Find research datasets worth reusing
Search datasets from major research repositories and use ShareScore to quickly assess how well each record supports discovery, access, and reuse.
27
datasets available to search
ShareScore release 0.7.1
Dataset results
27 results for “Fault detection”
Detecting repeating earthquakes on the San Andreas Fault with unsupervised machine-learning of spectrograms (supplementary material)
<p>Supplementary material for Sawi et al., 2023, <i>Detecting repeating earthquakes on the San Andreas Fault with unsupervised machine-learning of spectrograms </i>(The Seismic Record). Catalog of repeating earthquakes in sequences on a 10-km long segment of the San Andreas Fault in California from 1984-2019. </p><p> </p><p><strong>Catalog Header</strong></p><p>YR/MO/DY...........Date of event</p><p>HR/MN/SC...........Time of event</p><p>LAT/LON/DEP........Location of event</p><p>EX/EY/EZ...........Relative location uncertainty (in m)</p><p>MAG................NCSN magnitude</p><p>evID.................NCSN event ID</p><p>seqID................Repeating earthquake sequence ID</p><p>isRESp............Is quasi-periodic RES (bool)</p><p> </p><p><strong>References: </strong></p><p>Sawi T., Waldhauser F., Holtzman B. K., Groebner, N. (2023) Detecting repeating earthquakes on the San Andreas Fault with unsupervised machine-learning of spectrograms. The Seismic Record. </p><p>Waldhauser, F., and Schaff, D. P. (2021). A Comprehensive Search for Repeating Earthquakes in Northern California: Implications for Fault Creep, Slip Rates, Slip Partitioning, and Transient Stress. J Geophys Res B Solid Earth, 126(11), 1–22. <a href="https://doi.org/10.1029/2021JB022495">https://doi.org/10.1029/2021JB022495</a></p>
Generic, Scalable and Decentralized Fault Detection for Robot Swarms
<p>This raw data archive includes the data on fault detection in a simulated swarm of 20 e-puck robots. The data was used in the paper Generic, Scalable and Decentralized Fault Detection for Robot Swarms by D. Tarapore et al. (2017).</p> <p>See readme.txt for more details.</p>
Comprehensive Dataset for Fault Detection and Diagnosis in Inverter-Driven PMSM Systems
<p><span>#</span><span> New in Version 3.0</span> The dataset has been reorganized for improved accessibility and clarity:</p> <ul> <li>/code: Contains all source code (C++ and Python) for data acquisition and processing</li> <li>/metadata: Contains sensor specifications and fault definitions</li> <li>/processed_data: Contains the processed and derived features</li> <li>/raw_data: Contains: <ul> <li>Raw sensor measurements</li> <li>Fault scenario data</li> <li>Normal operation data</li> <li>Thermistor calibration data</li> </ul> </li> <li>/visualizations: Contains data visualization outputs</li> </ul> <p><br>This dataset contains multi-sensor measurements from an inverter-driven PMSM system under various fault conditions. It includes: </p> <ul> <li>10,892 samples across 9 operational conditions</li> <li>8 raw sensor measurements</li> <li>15 derived features</li> <li>Data collected at 10 Hz sampling rate</li> <li> Fault scenarios including open-circuit, short-circuit, and overheating conditions</li> </ul> <p> Keywords:</p> <ul> <li>PMSM</li> <li>Fault Detection</li> <li>Inverter Faults</li> <li>Motor Drive Systems</li> <li>Experimental Data</li> <li>Machine Learning</li> </ul>
Series AC Arc Fault Detection Method Based on High-Frequency Coupling Sensor and Convolution Neural Network
<p>The data provided can be used for the development of methods for the detection of arcing faults in a domestic low-voltage electrical networks (230V - 50 Hz). The data files are current and voltage signatures experimentally measured.</p> <p>Test for to produce an arcing fault : Open contact electrodes and Carbonized path wires</p> <p>The ReadMe file describes :</p> <p>- the test set up and the the procedure followed to make the measurements</p> <p>- the list of household appliances and their main characteristics.</p> <p>- the name of the data files</p> <p>- the type of arcing faults</p>
Arc fault detection and appliances classification in AC home electrical networks using Recurrence Quantification Plots and Image Analysis
