Wind turbine condition monitoring (CM) can potentially help the wind industry reduce turbine downtime and operation and maintenance (O&M) cost. NREL CM research has investigated various condition-monitoring techniques such as acoustic emission (AE specifically stress wave), vibration, electrical signature, lubricant and debris monitoring based on the Gearbox Reliability Collaborative dynamometer and field tests, and other test turbines and resources accessible by NREL. During the past several years, NREL CM research has shown that there are very few validation and verification efforts on commercial wind turbine CM systems. One of the reasons might be limited benchmarking datasets accessible by stakeholders. To fill this gap, NREL executed a data collection effort. The targeted users of these datasets include those investigating vibration-based wind turbine CM research, evaluating commercially available vibration-based CM systems, or testing prototyped vibration-based CM systems.

NREL collected data from a healthy and a damaged gearbox of the same design tested by the GRC. Vibration data were collected by accelerometers along with high-speed shaft RPM signals during the dynamometer testing. The healthy gearbox was only tested in the dynamometer. The damaged gearbox was first tested in the dynamometer and later sent to a wind farm close to NREL for field testing. In the field test, it experienced two loss-of-oil events that damaged its internal bearings and gear elements. The gearbox was brought back to NREL and it was retested in the dynamometer with CM systems deployed under controlled loading conditions that would not cause catastrophic failure of the gearbox.

The objective of releasing these datasets to the public along with information about the real damage that occurred to the damaged gearbox is to provide the wind industry with some benchmarking datasets. These datasets will benefit research, development, validation, verification, and advancement of vibration-based wind condition-monitoring techniques.

By accessing this data you acknowledge the terms outlined in the "License Information" document.

Please contract Shawn Sheng (NREL) if you have any questions on the data or would like to collaborate on publications based on the datasets.

Failure-induced vibration recordings on outer race and rolling elements of a spherical roller bearing (FAG 22205E1KC3)

This site allows access to vibration records of a bearing, in normal state and with combined failure, comprising localised defects induced in the outer raceway (OR) and rolling elements (RE). The experiment is carried out on a test bench, to validate a diagnostic method using "Contour Maps", proposed by Railway Technology Research Center (CITEF) of the Technical University of Madrid (Spain). The characteristics of the developed database are specified in the attached document "READ_ME.pdf".

The article link is available at: https://www.mdpi.com/2076-3417/11/14/6452

More information about the bearing test bench is available at: https://www.mdpi.com/1424-8220/20/12/3493/htm#

Response data for vibration under impact loading of three types of rocks with a height of 3 m, a width of 2 m, and lengths of 3 m, 4 m, and 5 m.

Scope:

This repository contains data provided by vibrations sensor that can be used in designing and testing ML algorithms for general classification problems or more specific one such as predictive maintenance.

Source of the data:

Data were obtained in the framework of CHIST-ERA SOON project with the aim of testing machine learning predictive maintenance algorithms.

Special remarks:

Each file name codes how the data was obtained and and implicitly the data label.

In experiment were used two electrical motors named m1 and m2, where m1 is the tested motor and m2 is a second motor for obtaining a more complex testing environment (eg. supplemental noise source).

34390 Global import shipment records of Vibration Speaker with prices, volume & current Buyer's suppliers relationships based on actual Global export trade database.

We present Molecular Vibration Explorer, a freely accessible online database and interactive tool for exploring vibrational spectra and tensorial light-vibration coupling strength of a large collection of thiolated molecules. The Gold' version of the database gathers the results from density functional theory calculations on 2'800 commercially available thiol compounds linked to a gold atom, with the main motivation to screen the best molecules for THz and mid-infrared to visible upconversion. Additionally, theThiol' version of the database contains results for 1'900 unbound thiolated compounds.They both provide access to a comprehensive set of computed spectroscopic parameters for all vibrational modes of all molecules in the database. Infrared absorption, Raman scattering and vibrational sum- and difference frequency generation cross sections can be simultaneously investigated by the user. Molecules can be screened for various parameters in custom frequency ranges, such as large Raman cross-section under specific molecular orientation, or large orientation-averaged sum-frequency generation (SFG) efficiency. The user can select polarization vectors for the electromagnetic fields, set the orientation of the molecule and customize parameters for plotting the corresponding IR, Raman and sum-frequency spectra.

The data consists of short examples of vibration signals in buildings. The examples were collected in a project focused on annoyance by vibration from construction work. The examples include tri-axial vibration signals from blasting (tunnels, general and rock extraction), soil compacting, piling, sheet wall piling and construction traffic. The data are shared for use by other researchers.

