DOE Patents title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Failure prediction and estimation of failure parameters

Abstract

Machine-learning methods and apparatus are disclosed to determine frictional state or other parameters in an earthquake zone or other failing medium, using acoustic emission, seismic waves, or other detectable indicators of microscopic processes. Predictions of future failures are demonstrated in different regimes. A classifier is trained using time series of acoustic emission data along with historic data of frictional state or failure events. In disclosed examples, random forests and gradient boost trees are used, and grid-search or EGO procedures are used for hyperparameter tuning. Once trained, the classifier can be applied to testing or live data in order to assess a frictional state, assess seismic hazard, or make predictions regarding a future failure event. The technology has been developed in a double direct shear apparatus, but can be widely applied to seismic faults, other terrestrial failures, or failures in man-made structures. Variations are disclosed.

Inventors:
; ;
Issue Date:
Research Org.:
Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)
Sponsoring Org.:
USDOE National Nuclear Security Administration (NNSA)
OSTI Identifier:
1860051
Patent Number(s):
11169288
Application Number:
16/212,448
Assignee:
Triad National Security, LLC (Los Alamos, NM)
Patent Classifications (CPCs):
G - PHYSICS G01 - MEASURING G01V - GEOPHYSICS
G - PHYSICS G06 - COMPUTING G06N - COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
DOE Contract Number:  
89233218CNA000001
Resource Type:
Patent
Resource Relation:
Patent File Date: 12/06/2018
Country of Publication:
United States
Language:
English

Citation Formats

Johnson, Paul Allan, Hulbert, Claudia L., and Rouet-Leduc, Bertrand. Failure prediction and estimation of failure parameters. United States: N. p., 2021. Web.
Johnson, Paul Allan, Hulbert, Claudia L., & Rouet-Leduc, Bertrand. Failure prediction and estimation of failure parameters. United States.
Johnson, Paul Allan, Hulbert, Claudia L., and Rouet-Leduc, Bertrand. Tue . "Failure prediction and estimation of failure parameters". United States. https://www.osti.gov/servlets/purl/1860051.
@article{osti_1860051,
title = {Failure prediction and estimation of failure parameters},
author = {Johnson, Paul Allan and Hulbert, Claudia L. and Rouet-Leduc, Bertrand},
abstractNote = {Machine-learning methods and apparatus are disclosed to determine frictional state or other parameters in an earthquake zone or other failing medium, using acoustic emission, seismic waves, or other detectable indicators of microscopic processes. Predictions of future failures are demonstrated in different regimes. A classifier is trained using time series of acoustic emission data along with historic data of frictional state or failure events. In disclosed examples, random forests and gradient boost trees are used, and grid-search or EGO procedures are used for hyperparameter tuning. Once trained, the classifier can be applied to testing or live data in order to assess a frictional state, assess seismic hazard, or make predictions regarding a future failure event. The technology has been developed in a double direct shear apparatus, but can be widely applied to seismic faults, other terrestrial failures, or failures in man-made structures. Variations are disclosed.},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = {2021},
month = {11}
}

Works referenced in this record:

State of stress in Texas: Implications for induced seismicity: STATE OF STRESS IN TEXAS
journal, October 2016


Tidal triggering of earthquakes suggests poroelastic behavior on the San Andreas Fault
journal, February 2017


Change of stress regime during geothermal reservoir stimulation
journal, February 2014


Identifying Fault Conditions in Combinations of Components
patent-application, March 2016


Road pavement deterioration inspection system
patent, September 2003


Fault mechanisms of induced seismicity at the superdeep German Continental Deep Drilling Program (KTB) borehole and their relation to fault structure and stress field
journal, February 2004


Potential slab deformation and plunge prior to the Tohoku, Iquique and Maule earthquakes
journal, April 2016


Sensitivity of stress inversion of focal mechanisms to pore pressure changes: Stress Inversion and Pore Pressure
journal, August 2016


A probabilistic neural network for earthquake magnitude prediction
journal, September 2009


Seismic activity prediction using computational intelligence techniques in northern Pakistan
journal, September 2017


Similarity of fast and slow earthquakes illuminated by machine learning
journal, December 2018


Continuous chatter of the Cascadia subduction zone revealed by machine learning
journal, December 2018


In Situ Stress and Active Faulting in Oklahoma
journal, December 2016


Earthquake prediction: 20 years of global experiment
journal, April 2012


Machine Learning Predicts Laboratory Earthquakes: MACHINE LEARNING PREDICTS LAB QUAKES
journal, September 2017


How will induced seismicity in Oklahoma respond to decreased saltwater injection rates?
journal, November 2016


Earthquake prediction in California using regression algorithms and cloud-based big data infrastructure
journal, June 2018


Estimating Fault Friction From Seismic Signals in the Laboratory
journal, February 2018


Stress tensor changes related to fluid injection at The Geysers geothermal field, California: STRESS TENSOR CHANGES AT THE GEYSERS
journal, June 2013