System and method for real-time root cause analysis and correction in power generation processes

1 . A processor implemented method for real-time root cause analysis, comprising:

obtaining, via one or more hardware processors, information pertaining to one or more industrial processes being executed by one or more equipment in an industry plant, wherein the information comprises piping and instrumentation diagram (PID), operational data, maintenance history, root cause knowledge, and a process model, and wherein the root cause knowledge is based on the PID, the operational data, the maintenance history, and the process model, wherein the information represents knowledge of the one or more equipment, a failure mode and the root cause analysis;

receiving, via the one or more hardware processors, a process ontology, and wherein the process ontology comprises information pertaining to one or more of (i) the one or more equipment, (ii) a location of one or more sensors deployed within the one or more equipment, (iii) sensory information captured through the one or more sensors thereof, wherein the one or more sensors measure one or more parameters including a velocity estimated by a velocity sensor, a quality estimated by a quality estimation sensor, a pressure or force estimated by a pressure sensor or a force sensor, a temperature estimated by a temperature sensor, a density estimated by a density sensor, corresponding to performance of the one or more equipment, (iv) information on an interaction between at least one of (a) the one or more equipment and (b) the one or more industrial processes, (v) one or more parameters of the one or more industrial processes, or (vi) one or more action plans, and wherein the one or more action plans comprise one or more of repair, mitigation, containment, or control of at least one of the one or more industrial processes and the one or more equipment,

wherein the process ontology is associated with a power generation industrial process in a thermal power plant and the power generation industrial process includes a sub-process including a coal combustion steam generation, wherein the power generation industrial process has a process parameter including a load and during operation of the thermal power plant, the thermal power plant generates the load through the power generation industrial process and the power generation industrial process starts with coal combustion through the sub-process producing gas as an output, wherein the thermal power plant comprises the one or more equipment including a boiler, a turbine, a generator, wherein the boiler further comprises equipment part including a super heater, a water wall, wherein the water wall further comprises a sub-equipment including a soot blower, and a value of a steam flow rate associated with the soot blower provides an indication of working of the soot blower;

transforming the root cause knowledge to a set of machine instructions, the set of machine instructions comprising an associated detection state of one or more detections identified through a detection model using data captured in real time by one or more sensors within the one or more equipment, wherein the associated detection state is at least one of a positive detection state and a negative detection state, wherein information from the one or more sensors is mapped to the process ontology, and wherein transforming the root cause knowledge to the set of machine instructions comprises deriving a logic in the set of machine instructions from the root cause knowledge by obtaining a pseudo code of the one or more detections along with the associated detection state;

generating, via the one or more hardware processors, a root cause path comprising one or more root causes and associated interdependencies using (i) the process ontology and (ii) the transformed root cause knowledge, and wherein the one or more root causes are detected using the detection model, each root cause being connected to at least one other root cause and each root cause having the one or more detections;

generating, via the one or more hardware processors, a root cause graph using the root cause path, wherein the root cause graph represents the one or more detections, root cause associated with each of the one or more detections, and detection state associated with each of the one or more detections, wherein the one or more root causes are detected using a binary detection based on a unique combination of the one or more detections and the associated detection state, through the detection model, wherein the root cause graph comprises a performance indicator (PI) that is used as a trigger for performing root cause analysis in real-time, wherein a first root cause comprised in the root cause graph is indicative of the performance indicator (PI) corresponding to the one or more industrial processes, wherein one or more root causes are hierarchical arranged after the first root cause in the root cause graph in a plurality of levels, wherein root causes of a level of the plurality of levels are directly affected by deviation in root causes of a previous level of the plurality of levels, wherein the root cause graph is a visual representation of the root cause along with the industrial process and equipment knowledge, wherein the root cause graph is created by combining knowledge from the process ontology and a cause and failure mode graph, and wherein combining the knowledge from the process ontology and the cause and failure mode graph enables i) passing of detections from the process ontology to the root cause uniquely and ii) identification of duplicate knowledge;

