Stefan Giurgea

Two-Stage Surrogate Model for Finite-Element-Based Optimization of Permanent-Magnet Synchronous Motor

The use of finite-element-method (FEM) simulation in electrical machine optimal design is affected by two main problems: the computation time in FEM simulations and the large number of parameters of the electrical machine. Here, we propose a surrogate model to use with electrical machines, based on statistical multiple correlation coefficients (R2) analysis and moving least squares (MLS) approximation. In the context of an optimization process, which needs a large number of evaluations strongly depending on the number of parameters, the computation effort is small compared to the time that can be saved. We validate this method by applying it to the optimal design of a synchronous machine. The results show that the torque per weight ratio improved by about 13% in comparison with that obtained by classical optimization methods.

Multimodel Optimization Based on the Response Surface of the Reduced FEM Simulation Model With Application to a PMSM

This paper presents an analytical method for improving the optimal design of electromagnetic devices obtained analytically. This method extracts the significant parameters by using the gradient of difference between the outputs of the analytical model and those obtained with a finite-element method. These parameters are then employed to build a response surface in a reduced dimension space by using the moving least square method. To assess its viability, we compared our method to another recent approach in the optimal design of a permanent-magnet synchronous motor. The results show our methods superiority in terms of improvement of the solution and approximation of the real objective function .

Diagnosis for PEMFC Systems: A Data-Driven Approach With the Capabilities of Online Adaptation and Novel Fault Detection

In this paper, a data-driven strategy is proposed for polymer electrolyte membrane fuel cell system diagnosis. In the strategy, features are first extracted from the individual cell voltages using Fisher discriminant analysis . Then, a classification method named spherical-shaped multiple-class support vector machine is used to classify the extracted features into various classes related to health states. Using the diagnostic decision rules, the potential novel failure mode can be also detected. Moreover, an online adaptation method is proposed for the diagnosis approach to maintain the diagnostic performance. Finally, the experimental data from a 40-cell stack are proposed to verify the approach relevance.

Optimal Design Analysis of a Stand-Alone Photovoltaic Hybrid System

The optimal design of a photovoltaic hybrid system is time consuming and complex. Therefore, this paper proposes a study of this problem by modelling the system from the energy point of view. The hybrid system is composed of photovoltaic cells, a battery, and a fuel cell supplying a stand-alone street lighting system. After characterizing the problem, an optimization method is selected because it seems that stochastic methods are the best at solving the problem. A genetic algorithm is used to design the hybrid system optimally.

Modeling and Analysis of a High Pressure Operating Fuel Cell Hydrogen/Air system

This paper presents a study of the fuel cell system performance operating at high pressure and different temperature levels. A polymer electrolyte fuel cell (PEFC) has analyzed in according with the possibility of using in transport applications. Therefore, it begin with the description of the model of the fuel cell which has been developed using a combination between empirical and theoretical modeling techniques. This model enables to simulate fuel cells V-J curves in dependences with the stack temperature and the oxygen partial pressure. In addition, it can be used to study the influence of the gases management (pressure) on the fuel cell stack performances. The study continues with the modeling and simulation of a turbo compressor as the active element for the compression air subsystem. One has used a least squares method for nonlinear curves fitting of fuel cell and compressor.

Fault diagnosis and novel fault type detection for PEMFC system based on spherical-shaped multiple-class support vector machine

In this paper, a data-based strategy is proposed for PEMFC (polymer electrolyte membrane fuel cell) diagnosis. In the strategy, the feature extraction method Fisher Discriminant Analysis (FDA) is used firstly to extract the features from individual cell voltages. After that, the classification method Spherical-Shaped Multiple-class Support Vector Machine (SSM-SVM) is used to classify the extracted features to various classes related to health states. The potential novel failure mode can be detected in the procedure. Experiments on a 40-cell stack are dedicated to verify the approach.

Diagnosis of PEMFC by using data-driven parity space strategy

In this paper, a data-driven strategy is proposed for PEMFC (polymer electrolyte membrane fuel cell) diagnosis. In the strategy, parity space is directly identified from normal process data without modeling. With the identified parity space, a group residuals can be generated and evaluated to achieve fault detection. In addition, a multi-class SVM (support vector machine) is adopted to realize fault isolation. Experiments of a 40-cell stack are dedicated to highlight the approach.

Multi Model Optimization based on the Response Surface of the Reduced FEM Simulation Model with Application to a Permanent Magnet Synchronous Motor

This paper presents a unifying optimization methodology to improve the electrical machine optimal design. A new simplified response surface is proposed to offer the precision of numerical models based on FEM simulations