1. This site uses cookies. By continuing to use this site, you are agreeing to our use of cookies. Learn More.
Dismiss Notice
You must be a registered member in order to post messages and view/download attached files in this forum.
Click here to register.

Control limits evaluation / recalculation

Discussion in 'SPC - Statistical Process Control' started by Miguel Aguiar, Nov 14, 2016.

  1. Miguel Aguiar

    Miguel Aguiar New Member

    Nov 14, 2016
    Likes Received:
    Trophy Points:

    I was assigned a task in the company I work for related to evaluate control limits from SPC charts periodically (yearly). The evaluation is to determine if control limits recalculation is required... this is easy for me to do in terms of reviewing a few charts... the problem is that there are around 5000 SPC charts in all the plant so my manager is asking me to define a "valid" criteria to choose some charts and evaluate them. At the end we are looking to have SPC charts with appropriated control limits (decrease SPC alarms the most).

    It is important to say that we are using InfinityQS software to monitor SPC charts.

    Do you have any idea about what to do in this case or have you experienced a similar situation?

    Thank you in advance for your help,
    Miguel A.
  2. Bev D

    Bev D Moderator Staff Member

    Jul 30, 2015
    Likes Received:
    Trophy Points:
    welcome Miguel!
    First I would respond that the goal of SPC is not to reduce the number of alarms, it is to improve the quality (variation) of processes.
    Do you have owners for each of the charts? They should be the ones who set and revise the control chart limits. Are you just auditing this process? Or does your boss want you to be responsible for all of the limits on all of the charts?

    You might consider looking at the charts with the most alarms or those that have been alarming of the longest time.

    Remember that given that the goal of PSC is to improve processes the rule is that in general we don't change the limits to accommodate quality degradation. In other words we don't widen the limits on continuous data charts and we don't increase the limits for defect charts. We sholuld also only improve the limits if we know what changes were put in place to achieve the improved level of performance.