<p>The data provided can be used for the development of methods for the detection of arcing faults in a domestic low-voltage electrical networks (230V - 50 Hz). The data files are current and voltage signatures experimentally measured.</p> <p>The ReadMe file describes :</p> <p>- the test set up and the the procedure followed to make the measurements</p> <p>- the list of household appliances and their main characteristics.</p> <p>- the name of the data files</p> <p>- the type of arcing faults</p> <p> </p>
Cascadia Subduction Zone Fault Heterogeneities from Newly Detected Small Earthquakes - Datasets
<p>Datasets associated with manuscript "Cascadia Subduction Zone Fault Heterogeneities from Newly Detected Small Earthquakes" by Morton et al. (2023), submitted to the <em>Journal of Geophysical Research: Solid Earth</em>. Three datasets are present in this upload:</p> <p><strong>ds01.xlsx</strong>: Catalog of 5,282 detected earthquakes along the Cascadia subduction margin, ordered by time. Events were located using Hypoinverse (Klein, 2002). Columns of the catalog are: Cascadia Initiative deployment year, Origin Time String (YYYYMMDDhhmmss), Origin Time (Year, Month, Day, Hour, Minute, Second), Latitude, Longitude, Event Depth (km), Duration Magnitude (Md), Number of P and S arrival picks with weights > 0.1, Maximum Azimuthal Gap (deg.), Distance to the Nearest Station (km), Travel Time Residual RMS (s), Horizontal Location Error (ERH; km), Vertical Location Error (ERZ; km), Focal Mechanism if applicable (Strike, Dip, Rake; deg.), Plate Designation (Slab, Interface, or Upper Plate), and Previous Existence in Regional Catalogs. Duration magnitudes that could not be constrained are listed as -9. Detected earthquakes that had previously been reported in other catalogs are listed as "Catalog" or "Stone" form the regional or Stone et al. (2018) catalogs, respectively; Those used as template events are marked as "T" or "ST", for those from regional catalogs or the Stone et al. (2018) catalog, respectively, in the last column.</p> <p><strong>ds02.xlsx</strong>: Table of earthquakes chosen as template events for subspace scanning from regional (NEIC, ANF, PNSN, CNDC) and Stone et al. (2018) catalogs. Columns of the template event table are: Catalog Source (T for regional, ST for Stone et al. 2018), Cascadia Initiative (CI) Deployment Year, Template Cluster ID, Date, Time (UTC), Catalog Location (Latitude, Longitude, Depth), Catalog Magnitude, and Whether the Template Event was Detected. Some of the templates were detected but were not included in the final catalog because the travel time residual RMS was greater than 1s and are noted in the table as "poorly located".</p> <p><strong>ds03.xlsx</strong>: Table of seismic stations used in subspace detection scanning, identified by the CI deployment year, Template Cluster ID, Station SEED, and Network Codes. Stations are listed with the corresponding high-pass (HP) or band-pass (BP) filter applied before scanning to maximize the signal-to-noise ratio.</p> <p>References</p> <p>Klein, F. W. (2002). <em>User’s Guide to HYPOINVERSE-2000, a Fortran Program to Solve for Earthquake Locations and Magnitudes</em> (Open File Report 02-171). U.S Geological Survey. https://doi.org/10.3133/ofr02171</p> <p>Stone, I., Vidale, J. E., Han, S., & Roland, E. (2018). Catalog of off-shore seismicity in Cascadia: Insights into the regional distribution of microseismicity and its relation to subduction processes. <em>Journal of Geophysical Research: Solid Earth, 123</em>, 1–12. https://doi.org/10.1002/2017JB014966</p>
Wind Turbine SCADA Data For Early Fault Detection
<p>This dataset is published together with the <a href="https://doi.org/10.3390/data9120138">paper</a> "CARE to Compare: A real-world dataset for anomaly detection in wind turbine data" which explains the dataset in detail and defines the CARE score that can be used to evaluate anomaly detection algorithms on this dataset. When referring to this dataset, please cite the paper mentioned in the related work section. </p> <p>The data consists of 95 datasets, containing 89 years of SCADA time series distributed across 36 different wind turbines<br>from the three wind farms A, B and C. The number of features depends on the wind farm; Wind farm A has 86 features, wind farm B has 257 features and wind farm C has 957 features. </p> <p>The overall dataset is balanced, as 45 out the 95 datasets contain a labeled anomaly event that leads up to a turbine fault and the other 50 datasets represent normal behavior. Additionally, the quality of training data is ensured by turbine-status-based labels for each data point and further information about some of the given turbine faults are included.