In this paper, a two-stage artificial intelligence framework for supporting the signal integrity compliant printed circuit board design process has been developed. This framework was applied to compare linear and non-linear data, which showed that the non-linear data source gains advantages over the linear data in terms of attainable regression accuracy. For the investigated application however, the linear model can be utilized directly or by utilizing transfer learning for adequate results.

The implementation of an anomaly detection with a decision tree was investigated with respect to the evaluation of selected SI effects in PCB design. The tree based approach allows the designer to understand the proposals more easily (explainable AI). High prediction accuracies for two simple networks were achieved with the proposed method. The use of anomaly detection with a decision tree will be further developed in future work for various more complex SI applications in circuit design.

The effects of parameters (decaps, power plane and stackup) affecting the input impedance of a power delivery network are investigated. An artificial neural network is trained using the generated data utilizing a process to generate suitable input for training a machine learning module, which is able to predict the impedance profile of the PDN. In order to obtain a more accurate prediction, Bayesian optimization is implemented and the results are compared to commercial power integrity software.

Further improvements on the novel method for state of charge (SOC) determination of lithium iron phosphate (LFP) cells based on the impedance spectra classification are presented.

Continuously increasing requirements for onboard system performances lead to new topologies for the energy distribution in vehicles. One promising concept is the usage of a dual-battery system instead of the conventional lead-acid battery. The conventional performance estimation method for standalone lead-acid batteries can no longer be applied to this system. Therefore, a new algorithm for the voltage drop calculation of the dual-battery system is proposed.