No abstract

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 𝑅² of 0.72 for the Multilayer Perceptron and 𝑅² 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.

No abstract

Currently, weather forecasting is the most commonly discussed topic by social and economic activists. It is also attracting widespread interest due to its application in various public and private sectors that include marine, agriculture, air traffic, and forestry. Recent developments have made climatic changes happen at a dramatic rate, making old methods of weather forecasting less effective, more hectic, and unreliable. Improved and efficient methods of weather prediction are needed to overcome these difficulties. This paper describes machine learning approaches using artificial neural networks to predict the weather of a particular city and compare the different weather conditions in different cities. We demonstrate empirically that Artificial Neural Networks produce very low deviations hence providing nearly accurate results for weather forecasts on a daily basis.

No abstract