LASPI: Detection and diagnostics of gearbox faults (2023)

Related person : Abdenour Soualhi [2]
[1] : Franche-Comté Electronique Mécanique Thermique et Optique - Sciences et Technologies (UMR 6174) (Université de Franche-Comté)
[2] : Laboratoire d'Analyse des Signaux et des Processus Industriels
[3] : Laboratoire Génie de production
[4] : Laboratoire Ampère
Description :
Dataset of current, voltage, and vibration measurements of an electromechanical driving system. The system is a three-phase asynchronous motor that drives a gearbox. The gearbox is composed of bearings and gears that are susceptible to fail. Seven experiments corresponding to different states of each component are performed. Each health state is performed under different operating conditions.
Disciplines :
computer science, artificial intelligence (engineering science), engineering, electrical & electronic (engineering science), engineering, industrial (engineering science), engineering, mechanical (engineering science), engineering, multidisciplinary (engineering science)

General metadata

Data acquisition date : 17 May 2017
Data acquisition methods :
  • Experimental data :
    The LASPI test bench is used for monitoring bearing and gear faults of a gearbox. It is composed of a three-phase inverter to supply and control a three-phase induction motor of 1.5 kW. This latter motor drives a gearbox on which the components of the study are positioned. Also, there is an electromagnetic brake connected to the gearbox. This latter component is used to simulate a load on the motor.

    In detail, the gearbox has three shafts, the input shaft, the intermediate shaft, where the studied components are placed, and the output shaft. The input shaft, which is directly connected to the rotating shaft of the motor, has one gear and two bearings installed on each side of the gearbox. The gear is installed at the brake side and contains 29 teeth. The two bearings contain 9 rolling balls with a diameter of 0.3125 inch, a pitch diameter of 1.5157 inch, and a contact angle equal to 0. Besides, the intermediate shaft has two bearings, with the same characteristics as the ones of the input shaft, and two gears. The first gear installed on the motor side has 36 teeth while the gear installed in the brake side has 100 teeth. Finally, the output shaft which is directly connected to the electromagnetic brake has the same bearings as the previous ones and a gear installed on the motor side with 90 teeth.

    This test bench is equipped with different sensors and an acquisition system to collect the monitoring data. It has three current and voltage sensors, placed at the output of the inverter that supplies the motor, and an accelerometer placed as near as possible to the studied components of the intermediate shaft. The data acquisition is performed by National Instrument 9234 cards.

    All acquisitions are performed in the permanent mode over a period of 10 seconds with a sampling frequency of 25.6 kHz. The data are stored in .csv files with 7 columns. The columns 1 to 3 represent the three-phase current signals with a reduction gain of 100. Column 4 represents the vibration signal with a sensitivity of 100 mV/g. The lats columns, from 5 to 7, represent the voltage signals of the three phases with a reduction gain of 200.

    Based on the test bench instrumentation mentioned above, 84 experiments were conducted to monitor separately the bearing and the gear faults, as well as their combination. In detail, 7 health states are studied: healthy states of the bearing and the gear, a gear surface fault, a gear half-tooth breakage fault, a bearing inner ring fault, a bearing outer ring fault, combined faults between the gear surface fault and the bearing inner ring fault, and finally combined faults between the gear half-tooth breakage fault and the bearing outer ring fault. In addition to these health states, each state is tested under three different rotating speeds, 1500 rpm, 2100 rpm, and 2700 rpm, and four load levels, 0%, 25%, 50%, and 75% on each speed and each health state.

    Two .pptx files containing the test bench figure and its scheme can be found in the LASPI dataset repository by clicking on "ACCESS TO DATA" on the home page of the site.
Update periodicity : no update
Language : English (eng)
Formats : text/csv
Audience : University: master, Research, Informal Education
Publications :
  • Lo, N. G., Soualhi, A., Frinì, M., & Razik, H. (2018, May). Gear and bearings fault detection using motor current signature analysis. In 2018 13th IEEE Conference on Industrial Electronics and Applications (ICIEA) (pp. 900-905). IEEE. (doi:10.1109/ICIEA.2018.8397840)
  • Soualhi, M., Nguyen, K. T., Soualhi, A., Medjaher, K., & Hemsas, K. E. (2019). Health monitoring of bearing and gear faults by using a new health indicator extracted from current signals. Measurement, 141, 37-51. (doi:10.1016/j.measurement.2019.03.065)
  • Soualhi, M., Nguyen, K. T., & Medjaher, K. (2020). Pattern recognition method of fault diagnostics based on a new health indicator for smart manufacturing. Mechanical Systems and Signal Processing, 142, 106680 (doi:10.1016/j.ymssp.2020.106680)
  • Gougam, F., Afia, A., Soualhi, A., Touzout, W., Rahmoune, C. & Benazzouz, D. (2024). Bearing faults classification using a new approach of signal processing combined with machine lerning alogorithms. J Braz. Soc. Mech. Sci. Eng. 46, 65 (doi:10.1007/s40430-023-04645-5)
Collection :
Additional information :
The platform is located at Signal and Industrial Process Analysis Laboratory, Roanne, France.
Record created 6 Mar 2023 by Moncef Soualhi.
Last modification : 5 Apr 2024.
Local identifier: FR-13002091000019-2023-03-06.


dat@UBFC is a metadata catalogue for research data produced at UBFC.

Terms of use
Université de Bourgogne, Université de Franche-Comté, UTBM, AgroSup Dijon, ENSMM, BSB, Arts des Metiers