An approach of classification and parameters estimation, using neural network, for lubricant degradation diagnosis

Condition monitoring and machine status classification are of great practical importance in the manufacturing industry as it provides online updates on the state of the machine, avoiding loss of production and minimizing the probability of generating catastrophic damage to the machine. In this paper, the classification of conditions is based on the processing of information using wavelets based on the results of the monitoring and the data collected during such an action, measuring the characteristics of the lubricating oil over some time sufficient to produce a time series of results. In this paper, the classification system is tested and validated using observation sequences based on the maximum wavelet distribution obtained from the collected signals, monitoring the state of the lubricating oil, to define and diagnose singularities in time series.

show abstract

A neural networks approach of process fault diagnosis using time series collected data through oil condition monitoring

Grebenişan

Salem

Bogdan

et al. 2019

IOP Conf. Ser.: Mater. Sci. Eng.

View full text Add to dashboard Cite

In this paper was used the data set collected in a research project between private companies from Romania and Italy, for the development of a basic approach of artificial neural network techniques, as an application in Matlab, aiming to detect the degree of degradation of oil, an automated installation, measuring online the physicochemical properties of the oil. Physical-chemical parameters measured lead to the creation of generous time series, but accessible by numerical and statistical calculation, for the application of artificial intelligence techniques. Applying neural network techniques to parameters that measure oil degradation, oxidation and humidity have generated the results of this work. The main function of monitoring the state of operation of a mechanical system, machine, or plant is to provide the almost correct diagnosis of the machine’s state and rate of change so that preventive measures can be taken at a given time.

show abstract

An approach of classification and parameters estimation, using neural network, for lubricant degradation diagnosis

Cited by 3 publications

References 10 publications

Forecasting of Overloading Volumes in Transport Systems Based on the Fuzzy-Neural Model

Forecasting of Overloading Volumes in Transport Systems Based on the Fuzzy-Neural Model

A brief assessment of outliers and malfunctions detecting techniques with an application on lubricant condition monitoring

A neural networks approach of process fault diagnosis using time series collected data through oil condition monitoring

Contact Info

Product

Resources

About