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.
16
datasets available to search
ShareScore release 0.9.0
Dataset results
16 results for “Predictive Maintenance”
Predictive maintenance of the Baghouse [CAO1]
<p> </p> <p>The baghouse filter consists of a collector which removes dust, mainly filler content in dry aggregates during drying process in drum. Baghouse performance is heavily depended on inlet and outlet gas temperature and flow speed as well as opacity climatic conditions and pressure drop, in the bag house (temperature and humidity, the recipe of asphalt). The final user of this asset is the plant operator (EIFFAGE), which is interested in the predictive maintenance of the baghouse.</p> <p>In the context of the developed Cognitive Solution (CS), two prediction models will be developed:</p> <ul> <li>The first model predicts if the baghouse is working properly by attempting to identify any abnormal behavior.</li> <li>The second model predict the remaining useful life of a component of baghouse (days or hours).</li> </ul> <p>The former is utilized for generating a set of alarms based on the process measurements while the latter is utilized for providing an estimation of the saturation level of the filters as well as a value of the evolution of the saturation level of the filters.</p>
TCM: Benchmark Datasets for Predictive Maintenance in Steel Manufacturing
<h1>Anomaly-TCM</h1> <p>Predictive Maintenance (PdM) is a strategy that uses advanced data analytics to predict equipment failures and maintain industrial machinery in good condition. Its goals are to minimize downtime, reduce operational costs, and ensure product quality. PdM methods are applicable across various industries, including steel manufacturing.</p> <p>In steel production, cold rolling is a critical process that reduces the thickness of hot-rolled steel. Developing PdM methods for tandem cold mills (TCM) can significantly improve production efficiency. However, researchers often rely on real manufacturing data, which is typically unavailable, unlabeled, and noisy, making it difficult to validate and compare methods.</p> <p>To overcome this, we created synthetic datasets for the cold rolling process to identify anomalies based on physical principles. These datasets were generated using a mathematical model of a 5-stand TCM, calculating key process parameters like rolling force, torque, speed, tension, gap, thickness reduction, and motor power. We introduced anomalies related to specific failures in the process.</p> <p>We produced six diverse datasets, each with varying complexity, to enable benchmarking of machine learning-based PdM methods for the cold rolling process. Four different types of anomalies were introduced, which are related to a physics-based deviations in the process:</p> <ol> <li>Anomaly in reduction scheme</li> <li>Anomaly in work roll (increased work roll friction)</li> <li>Anomaly in bearing (increased motor torque)</li> <li>Anomaly in electric motor (decrease efficiency)</li> </ol> <p> The details of the datasets are provided below.</p> <table> <tbody> <tr> <td><strong>Dataset</strong></td> <td><strong>Observations</strong></td> <td><strong>Anomalies</strong></td> <td><strong>Share of Anomalies</strong></td> <td><strong>Features</strong></td> <td><strong>Anomaly Types</strong></td> <td><strong>Products</strong></td> <td><strong>Data Drift</strong></td> </tr> <tr> <td>tcm5_dataset_1</td> <td>20009</td> <td>1045</td> <td>5.2%</td> <td>51</td> <td>1</td> <td>4</td> <td>FALSE</td> </tr> <tr> <td>tcm5_dataset_2</td> <td>20001</td> <td>1035</td> <td>5.2%</td> <td>51</td> <td>1</td> <td>20</td> <td>FALSE</td> </tr> <tr> <td>tcm5_dataset_3</td> <td>20003</td> <td>981</td> <td>4.9%</td> <td>51</td> <td>4 (16)</td> <td>4</td> <td>FALSE</td> </tr> <tr> <td>tcm5_dataset_4</td> <td>20001</td> <td>925</td> <td>4.6%</td> <td>51</td> <td>4 (16)</td> <td>20</td> <td>FALSE</td> </tr> <tr> <td>tcm5_dataset_5</td> <td>20005</td> <td>1031</td> <td>5.2%</td> <td>51</td> <td>4 (16)</td> <td>5</td> <td>TRUE</td> </tr> <tr> <td>tcm5_dataset_6</td> <td>20008</td> <td>954</td> <td>4.8%</td> <td>51</td> <td>4 (16)</td> <td>25</td> <td>TRUE</td> </tr> </tbody> </table> <p> </p> <p>Each dataset is generated as a data stream, meaning the observations follow a chronological order, represented by increasing work roll mileage (which is reset after a predefined threshold). The table below provides details about the features and labels present in the datasets. Several features are recorded for each rolling stand, totaling 51 features. Apart from the anomaly related to reduction, the other anomalies are specific to individual stands, resulting in 16 anomaly labels in total.