# Quality management: SPC II

## Presentation on theme: "Quality management: SPC II"— Presentation transcript:

Quality management: SPC II
Presented by: Dr. Husam Arman

Histograms do not take into account changes over time.
Control charts can tell us when a process changes

Control Chart Applications
Establish state of statistical control Monitor a process and signal when it goes out of control Determine process capability

Commonly Used Control Charts
Variables data x-bar and R-charts x-bar and s-charts Charts for individuals (x-charts) Attribute data For “defectives” (p-chart, np-chart) For “defects” (c-chart, u-chart)

Control chart functions
Control charts are decision-making tools - they provide an economic basis for deciding whether to alter a process or leave it alone Control charts are problem-solving tools - they provide a basis on which to formulate improvement actions SPC exposes problems; it does not solve them!

Control charts PROCESS
Control charts are powerful aids to understanding the performance of a process over time. Output Input PROCESS What’s causing variability?

Control charts identify variation
Chance causes - “common cause” inherent to the process or random and not controllable if only common cause present, the process is considered stable or “in control” Assignable causes - “special cause” variation due to outside influences if present, the process is “out of control”

Common Causes Special Causes

Separate common and special causes of variation Determine whether a process is in a state of statistical control or out-of-control Estimate the process parameters (mean, variation) and assess the performance of a process or its capability

Control charts to monitor processes
To monitor output, we use a control chart we check things like the mean, range, standard deviation To monitor a process, we typically use two control charts mean (or some other central tendency measure) variation (typically using range or standard deviation)

Control chart components
Centerline shows where the process average is centered or the central tendency of the data Upper control limit (UCL) and Lower control limit (LCL) describes the process spread

Control chart Control charts are practical tools to monitor the evolution of production processes. In any production process a certain amount of natural variability will always exist (this is the cumulative effect of small and unavoidable causes) A process that is operating in the presence of chance causes of variation only is said to be in statistical control.

Control chart A process that is operating in the presence of assignable causes (sources of variability that are not part of the chance causes) is said to be out of control. Three main sources of assignable causes: 1) improperly adjusted or controlled machines (or failures); 2) operator errors; 3) defective raw materials.

Control chart A control chart contains A center line (CL)
An upper control limit (UCL) A lower control limit (LCL) (LCL) (UCL) (CL) Control limits are different from specification limits

(LCL) (UCL) (CL) Basic criterion A point that plots within the control limits indicates that the process is in control → no action is necessary A point that plots outside the control limits is evidence that the process is out of control → Investigation and corrective action are required to find and eliminate assignable cause(s) There is a close connection between control charts and hypothesis testing (to test if the process is in a state of statistical control: we can fail to reject or reject this hypothesis)

… in general we use L=3 → ±3·sw control limits

Three standard deviations
3 3 99.73%

Control chart One of the two main types of control charts is chart for VARIABLES (quality characteristics measured on a numerical scale; e.g. geometrical dimensions, weights, tensile strengths…) - (mean) control charts - R (range) control charts - s2 (sample variance) control charts - s (sample standard deviation) control charts - xi (control charts for individual measurements)

Control chart for variables (Ch 5)
Variables are the measurable characteristics of a product or service. Measurement data is taken and arrayed on charts.

X-bar and R charts The X-bar chart - used to detect changes in the mean between subgroups tests central tendency or location effects The R chart - used to detect changes in variation within subgroups tests dispersion effects

Step 1 Define the problem
Use other quality tools to help determine the general problem that’s occurring and the process that’s suspected of causing it. brainstorm using cause and effect diagram, why-why, Pareto charts, etc.

Step 2 Select a quality characteristic to be measured
Identify a characteristic to study - for example, part length or any other variable affecting performance typically choose characteristics which are creating quality problems possible characteristics include: length, height, viscosity, temperature, velocity, weight, volume, density, etc.

