Electronics and Telecommunications Research Institute

Korea Atomic Energy Research Institute

Wan Seon Lim

Cheol Sig Pyo

Young Min Kim

Tae Hwan Kim

Nae Soo Kim

Kwi Hoon Kim

Hyun Jae Kim

Ho Sub Lee

Ji Hoon Bae

Yeon Hee Lee

Se Won Oh

Hyun Joong Kang

Sun Jin Kim

Tae Wan You

Hoo Young Ahn

Doo Byung Yoon

Gwan Joong Kim

Provided is an engine container configured by a workflow engine framework for a cross-domain extension, including a plurality of operators configured to interwork with a plurality of representational state transfer (REST) application programming interfaces (APIs), respectively, a runner configured to sequentially call the plurality of operators according to a request from a client, and a controller configured to control an operation of the plurality of operators and the runner, wherein each operator operates in a pipeline manner to call a corresponding REST API using uniform resource locator (URL) information transferred from the runner and to transfer a processing result obtained by processing data provided through the corresponding called REST API to a next operator.

Workflow engine framework for cross-domain extension

Provided are an apparatus and method for detecting an anomaly in a plant pipe using multiple meta-learning. When a multi-sensor data stream about a plant pipe is received, each of a plurality of meta-learning modules for processing different packet section ranges, extracts one or more preset types of features from sensor data of packet section ranges set according to trend from an arbitrary reception time point, generates 2D image features of the features according to multi-sensor-specific times, generates 3D volume features by accumulating the 2D image features in a depth direction according to multiple sensors, and learns the 3D volume features in parallel through multi-sensor-specific learning modules. Results of the learning of the meta-learning modules are aggregated, and it is determined whether there is an anomaly in a plant pipe according to a learning result selected based on an optimal combination of multiple features, multiple sensors, and multiple packet sections.

Apparatus and method for detecting anomaly in plant pipe using multiple meta-learning

Growing community of inventors

Daejeon, South Korea

Wan Seon Lim