Browsing by Subject "Predictive maintenance"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Publication
    Open Access
    Dynamic management of periodicity between measurements in predictive maintenance
    (Elsevier, 2023-03-16) Gómez de León Hijes, Félix; Sánchez Robles, J.; Martínez García, F. M.; Alarcón García, Mariano; Ingeniería de la Información y las Comunicaciones
    In practice, on a large number of machines in industrial plants, predictive maintenance relies on periodic measurements to diagnose the condition of the equipment, rather than continuous monitoring of vibrations. In those cases, choosing an appropriate period between measurements is the key to success. Setting a long period implies taking a serious risk of breakdown, while a very short time interval between measurements can unnecessarily increase the costs of the maintenance plan. This work shows a methodology to determine and manage this Time Interval Between Measurements (TIBeM) dynamically adapted to each machine and situation. Depending on the criticality of each machine and its reliability, more specifically, its present diagnosed functional condition and the history of failures and measurements, the most appropriate TIBeM is recalculated each time a new measurement and diagnostic is performed. The described method has been implemented and validated in a large process plant and has led to a considerable improvement in costs and the management of its predictive maintenance plan.
  • Thumbnail Image
    Publication
    Open Access
    Method for establishing reference limit values for vibration measurements in machines
    (Elsevier, 2025-07-12) Sánchez Robles, J. ; Gómez de León Hijes, Félix; Pastor Más, A. R.; Martínez García, F. M.; Ingeniería de la Información y las Comunicaciones; Facultades de la UMU::Facultad de Química
    When measuring, the accuracy of the measurement is as important as the reference level used. There is little point in taking very accurate measurements if the reference levels used to evaluate them are inappropriate. Therefore, when measuring vibrations in rotating equipment, the general rule is to use reference standards, such as ISO 20816, or set alarm levels according to the manufacturer’s recommendations. However, although setting specific vibration reference levels for each machine is recommended by international standards, there is no proposed method, or mathematical support, for doing so in either the standards or the related literature. This situation leads, in practice, to the use of general and, therefore, non-specific boundaries to assess the functional status of each particular machine (good, alert, alarm, etc.) and, consequently, to many false positives or, even worse, false negatives when detecting machine failures. The purpose of this study, and a novelty in this field, is precisely to present a method that allows statistically determining the most appropriate vibration reference levels for each rotating machine. Using a vibration database with measurements taken over twelve years for hundreds of machines, this study demonstrates that the vibration measurements of a rotating machine can be statistically modelled, with an accuracy close to 100 %, using the Rayleigh Distribution Function, which allows successive vibration reference levels to be formulated between functional categories from the mode and standard deviation of said statistical distribution function. The final section presents an example of the implementation of this methodology in an industrial plant.