executing, via the one or more hardware processors, pseudo codes which are machine readable codes or machine instructions for performing root cause analysis, in real time, after converting the root cause graph into the pseudo codes, wherein the root cause graph enables identification of at least one of a redundant knowledge and a conflicting knowledge of each root cause associated with each of the one or more detections, wherein if a same set of detections and their corresponding detection states are connected with more than one root cause, then a case of the redundant knowledge is identified, and if two different set of detections and their corresponding detection states are connected to a same root cause, then a case of the conflicting knowledge is identified, wherein the root cause analysis is triggered based on the redundant knowledge and the conflicting knowledge of each root cause when one of a failure occurs in a system or a subsystem of the industry plant, and when the system or the subsystem in the industry plant is indicating a possible failure, and wherein a pseudo code of the pseudo codes is a textual representation of unit knowledge of a root cause or a root cause path, wherein the root cause analysis in real-time requires knowledge of the root cause for the industrial process in a computer implementable format and real-time detection of failures as soon as they occur or as the system indicates a tendency towards the failure through information coming from the one or more sensors;

communicating, via the one or more hardware processors, one or more action plans to a controller for rectifying each root cause in the root cause graph based on the root cause analysis; and

executing, by the controller, one or more actions from the one or more action plans comprising one or more of repair, mitigation, containment, or control of at least one of the one or more industrial processes and the one or more equipment for rectifying each root cause in the root cause graph based on the root cause analysis, deviation in the performance indicator (PI), and the arrangement of root causes in the plurality of levels, wherein in response to rectifying the root cause, the deviation in the performance indicator returns back in normal operation range.

2 . The processor implemented method of claim 1 , wherein the process model is at least one of a data-based model, a physics-based model, an empirical model, and a hybrid model.

3 . The processor implemented method of claim 1 , wherein the detection model is at least one of a data-based model, a physics-based model, a pattern identification model, an empirical model, and a hybrid model.

4 . The processor implemented method of claim 1 , wherein the root cause graph is represented in at least one of a tree representation format, a tabular representation format, and a graphical representation format.

5 . A system, comprising:

a memory storing instructions;

one or more communication interfaces; and

one or more hardware processors coupled to the memory via the one or more communication interfaces, wherein the one or more hardware processors are configured by the instructions to:

obtain information pertaining to one or more industrial processes being executed by one or more equipment in an industry plant, wherein the information comprises piping and instrumentation diagram (PID), operational data, maintenance history, root cause knowledge, and a process model, and wherein the root cause knowledge is based on the PID, the operational data, the maintenance history, and the process model, wherein the information represents knowledge of the one or more equipment, a failure mode and the root cause analysis;

receive a process ontology, and wherein the process ontology comprises information pertaining to one or more of (i) the one or more equipment, (ii) a location of one or more sensors deployed within the one or more equipment, (iii) sensory information captured through the one or more sensors thereof, wherein the one or more sensors measure one or more parameters including a velocity estimated by a velocity sensor, a quality estimated by a quality estimation sensor, a pressure or force estimated by a pressure sensor or a force sensor, a temperature estimated by a temperature sensor, a density estimated by a density sensor, corresponding to performance of the one or more equipment, (iv) information on an interaction between at least one of (a) the one or more equipment and (b) the one or more industrial processes, (v) one or more parameters of the one or more industrial processes, or (vi) one or more action plans, and wherein the one or more action plans comprise one or more of repair, mitigation, containment, or control of at least one of the one or more industrial processes and the one or more equipment,

wherein the process ontology is associated with a power generation industrial process in a thermal power plant and the power generation industrial process includes a sub-process including a coal combustion steam generation, wherein the power generation industrial process has a process parameter including a load and during operation of the thermal power plant, the thermal power plant generates the load through the power generation industrial process and the power generation industrial process starts with coal combustion through the sub-process producing gas as an output, wherein the thermal power plant comprises the one or more equipment including a boiler, a turbine, a generator, wherein the boiler further comprises equipment part including a super heater, a water wall, wherein the water wall further comprises a sub-equipment including a soot blower, and a value of a steam flow rate associated with the soot blower provides an indication of working of the soot blower;

transform the root cause knowledge to a set of machine instructions, the set of machine instructions comprising an associated detection state of one or more detections identified through a detection model using data captured in real time by one or more sensors within the one or more equipment, wherein the associated detection state is at least one of a positive detection state and a negative detection state, wherein information from the one or more sensors is mapped to the process ontology, wherein transforming the root cause knowledge to the set of machine instructions comprises deriving a logic in the set of machine instructions from the root cause knowledge by obtaining a pseudo code of the one or more detections along with the associated detection state;

generate a root cause path comprising one or more root causes and associated interdependencies using (i) the process ontology and (ii) the transformed root cause knowledge, and wherein the one or more root causes are detected using the detection model, each root cause being connected to at least one other root cause and each root cause having the one or more detections;

