US 12,348,024 B2
Arc fault detection through mixed-signal machine learning and neural networks
John Edward Brower, Fairfield, CT (US); Brian S. Chia, Cheshire, CT (US); and Wenjing Chen, Newton, CT (US)
Assigned to Hubbell Incorporated, Shelton, CT (US)
Filed by Hubbell Incorporated, Shelton, CT (US)
Filed on Feb. 7, 2023, as Appl. No. 18/106,854.
Claims priority of provisional application 63/307,392, filed on Feb. 7, 2022.
Prior Publication US 2023/0307900 A1, Sep. 28, 2023
Int. Cl. H02H 1/00 (2006.01); G01R 31/52 (2020.01)
CPC H02H 1/0092 (2013.01) [H02H 1/0015 (2013.01); G01R 31/52 (2020.01)] 22 Claims
OG exemplary drawing
 
1. A circuit interrupting device comprising:
a line terminal;
a wideband current sensor configured to measure a current flowing through the line terminal;
a zero cross detection circuit configured to measure a voltage and a frequency of the line terminal;
a microcontroller including an electronic processor, the microcontroller configured to:
apply a digital filter to a line current measurement signal received from the wideband current sensor;
estimate the spectral density of the filtered line current measurement signal;
calculate an arcing characteristic based on the spectral density;
determine whether an arc fault is present within the circuit interrupting device based on a comparison of the arcing characteristic to one or more thresholds; and
activate an interrupting device when an arc fault is present;
a first printed circuit board configured to support the microcontroller; and
a second printed circuit board configured to support the wideband current sensor and a second microcontroller.