01

to truly get to those those real root

play09:03

causes that you need to address

play09:05

and then as you have that team

play09:06

discussion and you you go through the

play09:07

process

play09:08

you can identify potential root causes

play09:11

and contributing factors

play09:12

to the problem you're trying to solve

play09:14

now obviously again it's we have to go

play09:16

back to that parade of principle we

play09:17

can't focus on everything

play09:18

we have to talk about the most likely

play09:21

root causes and the most likely

play09:23

contributing factors

play09:24

so again at the end of your cause and

play09:25

effect diagram you might identify three

play09:27

or four issues that you need to study

play09:29

further

play09:29

now i wanna i wanna talk about this one

play09:31

high humidity during assembly

play09:33

now as we were working through the cause

play09:34

and effect diagram process the engineer

play09:37

who was helping us

play09:38

looked at our check sheet and noticed an

play09:40

interesting pattern

play09:42

what they noticed here and i've

play09:44

highlighted here in yellow is that

play09:45

sunday monday tuesday we

play09:47

we only had a few defects right six and

play09:49

four and one whereas on wednesday

play09:51

thursday friday you'll notice that our

play09:53

defect rate jumped up a little bit

play09:54

and what the engineer remembered is that

play09:56

we had a rainstorm come through

play09:58

on tuesday night and the humidity level

play10:00

in the facility really jumped up

play10:01

and so what the hypothesis here is that

play10:04

humidity

play10:05

is affecting our defect rate so i've

play10:07

created this little table here to show

play10:09

the days of the week

play10:10

along with the defects and the humidity

play10:13

now to truly understand this

play10:15

relationship

play10:15

we have to create a scatter diagram

play10:19

so here's exactly what that scatter

play10:20

diagram looks like

play10:22

what we do here is we're plotting pairs

play10:24

of data so for example on sunday we had

play10:26

six defects

play10:27

and 18 humidity you can see that right

play10:30

here that's this data point right here

play10:31

we had six defects

play10:32

18 humidity now the way this scatter

play10:35

diagram works

play10:36

or you might hear this called an xy

play10:37

scatter plot is here on the x-axis

play10:40

we put our controllable variable our

play10:42

independent variable

play10:43

and then on the y-axis we put our

play10:45

response variable so here we believe

play10:47

that

play10:47

relative humidity is the the independent

play10:50

variable that is affecting

play10:52

our response variable which is defects

play10:54

and you can see here that there appears

play10:56

to be some relationship

play10:58

between pcb failures and humidity

play11:01

now it's really important when you're

play11:03

looking at the scatter diagram not to

play11:04

assume that this relationship

play11:06

is a causal relationship right there's

play11:08

this really important concept that you

play11:09

can have

play11:10

correlation without causation two

play11:13

parameters or two variables can

play11:14

correlate

play11:15

without having a cause and effect

play11:17

relationship so let's assume though

play11:19

let's assume that we've done a doe here

play11:20

and we've proven

play11:22

that humidity has an effect on our pcb

play11:25

defects

play11:26

we could come back to the scatter

play11:27

diagram we could say okay

play11:29

our target for pcb defects is five or

play11:32

less let's call it let's call it five or

play11:34

less

play11:34

and so we come down here to humidity and

play11:36

say okay we wanna control

play11:38

humidity to around 20

play11:41

to keep our defects low does that make

play11:43

sense and that's a this is a great way a

play11:45

scatter diagram is a great way to

play11:47

understand the relationship

play11:48

between two possible variables now once

play11:50

you've done your scattered diagram

play11:52

you can quantify the relationship

play11:54

between those two variables

play11:55

so what i'm showing here is the pearson

play11:57

correlation coefficient

play11:58

and this coefficient ranges from

play12:00

positive 1 all the way

play12:02

over here on the left to negative 1 all

play12:04

the way over here on the right

play12:05

and that ranges from a perfectly

play12:07

positive correlation here you can see

play12:08

that as x changes y changes

play12:10

identically and then same thing here

play12:12

with r equals minus one this is a

play12:14

perfect negative correlation

play12:16

now as we get closer to zero we start to

play12:18

lose that relationship

play12:19

so an r value of zero means there's no

play12:22

correlation between those two parameters

play12:24

as x changes

play12:26

y basically does whatever it wants

play12:27

there's no relationship between those

play12:29

two variables

play12:30

now the next thing we could do in our

play12:31

analysis is to look at

play12:33