The zip file contains a table summarising the vibration measurements in Excel and Open Office formats, and a folder with 257 .csv files with raw data from each measurement. The measurements have a unique ID in the file name that is also presented in the Excel file.

This dataset discloses vibration and motor current data for bearing faults under varying speed conditions from 680 RPM to 2460 RPM. The bearing conditions include healthy bearing, bearings with inner race faults, and bearings with outer race faults. For each faulty bearing condition, the three-phase induction motor is operated under randomly varying speed conditions. Important: Datasets are divided into three parts because of storage limitations (Subset1, Subset2, and Subset3).

---- Description of vibration file format ---- Vibration data file contains five columns namely ‘Time Stamp’, ‘x_direction_housing_A’, ‘y_direction_housing_A’, ‘x_direction_housing_B’, and ‘y_direction_housing_B’. The unit of the vibration is ‘gravitational constant (g)’. vibration_aaaa_bbbb.csv : This file is "bbbb"-th vibration data includes rotating speed data of the condition of "aaaa".

---- Description of motor current file format ---- Motor current data file contains five columns namely ‘Time Stamp’, ‘R_phase’, ‘S_phase’, and ‘T_phase’. The unit of the motor current is ‘Ampare (A)’.

current_aaaa_bbbb.csv : This file is "bbbb"-th motor current data includes rotating speed data of the condition of "aaaa".

---- Description of rotating speed file format ---- Rotating speed data file contains two columns namely ‘Time Stamp’, and ‘speed’. The unit of the acoustic is revolutions per minute (RPM)’. rpm_aaaa_bbbb.csv : This file is "bbbb"-th speed data includes rotating speed data of the condition of "aaaa".

For more detailed information, check our published paper. Title: Vibration, Acoustic, Temperature, and Motor Current Dataset of Rotating Machine Under Varying Operating Conditions for Fault Diagnosis Link: https://www.sciencedirect.com/journal/data-in-brief

Basin tests were performed at the Aalto Ice Tank to gather data on ice action and ice-structure interaction. A real-time hybrid test setup was mounted to a carriage on a bridge spanning the ice tank. A vertically sided cylindrical pile was moved through the ice by moving the carriage along the bridge. The dynamic response to the measured ice loads was simulated by the real-time hybrid test setup for a range of test structures including offshore wind turbines, a series of single- and multi-degree-of-freedom oscillators, the Norströmsgrund lighthouse and the Molikpaq caisson structure. In addition, ice loads were measured in forced vibration tests and while moving the rigid pile through the ice with a constant speed.

A full description of the data and experimental design has been published in Data in Brief, see the project references. For questions about the data contact Hayo Hendrikse (h.hendrikse@tudelft.nl).

Labelled industry datasets are one of the most valuable assets in prognostics and health management (PHM) research. However, creating labelled industry datasets is both difficult and expensive, making publicly available industry datasets rare at best, in particular labelled datasets. Recent studies have showcased that industry annotations can be used to train artificial intelligence models directly on industry data ( https://doi.org/10.36001/ijphm.2022.v13i2.3137 , https://doi.org/10.36001/phmconf.2023.v15i1.3507 ), but while many industry datasets also contain text descriptions or logbooks in the form of annotations and maintenance work orders, few, if any, are publicly available. Therefore, we release a dataset consisting with annotated signal data from two large (80mx10mx10m) paper machines, from a Kraftliner production company in northern Sweden. The data consists of 21 090 pairs of signals and annotations from one year of production. The annotations are written in Swedish, by on-site Swedish experts, and the signals consist primarily of accelerometer vibration measurements from the two machines. The dataset is structured as a Pandas dataframe and serialized as a pickle (.pkl) file and a JSON (.json) file. The first column (‘id’) is the ID of the samples; the second column (‘Spectra’) are the fast Fourier transform and envelope-transformed vibration signals; the third column (‘Notes’) are the associated annotations, mapped so that each annotation is associated with all signals from ten days before the annotation date, up to the annotation date; and finally the fourth column (‘Embeddings’) are pre-computed embeddings using Swedish SentenceBERT. Each row corresponds to a vibration measurement sample, though there is no distinction in this data between which sensor or machine part each measurement is from.

This is the vibration data of rehabilitation training, collected by EPH_V11 vibration sensor.

3872 Global exporters importers export import shipment records of Vibration shaker with prices, volume & current Buyer's suppliers relationships based on actual Global export trade database.