</p> <p>The data for Wind farm A is based on data from the EDP open data platform (https://www.edp.com/en/innovation/open-data/data), <br>and consists of 5 wind turbines of an onshore wind farm in Portugal. <br>It contains SCADA data and information derived by a given fault logbook which defines start timestamps for specified faults. <br>From this data 22 datasets were selected to be included in this data collection. <br>The other two wind farms are offshore wind farms located in Germany. All three datasets were anonymized due to confidentiality reasons for the wind farms B and C.<br>Each dataset is provided in form of a csv-file with columns defining the features and rows representing the data points of the time series. Files</p> <p>More detailed information can be found in the included README-file.</p> <p><strong>Notes</strong></p> <p>In wind farm A status_type_id labels can be ignored while evaluating prediction time frames of error events with metrics like the CARE-score since the status_type_id is of wind farm A is based on the EDP failure logbook and it is intended to be used for filtering of the training data.</p> <p><strong>Version Changes:</strong></p> <p><em>Version 5 -> 6:</em></p> <ul> <li>Changed unit of sensor_40 and sensor_61 for wind farm C to hPa instead of bar. This unit error became obvious when looking at the data and comparing it to the standard air pressure.</li> <li>Edited event_description of events 34, 7 and 19 to high temperature in transformer cell.</li> <li>Changed date in event description of event 44 since it was not affected by the change in the date anonymization procedure from version 2.</li> <li>Changed date in event description of event 47 since it was not affected by the change in the date anonymization procedure from version 2 and edited the description text</li> <li> Changed date format in event_info files to match the date format in the dataset files.</li> <li>Fixed typo in Readme</li> <li>Re-added Readme files</li> </ul> <p><em>Version</em> 4->5:</p> <p>Corrections to labels were made:</p> <ul> <li>Previously missing status_type_id 4 labels were added to datasets in Wind Farm A. </li> <li>Event 51 from Wind Farm A was wrongly labeled as a normal event. With the newly added status_type_id 4 occurences, it is to be considered an anomaly event due to a gearbox bearing damage within the prediction data.</li> <li>Wind Farm A no longer contains status_type_id 5. All occurences of status_type_id 5 have been changed to 0 and are considered normal time stamps. This change is done, because status_type_id 5 was set as a result of a wind speed and power analysis, flagging potential anomalous data. This is not based on a fixed ground truth, so status_type_id 5 was removed. For Wind Farms B and C status_type_id 5 is still valid since it is based on real SCADA-status codes.</li> <li>The event_info.csv files now contain an additional column 'asset_id'.</li> </ul> <p><em>Version 3->4:<br></em></p> <ul> <li>The change of the timestamp anonymization lead to duplicate timestamps when transitioning from a leap year to 2022. This is now fixed in Version 4.</li> </ul> <p><em>Version 2->3:</em></p> <ul> <li>In version 2 timestamp changes were not consistent with the timestamps in the event-info-files. Version 3 fixes this.</li> </ul> <p><em>Version 1->2:<br></em></p> <ul> <li>Version 2 contains one deviation from version 1 regarding the anonymization procedure. Instead of shifting the timestamps of each sub-dataset by a random number of years, the size of the time shift is now determined to be the number of years so that each sub-dataset starts in 2022. This change is made to make the timestamp anonymization more consistent and to avoid future timestamps being present within the data.</li> </ul>
Fault Detection and Inventory Management in Manufacturing with Plastic Bricks: A Dataset
<p><strong>Dataset for Smart Manufacturing</strong></p> <p>The dataset contains images of plastic bricks showcasing various colors, shapes, and minor surface damages, designed to represent the use-cases of quality classification and inventory management in manufacturing. The use cases are separated and include 3 categories for quality classification and 24 categories for inventory classification. The data is analyzed in the publication titled "Demonstrating Computer Vision to Small- and Medium-sized Enterprises in Manufacturing: Towards Overcoming Costs and Implementation Challenges". The associated research explores the development of a simple computer vision demonstrator and its demonstration to small- and medium-sized enterprises. </p> <p><strong>Structure of Files</strong></p> <blockquote> <p>quality_classification (224 images)</p> <p> defect</p> <p> defect_free</p> <p> empty</p> <p>inventory_classification (2732 images)</p> <p> beige_large</p> <p> beige_small</p> <p> blue_bright_large</p> <p> 21 further categories (colour_shape)</p> </blockquote>
