Disclosed are embodiments for automatically resolving faults in a complex network system. Some embodiments monitor one or more of system operational parameter values and message exchanges between network components. A machine learning model detects a fault in the complex network system, and an action is selected based on a cause of the fault. After the action is applied to the complex network system, additional monitoring is performed to either determine the fault has been resolved or additional actions are to be applied to further resolve the fault.

Disclosed are embodiments for automatically resolving faults in a complex network system. Some embodiments monitor one or more of system operational parameter values and message exchanges between network components. A machine learning model detects a fault in the complex network system, and an action is selected based on a cause of the fault. After the action is applied to the complex network system, additional monitoring is performed to either determine the fault has been resolved or additional actions are to be applied to further resolve the fault.

Disclosed are embodiments for automatically resolving faults in a complex network system. Some embodiments monitor one or more of system operational parameter values and message exchanges between network components. A machine learning model detects a fault in the complex network system, and an action is selected based on a cause of the fault. After the action is applied to the complex network system, additional monitoring is performed to either determine the fault has been resolved or additional actions are to be applied to further resolve the fault.

A field device includes a controller and a process communication module. The controller is configured to perform at least one operation related to process control and is also configured to perform at least one self-recovery operation relative to the field device. The process communication module is coupled to the controller and is configured to couple to a process communication segment and communicate in accordance with a process communication protocol. The controller is configured to detect an erroneous condition and selectively apply the at least one self-recovery operation in response to the detected erroneous condition.

Disclosed are embodiments for automatically resolving faults in a complex network system. Some embodiments monitor one or more of system operational parameter values and message exchanges between network components. A machine learning model detects a fault in the complex network system, and an action is selected based on a cause of the fault. After the action is applied to the complex network system, additional monitoring is performed to either determine the fault has been resolved or additional actions are to be applied to further resolve the fault.

According to one embodiment, a system includes control apparatus and server. Control apparatus includes collector, transmitter, receiver and main controller. Collector collects sensing data concerning control targets in social infrastructure. Transmitter transmits collected sensing data to server. Receiver receives control instruction from server. Main controller controls control targets based on control instruction. Server includes acquisition unit, database, generator and instructor. Acquisition unit acquires sensing data from control apparatus. Database stores sensing data. Generator generates control instruction by processing sensing data. Instructor transmits generated control instruction to control apparatus.

Disclosed are embodiments for automatically resolving faults in a complex network system. Some embodiments monitor one or more of system operational parameter values and message exchanges between network components. A machine learning model detects a fault in the complex network system, and an action is selected based on a cause of the fault. After the action is applied to the complex network system, additional monitoring is performed to either determine the fault has been resolved or additional actions are to be applied to further resolve the fault.

A numerical control device including a programmed machining restart function includes a first display unit for displaying, as a list, specific codes indicating limit points of machining steps of a machining program, a specification unit for specifying, among the specific codes displayed as a list by the first display unit, a specific code that is selected, and a program restart unit for executing, by using a location in a memory of the specific code that is specified by the specification unit, a restart operation of the machining program from a machining step including the specific code that is specified.

According to one embodiment, a system includes control apparatus and server. Control apparatus includes collector, transmitter, receiver and main controller. Collector collects sensing data concerning control targets in social infrastructure. Transmitter transmits collected sensing data to server. Receiver receives control instruction from server. Main controller controls control targets based on control instruction. Server includes acquisition unit, database, generator and instructor. Acquisition unit acquires sensing data from control apparatus. Database stores sensing data. Generator generates control instruction by processing sensing data. Instructor transmits generated control instruction to control apparatus.

A field device includes a controller and a process communication module. The controller is configured to perform at least one operation related to process control and is also configured to perform at least one self-recovery operation relative to the field device. The process communication module is coupled to the controller and is configured to couple to a process communication segment and communicate in accordance with a process communication protocol. The controller is configured to detect an erroneous condition and selectively apply the at least one self-recovery operation in response to the detected erroneous condition.