generate a root cause graph using the root cause path, wherein the root cause graph represents the one or more detections, root cause associated with each of the one or more detections, and detection state associated with each of the one or more detections, wherein the one or more root causes are detected using a binary detection based on a unique combination of the one or more detections and the associated detection state, through the detection model, wherein the root cause graph comprises a performance indicator (PI) that is used as a trigger for performing root cause analysis in real-time, wherein a first root cause comprised in the root cause graph is indicative of the performance indicator (PI) corresponding to the one or more industrial processes, wherein one or more root causes are hierarchical arranged after the first root cause in the root cause graph in a plurality of levels, wherein root causes of a level of the plurality of levels are directly affected by deviation in root causes of a previous level of the plurality of levels, wherein the root cause graph is a visual representation of the root cause along with the industrial process and equipment knowledge, wherein the root cause graph is created by combining knowledge from the process ontology and a cause and failure mode graph, and wherein combining the knowledge from the process ontology and the cause and failure mode graph enables i) passing of detections from the process ontology to the root cause uniquely and ii) identification of duplicate knowledge;

execute pseudo codes which are machine readable codes or machine instructions for performing root cause analysis, in real time, after converting the root cause graph into the pseudo codes, wherein the root cause graph enables identification of at least one of a redundant knowledge and a conflicting knowledge of each root cause associated with each of the one or more detections, wherein if a same set of detections and their corresponding detection states are connected with more than one root cause, then a case of the redundant knowledge is identified, and if two different set of detections and their corresponding detection states are connected to a same root cause, then a case of the conflicting knowledge is identified, wherein the root cause analysis is triggered based on the redundant knowledge and the conflicting knowledge of each root cause when one of a failure occurs in a system or a subsystem of the industry plant, and when the system or the subsystem in the industry plant is indicating a possible failure, wherein a pseudo code of the pseudo codes is a textual representation of unit knowledge of a root cause or a root cause path, wherein the root cause analysis in real-time requires knowledge of the root cause for the industrial process in a computer implementable format and real-time detection of failures as soon as they occur or as the system indicates a tendency towards the failure through information coming from the one or more sensors;

communicate, via the one or more hardware processors, one or more action plans to a controller for rectifying each root cause in the root cause graph based on the root cause analysis; and

execute by the controller one or more actions from the one or more action plans comprising one or more of repair, mitigation, containment, or control of at least one of the one or more industrial processes and the one or more equipment for rectifying each root cause in the root cause graph based on the root cause analysis, deviation in the performance indicator (PI), and the arrangement of root causes in the plurality of levels, wherein in response to rectifying the root cause, the deviation in the performance indicator returns back in normal operation range.

6 . The system of claim 5 , wherein the process model is at least one of a data-based model, a physics-based model, an empirical model, and a hybrid model.

7 . The system of claim 5 , wherein the detection model is at least one of a data-based model, a physics-based model, a pattern identification model, an empirical model, and a hybrid model.

8 . The system of claim 5 , wherein the root cause graph is represented in at least one of a tree representation format, a tabular representation format, and a graphical representation format.

9 . One or more non-transitory machine-readable information storage mediums comprising one or more instructions which when executed by one or more hardware processors cause a method for real-time root cause analysis, comprising:

obtaining information pertaining to one or more industrial processes being executed by one or more equipment in an industry plant, wherein the information comprises piping and instrumentation diagram (PID), operational data, maintenance history, root cause knowledge, and a process model, and wherein the root cause knowledge is based on the PID, the operational data, the maintenance history, and the process model, wherein the information represents knowledge of the one or more equipment, a failure mode and the root cause analysis;

receiving a process ontology, and wherein the process ontology comprises information pertaining to one or more of (i) the one or more equipment, (ii) a location of one or more sensors deployed within the one or more equipment, (iii) sensory information captured through the one or more sensors thereof, wherein the one or more sensors measure one or more parameters including a velocity estimated by a velocity sensor, a quality estimated by a quality estimation sensor, a pressure or force estimated by a pressure sensor or a force sensor, a temperature estimated by a temperature sensor, a density estimated by a density sensor, corresponding to performance of the one or more equipment, (iv) information on an interaction between at least one of (a) the one or more equipment and (b) the one or more industrial processes, (v) one or more parameters of the one or more industrial processes, or (vi) one or more action plans, and wherein the one or more action plans comprise one or more of repair, mitigation, containment, or control of at least one of the one or more industrial processes and the one or more equipment,