</p> <table> <tbody> <tr> <td><strong>Feature</strong></td> <td><strong>Suffixes</strong></td> <td><strong>Unit</strong></td> <td><strong>Description</strong></td> </tr> <tr> <td>thickness_entry</td> <td>-</td> <td>mm</td> <td>steel entry thickness</td> </tr> <tr> <td>thickness_exit</td> <td>-</td> <td>mm</td> <td>steel exit thickness</td> </tr> <tr> <td>width</td> <td>-</td> <td>mm</td> <td>steel width</td> </tr> <tr> <td>ys_entry</td> <td>-</td> <td>MPa</td> <td>steel entry yield strength</td> </tr> <tr> <td>ys_exit</td> <td>-</td> <td>MPa</td> <td>steel exit yield strength</td> </tr> <tr> <td>work_roll_diam</td> <td>1 to 5</td> <td>mm</td> <td>work roll diamaeter (stands 1 to 5)</td> </tr> <tr> <td>work_roll_mileage</td> <td>1 to 5</td> <td>km</td> <td>work roll mileage (stands 1 to 5)</td> </tr> <tr> <td>reduction</td> <td>1 to 5</td> <td>-</td> <td>thickness reduction (stands 1 to 5)</td> </tr> <tr> <td>tension</td> <td>0 to 5</td> <td>N</td> <td>interstand tension (0 is tension before stand 1, 1-5 refer to tension after stands 1-5)</td> </tr> <tr> <td>roll_speed</td> <td>1 to 5</td> <td>NaN</td> <td>linear work roll speed (stands 1 to 5)</td> </tr> <tr> <td>force</td> <td>1 to 5</td> <td>N</td> <td>rolling force (stands 1 to 5)</td> </tr> <tr> <td>torque</td> <td>1 to 5</td> <td>Nm</td> <td>rolling torque (stands 1 to 5)</td> </tr> <tr> <td>gap</td> <td>1 to 5</td> <td>mm</td> <td>stand gap (stands 1 to 5)</td> </tr> <tr> <td>motor_power</td> <td>1 to 5</td> <td>kW</td> <td>electric motor power (stands 1 to 5)</td> </tr> <tr> <td>Anomaly_Reduction</td> <td>-</td> <td>-</td> <td>(label) anomaly in reduction scheme</td> </tr> <tr> <td>Anomaly_Electric</td> <td>1 to 5</td> <td>-</td> <td>(label) anomaly in electric motor (stands 1 to 5)</td> </tr> <tr> <td>Anomaly_Bearing</td> <td>1 to 5</td> <td>-</td> <td>(label) anomaly in stand bearing (stands 1 to 5)</td> </tr> <tr> <td>Anomaly_WorkRoll</td> <td>1 to 5</td> <td>-</td> <td>(label) anomaly in work roll friction (stands 1 to 5)</td> </tr> </tbody> </table>
Disk replacement log file examples from a very large RAID disk system for predictive maintenance analysis
<p>README.txt</p> <p>Maintenance example belonging to: </p> <p> The MANTIS Book: Cyber Physical System Based Proactive Collaborative Maintenance<br> Chapter 9, The Future of Maintenance (2019).<br> Lambert Schomaker, Michele Albano, Erkki Jantunen, Luis Lino Ferreira<br> River Publishers (DK)<br> ISBN: 9788793609853, e-ISBN: 9788793609846, https://doi.org/10.13052/rp-9788793609846</p> <p>The figure .pdf did not make it into the book. Here are the raw data, processed <br> logs and .gnu script to produce it.</p> <p>Data: event logs on disk failure in two racks of a huge RAID disk system (2009-2016).</p> <p>disks1.raw<br> disks2.raw</p> <p>Event logs to RC-filtered time series:<br> RC-filt-disks-log.c <br> do-RC-filter-to-make-spikes-more-visible (bash script)<br> --><br> disks1.log<br> disks2.log</p> <p>Constant (horizontal line) indicating the level where users experienced system-down time<br> Disrupted-operations-threshold</p> <p>disk-replacement-log.gnu<br> disk-replacement-log.pdf<br> </p>
MetroPT2: A Benchmark dataset for predictive maintenance