This dataset is about using vibration sensing as a preventative maintenance strategy on the railway lines. Railway lines are suspectable to faults because of continuous movement of train on the track. These faults on track increase vibration frequencies on the track and if not corrected they will lead to catastrophic failures. Vibration sensors are used to detect the track frequencies, the higher the frequencies the more the deterioration of the track. Data is then retrieved from the sensor and analyzed if the data shows higher frequencies than the threshold, then appropriate actions are taken immediately.Installation of the vibration sensors on the track are done by using maintenance and system engineering principles these principles are used also in utilization on the sensors.

The data of human vibration collected in the University of Rochester campus.

Data measured for the completion of masters in mechanical engineering thesis "Towards a hybrid approach for diagnostics and prognostics of planetary gearboxes" under the supervision of Prof P.S. Heyns and Dr S. Schmidt.The data set consist of accelerometer measurements on the gearbox housing of a planetary gearbox with varying degrees of seeded damage.The experimental setup and methodology are described in the dissertation. Additional information about the respective datasets is listed in the README.md file.

60 Global export shipment records of Vibration with prices, volume & current Buyer's suppliers relationships based on actual Global export trade database.

Note: Due to the data storage limitation, our dataset is divided into three subsets for each bearing type. This subset includes the data collected from the tapered roller bearing (NTN 30204).

This dataset provides vibration data collected under various fault conditions, including compound faults, and multiple domain environments. The faults include three single-bearing faults, seven single rotating component faults, and 21 compound faults. The domain configurations are categorized into the rotating speed, bearing type, and sampling rate. The data were collected for 160 seconds at an 8 kHz sampling rate and 80 seconds at a 16 kHz sampling rate, resulting in a uniform sample length of 1,280,000 for each raw vibration signal.

The data files are organized in a hierarchical directory structure. The top-level directories are based on the sampling rate (8 kHz and 16 kHz). Each sampling rate directory has subdirectories for six rotating speeds (600, 800, 1,000, 1,200, 1,400, and 1,600 RPM). Each rotating speed subdirectory contains 32 files collected under different fault conditions.

Data samples are stored in binary MATLAB (MAT) file. The naming convention of each file follows the format comprising five properties: {rotating component condition}_{bearing condition}_{sampling rate}_{bearing model}_{rotating speed}.mat.

The fault conditions are denoted by one capital letter, and unbalance and misalignment faults include three severity levels, where a higher number indicates that a more significant fault occurs. Available values of each property in the file name are as follows: 1. Rotating component condition - ‘H’: healthy (no severity level) - ‘M’: misalignment (severity level 1-3) - ‘U’: unbalance (severity level 1-3) - ‘L’: looseness (no severity level) 2. Bearing condition - ‘H’: healthy - ‘B’: ball fault - ‘IR’: inner race fault - ‘OR’: outer race fault 3. Sampling rate - ‘8’: 8 kHz - ‘16’: 16 kHz 4. Bearing model - ‘30204’: bearing model for H, B, IR, and OR conditions 5. Rotating speed - ‘600’, ‘800’, ‘1000’, ‘1200’, ‘1400’, or ‘1600’: numbers represent RPM.

The data are available in two formats: 1-D raw vibration signal and 2-D spectrogram. These time and time-frequency domain data are stored in separate fields of a MAT file. Data fields in each MAT file are as follows: 1. ‘Data’: raw vibration signal (unit: g [9.80665 m/s2]). 2. ‘Spectrogram’: spectrograms (unit: dB scale magnitude). 3. ‘STFTFreq’: frequency instant vector of the spectrogram (unit: Hz). 4. ‘STFTTime’: time instant vector of the spectrogram (unit: seconds).

For each data file, 78 spectrograms with a size of 128 x 128 were generated by the short-time Fourier transform (STFT) method with the Kaiser window function. In doing so, raw vibration data were sliced into 16,384-length segments without overlapping. Each segment was then converted to a spectrogram with a window size of 192, an FFT size of 256, and an overlap size of 65.

Elkem Facility

The facility specializes in producing ferrosilicon (FeSi) and ferrosilicon magnesium (FSM) master alloys. Elkem Bjølvefossen is among the world’s largest producers of FSM. Three reduction furnaces deliver the base metal which is then alloyed and refined to the right quality of FeSi or FSM. These alloys are important additives in the manufacturing of steel products. Silicon in the form of FeSi is used to remove oxygen from the steel and as an alloying element to improve the final quality of the steel. Silicon increases strength and wear resistance, elasticity, i.e., spring steels, scale resistance, and heat resistant steels and lowers electrical conductivity and magnetostriction.

