Chapter 9 Quality Assurance Inspection Monitoring in the production process can occur at three points: before production, during

production, and after production. Monitoring before and after production involves acceptance sampling procedures; monitoring during the production process is referred to as process control. To determine whether a process is functioning as intended or to verify that a shipment of raw materials or final products does not contain more than a specified percentage of defectives, it is necessary to physically examine at least some of the items in question. The purpose of inspection is to provide information on the degree to which items conform to a standard. The basic issues are: 1. How much to inspect and how often 2. At what points in the processing inspection should occur 3. Whether to inspect in a centralized or on-site location 4. Whether to inspect attributes or variables How much to Inspect and How often The amount of inspection can range from no inspection whatsoever to inspecting each item numerous times. Low-cost, high volume items such as paperclips often require little inspection because (1) the cost associated with passing defectives is quite low and (2) the processes that produce these items are usually highly reliable, so that defectives are rare. Conversely, high cost, low volume items that have large costs associated with passing defectives often require more inspections. Thus critical components of a manned-flight space vehicle are closely scrutinized because of the risk to human safety and the high cost of mission failure. In high volume systems, automated inspection is one option that may be employed. Where 1. 2. 3. 4. 5. to Inspect in the Process Raw materials and purchased parts. Finished products. Before a costly operation Before an irreversible process Before a covering process

Statistical Process Control Standard process control. Statistical evaluation of the output a process during production. Quality of conformance. A product or service conforms to specifications. Effective control requires the following steps: 1. define 2. Measure 3. Compare to a standard 4. Evaluate 5. Take corrective action if necessary 6. Evaluate corrective action Random variation (common variability). Natural variations in the output of process, created by countless minor factors. Assignable variation (special variation). In process output, a variation whose cause can be identified.

Central limit theorem. Provides the basis for the assumption that the sampling distribution to will be normal or at least approximately normal, even if the population. Type I error. Concluding a process is not in control when it actually it. Type II error. Concluding a process is not in control when it is not. Two statistical tools rare used: 1. Control charts. A time-ordered plot of ample statistics, used to distinguish between random and nonrandom variability. Control limits is the dividing lines between random and nonrandom deviations from the mean of the distribution. Control charts have two limits that separate random variation and nonrandom variation. The larger value is the upper control limits (UCL), and the smaller value is the lower control limit (LCL) There are four different types of control charts. Two are used for variables, and two are used for attributes. Variables are generates data that are measured. Attributes are generates data that are counted. Control charts for variables 1. Mean control chart. Control chart used to monitor the central tendency of a process. 2. Range control chart. Control chart used to monitor process dispersion. Control charts for Attributes 1. p-chart. Control chart for attributes, used to monitor the proportion of defectives in a process. 2. c-chart. Control chart for attributes, used to monitor the number of defects per unit. Tolerances. Specifications for range of acceptable values established by engineering design or customer requirements. Process variability. Natural or inherent variability in a process. Managerial Considerations Concerning Control Charts 1. At what points in the process to use control charts 2. what size samples to take 3. what type of control chart to use. 2. Run test. A test for randomness. Run is a sequence of observations with a certain characteristics. E(r)med = (N/2) + 1 E(r)u/d = (2N - 1) / 3 Where N number of observations Chances variability is measured by the standard deviations of runs. med = (N 1)/4 u/d = (16N 29)/90 computation of z ztest = (observed no. of runs expected no. of runs) / standard deviation of no. of runs for median z = r [(N/2) + 1] / (N 1)/4 up/down tests

z = r [(2N 1 )/3] / (16N 29)/90 Process Capability. The inherent variability of process output relative to the variation allowed by the design specification. Process capability index, CP = specification width / process width OPERATIONS STRATEGY It is neither necessary not desirable to use control charts on every production process. Some processes are highly stable; other processes that previously produced unacceptable output may have been subjected to improvements that resulted in quality being designed into the process or product, making continual monitoring unnecessary. To use a shotgun approach that puts control charts on many processes is wasteful. Managers should use control charts on processes that tend to go out of control and, even then, only on a temporary basis until the causative problems have been permanently corrected. Similarly, when a process is changed significantly or a new process is introduced, it makes sense to monitor the output until it becomes apparent that the process is stable. After that, unless there is some compelling reason to believe that the process is apt to become unstable, there would be no reason to continue with a control chart.