Apparatus and method for identifying impacts and causes of variability or control giveaway on model-based controller performance

Abstract

A method includes obtaining data identifying values of one or more controlled variables associated with an industrial process controller. The method also includes identifying periods when at least one of the one or more controlled variables has been moved to an associated limit by the controller. The method further includes, for each identified period, (i) identifying a standard deviation of predicted values for the associated controlled variable and (ii) determining a control giveaway value for the associated controlled variable based on the standard deviation. The control giveaway value is associated with an offset between the associated controlled variable's average value and the associated limit. In addition, the method includes identifying variances in the one or more controlled variables using the control giveaway values and generating a graphical display identifying one or more impacts or causes for at least some of the variances.

1 . (canceled) 
     
     
         2 . An automated method comprising:
 obtaining data identifying values of a controlled variable associated with an industrial process controller that is controlling at least part of an industrial process;   identifying periods when the controlled variable has been moved by the industrial process controller to an associated limit;   for at least some of the identified periods:
 predicting two or more values of the controlled variable; 
 determining a variability in the two or more predicted values of the controlled variable; 
 determining a variability in the controlled variable based at least in part on the variability in the two or more predicted values; 
   determining when the variability in the controlled variable meets one or more predetermined criteria;   generating an alert when the variability in the controlled variable meets the one or more predetermined criteria; and   outputting the alert for use in making the industrial process controller control the industrial process more optimally.   
     
     
         3 . The automated method of  claim 2 , wherein the one or more predetermined criteria comprises meeting a predetermined threshold. 
     
     
         4 . The automated method of  claim 2 , wherein the one or more predetermined criteria comprises meeting a predetermined change. 
     
     
         5 . The automated method of  claim 2 , further comprising identifying one or more impacts or causes for the generated alert. 
     
     
         6 . The automated method of  claim 5 , further comprising accessing a data historian to generate the one or more impacts or causes for the generated alert comprise. 
     
     
         7 . The automated method of  claim 6 , further comprising using the data historian to learn the one or more impacts or causes for the generated alert. 
     
     
         8 . The automated method of  claim 5 , further comprising outputting the one or more impacts or causes for the generated alert. 
     
     
         9 . An apparatus comprising:
 at least one interface configured to receive data identifying values of a controlled variable associated with an industrial process controller that is controlling at least part of an industrial process; and   at least one processor configured to:
 identify periods when the controlled variable has been moved by the industrial process controller to an associated limit; 
 for at least some of the identified periods:
 generate two or more predicted values for the controlled variable; 
 determine a variance based at least on part on a variability in two or more of the predicted values; 
 
 determine when the variance meets one or more predetermined criteria; 
 generate an alert when the variance meets the one or more predetermined criteria; and 
 output the alert for use in making the industrial process controller control the industrial process more optimally. 
   
     
     
         10 . The apparatus of  claim 9 , wherein the one or more predetermined criteria comprises meeting a predetermined threshold. 
     
     
         11 . The apparatus of  claim 9 , wherein the one or more predetermined criteria comprises meeting a predetermined change. 
     
     
         12 . The apparatus of  claim 9 , wherein the at least one processor is further configured to identify one or more impacts or causes for the generated alert. 
     
     
         13 . The apparatus of  claim 12 , wherein the at least one processor is further configured to access a data historian to generate the one or more impacts or causes for the generated alert comprise. 
     
     
         14 . The apparatus of  claim 13 , wherein the at least one processor is further configured to use the data historian to learn the one or more impacts or causes for the generated alert. 
     
     
         15 . The apparatus of  claim 12 , wherein the at least one processor is further configured to output the one or more impacts or causes for the generated alert. 
     
     
         16 . A non-transitory computer readable medium containing instructions that when executed cause at least one processing device to:
 obtain data identifying values of a controlled variable associated with an industrial process controller that is controlling at least part of an industrial process;   identify periods when the controlled variable has been moved by the industrial process controller to an associated limit;   for at least some of the identified periods:
 generate one or more predicted values for the controlled variable; 
 compare one or more of the predicted values with one or more of the identified values of the controlled variable; 
 determine a variance between the one or more of the predicted values and the one or more identified values of the controlled variable; 
   determine when the variance meets one or more predetermined criteria;   generate an alert when the variance meets the one or more predetermined criteria; and   output the alert for use in making the industrial process controller control the industrial process more optimally.   
     
     
         17 . The non-transitory computer readable medium of  claim 16 , wherein the one or more predetermined criteria comprises meeting a predetermined threshold. 
     
     
         18 . The non-transitory computer readable medium of  claim 16 , wherein the one or more predetermined criteria comprises meeting a predetermined change. 
     
     
         19 . The non-transitory computer readable medium of  claim 16 , further comprising identifying one or more impacts or causes for the generated alert. 
     
     
         20 . The non-transitory computer readable medium of  claim 19 , further comprising accessing a data historian to generate the one or more impacts or causes for the generated alert. 
     
     
         21 . The non-transitory computer readable medium of  claim 19 , further comprising outputting the one or more impacts or causes for the generated alert.