Contaminations on Lidar Sensor Covers: Performance Degradation including Fault Detection and Modeling as Potential Applications
<p><strong>Data description of contamination measurements with lidar sensors RIEGL LD05-A20 and Ouster OS1-64</strong></p> <p><em><strong>Photos of the measurement setup</strong></em></p> <p>We provide photos of the measurement setup and the contaminations applied in the folder "/photos".</p> <p> </p> <p><em><strong>Riegl LD05-A20 data</strong></em></p> <p>The data of the Riegl LD05-A20 can be found in the folder "riegl_LD05-A20_full_waveforms" - one file per experiment. An example notebook for reading the data is provided in "/notebooks/example_riegl_LD05-A20.ipynb". Note that the files contain only the prominent peaks of the full waveform calculated by the V08Wave software provided by RIEGL. If you are interested in the entire full waveforms, please contact the authors.</p> <p> </p> <p><em><strong>Ouster OS1-64</strong></em></p> <p>The data of the Ouster OS1-64 can be found in the folder "ouster_OS1-64_point_clouds" - one folder per experiment. An example notebook for reading the data is provided in "/notebooks/example_ouster_OS1-64.ipynb". The python package <strong><em>pointcloudset</em></strong> (https://github.com/virtual-vehicle/pointcloudset) and its documentation is suggested for further data analytics of the point cloud data.</p> <p> </p>
Replication package of "Higher Fault Detection Through Novel Density Estimators in Unit Test Generation"
<p>Replication package for the paper "Higher Fault Detection Through Novel Density Estimators in Unit Test Generation" accepted at the Symposium on Search-based Software Engineering (SSBSE) 2024.</p> <p> </p> <p> </p>
UAV-FD: a dataset for actuator fault detection in multirotor drones
<p>This dataset collects real flight data from a hexarotor under the effects of a chipped blade. A conventional ArduPilot based controller is employed, where the ArduPilot firmware is customized to increase the signal logging rate of the IMU variables, thus capturing enough information at higher frequencies. Additional variables are available, including on-board measurements, commands, estimations, and parameters; in particular, the actual speed of each motor is measured as well.</p> <p>The purpose of the UAV-FD dataset is to accelerate the research on actuator fault diagnosis for multirotor vehicles.</p>
Generic, Scalable and Decentralized Fault Detection for Robot Swarms
<p>This raw data archive includes the data on fault detection in a simulated swarm of 20 e-puck robots. The data was used in the paper Generic, Scalable and Decentralized Fault Detection for Robot Swarms by D. Tarapore et al. (2017).</p> <p>See readme.txt for more details.</p>
Machine-learning-based seismic detection and location around the Tanlu fault zone in eastern China
<p>REAL, HypoInverse, and HypoDD catalog around the Tanlu fault zone in eastern China.</p>
Vibration-Based Fault Detection in Drone using Artificial Intelligence
<p>Recent years have seen a huge increase in the study of drones. There is a lot of published articles regarding drone, focusing on control optimization, fault detection, safety mechanisms, etc. In fault detection, most of the studies focused on the effects of faulty propellers and rotors, and there is very limited academic research on drone arms. In this paper, a fault detection based on the vibration of the multirotor arms using artificial intelligence (AI) is proposed. There are some cases where due to an accident, the arm<br> of the multirotor crack or loose. This is normally unnoticeable without disassembly and if not taken care of, it would have likely resulted in a sudden loss of flight stability, which will lead to a crash.