<p><strong>Abstract</strong></p> <p>The MetroPT2 data set is an outcome of a eXplainable Predictive Maintenance (XPM) project with an urban metro public transportation service in Porto, Portugal. The data was collected in 2022 that aimed to evaluate machine learning methods for online anomaly detection and failure prediction. By capturing several analogic sensor signals (pressure, temperature, current consumption), digital signals (control signals, discrete signals), and GPS information (latitude, longitude, and speed), we provide a dataset that can be easily used to evaluate online machine learning methods. This dataset contains some interesting characteristics and can be a good benchmark for predictive maintenance models.</p> <table> <tbody> <tr> <td> <p>Data Set Characteristics:</p> </td> <td> <p>Multivariate Time series</p> </td> <td> <p>Number of Instances:</p> </td> <td> <p>7116940</p> </td> </tr> <tr> <td> <p>Attribute Characteristics:</p> </td> <td> <p>Real</p> </td> <td> <p>Number of Attributes</p> </td> <td> <p>21</p> </td> </tr> <tr> <td> <p>Associated Tracks:</p> </td> <td> <p>Classification, Regression</p> </td> <td> <p>Missing Values</p> </td> <td> <p>N/A</p> </td> </tr> </tbody> </table> <p><strong>Data Set Information:</strong></p> <p>The dataset was collected to support the development of predictive maintenance, anomaly detection, and remaining useful life (RUL) prediction models for compressors using deep learning and machine learning methods.</p> <p>It consists of multivariate time series data obtained from several analogue and digital sensors installed on the compressor of a train. The data span between 2022-04-28 and 2022-07-28 and includes 16 signals, such as pressures, motor current, oil temperature, flowmeter and electrical signals of air intake valves. The monitoring and logging of industrial equipment events, such as temporal behaviour and fault events, were obtained from records generated by the sensors. The data were logged at 1Hz by an onboard embedded device. You can find a schematic diagram of the air production unit of the compressor system in Figure 4 of the accompanying paper [1]. Also, the paper [2] provides a detailed examination of data collection and specifications of various types of potential failures in an air compressor system. </p> <p><strong>Relevant Papers:</strong></p> <p>[1]- Davari, N., Veloso, B., Ribeiro, R.P., Pereira, P.M., Gama, J.: Predictive maintenance based on anomaly detection using deep learning for air production unit in the railway industry. In: 2021 IEEE 8th International Conference on Data Science and Advanced Analytics (DSAA). pp. 1–10. IEEE (2021) (DOI: <a href="https://doi.org/10.1109/DSAA53316.2021.9564181">10.1109/DSAA53316.2021.9564181</a>)</p> <p>[2] Veloso, B., Ribeiro, R.P., Pereira, P.M., Gama, J.: The MetroPT dataset for predictive maintenance. Scientific Data 9, no. 1 (2022): 764. (DOI: 10.1038/s41597-022-01877-3)</p> <p>[3]-Barros, M., Veloso, B., Pereira, P.M., Ribeiro, R.P., Gama, J.: Failure detection of an air production unit in the operational context. In: IoT Streams for Data-Driven Predictive Maintenance and IoT, Edge, and Mobile for Embedded Machine Learning, pp. 61–74. Springer (2020) (DOI: 10.1007/978-3-030-66770-2_5)</p> <p><strong>Failure Information:</strong></p> <p>The dataset is unlabeled, but the failure reports provided by the company are available in the following table. This allows for evaluating the effectiveness of anomaly detection, failure prediction, and RUL estimation algorithms.</p> <p> </p> <table> <tbody> <tr> <td> <p>Nr.</p> </td> <td> <p>Start Time</p> </td> <td> <p>End Time</p> </td> <td>Failure</td> </tr> <tr> <td> <p>1</p> </td> <td> <p>2022-06-04 10:19:24.300</p> </td> <td> <p>2022-06-04 14:22:39.188</p> </td> <td>Air Leak</td> </tr> <tr> <td> <p>2</p> </td> <td> <p>2022-07-11 10:10:18.948</p> </td> <td> <p>2022-07-14 10:22:08.046</p> </td> <td>Oil Leak</td> </tr> </tbody> </table> <p> </p>
Predictive Maintenance Literature Review Framework
<p>This dataset contains information collected during a literature review in the domain of Predictive Maintenance in Industry 4.0. It consists of Two Tables:</p><ol><li>Paper references and their contribution to individual topics</li><li>Types of Neural Networks that have been used in the Papers</li></ol>
Channel State Information (CSI) analysis for predictive maintenance using Convolutional Neural Network (CNN)
