Weighted LASSO variable selection for the analysis of FTIR spectra applied to the prediction of engine oil degradation

Pfeiffer, Pia; Ronai, Bettina; Vorlaufer, Georg; Dörr, Nicole; Filzmoser, Peter

doi:10.1016/j.chemolab.2022.104617

Cited by 9 publications

(4 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To decrease friction power loss and increase engine efficiency, the clearance in the piston is frequently filled with lubricant [23]. The engine oil condition monitoring is instrumental in explaining the lubricant's state of health [24,25]. It is observed that Ashok kumar S et al the piston's lubrication will be more affected by the connecting rod's inertia when the engine is operating quickly [26].…”

Section: Literature Reviewmentioning

confidence: 99%

Comparative study of vibration signatures by correlating them with engine oil degradation for diesel and blended fuel DBD20 in a CI engine

2023

IJATEE

View full text Add to dashboard Cite

The use of biofuels as a sustainable alternative to fossil fuels has garnered significant attention. However, several factors, including oil degradation, can impact the effectiveness of biofuels. It is recommended to regularly change and maintain the oil to minimize the impact of oil degradation on biofuel performance. This can be achieved by monitoring the engine's vibration signature without draining any oil from the engine. This study aimed to investigate the correlation between engine vibration signatures and the degradation of lubricating oil. A 5 horse power (HP) compression ignition (CI) engine fuelled with a mixture of 80% diesel and 20% biodiesel, referred to as diesel biodiesel (DBD)20, was used for the study. The engine operated at a steady load, equivalent to 50% of its rated power at 1500 rpm. The vibration signatures, including amplitude and frequency of vibration in the longitudinal direction, were recorded at regular intervals of 2 hours using an accelerometer placed on top of the engine head. Samples of used lubricating oil were collected every 20 hours of operation, and properties such as viscosity, density, soot content, and moisture were measured and compared with the vibration signatures. The analysis revealed distinguishable differences in vibration signatures and lubricating oil properties between diesel and DBD fuelled engines. The findings indicated a significant decline in oil quality and corresponding vibration signatures after 80 hours of engine operation. Therefore, it is recommended to replace the engine oil every 80 hours of engine run for stationary field engines.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Comparative study of vibration signatures by correlating them with engine oil degradation for diesel and blended fuel DBD20 in a CI engine

2023

IJATEE

View full text Add to dashboard Cite

show abstract

“…Shen et al [15] proposed a spectral identification method by combining a generalized interaction validation criterion with a common variable selection method. Pfeiffer et al [16] proposed a weighted least absolute shrinkage and selection operator (LASSO) variable selection method of FTIR spectroscopy and used it for engine oil degradation prediction. Adiani et al [17] developed a model for FTIR spectral analysis of fresh-cut pineapple based on an Artificial Neural Network (ANN) and partial least squares.…”

Section: Introductionmentioning

confidence: 99%

Quantitative analysis method for the Fourier transform Infrared spectroscopy of gases

Li,

Tang,

Chen

et al. 2024

International Academic Conference on Optics and Photonics (IACOP 2023)

View full text Add to dashboard Cite

Fourier transform infrared (FTIR) spectroscopy can be used for fast, sensitive, and non-destructive quantitative analysis of gases. It is essential to extract useful information from the spectra accurately. Therefore, in this paper, a method for analyzing the FTIR spectra of gases is proposed. Savitzky-Golay convolutional smoothing is used to eliminate the noise in the spectra. A modified adaptive smoothing parameter penalized least squares method is used to eliminate baseline drift. Competitive adaptive reweighted sampling is used to select feature variables. Partial least squares regression was used to model the quantitative analysis. The infrared spectra of methane and ethane at different concentrations are obtained experimentally to verify the performance of the proposed method. The experimental results show that the proposed method can achieve smooth denoising and baseline correction of the raw spectra without losing spectral information. The screened feature variables reduce the data volume of the spectra and improve the analysis efficiency. The coefficient of determination for cross-validation (Q 2 ) of the established quantitative analysis model was 0.99995 for the regression result of methane concentration and 0.99906 for the regression result of ethane concentration. The proposed analytical method can improve the accuracy of the FTIR spectral analysis of gases. Meanwhile, the method can also be used in other fields, such as Raman spectroscopy, laser-induced spectroscopy, and mass spectrometry.

show abstract

“…15 The Fourier transform-infrared (FT-IR) spectroscopy analyses the oxidation index as the major parameter in the used oil analysis procedure. [16][17][18][19] Similarly, the oxidation level of deteriorated engine oil can be predicted by the ultravioletvisible (UV-Vis) micro-volume spectrometer instrument. 15 Also, various latest handy instruments were developed for degradation analysis.…”

Section: Introductionmentioning

confidence: 99%

Engine oil quality deterioration estimation using an integrated sensory system

Shinde

Bewoor

Kumar

et al. 2022

Proceedings of the Institution of Mechanical Engineers, Part E:

View full text Add to dashboard Cite

Engine oil degradation impacts the operation and performance of an internal combustion engine. As a result, it is crucial to compare the degradation level of engine oils, with a particular emphasis on kinematic viscosity, oxidation, nitration, and critical oil testing characteristics. Suppose engine oil changes too soon without first calculating its remaining usable life. In that case, it wastes already scarce resources and has an unfavourable environmental influence. Engine performance may suffer if oil is changed too late and is of poor quality. In the current research, oil testing is performed on vehicles due to maintenance to find the best moment for changing engine oil. Oil samples were taken randomly from cars that came to an authorized service facility for maintenance, comprising a wide range from the first to the fifth servicing. Oil samples were initially evaluated in a laboratory using a viscometer and Fourier transform-infrared spectroscopy in conformity with industry standards. The samples were then evaluated using an integrated sensor system developed and built by the authors. The determination coefficient R2 = 0.97 showed a significant positive association between major engine oil degradation characteristics such as kinematic viscosity, oxidation, and nitration at reasonable sensitivity. Approximately 8% of the total gathered samples were useable. The research identifies several oil degradation sensor systems that give low-cost, on-site convenient options for oil condition monitoring and predicting the remaining usable life of engine oil.

show abstract

Weighted LASSO variable selection for the analysis of FTIR spectra applied to the prediction of engine oil degradation

Cited by 9 publications

References 22 publications

Comparative study of vibration signatures by correlating them with engine oil degradation for diesel and blended fuel DBD20 in a CI engine

Comparative study of vibration signatures by correlating them with engine oil degradation for diesel and blended fuel DBD20 in a CI engine

Quantitative analysis method for the Fourier transform Infrared spectroscopy of gases

Engine oil quality deterioration estimation using an integrated sensory system

Contact Info

Product

Resources

About