The present invention relates to a dual controller system for analyzing a control signal received from two dual controllers, both of which operate in an active state, to check whether an error occurs in the controllers and to perform operation with a controller in a normal state. A dual controller system according to the present invention includes a plurality of lower-layer modules performing respective functions, and first and second controllers for controlling each of the plurality of lower-layer modules, wherein the first and second controllers transmit control signals to the plurality of lower-layer modules, and the lower-layer modules determine whether an error occurs in the two received control signals, remove an erroneous control signal and perform a function according to a normal control signal.

Disclosed is a redundant hot standby control system including K industrial personal computers, with a plurality of virtual control devices being established thereon respectively, at least one of the plurality of virtual control devices being established on each IPC as a main control device; and the other virtual control devices being standby control devices. Each of the standby control devices corresponds to a virtual control device, which serves as the main control device on another IPC, except for the IPC to which the standby control device itself belongs. A procedure, which is the same as that operated on the main control device corresponding thereto, is operated on the standby control device. A control bus of the system is used for connecting a plurality of the M IPCs; and a field bus is used for connecting the M IPCs and a plurality of field devices.

Disclosed is a redundant hot standby control system including K industrial personal computers, with a plurality of virtual control devices being established thereon respectively, at least one of the plurality of virtual control devices being established on each IPC as a main control device; and the other virtual control devices being standby control devices. Each of the standby control devices corresponds to a virtual control device, which serves as the main control device on another IPC, except for the IPC to which the standby control device itself belongs. A procedure, which is the same as that operated on the main control device corresponding thereto, is operated on the standby control device. A control bus of the system is used for connecting a plurality of the M IPCs; and a field bus is used for connecting the M IPCs and a plurality of field devices.

An apparatus, method, and non-transitory machine-readable medium provide for improved feature extraction and fault detection in a non-stationary process through unsupervised machine learning. The apparatus includes a memory and a processor operably connected to the memory. The processor receives training data regarding a field device in an industrial process control and automation system; extracts a meaningful feature from the training data; performs an unsupervised classification to determine a health index for the meaningful feature; identifies a faulty condition of real-time data using the health index of the meaningful feature; and performs a rectifying operation in the industrial process control and automation system for correcting the faulty condition of the field device.

The present invention relates to a dual controller system for analyzing a control signal received from two dual controllers, both of which operate in an active state, to check whether an error occurs in the controllers and to perform operation with a controller in a normal state. A dual controller system according to the present invention includes a plurality of lower-layer modules performing respective functions, and first and second controllers for controlling each of the plurality of lower-layer modules, wherein the first and second controllers transmit control signals to the plurality of lower-layer modules, and the lower-layer modules determine whether an error occurs in the two received control signals, remove an erroneous control signal and perform a function according to a normal control signal.

An apparatus, method, and non-transitory machine-readable medium provide for improved feature extraction and fault detection in a non-stationary process through unsupervised machine learning. The apparatus includes a memory and a processor operably connected to the memory. The processor receives training data regarding a field device in an industrial process control and automation system; extracts a meaningful feature from the training data; performs an unsupervised classification to determine a health index for the meaningful feature; identifies a faulty condition of real-time data using the health index of the meaningful feature; and performs a rectifying operation in the industrial process control and automation system for correcting the faulty condition of the field device.