wherein the process ontology is associated with a power generation industrial process in a thermal power plant and the power generation industrial process includes a sub-process including a coal combustion steam generation, wherein the power generation industrial process has a process parameter including a load and during operation of the thermal power plant, the thermal power plant generates the load through the power generation industrial process and the power generation industrial process starts with coal combustion through the sub-process producing gas as an output, wherein the thermal power plant comprises the one or more equipment including a boiler, a turbine, a generator, wherein the boiler further comprises equipment part including a super heater, a water wall, wherein the water wall further comprises a sub-equipment including a soot blower, and a value of a steam flow rate associated with the soot blower provides an indication of working of the soot blower;

transforming the root cause knowledge to a set of machine instructions, the set of machine instructions comprising an associated detection state of one or more detections identified through a detection model using data captured in real time by one or more sensors within the one or more equipment, wherein the associated detection state is at least one of a positive detection state and a negative detection state, wherein information from the one or more sensors is mapped to the process ontology, and wherein transforming the root cause knowledge to the set of machine instructions comprises deriving a logic in the set of machine instructions from the root cause knowledge by obtaining a pseudo code of the one or more detections along with the associated detection state;

generating a root cause path comprising one or more root causes and associated interdependencies using (i) the process ontology and (ii) the transformed root cause knowledge, and wherein the one or more root causes are detected using the detection model, each root cause being connected to at least one other root cause and each root cause having the one or more detections;

generating a root cause graph using the root cause path, wherein the root cause graph represents the one or more detections, root cause associated with each of the one or more detections, and detection state associated with each of the one or more detections, wherein the one or more root causes are detected using a binary detection based on a unique combination of the one or more detections and the associated detection state, through the detection model, wherein the root cause graph comprises a performance indicator (PI) that is used as a trigger for performing root cause analysis in real-time, wherein a first root cause comprised in the root cause graph is indicative of the performance indicator (PI) corresponding to the one or more industrial processes, wherein one or more root causes are hierarchical arranged after the first root cause in the root cause graph in a plurality of levels, wherein root causes of a level of the plurality of levels are directly affected by deviation in root causes of a previous level of the plurality of levels, wherein the root cause graph is a visual representation of the root cause along with the industrial process and equipment knowledge, wherein the root cause graph is created by combining knowledge from the process ontology and a cause and failure mode graph, and wherein combining the knowledge from the process ontology and the cause and failure mode graph enables i) passing of detections from the process ontology to the root cause uniquely and ii) identification of duplicate knowledge; and

executing pseudo codes which are machine readable codes or machine instructions for performing root cause analysis, in real time, after converting the root cause graph into the pseudo codes, wherein the root cause graph enables identification of at least one of a redundant knowledge and a conflicting knowledge of each root cause associated with each of the one or more detections, wherein if a same set of detections and their corresponding detection states are connected with more than one root cause, then a case of the redundant knowledge is identified, and if two different set of detections and their corresponding detection states are connected to a same root cause, then a case of the conflicting knowledge is identified, wherein the root cause analysis is triggered based on the redundant knowledge and the conflicting knowledge of each root cause when one of a failure occurs in a system or a subsystem of the industry plant, and when the system or the subsystem in the industry plant is indicating a possible failure, wherein a pseudo code of the pseudo codes is a textual representation of unit knowledge of a root cause or a root cause path, wherein the root cause analysis in real-time requires knowledge of the root cause for the industrial process in a computer implementable format and real-time detection of failures as soon as they occur or as the system indicates a tendency towards the failure through information coming from the one or more sensors;

communicating one or more action plans to a controller for rectifying each root cause in the root cause graph based on the root cause analysis; and

executing by the controller one or more actions from the one or more action plans comprising one or more of repair, mitigation, containment, or control of at least one of the one or more industrial processes and the one or more equipment for rectifying each root cause in the root cause graph based on the root cause analysis, deviation in the performance indicator (PI), and the arrangement of root causes in the plurality of levels, wherein in response to rectifying the root cause, the deviation in the performance indicator returns back in normal operation range.

10 . The one or more non-transitory machine-readable information storage mediums of claim 9 , wherein the process model is at least one of a data-based model, a physics-based model, an empirical model, and a hybrid model, and wherein the detection model is at least one of a data-based model, a physics-based model, a pattern identification model, an empirical model, and a hybrid model.