Apparatus and method for automated identification and diagnosis of constraint violations

An apparatus comprising:

• at least one interface configured to receive 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;
• and
• at least one processor configured to:
• identify 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;
• analyze 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;
• analyze for a second time period, the behavior of the industrial process controller during the each of the one or more identified constraint violations;
• identify 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;
• define 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;
• identify 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;
• calculate a contribution percentage for each of the one or more manipulated variables to each of the 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;
• generate 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;
• generate 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
• modify 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.

A non-transitory computer readable medium containing instructions that when executed cause at least one processing device to:

• obtain 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;
• identify 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;
• analyze 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;
• analyze for a second time period, the behavior of the industrial process controller during the each of the one or more identified constraint violations;
• identify 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;
• define 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;
• identify 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;
• calculate a contribution percentage for each of the one or more manipulated variables to each of the 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;
• generate 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;
• generate 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 the contribution percentage of each of the one or more manipulated variables for each of the one or more identified constraint violations;
• and
• modify 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.