</p> <p>Two types of AI methods are incorporated in this study, namely, fuzzy logic and neuro-fuzzy, using the fuzzy logic and ANFIS toolbox in the MATLAB software, respectively. For the neuro-fuzzy approach, we use 100 and 1000 datasets to determine the effects of the dataset size on the neuro-fuzzy performance. Both datasets are divided into training (80%), testing (10%), and checking data (10%). The guidelines for constructing the AI algorithms are based on the experimental data for five experimental conditions; (i) (a) Original multirotor condition without modifying the multirotor arms, (b) 100% screwed multirotor arms condition (full tighten), (c) 50% screwed multirotor<br> arms condition (half tighten), (d) 10% screwed multirotor arms condition, and (e) Unscrewed multirotor arm conditions.</p> <p>Their results are compared to determine the best method in predicting the safety of the multirotor. Both methods provided acceptable decision making but the neuro-fuzzy approach depends on the dataset used as overfit model might give incorrect decision making. Because the vibration data are collected in an indoor environment, this framework is more suitable for early prediction before flying the multirotor outdoor. A video demonstrating the real-time deployment of our proposed method is included in the mp4 format.</p>
Dataset for intelligent fault detection
Open the record for dataset details and reuse information.
The 2023 Mw 6.0 Jishishan Earthquake: A Slow Unilateral Rupture on a Blind Thrust Fault Revealed by High-Precision Earthquake Detection, Location, and Dynamic modeling
Open the record for dataset details and reuse information.
Fault detection in Robotic Swarm Aggregation using a Kalman Filter - Appendix
<p>The appendix for my bachelor thesis: Fault detection in Robotic Swarm Aggregation using a<br> Kalman Filter. In the images of the aggregation experiments the different lines refer to the number of clustering robots.</p>
Fault Detection, Zone MPC and DiAs System in T1D
ClinicalTrials.gov study NCT02773875. IPD Sharing: NO. Countries: 0. Publications: 2.
Vibration-Based Fault Detection in Drone using Artificial Intelligence
Open the record for dataset details and reuse information.
Model-Based Fault Detection and Diagnosis System for NASA Mars Subsurface Drill Prototype
The Drilling Automation for Mars Environment (DAME) project, led by NASA Ames Research Center, is aimed at developing a lightweight, low-power drill prototype that can be mounted on a Mars lander and be capable of drilling down several meters below the Mars surface for conducting geology and astrobiology research. The DAME drill system incorporates a large degree of autonomy - from quick diagnosis of system state and fault conditions to making the appropriate recovery actions - while also striving to achieve as many of the operational objectives as possible. This paper outlines, on a general level, the overall DAME architecture, equipment, and autonomy package. The main focus, however, is on describing the model-based fault detection and diagnosis system, including the modeling approach, the fault modes handled, and the diagnostic algorithms. The results of the latest field tests, conducted in 2006 in Haughton Crater on Devon Island (a Mars analogue site in Canadian Arctic), are also discussed.
ScienceDex guides
Understand access before you commit
These curated guides explain access requirements, typical timelines, costs, and reuse considerations for widely used research datasets.
Allen Brain Atlas
Allen Brain Atlas is an Allen Institute collection of brain map atlases, datasets, APIs, and analysis tools covering mouse, human, and non-human primate brain resources.
Annotated Behaviour and Observability Dataset (ABODe)
ABODe is a University of Edinburgh DataShare dataset for behavior classification in group-housed mice using home-cage video, identities, bounding boxes, ground-plate positions, and annotator labels.
DANDI Archive for NWB datasets
DANDI is a BRAIN Initiative archive for publishing and sharing neurophysiology data, including electrophysiology, optophysiology, and behavioral data packaged as NWB and related standards.
International Brain Laboratory public data
The International Brain Laboratory public data releases expose standardized mouse decision-making experiments, including Neuropixels recordings, widefield calcium imaging, behavior, and session metadata accessed through the ONE API.
OpenNeuro
OpenNeuro is a free, open platform for sharing neuroimaging datasets, with public search, dataset pages, and download paths for web, S3, DataLad, and the OpenNeuro CLI.