SPC Visual

SPC- Statistical Process Control is a method utilized in manufacturing and process industries to monitor, control, and improve processes by employing statistical techniques. The primary objective of SPC is to ensure that processes operate efficiently and consistently, producing high-quality output while minimizing variation.

SPC apply statistical probability theory to monitor process fluctuations and to keep them under control.
One of the main metrics in SPC is the Process Performance Index (Ppk) or its short term equivalent Process Capability Index (Cpk). Both are powerful statistical measure to assess the performance and capability of a process. They quantifies the process’s ability to meet specifications and provides insights into how well a process can consistently produce results within specified limits.

Ppk/Cpk helps quality professionals and process engineers assess process performance. It ensures products or services meet customer expectations and maintain a competitive edge. The SPC Visual calculates the Ppk/Cpk values according to ISO 22514 norm considering different probability distributions such as normal, weilbull, exponential, beta, logistic, gamma, cauchy, ..etc.

History / Versions:

• 1.0 First version.
  Integrates: Individual chart, Capability chart, Probability chart, Moving range chart, Distribution estimation (according to ISO 22514 norm).
• 1.1 Integration of online/real-time spc capability.
  This feature allows to differentiate between various value categories (product categories) mixed in one measure, enabling process operators to utilize the visual in real-time environment.
• 1.2 Integration of action log.
  This feature enables the visualization of actions within Individuals chart. In addition, distribution model approximation can consider the last action event helping to take into account the effects of actions on the distribution model.
• 1.3 Integration of progression analysis.
  This feature allows to separate data in segments and to analyze how main key performance indicators such as Cpk/Cp develop between the segments. The parameters of the distribution model are adjusted automatically for each segment according to data set belonging to the segment, whereby the distribution model type is retained. Please notice, the segments can be build also based on action events.
• 1.4 Integration of Ppk and Pp values.
  From this version, Ppk and Pp values are integrated in the visual. As the distinction between Ppk and Cpk or between Pp and Cp is based solely on the period under consideration, the differentiation within the visual is made as follows:
  • Ppk/Pk values are calculated based on data set called {Model data}.
    This data is used to estimate the distribution model and can be specified within "SPC Settings/Distribution approximation" settings.
  • Cpk/Cp values are calculated based on data set called {View data}.
    This data is the visible data in the Individuals chart. The period of {View data} sample set can be specified within "General settings/Show n last points" settings.
  Please consider, for the calculation of Cpk/Cp values the distribution model parameters are adjusted according to {View data} data set. That means the type of distribution model (e.g. weibull) is equall for Ppk and Cpk, but the parameters of the distriution model might differentiate according to the corresponding data set (View vs. Model). By default the Cpk/Cp values are equal with Ppk/Pp values, because {View data} option is disabled in default setup. Please adapt it to enable the differentiation.

Comments or questions:

Please don't hesitate to contact us at www.nextgen-industries.com

More insights:

Please check our YouTube channel (www.youtube.com/@NextGenIndustries) and our WebSite (www.nextgen-industries.com) for more details.