Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Fault Types01:18

Fault Types

86
When analyzing a single line-to-ground fault from phase A to ground at a three-phase bus, it is important to consider the fault impedance. This impedance is zero for a bolted fault, equal to the arc impedance for an arcing fault, and represents the total fault impedance for a transmission-line insulator flashover. To derive sequence and phase currents, fault conditions are translated from the phase domain to the sequence domain.
For line-to-line faults occurring between phases B and C, the...
86
Random Error01:04

Random Error

882
Random or indeterminate errors originate from various uncontrollable variables, such as variations in environmental conditions, instrument imperfections, or the inherent variability of the phenomena being measured. Usually, these errors cannot be predicted, estimated, or characterized because their direction and magnitude often vary in magnitude and direction even during consecutive measurements. As a result, they are difficult to eliminate. However, the aggregate effect of these errors can be...
882
Detection of Gross Error: The Q Test01:00

Detection of Gross Error: The Q Test

6.1K
When one or more data points appear far from the rest of the data, there is a need to determine whether they are outliers and whether they should be eliminated from the data set to ensure an accurate representation of the measured value. In many cases, outliers arise from gross errors (or human errors) and do not accurately reflect the underlying phenomenon. In some cases, however, these apparent outliers reflect true phenomenological differences. In these cases, we can use statistical methods...
6.1K
Expected Frequencies in Goodness-of-Fit Tests01:19

Expected Frequencies in Goodness-of-Fit Tests

2.5K
A goodness-of-fit test is conducted to determine whether the observed frequency values are statistically similar to the frequencies expected for the dataset. Suppose the expected frequencies for a dataset are equal such as when predicting the frequency of any number appearing when casting a die. In that case, the expected frequency is the ratio of the total number of observations (n)  to the number of categories (k).
2.5K
Quantifying and Rejecting Outliers: The Grubbs Test01:02

Quantifying and Rejecting Outliers: The Grubbs Test

1.6K
Sometimes, a data set can have a recorded numerical observation that greatly  deviates from the rest of the data. Assuming that the data is normally distributed, a statistical method called the Grubbs test can be used to determine whether the observation is truly an outlier.  To perform a two-tailed Grubbs test, first, calculate the absolute difference between the outlier and the mean. Then, calculate the ratio between this difference and the standard deviation of the sample. This...
1.6K
Classification of Signals01:30

Classification of Signals

456
In signal processing, signals are classified based on various characteristics: continuous-time versus discrete-time, periodic versus aperiodic, analog versus digital, and causal versus noncausal. Each category highlights distinct properties crucial for understanding and manipulating signals.
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
456

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Relationship Between Cerebral Oximetry and Outcomes in Post-Cardiac Arrest Patients: A Systematic Review and Meta-Analysis.

Critical care explorations·2026
Same author

A multi-method study on GPs' perspectives on Lipoprotein(a) as an actionable cardiovascular risk factor.

Frontiers in medicine·2026
Same author

Dairy byproducts as sustainable alternatives to FCS in 2D and 3D skeletal muscle cell cultures.

Bioresources and bioprocessing·2025
Same author

A Multimodal Deep Learning Ensemble Framework for Building a Spine Surgery Triage System.

Studies in health technology and informatics·2025
Same author

Effects of Betulinic Acid and Ursolic Acid on IL-17-Induced CCL20 Release in Normal Human Epidermal Keratinocytes.

Life (Basel, Switzerland)·2025
Same author

Metabolomic in severe traumatic brain injury: exploring primary, secondary injuries, diagnosis, and severity.

Critical care (London, England)·2025

Related Experiment Video

Updated: Jun 29, 2025

Basics of Multivariate Analysis in Neuroimaging Data
06:35

Basics of Multivariate Analysis in Neuroimaging Data

Published on: July 24, 2010

16.9K

General value functions for fault detection in multivariate time series data.

Andy Wong1, Mehran Taghian Jazi1, Tomoharu Takeuchi2

  • 1Computing Science Department, Alberta Machine Intelligence Institute, University of Alberta, Edmonton, AB, Canada.

Frontiers in Robotics and AI
|March 28, 2024
PubMed
Summary

This study introduces a new machine fault detection method using temporal-difference learning and General Value Functions (GVFs). The GVF outlier detection (GVFOD) algorithm offers more precise detection of abnormal machine behavior for better maintenance planning.

Keywords:
fault detectiongeneral value functionsoutlier detectionreinforcement learningtemporal difference (TD) learning

More Related Videos

Design and Application of a Fault Detection Method Based on Adaptive Filters and Rotational Speed Estimation for an Electro-Hydrostatic Actuator
06:45

Design and Application of a Fault Detection Method Based on Adaptive Filters and Rotational Speed Estimation for an Electro-Hydrostatic Actuator

Published on: October 28, 2022

1.6K
Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

10.7K

Related Experiment Videos

Last Updated: Jun 29, 2025

Basics of Multivariate Analysis in Neuroimaging Data
06:35

Basics of Multivariate Analysis in Neuroimaging Data

Published on: July 24, 2010

16.9K
Design and Application of a Fault Detection Method Based on Adaptive Filters and Rotational Speed Estimation for an Electro-Hydrostatic Actuator
06:45

Design and Application of a Fault Detection Method Based on Adaptive Filters and Rotational Speed Estimation for an Electro-Hydrostatic Actuator

Published on: October 28, 2022

1.6K
Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

10.7K

Area of Science:

  • Industrial Automation
  • Machine Learning
  • Predictive Maintenance

Background:

  • Equipment malfunction is a major challenge in automated production, leading to downtime.
  • Traditional condition-based maintenance (CBM) is costly; machine learning offers a data-driven alternative using existing sensors.
  • Existing data-driven CBM often requires costly labeled fault data for supervised learning.

Purpose of the Study:

  • To develop a novel machine fault detection method that identifies abnormal behavior instead of classifying specific faults.
  • To leverage temporal-difference learning and General Value Functions (GVFs) for anomaly detection in industrial settings.
  • To improve the reliability and efficiency of predictive maintenance through accurate fault detection.

Main Methods:

  • Utilized General Value Functions (GVFs) to create a predictive model of sensor data for detecting operational anomalies.
  • Employed temporal-difference learning, suitable for non-i.i.d. (Markovian) sensor data from industrial equipment.
  • Developed the GVF outlier detection (GVFOD) algorithm and compared it against established multivariate and temporal outlier detection methods.

Main Results:

  • The GVFOD algorithm achieved comparable recall to existing multivariate outlier detection methods.
  • GVFOD demonstrated significantly higher precision in detecting abnormal machine behavior compared to other algorithms.
  • The algorithm features intuitive hyperparameters, allowing for integration of expert knowledge.

Conclusions:

  • The GVFOD method provides a more reliable approach to detecting abnormal machine behavior, enabling optimized maintenance scheduling.
  • This advancement can lead to significant savings in resources, time, and costs for automated production.
  • The findings support the use of GVF-based anomaly detection for effective industrial fault prediction.