Proton exchange membrane fuel cell (PEMFC) degradation prediction is essential especially in transportation applications, since one of the major issues that hinder its worldwide commercialization is represented by its durability. However, due to the complex physical phenomena inside the fuel cell, which are usually strongly inter-coupled, the conventional semi-empirical model-based prognostics approach may fail to predict the aging phenomena under varies fuel cell operating conditions. In order to improve prognostics accuracy, this paper proposed a data-fusion approach to forecast the fuel cell performance based on long short-term memory (LSTM) recurrent neuron network (RNN) and auto-regressive integrated moving average (ARIMA) method. LSTM can efficiently make a prediction regarding a long-term physical degradation, whereas the fusion with ARIMA can effectively track the degradation tendency. In order to validate the performance of the proposed data-fusion approach, two different PEMFCs are tested for recording the aging experimental datasets. The forecasting results indicate that the proposed LSTM-ARIMA approach can accurately predict PEMFC degradation, which can be then used directly to optimize fuel cell performance implemented in transportation applications.

This paper presents a novel Insulated Gate Bipolar Transistor (IGBT) behavioral model on the field programmable gate array (FPGA), which is suitable for the real-time simulation of fast transients in power electronics circuits. In this model, the static and dynamic behaviors of the IGBT switch are described and modeled separately. The static IGBT model is represented by the saturation region of output characteristic and is a part of the circuit network model. The dynamic IGBT model is combined with the static one to describe the fast switching transient behaviors by using IGBT equivalent circuit model. The presented dynamic model in this paper does not involve any iterative solving algorithm and can be designed with highly pipelined structures on FPGA. Therefore, the IGBT switching transient waveforms can be generated precisely with a 5ns resolution. The proposed model is tested with two cases - a four-phase floating interleaved boost converter and a three-phase five-level modular multilevel converter. The effectiveness and accuracy of the model are validated by comparing the real-time simulation results with offline simulation software.

The device-level real-time simulation of power converters is constrained by the contradiction between the required short simulation time-step to describe the transient behaviors and the large computational amount caused by the nonlinearities of switches' models. In this paper, a novel low-latency device-level power converter modeling approach is proposed for FPGA-based real-time simulation. A piecewise linear IGBT/Diode transient model is proposed based on the inductive switching behaviors. The switching transient is modeled into four phases, which are identified by the boundaries between three operating regions of IGBT and between two operating modes of diode. Moreover, each phase is approximated by a linear continuous behavior in order to reduce the real-time computational amounts. Accompanied by the effective boundary identification, the device-level IGBT/Diode model can be efficiently integrated into the real-time simulation with low computational latency. A DC-DC-AC topology model is implemented on the FPGA-based real-time platform, as a case study to verify the effectiveness and practicability of proposed approach. With the help of circuit partitioning techniques, the device-level converter model can be simulated with 50 ns time-step on FPGA. Moreover, the accuracy of FPGA-based simulation results is validated by the error evaluation with respect to the results from offline simulation tools.

The field-programmable gate array (FPGA) based hardware-in-the-loop (HiL) test, which minimizes the time-step of the real-time simulation below 500 -ns, is an enabling technology for the development of the control unit of high-power electronic systems (HPE). In order to improve the time timing performance of FPGA-based HiL, this paper proposes a novel parallel structure using the predictive behavior of the power electronic system. With this structure, we design an improved system-level solver applied to HPE. A piece-wise insulated-gate bipolar transistor (IGBT) model is used to determine the state of the switch, offering a quasi-realistic model of the power converter. A parallel integration method is also implemented to solve the status of the circuit elements. Moreover, the proposed parallel structural can execute both the IGBT model and circuit element model at the same time, thus reducing the simulation time-step significantly. The numerical accuracy of the solution, the architecture design, and the issue of the parallel computation are discussed in detail. An AC-DC-AC topology is presented as a case study. At last, a 25 -ns time step in the National Instruments FlexRIO platform is achieved. Results comparison with the reference model is also identified and discussed.

Digital twins are emerging in power electronics as a tool for optimized design, fast prototyping, and smart maintenance, given the increasing demand in terms of high power density, reliability, and low cost. A power electronics digital twin can be regarded as a virtual representation of a power electronics system, embodied by a high-fidelity model running in real time, of which the states and model parameters are updated based on the feedback from the sensors or their data fusions. Digital twin models are developed in multiple domains and run in real time or even faster than real time. The data collected from the physical entities are transferred with controlled latencies and quality, and then processed to iterate the models to represent physical power electronics from application-oriented views. However, due to the nonlinearities and fast switching behaviors of power electronics, one significant challenge is to ensure high fidelity and fast computation simultaneously, which stimulates the real-time simulation (RTS) of power electronics with an ultralow time step. Moreover, the electrical, thermal, and electrothermal aspects shall all be considered to improve the model’s accuracy. To consider the uncertainties, the parameters of the digital twin models are either identified by advanced optimization algorithms or represented by probabilistic expressions. To make it possible, real-time communication should be established between the physical and digital twins. Empowered by modern Internet of Things (IoT) technology, many sensor signals can be transferred in a timely fashion to ensure real-time capability of the digital twin. The digital twin gives insightful information about its physical counterpart based on which smart decisions can be made to improve the design, prototyping, control, and lifecycle management of power electronics converters and systems. In this article, we review the digital twin of modern power electronics, and get an insight into its enabling technologies and possible applications.