Model Predictive Control for Electrochemical Impedance Spectroscopy Measurement of Fuel Cells Based on Neural Network Optimization

Critical Review of Intelligent Battery Systems: Challenges, Implementation, and Potential for Electric Vehicles

“…Low-cost implementations use MCU internal SAR ADCs [157,292,300,301,304] in most cases. For more performant systems, with an accuracy of >12 bit, standalone SAR or delta-sigma ADCs are employed typically [296,299,[311][312][313].…”

“…Before transformation of the acquired data to the frequency domain, preprocessing is performed. Preprocessing steps may include, for example, digital filtering [268,290,314], gain and offset compensation [290,292], segmentation [112,315], windowing [112,306,307,316], zeropadding [308], and down sampling [293,296,312]. Potential uses of digital filtering include HPFs to remove low frequency components [290] and compensate for drift [314], Bandpass Filters (BPFs) as preparation for correlation based postprocessing [268] as well as decimation filters for down sampling [293,296].…”

Filter Design and Optimization of Electromechanical Actuation Systems Using Search and Surrogate Algorithms for More-Electric Aircraft Applications

“…(2SA) In this section, we give a novel category strategy for different commonly used algorithms including GA, particle swarm [25], tabu search [16], [26] and artificial neural network (ANN) [18], [19], [23], [24], Bayesian network [27], support vector machine (SVM) [20] etc. Based on this strategy, the relations (x-to-o) between inputs (x 1 , x 2 ...) and outputs (o 1 , o 2 ...) in algorithm categories can be simply described and compared.…”

“…Then, the target LC filter optimization problem (MOOP) is studied based on an established inverter-based EMA system [4] using a search algorithm, genetic algorithm (GA) [16], [17], [22], which is similar to the algorithm used in [3]. Furthermore, machine learning (ML) algorithms are explored as the surrogate algorithms for the same MOOP and there are two data-driven modes: classification [20], [21] and fitting [18], [19], [23], [24]. This paper uses both modes to demonstrate the surrogate algorithm and proposes a ML structure for the target MOOP which can be generally used in any discipline.…”

Attitude stabilization of Marine Satellite Tracking Antenna using Model Predictive Control

“…Recently, there is an increasing interest in the application of Field Programmable Gate Array (FPGA) on computational acceleration (Tu et al (2019); Zhang et al (2019); Kosan et al (2018); Lucia et al (2018)). This is mainly due to its special hardware architecture, which is completely different from CPU.…”