US 11,856,344 B2
Self-powered sensor, and monitoring system including same
Johannes Jozef Franciscus Rijns, Weert (NL); Sangjoon Nam, Seoul (KR); and Charles Kiseok Song, Seoul (KR)
Assigned to GENTLE ENERGY CORP., Seoul (KR)
Filed by GENTLE ENERGY CORP., Seoul (KR)
Filed on Mar. 10, 2022, as Appl. No. 17/691,925.
Application 17/691,925 is a continuation of application No. PCT/KR2020/013042, filed on Sep. 25, 2020.
Claims priority of application No. 10-2019-0119526 (KR), filed on Sep. 27, 2019; and application No. 10-2020-0124404 (KR), filed on Sep. 25, 2020.
Prior Publication US 2022/0201375 A1, Jun. 23, 2022
Int. Cl. H04Q 9/00 (2006.01); G08B 21/08 (2006.01); H02N 2/18 (2006.01); G06F 18/24 (2023.01); G08B 21/18 (2006.01)
CPC H04Q 9/00 (2013.01) [G06F 18/24 (2023.01); G08B 21/182 (2013.01); H02N 2/181 (2013.01); H02N 2/186 (2013.01); H04Q 2209/88 (2013.01)] 3 Claims
OG exemplary drawing
 
1. A monitoring system comprising:
a self-powered sensor mounted on a monitoring target device to generate and transmit a sensing signal corresponding to physical energy generated by the monitoring target device; and
a monitoring device configured to collect the sensing signal transmitted by the self-powered sensor and monitoring a status of the monitoring target device,
wherein the monitoring device comprises:
a first generator configured to generate monitoring sensing data as time series data combining the sensing signal and a signal receiving period indicating how frequently the sensing signal is received at the monitoring device;
a classification unit configured to classify status information of the monitoring target device corresponding to the monitoring sensing data by using an unsupervised learning-based deep learning model trained in advance to classify the status information of the monitoring target device when monitoring sensing data is input; and
a determination unit configured to determine an abnormal state of the monitoring target device using a deep neural network model trained in advance to determine the abnormal state of the monitoring target device using the status information of the monitoring target device,
wherein the deep neural network model is a neural network model trained in advance using training data comprising whether the monitoring target device is in an idle state, whether the monitoring target device is in operation, a type of product produced by the monitoring target device, and a daily output of the product.