arXiv subjects

Leonhard Heindel

Publications and source records attributed to Leonhard Heindel.

3 recordsLinked to original sources

arXiv2023

Fatigue monitoring and maneuver identification for vehicle fleets using a virtual sensing approach

Extensive monitoring comes at a prohibitive cost, limiting Predictive Maintenance strategies for vehicle fleets. This paper presents a measurement-based virtual sensing technique where local strain gauges are only required for few reference vehicles, while the remaining fleet relies exclusively on accelerometers. The scattering transform is used to perform feature extraction, while principal component analysis provides a reduced, low dimensional data representation. This enables direct fatigue damage regression, parameterized from unlabeled usage data. Identification measurements allow for a physical interpretation of the reduced representation. The approach is demonstrated using experimental data from a sensor equipped eBike, which is made publicly available.

eess.SP↗

arXiv2022

Performance Assessment of different Machine Learning Algorithm for Life-Time Prediction of Solder Joints based on Synthetic Data

This paper proposes a computationally efficient methodology to predict the damage progression in solder contacts of electronic components using temperature-time curves. For this purpose, two machine learning algorithms, a Multilayer Perceptron and a Long Short-Term Memory network, are trained and compared with respect to their prediction accuracy and the required amount of training data. The training is performed using synthetic, normally distributed data that is realistic for automotive applications. A finite element model of a simple bipolar chip resistor in surface mount technology configuration is used to numerically compute the synthetic data. As a result, both machine learning algorithms show a relevant accuracy for the prediction of accumulated creep strains. With a training data length of 350 hours (12.5% of the available training data), both models show a constantly good fitting performance of $R^2$ of 0.72 for the Multilayer Perceptron and $R^2$ of 0.87 for the Long Short-Term Memory network. The prediction errors of the accumulated creep strains are less than 10% with an amount of 350 hours training data and decreases to less than 5 % when using further data. Therefore, both approaches are promising for the lifetime prediction directly on the electronic device.

cs.LG↗

arXiv2021

Assessment of hybrid machine learning models for non-linear system identification of fatigue test rigs

The prediction of system responses for a given fatigue test bench drive signal is a challenging task, for which linear frequency response function models are commonly used. To account for non-linear phenomena, a novel hybrid model is suggested, which augments existing approaches using Long Short-Term Memory networks. Additional virtual sensing applications of this method are demonstrated. The approach is tested using non-linear experimental data from a servo-hydraulic test rig and this dataset is made publicly available. A variety of metrics in time and frequency domains, as well as fatigue strength under variable amplitudes, are employed in the evaluation.

eess.SP↗