Data-Driven Sliding Bearing Temperature Model for Condition Monitoring in Internal Combustion Engines

Abstract

Condition monitoring of components in internal combustion engines is an essential tool for increasing engine durability and avoiding critical engine operation. If lubrication at the crankshaft main bearings is insufficient, metal-to-metal contacts become likely and thus wear can occur. Bearing temperature measurements with thermocouples serve as a reliable, fast responding, individual bearing-oriented method that is comparatively simple to apply. In combination with a corresponding reference model, such measurements could serve to monitor the bearing condition. Based on experimental data from an MAN D2676 LF51 heavy-duty diesel engine, the derivation of a data-driven model for the crankshaft main bearing temperatures under steady-state engine operation is discussed. A total of 313 temperature measurements per bearing are available for this task. Readily accessible engine operating data that represent the corresponding engine operating points serve as model inputs. Different machine learning methods are thoroughly tested in terms of their prediction error with the help of a repeated nested cross-validation. The methods include different linear regression approaches (i.e., with and without lasso regularization), gradient boosting regression and support vector regression. As the results show, support vector regression is best suited for the problem. In the final evaluation on unseen test data, this method yields a prediction error of less than 0.4 ∘C (root mean squared error). Considering the temperature range from approximately 76 to 112 ∘C, the results demonstrate that it is possible to reliably predict the bearing temperatures with the chosen approach. Therefore, the combination of a data-driven bearing temperature model and thermocouple-based temperature measurements forms a powerful tool for monitoring the condition of sliding bearings in internal combustion engines.

Gas Turbine Bearing Temperature Monitoring via Regression Modelling

“…Jeng and Huang [17] predicted the temperature rise of a ball bearing using a computer code that compares favourably with experimental data. In a similar trend, Laubichler [18] worked on data driven model for temperature monitoring of a sliding bearing in an internal combustion engine. Regression models like support vector, regression with Lasso boosting and without Lasso boosting were tried and the researcher concluded that the comparative studies of the models shows that the support vector regression model gave the best prediction based on the fact that it had the least root mean square error (RMSE).…”

AI techniques for evaluating misaligned journal bearing performance: An approach beyond the Sommerfeld number

“…On a similar approach Moosavian et al (2013) 10 compared two different methods, k-nearest neighbor and Artificial Neural Networks, to diagnose problems in ME journal bearings. Later, Laubichler et al 11 suggested a combination of data-driven bearing temperature model and thermocouple-based temperature measurements to form a powerful tool for monitoring the condition of sliding bearings in internal combustion engines. Kumar et al 12 used feed-forward neural networks to predict the minimum film thickness in plain journal bearings.…”