Step 3 Choose a subgroup size to be sampled
Choose homogeneous subgroups Homogeneous subgroups are produced under the same conditions, by the same machine, the same operator, the same mold, at approximately the same time. Try to maximize chance to detect differences between subgroups, while minimizing chance for difference with a group.

Other guidelines The larger the subgroup size, the more sensitive the chart becomes to small variations in the process average. This increases data collection costs. Destructive testing may make large subgroup sizes infeasible. Subgroup sizes smaller than 4 aren’t representative of the distribution averages. Subgroups over 10 should use S chart.

Step 4 Collect the data Run the process untouched to gather initial data for control limits. Generally, collect subgroups (100 total samples) before calculating the control limits. Each time a subgroup of sample size n is taken, an average is calculated for the subgroup and plotted on the control chart.

Step 5 Determine trial centerline for the Xbar chart
The centerline should be the population mean,  Since it is unknown, we use X double bar, or the grand average of the subgroup averages.

1) x11, x12, … , x1n R1 2) x21, x22, … , x2n R2 . m) xm1, xm2, … , xmn Rm

Step 6 Determine trial control limits - Xbar chart
The normal curve displays the distribution of the sample averages. A control chart is a time-dependent pictorial representation of a normal curve. Processes that are considered under control will have 99.73% of their graphed averages fall within six standard deviations.

UCL & LCL calculation

Determining an alternative value for the standard deviation (Xbar chart)

Step 7 Determine trial control limits - R chart
The range chart shows the spread or dispersion of the individual samples within the subgroup. If the product shows a wide spread, then the individuals within the subgroup are not similar to each other. Equal averages can be deceiving. Calculated similar to x-bar charts; Use D3 & D4

R-chart

Determining an alternative value for the standard deviation (R chart)

Example

R-bar chart exceptions
Because range values cannot be negative, a value of 0 is given for the lower control limit of sample sizes of six or less (see D3 value in the previous table).

Step 8 Examine the process - Interpret the charts
A process is considered to be stable and in a state of control, or under control, when the performance of the process falls within the statistically calculated control limits and exhibits only chance, or common causes.

Consequences of misinterpreting the process
Blaming people for problems that they can’t control Spending time and money looking for problems that do not exist Spending time and money on unnecessary process adjustments Taking action where no action is warranted Asking for worker-related improvements when process improvements are needed first

Process variation When a system is subject to only chance causes of variation, 99.73% of the measurements will fall within 3 standard deviations If 1000 subgroups are measured, 997 will fall within the six sigma limits.

Chart zones Based on our knowledge of the normal curve, a control chart exhibits a state of control when: Two thirds of all points are near the center value. A few of the points are on or near the center value The points appear to float back and forth across the centerline. The points are balanced on both sides of the centerline. No points beyond the control limits. No patterns or trends.

Identifying patterns Sudden shift in the process average Cycles Trends

Shift in Process Average

Identifying Potential Shifts

Cycles

Trend

Step 9 Revise the charts In certain cases, control limits are revised because: out-of-control points were included in the calculation of the control limits. The process is in-control but the within subgroup variation significantly improves.

Revising the charts Interpret the original charts Isolate the causes
Take corrective action Revise the chart Only remove points for which you can determine an assignable cause

Step 10 Achieve the purpose
Our goal is to decrease the variation inherent in a process over time. As we improve the process, the spread of the data will continue to decrease. Quality improves!!

Charts for Attributes Fraction nonconforming (p-chart)
Fixed sample size Variable sample size np-chart for number nonconforming Charts for defects c-chart u-chart

Control Chart Selection
Quality Characteristic variable attribute defective defect no n>1? x and MR constant sampling unit? yes constant sample size? yes p or np no n>=10 ? x and R yes no no yes p-chart with variable sample size c u x and s

Control Chart Design Issues
Basis for sampling Sample size Frequency of sampling Location of control limits

SPC Implementation Requirements
Top management commitment Project champion Initial workable project Employee education and training Accurate measurement system