US 12,298,722 B2
Apparatus and method for automated identification and diagnosis of constraint violations
Andrew John Trenchard, Romsey (GB); Christopher J. Webb, Scottsdale, AZ (US); Sanjay K. Dave, Bangalore (IN); Michael Niemiec, Dexter, MI (US); Mandar Vartak, Bangalore (IN); and Sriram Hallihole, Bangalore (IN)
Assigned to HONEYWELL INTERNATIONAL INC., Charlotte, NC (US)
Filed by Honeywell International Inc., Morris Plains, NJ (US)
Filed on May 7, 2018, as Appl. No. 15/972,432.
Claims priority of provisional application 62/518,474, filed on Jun. 12, 2017.
Claims priority of provisional application 62/518,397, filed on Jun. 12, 2017.
Claims priority of provisional application 62/518,478, filed on Jun. 12, 2017.
Claims priority of provisional application 62/518,352, filed on Jun. 12, 2017.
Prior Publication US 2018/0356811 A1, Dec. 13, 2018
Int. Cl. G05B 19/4063 (2006.01); G05B 13/04 (2006.01); G05B 19/406 (2006.01); G05B 19/418 (2006.01); G05B 23/02 (2006.01)
CPC G05B 13/041 (2013.01) [G05B 19/406 (2013.01); G05B 19/4063 (2013.01); G05B 19/41875 (2013.01); G05B 19/41885 (2013.01); G05B 23/0272 (2013.01); G05B 2219/23292 (2013.01); G05B 2219/31359 (2013.01); G05B 2219/37001 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
obtaining data identifying values of one or more process variables associated with an industrial process controller, wherein the industrial process controller is configured to control the one or more process variables, wherein the one or more process variables comprises one or more manipulated variables and one or more controlled variables for controlling an industrial process, wherein the one or more controlled variables are controllable at a desired set point or within a predefined range of values and the one or more manipulated variables are adjustable in order to alter the one or more controlled variables;
identifying one or more constraint violations corresponding to the one or more process variables based on the obtained data and a number of consecutive intervals when at least one controlled variable of the one or more controlled variables rises to exceed an upper limit or falls below a lower limit;
analyzing for a first time period prior to each of the one or more identified constraint violations each of: a behavior of the industrial process controller and one or more operator actions;
analyzing for a second time period, the behavior of the industrial process controller during the each of the one or more identified constraint violations;
identifying one or more probable causes of each of the one or more identified constraint violations based on the analysis for the first time period and the second time period;
defining the one or more probable causes based on each of: the behavior of the industrial process controller and the one or more operator actions, wherein the behavior of the industrial process controller is associated with at least one of: a component failure, a state of the industrial process controller, one or more process limitations, one or more process disturbances, and one or more controller actions;
identifying each of the one or more manipulated variables associated with the one or more probable causes for each of the one or more identified constraint violations;
calculating a contribution percentage for each of the one or more manipulated variables to at least one identified constraint violation between the first time period and the second time period, wherein the contribution percentage for each of the one or more manipulated variables is above a specific threshold value;
generating a ranked list of the one or more probable causes of each of the one or more identified constraint violations, wherein the one or more probable causes are ranked in one of increasing order or decreasing order indicating likelihood of each of the one or more probable causes to be an actual cause of the one or more identified constraint violations;
generating a display output configured to display the ranked list of the one or more probable causes for each of the one or more identified constraint violations and the contribution percentage of each of the one or more manipulated variables for each of the one or more identified constraint violations; and
modifying each of the one or more manipulated variables in order to set the one or more controlled variables within predefined limits to resolve each of the one or more identified constraint violations.