Process Capability Studies are used to determine whether a process is capable of consistently achieving the specifications. This design process has three stages:
- System design, which uses scientific and engineering principles to create a prototype
- Parameter design for products and processes which minimize variation
- Tolerances are used to set parameters to minimize loss
Process Capability Indices show the value of the tolerance specified for the characteristic divided by the process capability. Cpk, Cp, Pp, and Ppk are most commonly used and defined as follows:
- Cp= Process Capability. A simple and straightforward indicator of process capability.
- Cpk= Process Capability Index. Adjustment of Cp for the effect of non-centered distribution.
- Pp= Process Performance. A simple and straightforward indicator of process performance.
- Ppk= Process Performance Index. Adjustment of Pp for the effect of non-centered distribution.
Process Capability Studies are short-term studies conducted to collect information on the performance of new or revised processes related to customer requirements. This occurs when processes, employees, or equipment change and as many possible measurements should be used to get an accurate reflection.
Process capability examines the variability in process characteristics and whether the process is capable of producing products which conform to the required specifications. These are the formulas to calculate process capability:
- Cp = (USL-LSL)/6s
- Cpu = (USL-Xbar)/3s
- Cpl = (Xbar-LSL)/3s
- Cpk = Minimum of (Cpu,Cpl)
A capability analysis is a graphical or statistical analysis tool that visually or mathematically compares actual process performance to a set of performance standards. It is used to assess whether a system is statistically able to specifications or requirements of a process. Capability analysis is most easily calculated using prebuilt calculations and formulas.
Control chart monitoring can display historical record of the behavior of a process, allow for monitoring a process for stability, detecting changes from a previously stable pattern of variation, signaling the need for the adjustment of a process, and helping detect special causes of variation.
Discrete variables are data that cannot be broken down into smaller units. Only a finite number of values are possible. Discrete data has one set of discrete values such as pass or fail or yes or no.
Monitoring and measurement of processes is a continuous process for organizational quality improvement.
Methods for monitoring should demonstrate the ability of processes to achieve planned results.
When the planned results are not achieved, corrective action should be taken. Measurement tools will aid in monitoring techniques. These are tools you can use to measure processes and change:
- Process Maps
- Takt Time
- Data Sampling – Population vs. Sample
- Data Classification
- Data Collection
- SPC-Charts to assess Measurement System Stability
- MSA – Measurement System Analysis
- Statistical Process Control (SPC) Charts
- Root Cause Analysis
- Fishbone Diagram / Cause and Effect Diagram
- Correlation Matrix
- FMEA – Failure Mode Effects and Analysis
- Overall Equipment Effectiveness (OEE)
- Spaghetti Diagram
- Establishing a Baseline Measurement
- DPU – Defects per Unit
- DPO – Defects per Opportunity
- DPMO – Defects per Million Opportunities
- Process Yield Metrics
- FY – Final Yield
- TPY – Throughput Yield
- RTY – Rolled Throughput Yield