A review on lubricant condition monitoring information analysis for maintenance decision support

Wakiru, James; Pintelon, Liliane; Muchiri, Peter; Chemweno, Peter

doi:10.1016/j.ymssp.2018.08.039

Cited by 120 publications

(86 citation statements)

References 180 publications

(158 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…− the limits themselves are more proactive than predictive, which results from the actual maintenance and repair activities of machines and equipments. Proactive signals are often critical to determine the suitability and quality of measured values [6,14,15,23]. In practice, the following are used:…”

Section: Resultsmentioning

confidence: 99%

Lubricant Analysis as the Most Useful Tool in the Proactive Maintenance Philosophies of Machinery and its Components

Kučera

Kopčanová

Sejkorová

2020

Management Systems in Production Engineering

View full text Add to dashboard Cite

Condition monitoring and fault diagnosis of engineering systems are critical for the stable and reliable operation in various areas as mobile technology (primarily agricultural, forestry, mining and construction machinery), railways, airlines and large fleets. Thus, to achieve a satisfactory level of reliability for the life of a machine, proactive maintenance strategy is the only key. This means that the application of classical reliability methods suitable for components with sudden failures can be complemented by technical diagnostic methods which have the potential to provide the information about the system condition. In this article we focus on the diagnostic signal related to the used oil – tribodiagnostic measures and is an interesting theoretical item related to the evaluation of the quality of lubricants in the aspect of operation. This is because the oil is in direct contact with single parts of the assessed technical systems. Results tests were reviewed and derived from various parameters of lubricants and their limits that highlight the condition and state of the lubricants under varying categories which include, physiochemical, elemental (wear), contamination and additive analysis.

show abstract

Section: Resultsmentioning

confidence: 99%

Lubricant Analysis as the Most Useful Tool in the Proactive Maintenance Philosophies of Machinery and its Components

Kučera

Kopčanová

Sejkorová

2020

Management Systems in Production Engineering

View full text Add to dashboard Cite

show abstract

“…Clustering aims to seek natural groupings in the data based on the similarity of individual components or objects, such that the objects of the same group, or cluster, are more similar than different groups [48][49][50]. CA is considered a principal task of data exploration, is a common technique for statistical analysis and chemometric approaches, and is widely used in molecular spectroscopy [51][52][53]. The results of CA were intended to elucidate the compound structure and compositional changes of SHALOs resulting from oxidative high-temperature degradation, allowing detection of the degradation stages of SHALOs and signaling of the need for an oil change when warranted by the oil conditions [54].…”

Section: Ca Of the Oil Samplesmentioning

confidence: 99%

“…for statistical analysis and chemometric approaches, and is widely used in molecular spectroscopy [51][52][53]. The results of CA were intended to elucidate the compound structure and compositional changes of SHALOs resulting from oxidative high-temperature degradation, allowing detection of the degradation stages of SHALOs and signaling of the need for an oil change when warranted by the oil conditions [54].…”

Section: Ca Of the Oil Samplesmentioning

confidence: 99%

Effect of Temperature on the Composition of a Synthetic Hydrocarbon Aviation Lubricating Oil

et al. 2020

View full text Add to dashboard Cite

Synthetic hydrocarbon aviation lubricating oils (SHALOs) gradually degrade over time when subjected to high temperatures, resulting in their composition and properties varying over the operation lifetime. Therefore, understanding the SHALO degradation properties by elucidating the mechanism on a molecular level, as a function of high temperature, is of interest. A SHALO was subjected to thermal treatment (TT) at 180, 200, 230, 250, 270, or 300 °C for 2 h. The chemical compositions of six TT samples and one fresh oil were analyzed by fourier transform infrared F spectroscopy, advanced polymer chromatography, and gas chromatography/mass spectrometry. Furthermore, the physicochemical properties, such as kinematic viscosity, pour point, and acid number, of seven samples were determined. The oil samples were grouped by cluster analysis (CA) using a statistical method. The SHALO was identified to comprise 20 functional groups, including comb-like alkanes, long-chain diesters, amines, phenols, and other compounds. TT at <230 °C caused partial cracking of the SHALO base oils, with a concomitant change in the antioxidant content and type, and the polycondensation reactions were dominant. The observed antioxidant changes were not obvious from TT at >230 °C. A large number of small-molecule compounds were detected, including n-alkanes and olefins. TT at 250 °C was shown to be an important threshold for the kinematic viscosity, pour point, and acid number of the samples. Below 250 °C, the sample properties were relatively stable; but at elevated TT temperatures (>250 °C), the properties were observed to dramatically degrade. As the sample color was highly sensitive to temperature, the TT temperature induced rapid and significant color changes. The CA analysis results for the oil compounds at the molecular level were in good agreement with observed changes in the physicochemical properties at the macro level.

show abstract

“…By analyzing the concentration, size, shape, and composition of the wear particles, we can identify the class of wear particles, and then reveal the degree and mechanism of wear. Therefore, Wear particles monitoring and analysis has been deemed as a powerful technology for machine wear assessment [2] [3]. In order to identify the classes of wear particles based on their morphological characteristics, some methods have been proposed to obtain the characteristics of the wear particles [4].…”

Section: Introductionmentioning

confidence: 99%

“…(2) The CDCNN can classify the classes that have appeared in the training set, and can identify new classes that have not been seen in the training set without retraining the model. (3) The structure of the model has been simplified, the model parameters are less than the previous convolutional neural network model, which can reduce the hardware requirements and improve the model training efficiency.…”

Section: Introductionmentioning

confidence: 99%

CDCNN: A Model Based on Class Center Vectors and Distance Comparison for Wear Particle Recognition

Zhang

Fan

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Mechanical wear failure is the main cause of device failure, and wear particles can be utilized to judge the degree and mechanism of mechanical wear. However, with the further study by researchers, the classes of wear particles are likely to increase. As the number of classes increases, it is necessary to reconstruct and retrain the previous automatic recognition model of wear particles. To solve this problem, a novel convolutional neural network (CNN) model based on class center vectors and distance comparison, called CDCNN, is proposed in this study. The model can not only accurately classify the particles that appear in the training set, but also identify the new classes that were not seen during training. This work can show its advantages when the classification criteria for wear particles have changed or new classes of particles have appeared. We applied the proposed model and the previous convolutional neural network model for the wear particle dataset, and compared the classification results of the models. The comparison results show that the model has strong classification ability and generalization ability.

show abstract

A review on lubricant condition monitoring information analysis for maintenance decision support

Cited by 120 publications

References 180 publications

Lubricant Analysis as the Most Useful Tool in the Proactive Maintenance Philosophies of Machinery and its Components

Lubricant Analysis as the Most Useful Tool in the Proactive Maintenance Philosophies of Machinery and its Components

Effect of Temperature on the Composition of a Synthetic Hydrocarbon Aviation Lubricating Oil

CDCNN: A Model Based on Class Center Vectors and Distance Comparison for Wear Particle Recognition

Contact Info

Product

Resources

About