After tapping and refining, the ferro-alloys are crushed to grains ranging from 1 mm to 25 mm in size. Consumers of FeSi and FSM have strict requirements for particle size, related mainly to the chemical kinetics of their refining and alloying processes. For this reason, the crushed material is separated in sieves and packaged by particle size before shipment. Two lattice gratings inside the Mogensen shaker separate the material according to required particle size.

The subject of the present study is a mechanical shaker platform containing one or more such sieves. The shaker is a Mogensen S0556 that was installed in 1996 in Bjølvefossen and is no longer produced in this type. This device is powered by two counter-rotating 1.2-horsepower AC motors operating at 960 RPM. Together with the spring suspension, these cause an elliptical motion that both transports and scatters the incoming material across the sieve. The shaker is engineered so that the motion transitions from a slanted ellipse at the in-feed to nearly linear at the output.

Vibration Data

Vibration data from two sensors. Each sensor measures acceleration in three axes with three different ADCs.

ERP and MES data

Manufacturing Execution System (MES) data as well as process data from the Enterprise Resource Planning (ERP) is given. It is providing information about the material that is currently being produced as well as the data from the scales from the material packing station where the bags with completed production were packed. MES data has a resolution of 5 seconds and the process data from ERP has a resolution of roughly 10 minutes. This operational data is meant to provide insight into the current state and throughput of the facility and will serve as labels for the correlation analysis with the vibration data.

Due to the influence of coal rock shape, hardness, working environment and other factors in the cutting process of cantilever roadheader, the cutting head will produce irregular and violent vibration. As the rotary table of key stress components, its operation process stability, dynamic reliability and life affect the cutting efficiency and cutting stability of cantilever roadheader. In order to study the vibration characteristics of the rotary table in the cutting process, firstly, based on the theory of spatial force analysis and calculation, the spatial mechanical model of the rotary table of the cantilever roadheader is established. By solving the balance equation of the rotary table force system, the variation law of the load at the hinge ear of the rotary table with the cutting pitch angle and the horizontal angle is obtained. Secondly, based on the path transfer analysis method of working condition, the vibration data of cutting head, cutting cantilever, cutting lifting and rotary hydraulic cylinder under stable cutting condition are taken as input signals. By constructing the transfer path analysis model of rotary table working condition, the synthetic vibration of rotary table in cutting process is simulated, and the main vibration source of rotary table is determined. Then, the vibration contribution and contribution degree of each vibration excitation point to the hinge ear of rotary table are studied. By building a cutting test bench, the vibration response of rotary table in cutting process is tested to verify the correctness of the theoretical model.Thirdly, based on the frequency domain analysis method of random vibration fatigue life, combined with the S-N curve of the rotary table, the PSD curve at the maximum stress of the rotary table is obtained by modal excitation method, and the load data is imported into ANSYS nCode software to obtain the life cloud diagram and damage cloud diagram of the rotary table, and then the fatigue life of the rotary table under symmetrical cyclic load is solved. Finally, based on the response surface optimization analysis method, the maximum stress and maximum deformation of the rotary table are taken as the optimization objectives, and the aperture of each hinge ear of the rotary table is taken as the optimization variable. Based on Design Expert, a second-order regression model is established to realize the multi-objective optimization design of the key stress parts of the rotary table in the cutting process. The simulation results show that under the same cutting conditions, the maximum stress of the optimized rotary table is reduced by 15.82% year-on-year, and the maximum deformation is reduced by 24.70% year-on-year. The optimized rotary table structure can better adapt to the cutting process, which is beneficial to improve the service life of the rotary table and enhance its operation stability. The research results are beneficial to enrich the relevant research theory in the field of rotary table vibration of cantilever roadheader, and are beneficial to improve the service life of the rotary table and the efficiency of tunneling and mining.

This database includes series of measurements of the structure's response taken in six-dimensional space using two 6D sensors, coaxially positioned in two different ways on either side of the investigated panel-to-panel connection. Presented data related to ten different states of joints, two load levels, and two type of input signal (short impulse and sweep signal with duration 0.5 seconds with frequency range from 10 Hz to 2000 Hz). In the "Read_me_first.pdf" is described the experiment, the format of .csv files names and files' structure. Used materials, methods and results for the case of static load equal to 151.8 kg with sweep-type input signal, and T2 scheme of sensors placement is described in Kurtenoks, V.; Kurajevs, A.; Buka-Vaivade, K.; Serdjuks, D.; Lapkovskis, V.; Mironovs, V.; Podkoritovs, A.; Vilnitis, M. The Quality Assessment of Timber Structural Joints Using the Coaxial Correlation Method. Buildings 2023, 13, 1929. https://doi.org/10.3390/buildings13081929