The research focused on the elaboration of the Condition-Based Maintenance (CBM) for the optimization of Smart Manufacturing Processes (SMP) using three types of condition monitoring (CM). The paper presents some considerations regarding the Smart Manufacturing Processes (SMP), especially focused on the Additive Manufacturing (AM) process, by Fused Deposition Modelling (FDM) technology and the way in which the CM and mathematical and probabilistic models can be used, for achieving CBM. The experiments focused on testing three different types of CM: vibration (by vibrometers), sound (by sound level meters) and temperature (by thermal camera and infrared thermography). The experiments and results were analysed, data were processed and a probabilistic model was designed, based on statistical methods, using features/key indicators and their thresholds values. Furthermore, a specific model based on Bayesian network was developed, for achieving CBM of the SMP, specifically to the AM/FDM process. This technique and approach can represent a successful integration of a large number of data monitoring sets and complex modelling and analysis capabilities which can lead in the end to an optimisation of the SMP.
It is known that supported ball bearings have great effects on the vibrations of the gear transmission system, above in all the presence of local faults as well as the crack growths. For this purpose, this paper focuses on shock and vibration crack growth diagnostic of ball bearing using vibration analysis. Our work is devoted first to a study the static behaviour of the ball bearing by determining the stress, strain and displacement, then its dynamic behaviour by determining the first four natural frequencies. Secondly, a dynamic analysis study of the bearing was carried with defects as a function of crack size and location. The obtained results clearly show that the natural frequencies decrease in a non-linear way with the growth of the length of the crack, on the other hand the stress increases with the presence of the singular points of the crack. Finally, this residual decrease in natural frequencies can be used as an indicator of the state of failure, as well as a parameter used for the diagnosis and screening, and to highlight the fatigue life of the bearing
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.