Intelligent edge interrogator, server, and control method of integrated facility safety control system including the intelligent edge interrogator and the server

A learning method of an artificial intelligence (AI) model for predicting safety of a facility, the learning method comprising:

• collecting learning sensing data corresponding to an optical signal based on a physical change in a facility by using an intelligent edge interrogator;
• preprocessing, by a preprocessor, the learning sensing data to extract learning short-term sensing data and learning short-term sensing data by using the intelligent edge interrogator;
• learning the learning short-term sensing data to predict short-term safety of the facility by using a short-term safety analysis AI model embedded in the intelligent edge interrogator;
• transmitting, to a server, the learning long-term sensing data and learning short-term diagnosis data obtained by the short-term safety analysis AI model through prediction performed based on the learning short-term sensing data by using the intelligent edge interrogator;
• and
• learning the learning short-term sensing data and learning short-term sensing data to predict long-term safety of the facility by using a long-term safety analysis AI model embedded in the server,
• wherein, when the short-term diagnosis data represents a risk situation to the facility, the preprocessor stops a preprocessing process of extracting the long-term sensing data from the sensing data.

An intelligent edge interrogator comprising:

• a processor and a memory;
• a light receiver configured to receive an optical signal from an optical fiber sensor attached on a facility, based on control by the processor;
• an optical signal measurer configured to measure an optical wavelength of the optical signal to output sensing data representing a physical change in the facility, based on control by the processor;
• a preprocessor loaded into the memory and configured to extract at least one of short-term sensing data and long-term sensing data from the sensing data, based on control by the processor;
• a short-term safety analysis artificial intelligence (AI) model loaded into the memory and configured to analyze the short-term sensing data to output short-term diagnosis data representing short-term safety of the facility, based on control by the processor;
• and
• a communication interface configured to transmit the short-term diagnosis data and the long-term sensing data to a server, based on control by the processor,
• wherein, when the short-term diagnosis data represents a risk situation to the facility, the preprocessor stops a preprocessing process of extracting the long-term sensing data from the sensing data.