Beruflich Dokumente
Kultur Dokumente
Process Capability
Process Capability is an important concept in SPC. Process capability examines -- the variability in process characteristics -- whether the process is capable of producing products which conforms to specifications
Process Capability
Process capability studies distinguish between conformance to control limits and conformance to specification limits (also called tolerance limits) -- if the process is in control, then virtually all points will remain within control limits -- staying within control limits does not necessarily mean that specification limits are satisfied -- specification limits are usually dictated by customers
The following distributions show different process scenarios. Note the relative positions of the control limits and specification limits.
In control and product meets specifications. Control limits are within specification limits
UCL: Upper Control Limits LCL: Lower Control Limits USL: Upper Specification Limits LSL: Lower Specification Limits
In control but some products do not meet specifications. Specification limits are within control limits
relative capability
The capability index is defined as: Cp = (allowable range)/6 =T (Tolerance)/ 6= (USL - LSL)/6s
The distribution of process quality is often assumed to be approximated with a normal distribution. Px3=99.73%,
Normal Distribution
The normal distribution N(,2) has several distinct properties: --The normal distribution is bell-shaped and is symmetric --The mean, , is located at the centre -- is the standard deviation of the data
f (x)
=0.5 =1 =2
0
f (x)
The smaller the steeper the curve For same changing the value of is to move the curve without any change in its shape
3 Principle
0.9974
The probability for X to fall within (3,+3)is 99.74%, and the probability for falling outside this interval is only 0.26% which is considered almost impossible. That characteristic of normal distribution is called 3 principle. Applying this principle in QM can judge whether there is abnormity appearing in the process, since three standard deviations above and below the process mean represent almost all the fluctuation range of the process.
-3
+3
Sampling to determine if the process is within acceptable limits (Statistical Process Control).
Sampling to accept or reject the immediate lot of product at hand (Acceptance Sampling).
Process Control
Process Control is concerned with monitoring quality while the production or service is being conducted.
UCL
Control charts
Processes that are not in a state of statistical control -- show excessive variations -- exhibit variations that change with time A process in a state of statistical control is said to be statistically stable. Control charts are used to detect whether a process is statistically stable. Control charts differentiates between variations -- that is normally expected of the process due chance or common causes -- that change over time due to assignable or special causes
the nature of the system the way the system is managed the way the process is organized and operated making modifications to the process changing the process
The assumptions of normality and independence enable predictions to be made about the data.
attention
UCL
CL
LCL
Trend
UCL
CL
LCL
If only chance variation is present in the process, the points plotted on a control chart will not typically exhibit any pattern. If the points exhibit some systematic pattern, this is an indication that assignable variation may be present and corrective action should be taken.
55 p = = 0.036 1500
3. Calculate the standard deviation of the sample proportion
sp =
p (1 - p) = n
.036 3(.0188)
UCL UCL
CL