In order to rise to global challenges such as climate change, environmental pollution and conservation of resources, internal combustion engine manufacturers must meet the requirements of substantially reduced emissions of CO2 and other greenhouse gases, zero pollutant emissions and increased durability. This publication addresses approaches that can help improve engine efficiency and durability through the engine crankshaft bearing and lubricant system. An understanding of the operating behavior of key engine components such as crankshaft main bearings in fired engine operation allows the development of appropriate tools for bearing condition monitoring and condition-based maintenance so as to avoid critical engine operation and engine failure as well as unnecessary engine downtime. Such tools are especially important when newly developed low viscosity oils are employed. Though these oils have the potential to reduce friction and to increase engine efficiency, their use comes with a higher risk of accelerated bearing wear and ultimately bearing failure. The specific target of this paper is therefore to obtain detailed knowledge of the influence of engine operating parameters and oil parameters on crankshaft main bearing temperature behavior and engine friction behavior in fired operation as a starting point for condition monitoring and condition-based maintenance approaches and as a basis for improving the bearing and lubricant system as a whole. To achieve this target, experimental investigations were carried out on an engine test bed employing an in-line six-cylinder heavy-duty diesel engine with a displacement of approximately 12.4 dm3. Defined and accurately reproducible engine operating conditions were ensured by comprehensive external conditioning systems for the coolant, lubricating oil, fuel, charge air and ambient air. Since the focus was on investigating the bearing and friction behavior by means of the base engine, several auxiliary systems were removed; these included the lubricating oil and coolant pumps, the front-end accessory drive and the generator. Each crankshaft main bearing was instrumented with a thermocouple on the back of its bottom bearing shell to measure the bearing temperature. Piezoelectric pressure transducers were applied to all six cylinders in order to facilitate the accurate determination of the friction mean effective pressure (FMEP) based on indicated and brake mean effective pressures. The variations in engine operating parameters (engine speed and torque) mainly serve as a reference for the variations in oil parameters. They confirm the existing knowledge that engine speed has a significant impact on FMEP and bearing temperature while the impact of engine torque is comparatively low. The variations in oil parameters reveal that lowering the viscosity grade from SAE 10W-40 to 5W-20 leads to a decrease in both bearing temperature and FMEP, which can be explained by the lower fluid friction in the bearing system and the increased mass flow and convective heat transport with the lower viscosity oil. An increase in the lubricating oil temperature at the engine inlet leads to a significant increase in bearing temperature and a decrease in FMEP; the former is explained by the increased heat influx from the lubricant oil, and the latter is caused mainly by the temperature dependency of the lubricant oil viscosity and its impact on fluid friction. The impact of engine oil inlet pressure on bearing temperature and FMEP is generally found to be low. The results will serve as the basis for future research that includes approaches to condition monitoring and evaluating improved engine operating strategies with regard to oil parameters.

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.

Modo de acesso: World Wide Web Inclui bibliografia 1. Educação 2. Matemática 3. Química 4. Física I. Título CDD-370 O conteúdo dos artigos e seus dados em sua forma, correção e confiabilidade são de responsabilidade exclusiva dos seus respectivos autores www.poisson.com.br

Todo o conteúdo deste livro está licenciado sob uma Licença de Atribuição Creative Commons. Atribuição 4.0 Internacional (CC BY 4.0). O conteúdo dos artigos e seus dados em sua forma, correção e confiabilidade são de responsabilidade exclusiva dos autores. Permitido o download da obra e o compartilhamento desde que sejam atribuídos créditos aos autores, mas sem a possibilidade de alterá-la de nenhuma forma ou utilizá-la para fins comerciais.