Multi-plate clutches play safety-critical roles in many applications. For this reason, correct functioning and safe operation are essential. Spontaneous damages are particularly critical because the failure of the clutch can lead to a failure of the system. Such damage mainly occurs due to very high loads and ultimately very high temperatures. Finite Element Analysis (FEA) enables simulation and prediction of these temperatures, but it is very time-consuming and costly. In order to reduce this computational effort, surrogate models can be created using machine learning (ML) methods, which reproduce the input and output behavior. In this study, various ML methods (polynomial regression, decision tree, support vector regressor, Gaussian process and neural networks) are evaluated with respect to their ability to predict the maximum clutch temperature based on the loads of a slip cycle. The models are examined based on two use cases. In the first use case, the axial force and the speed are varied. In the second use case, the lining thickness is additionally modified. We show that ML approaches fundamentally achieve good results for both use cases. Furthermore, we show that Gaussian process and backpropagation neural network provide the best results in both cases and that the requirement to generate predictions during operation is fulfilled.

In wet clutches, load-independent drag losses occur in the disengaged state and under differential speed due to fluid shearing. The drag torque of a wet clutch can be determined accurately and reliably by means of costly and time-consuming measurements. As an alternative, the drag losses can already be precisely calculated in the early development phase using computing-intensive CFD models. In contrast, simple analytical calculation models allow a rough but non-time-consuming estimation. Therefore, the aim of this study was to develop a methodology that can be used to build a data-driven model for the prediction of the drag losses of wet clutches with low computational effort and, at the same time, sufficient accuracy under consideration of a high number of influencing parameters. For building the model, we use supervised machine learning algorithms. The methodology covers all relevant steps, from data generation to the validated prediction model as well as its usage. The methodology comprises six main steps. In Step 1, the data is generated on a suitable test rig. In Step 2, characteristic values of each measurement are evaluated to quantify the drag loss behavior. The characteristic values serve as target values to train the model. In Step 3, the structure and quality of the dataset are analyzed and, subsequently, the model input parameters are defined. In Step 4, the relationships between the investigated influencing parameters (model input) and the characteristic values (model output) are determined. Symbolic regression and Gaussian process regression have both been proven to be suitable for this task. Lastly, the model is used in Step 5 to predict the characteristic values. Based on the predictions, the drag torque can be predicted as a function of differential speed in Step 6, using an approximation function. The model allows a user-oriented prediction of the drag torque even for a high number of parameters with low computational effort and sufficient accuracy at the same time.

Failures of multi-plate clutches must be reliably excluded due to safety-critical functionalities in the drive train. The main reason for failures of multi-plate clutches due to long-term and spontaneous damage is thermal damage. In this paper, a parameterizable two-dimensional finite element model is developed and validated for damage prevention and for analyzing the thermo-mechanical behavior of a clutch in transient operation. Both numerical verification and validation with experimental results are very good despite the simplifications in the model. Subsequently, the temperature and pressure distribution of the individual friction areas is determined. The results show that the maximum temperatures tend to occur at the outer diameter of the friction area. The pressure distribution is very homogeneous. In a parameter study, the influence of Young’s modulus of the friction lining, the thermal conductivity of the friction lining, and the steel plate thickness on the temperature and pressure behavior in the clutch is investigated. Although the Young’s modulus of the friction lining influences the pressure distribution in the friction contact, the temperature behavior is only slightly changed by the variation of the elastic modulus due to the load case. The thermal conductivity of the lining and steel plate thickness have a strong influence on the temperature level in the clutch. However, the distribution of pressures is still very homogeneous compared to the reference model.

Synchronizers are widely used in gear boxes of car and truck transmissions. Optimizing costs and improving the efficiency of gear boxes require knowledge about the relative load limits of single and multi-cone synchronizers with carbon friction linings and their corresponding deterioration mechanisms. Load limits for single and multi-cone synchronizers with carbon friction lining used in cars were determined experimentally using the component test rig SSP-180 and compared against each other. Different load stages were run in life cycle tests and the influences of pressure, sliding velocity, friction work, frictional power and oil temperature were investigated. The synchronizers’ failure mode is described and the novel specific value μ_min,grad is introduced that is able to quantify the deterioration of different synchronizer systems. During life cycle tests at the same specific load level, the single cone synchronizers, contrary to expectations, displayed greater damage compared to the multi-cone synchronizers. Calculations of the friction surface temperature in thermo-mechanical simulations, in combination with experiments on the test rig, show that the maximum temperature during the engagement has a significant influence on deterioration and endurance life of synchronizers with carbon friction lining.

Wet-running multi-plate clutches should be prevented from failing due to the often safety-relevant functions they fulfill in the drive train. In addition to long-term damage, spontaneous damage is of particular relevance for failures. This paper focuses on the influence of spontaneous damage on frictional behavior in the later life cycle. The aim of the experimental investigations is to initially cause spontaneous damage in wet-running multi-plate clutches with sintered friction linings. For this purpose, three clutches are first pre-damaged in stage tests with different intensities, so that the first spontaneous damage (local discoloration, sinter transfer) occurs. In the second step, an endurance test is carried out with the pre-damaged clutch packs and a non-pre-damaged reference clutch. The friction behavior of the clutches during the endurance test is compared and evaluated. It shows that local discoloration and sinter transfer are no longer visible after the endurance tests. At the beginning of the endurance test, the values of coefficient of friction are higher over the entire speed range of the heavily pre-damaged clutches than with the slightly pre-damaged clutch and the non-pre-damaged reference clutch. At the end of the endurance test, it can be observed that the greater the pre-damage to the clutches is, the greater the coefficient of friction increases with decreasing sliding speed.

Wet multi-plate clutches are relevant components of modern drivetrain applications, not only in terms of function but also safety and comfort. Especially at the beginning of their lifetime, distinct changes of the friction behavior may occur and make the actuation of the clutch challenging. This transcript describes the typical running-in behavior of wet multi-plate clutches and gives a general definition for running-in of clutches. Moreover, a new test method to systematically investigate the running-in behavior of clutches is introduced. This test method contains a test procedure to characterize the running-in behavior on different load levels. Furthermore, a multi-stage procedure to evaluate and characterize the running-in behavior of clutches with mathematical approaches and new characteristic values is given. The quality of the test method is demonstrated on the example of three different tribological systems from dual clutch transmissions (DCT) and automatic transmissions (AT) application using paper friction linings.