relative humidity over time so let's say

play12:36

we go out

play12:37

we talk to our facilities engineers we

play12:38

say okay give us the relative humidity

play12:40

within our environment

play12:42

you know every six hours for the last

play12:44

six months and we can take that data and

play12:46

we want to plot it because we need to

play12:48

understand

play12:49

how relative humidity is changing within

play12:51

our facility

play12:52

and one of the ways you could analyze

play12:54

that data is with a histogram

play12:56

so a histogram is just a very simple bar

play12:58

chart that graphs the frequency of

play13:00

occurrence

play13:01

of continuous data and again this is a

play13:03

great way to talk about your process

play13:05

every process or every product or every

play13:07

quality attribute out there

play13:09

has some level of random normal

play13:11

variation

play13:12

that will often occur in a pattern and

play13:15

as engineers we need to understand what

play13:17

is the pattern

play13:18

associated with with our outputs or our

play13:20

process and a histogram is a great way

play13:23

to understand the pattern or the

play13:25

variation in your process

play13:27

now you might grab this data and you

play13:28

might get like a skewed distribution or

play13:31

maybe a bimodal distribution

play13:33

or exponential distribution there's all

play13:35

sorts of distributions you might get

play13:37

but it's great to know how your process

play13:39

is behaving

play13:40

now the other beautiful part about a

play13:42

histogram is you can take this data

play13:44

and let's overlay some some

play13:46

specification limits right

play13:48

now what we have is the beginnings of

play13:50

process capability

play13:51

so the histogram is a fantastic tool to

play13:54

quantify and understand how your process

play13:56

behaves

play13:57

and if you compare that against the

play13:58

specification limits we can now start

play14:00

talking about process capability

play14:02

okay so we're on to the very last and

play14:04

final qc tool

play14:05

let's assume we now control for humidity

play14:09

and we want to make sure that that

play14:10

change has been effective over time

play14:12

a control chart is the right tool or the

play14:15

perfect tool to do that

play14:16

so what is a control chart it is

play14:18

essentially a tool that allows you to

play14:20

confirm that your process

play14:22

is in control now when i say in control

play14:24

what i mean is

play14:25

that you're only experiencing normal

play14:27

variation when your process is

play14:29

experiencing normal cause variation

play14:31

your data should fall with within those

play14:34

control limits

play14:35

by the way if you're new to spc i have a

play14:37

whole separate video on control charts

play14:39

you can go check it out

play14:40

i've got both the x bar on our chart as

play14:41

well as attribute data

play14:43

and a control chart is a fantastic tool

play14:45

to use at the end of a project

play14:46

to monitor and control your process and

play14:48

make sure that your changes were

play14:50

effective

play14:50

and let's take a look at what this looks

play14:52

like for our particular process

play14:54

so here's our process right the first

play14:56

week of data you can see we're really

play14:58

all over the place

play14:59

and our control limits are really wide

play15:00

because we're not controlling for

play15:02

humidity

play15:02

and we've got all this data and you can

play15:04

see on average we have about

play15:06

eight defects per day right we're really

play15:08

jumping around here and then let's say

play15:10

on day nine we start controlling for

play15:12

relative humidity

play15:13

and we've got our our control chart

play15:14

we're collecting data and you can see

play15:16

that for the next

play15:17

you know 20 plus days our defect rate

play15:20

has dramatically fallen in fact our new

play15:23

mean defects per day is around three

play15:26

so essentially we've gone from eight

play15:28

defects per day down to three defects

play15:30

per day

play15:31

and we've hit our target of reducing

play15:33

defects by 25 percent

play15:35

we've gone from 20 plus defects a day

play15:38

down to about 15

play15:39

all by controlling relative humidity in

play15:41

our process all right that's it for

play15:43

today

play15:44

i hope you enjoyed it if you did hit

play15:45

that like button also if you're serious

play15:47

about becoming a cqe

play15:49

i've got a free course go check it out

play15:50

it's at cqe academy.com

play15:52

free course where i cover the top 10

play15:54

topics on the cq exam

play15:55

and i also give you a bunch of great

play15:57

free practice exams to help you on that

play15:59

journey

play16:00

all right i hope you enjoyed it thanks

play16:01

so much i'll see you again bye

Rate This
β˜…
β˜…
β˜…
β˜…
β˜…

5.0 / 5 (0 votes)

Related Tags
QC ToolsProblem SolvingQuality ControlSix SigmaGreen BeltBlack BeltEngineeringProcess ImprovementData AnalysisRoot Cause