Kaoru Ishikawa
- Developed the seven basic visual tools of quality so that the average person could analyze and interpret data
- “95% of a company’s problems can be solved using these 7 tools”
7 quality tools
- ishikawa diagram
- check sheet
- control chart
- histogram
- pareto chart
- scatter diagram
- flow chart
ishikawa diagram
- Fishbone diagram, cause-and-effect diagram
- Sometimes referred to as a 4M analysis (man, machinery, material, method)
- Identifies many possible causes for an effect or problem and sorts ideas into useful categories
check sheet
a structured, prepared form for collecting and analyzing data; a generic tool that can be adapted for a wide variety of purposes
control chart
- graphs used to study how a process changes over time
- monitors your chosen process and alerts you when there exists an “out of control” condition
histogram
- the most commonly used graph for showing frequency distributions, or how often each different value in a set of data occurs
- provide easiest way to evaluate distribution of data
- no gaps (shows # ranges)
- suggest the nature and possible improvements for physical mechanisms at work in progress
pareto chart
- shows on a bar graph which factors are more significant
- used to identify and prioritize problems to be solved
- actually histograms aided by the 80/20 rule
- helps an organization know how to utilize resources
scatter diagram
- graphs pairs of numerical data, one variable on each axis, to look for a relationship
- these relationships can be used to recognize indicator variables in organizations
flow chart
- aka stratification
- a flow chart is a visual representation of a process. seeing it visually makes identifying both inefficient and potential improvements easier
- a technique that separates data gathered from a variety of sources so that patterns can be seen
Fishbone diagram process
- define problem : be specific
- choose categories
- brainstorm possible causes
- 5 why analysis - really want to find root causes
- investigate - now that youve come up with possible causes, it’s time to gather data to confirm which causes are real or not
an “out of control” condition in a control chart
this means that the process has changed from “normal” as defined by the process itself
UCL and LCL for control charts
calculated as 3 standard deviation from the mean with the standard deviation being determined by the current process
an “in control” process can be..
can be producing defective product due to the fact that the spec limits which define requirements are independent and unrelated to the actual process capability
Nelsons 8 rules for control charts
- one point is more than 3 stdv from mean
- 9 or more points in a row are on same side as mean
- 6 or more points in a row are continually increasing or decreasing
- 14 or more points in a row alternate direction
- 2 or 3 out of 3 points in a row are more than 2 stdv from mean in same direction
- 4 or 5 out of 5 points in a row are more than 1 stdv from mean in same direction
- 15 points in a row are all within 1 stdv of the mean on either side
- 8 points in a row exist within 1 stdv of the mean and the points are in both directions of mean
constructing a pareto chart
- first, information must be selected based on types of classifications of defects that occur as a result of process
- data must be collected and classified into categories
- then a histogram or frequency chart is constructed showing # of occurences
constructing a scatter diagram
- collect 2 pieces of data and create summary table of data
- draw a diagram labeling the horizontal and vertical axes - Cause variable labeled on X axis (independent) and Effect labeled on Y axis (dependent)
- plot the data pairs on the diagram
- interpret the scatter diagram for direction and strength
