Wet multi-plate clutches are safety-critical components of drive trains. Failure and damage must therefore be strongly avoided. In contrast to longterm damage, spontaneous damage and failures are difficult to predict. Different authors have already theorized the influence of different parameters on the carrying capacity. This paper extends the analysis of these effects by conducting experimental investigations. Furthermore, an evaluation method that allows to compare different clutch systems regarding their load carrying capacity is presented. Clutch systems with variation of oil flow, plate thickness, coating and groove pattern were tested, and their results analyzed. Statistical methods were used to consider the variance of the measurements. Lastly, recommendations are formulated for the development of clutch systems concerning the load carrying capacity. Strong trends can be seen for the influences of the thickness of the steel plate and oil flow rate, but these can only be statistically substantiated for the variation of the oil flow rate. For the variation of the coating and the grooving, only slight to no differences are discernible.

As in manufacturing with its Industry 4.0 transformation, the enormous potential of artificial intelligence (AI) is also being recognized in the construction industry. Specifically, the equipment-intensive construction industry can benefit from using AI. AI applications can leverage the data recorded by the numerous sensors on machines and mirror them in a digital twin. Analyzing the digital twin can help optimize processes on the construction site and increase productivity. We present a case from special foundation engineering: the machine production of bored piles. We introduce a hierarchical classification for activity recognition and apply a hybrid deep learning model based on convolutional and recurrent neural networks. Then, based on the results from the activity detection, we use discrete-event simulation to predict construction progress. We highlight the difficulty of defining the appropriate modeling granularity. While activity detection requires equipment movement, simulation requires knowledge of the production flow. Therefore, we present a flow-based production model that can be captured in a modularized process catalog. Overall, this paper aims to illustrate modeling using digital-twin technologies to increase construction process improvement in practice.

Wet-running multi-plate clutches fulfill a major safety-relevant role in drive trains and, as a result, damage to and failure of the clutch system must be strictly avoided, especially spontaneous damage. This paper deals with spontaneous damage to wet-running multi-plate clutches with paper friction lining with respect to spontaneous damage behavior. The paper presents a comparison method, by means of which the load-carrying capacity of various multi-plate clutches can be compared with regard to spontaneous damage based on experimental data and recommendations can be formulated. The experiments were performed on six different clutch variants, and the results were examined for significant differences. Various statistical tools were used to detect statistically significant variations. The experiments showed that higher load levels have a greater dispersion of the measured values, thus making comparisons more difficult. In the clutch variants investigated, significant changes in spontaneous damage behavior could only be detected when the cooling plate thickness or the carbon content was changed.

No abstract

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.