Method and a system for an automatic recovery from a fault situation in a production plant
View Patent ↗A method automatically recovers from a fault situation in a production plant and provides production resources and a manufacturing execution system having a production modeler for modeling the production resources into a plant model and a production scheduler to schedule operations of the modeled production resources. A production controller executes the production process and a fault manager detects fault situations and automatically decides a corrective action. A production resource runs an application for the operation of the production resource and a fault analysis agent provides categorized error situations and checks operational data representing the operation of the production resource against the categorized error situations and when, an error situation occurs, forwards an error event to the fault manager. The error events are collected and then analyzed by a neural network system to assign the error event to an error category. A corrective action is executed on the production resource.
1. A method for automatic recovery from a fault situation in a production plant, which comprises the steps of:
providing a number of production resources being machines for operating manufacturing processes;
providing a manufacturing execution system containing at an engineering level a production modeler modeling available production resources into a plant model and a production scheduler scheduling operations of modeled production resources according to a number of production orders, the manufacturing execution system further containing at an execution level a production controller to execute a production process according to a production schedule and a fault manager for detecting fault situations and automatically decide a corrective action in response to at least one fault situation;
running on a computer, for at least one of the production resources, an application for the operation of the production resource and a fault analysis agent that initially provides at the engineering level a number of categorized error situations to the fault manager and checks at the execution level operational data representing the operation of the production resource against the categorized error situations and when, an error situation is present, forwards an error event to the fault manager;
collecting error events by the fault manager and analyzing the error events by a neural network system for assigning the error event to an error category;
according to an assignment of the error category, deciding by the fault manager on a corrective action determined for the error category and forwarding the corrective action to a fault analysis agent for getting the corrective action executed on the production resource and its application respectively for continuing an uninterrupted production process;
analyzing production process data for predicting future error situations thus predicting a future error situation before the future error situation becomes an actual error situation and a future corrective action is determined based on the categorized error situations stored in the fault manager; and
executing, automatically, the corrective action on the application of the production resource by the fault analysis agent.
2. A system for automatic recovery from a fault situation in a production plant, the system comprising:
a number of production resources being machines for operating manufacturing processes;
a manufacturing execution system containing at an engineering level a production modeler modeling available production resources into a plant model and a production scheduler scheduling operations of modeled production resources according to a number of production orders, said manufacturing execution system having at an execution level a production controller to execute a production process according to a production schedule and a fault manager for detecting fault situations and automatically deciding for a corrective action in response to at least one fault situation;
a number of computing devices for running for at least one of said production resources an application for an operation of said production resource and a fault analysis agent that initially provides at the engineering level a number of categorized error situations to said fault manager and checks at the execution level for operational data representing the operation of the production resource against categorized error situations and when, an error situation is present, forwards an error event to said fault manager;
said fault manager collecting error events and analyzing the error events by a neural network system for assigning the error event to an error category;
said fault manager deciding on a corrective action determined for the error category in accordance with an assignment of the error category and forwarding the corrective action to a fault analysis agent for getting the corrective action executed on the production resource and its application respectively for continuing an uninterrupted production process;
said fault manager analyzing production process data for predicting future error situations thus predicting a future error situation before the future error situation becomes an actual error situation and a future corrective action is determined based on the categorized error situations stored in the fault manager; and
the fault analysis agent automatically executes the corrective action on the application of the production resource.