<p>Dataset manual:</p> <p>This dataset contains CSI amplitude values for rotating motors in an office environment. Details of the experiments may be found in the corresponding paper published in the DATA'19 workshop, SenSys (<a href="https://doi.org/10.1145/3359427.3361917">https://doi.org/10.1145/3359427.3361917</a>). </p> <p>Folder structure:<br> The folders for servo motor and stepper motor contains separate folders for network reconnection conditions (w_recc: with reconnections, wo_recc: without recconnections) and load conditions (w_load: with load and wo_load: without load). The data is stores as Matlab files with .mat extentions. </p> <p>File structure:<br> In each file name, the digits after the '_' at the end of the file name correspond to the speed of the motor. In case of stepper motor these numbers could be directly interpreted as rpm. Ex: table_inj_with_load_5_0.mat corresponds to stationary motor (0 rpm) and table_inj_with_load_5_250.mat corresponds to motor rotating with 250 rpm speed. In the case of servo motor these numbers should be mapped with the following table in order to get the speeds.</p> <p>0: 0 rpm<br> 50: 14.45 rpm<br> 100: 8.02 rpm<br> 150: 5.38 rpm<br> 200: 4.05 rpm<br> 250: 3.26 rpm<br> 300: 2.67 rpm<br> Ex: table_inj_with_load_50.mat corresponds to motor running with 14.45 rpm.</p> <p>Each file has 3 columns, each corresponding to CSI value, labels (speed/last digits in the file name) and the data sample number (not in sequence as a result of packer loss) respectively. CSI values are typically a matrix of size 3000*180 (3000 CSI samples for 3sec data @1kHz sampling rate and 180 channels for 6 antenna pairs @ 30 subcarrier data per antenna).</p>
Identification of Phenotypic Factors That Predict Success for Weight Loss and Long-term Weight Maintenance
ClinicalTrials.gov study NCT02043457. IPD Sharing: Not stated. Countries: 1. Publications: 2.
Predictive maintenance dataset.
<p><em>Public (anonymized) predictive maintenance datasets from Huawei Munich Research Center.</em></p> <p>Datasets from a variety of IoT sensors for predictive maintenance in elevator industry. The data is useful for predictive maintenance of elevators doors in order to reduce unplanned stops and maximizing equipment life cycle.</p> <p>The dataset contains operation data, in the form of timeseries sampled at 4Hz in high-peak and evening elevator usage in a building (between 16:30 and 23:30). For an elevator car door the system we consider: Electromechanical sensors (Door Ball Bearing Sensor), Ambiance (Humidity) and Physics (Vibration).</p>
Significance of longitudinal muscle loss in predicting the maintenance efficacy of durvalumab treatment following con-current chemoradiotherapy in patients with NSCLC: a retro-spective study Supplementary Figure
Open the record for dataset details and reuse information.
Prediction and Maintenance of Sinus Rhythm Among Atrial Fibrillation Patients
ClinicalTrials.gov study NCT04313296. IPD Sharing: NO. Countries: 1. Publications: 0.
A Study of PC Sequential Pemetrexed Single Drug Maintenance Treatment for NSCLC and Related Predictive Biomarkers
ClinicalTrials.gov study NCT01860508. IPD Sharing: Not stated. Countries: 1. Publications: 1.
Value of Pharmacokinetic Assays in the Prediction of Induction and Maintenance Therapeutic Response in Crohn's Disease
ClinicalTrials.gov study NCT02768532. IPD Sharing: NO. Countries: 1. Publications: 0.
Pleth Variability Index for Predicting Low Blood Pressure During Maintenance Hemodialysis
ClinicalTrials.gov study NCT07022847. IPD Sharing: NO. Countries: 1. Publications: 0.
Complementary patterns of gene expression by human oligodendrocyte progenitors and their environment predict determinants of progenitor maintenance and differentiation.
GEO Series GSE26535. Homo sapiens. 6 samples. Type: Expression profiling by array.
A New Risk Score for Predicting 1-year Mortality in Older r Maintenance Hemodialysis Patients.
ClinicalTrials.gov study NCT05699447. IPD Sharing: Not stated. Countries: 0. Publications: 0.
Characterization of the regulatory network of linc1393 in the maintenance of pluripotency provides the principles for lncRNA targets prediction [RNA-seq]
GEO Series GSE214671. Mus musculus. 8 samples. Type: Expression profiling by high throughput sequencing.
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.