Electric Vehicles - Design, Modelling and Simulation [Working Title]
This research investigated different nonlinear models, state estimation techniques and control st... more This research investigated different nonlinear models, state estimation techniques and control strategies applied to rechargeable Li-ion batteries and electric motors powered and adapted to these batteries. The finality of these investigations was achieved by finding the most suitable design approach for the real-time implementation of the most advanced state estimators based on intelligent neural networks and neural control strategies. For performance comparison purposes, was chosen as case study an accurate and robust EKF state of charge (SOC) estimator built on a simple second-order RC equivalent circuit model (2RC ECM) accurate enough to accomplish the main goal. An intelligent nonlinear autoregressive with exogenous input (NARX) Shallow Neural Network (SSN) estimator was developed to estimate the battery SOC, predict the terminal voltage, and map the nonlinear open circuit voltage (OCV) battery characteristic curve as a function of SOC. Focusing on nonlinear modeling and linear...
The main objective of this research paper was to develop two intelligent state estimators using s... more The main objective of this research paper was to develop two intelligent state estimators using shallow neural network (SNN) and NARX architectures from a large class of deep learning models. This research developed a new modelling design approach, namely, an improved hybrid adaptive neural fuzzy inference system (ANFIS) battery model, which is simple, accurate, practical, and well suited for real-time implementations in HEV/EV applications, with this being one of the main contributions of this research. On the basis of this model, we built four state of charge (SOC) estimators of high accuracy, assessed by a percentage error of less than 0.5% in a steady state compared to the 2% reported in the literature in the field. Moreover, these estimators excelled by their robustness to changes in the model parameters values and the initial “guess value” of SOC from 80–90% to 30–40%, performing in the harsh and aggressive realistic conditions of the real world, simulated by three famous driv...
This research paper aims to design and implement an intelligent least short time memory (LSTM) de... more This research paper aims to design and implement an intelligent least short time memory (LSTM) deep learning classification technique to detect possible anomalies in measurements dataset within a particular Li-ion battery type. For the state of charge (SOC) and battery faults estimation, a Joint State and Parameter Extended Kalman Filter (JEKF) estimator is developed. The SOC accuracy performance is excellent, with less than 0.5% error during steady-state, compared to the 2% error reported in the literature. For the design and implementation of JEKF SOC and parameter estimation is chosen a preset Li-ion battery Simulink Simscape generic model. It is also helpful to generate the healthy and faulty measurement dataset to design and implement the proposed intelligent LSTM classifier deep learning technique. The generic Li-ion battery model is wisely selected for the “proof concept” purpose, model validation, and algorithms’ robustness, accuracy, and effectiveness. Compared to the tradi...
Smart Mobility - Recent Advances, New Perspectives and Applications [Working Title], 2022
This research paper will propose an incentive topic to investigate the accuracy of an adaptive ne... more This research paper will propose an incentive topic to investigate the accuracy of an adaptive neuro-fuzzy modeling approach of lithium-ion (Li-ion) batteries used in hybrid electric vehicles and electric vehicles. Based on this adaptive neuro-fuzzy inference system (ANFIS) modeling approach, we will show its effectiveness and suitability for modeling the nonlinear dynamics of any process or control system. This new ANFIS modeling approach improves the original nonlinear battery model and an alternative linear autoregressive exogenous input (ARX) polynomial model. The alternative ARX is generated using the least square errors estimation method and is preferred for its simplicity and faster implementation since it uses typical functions from the MATLAB system identification toolbox. The ARX and ANFIS models’ effectiveness is proved by many simulations conducted on attractive MATLAB R2021b and Simulink environments. The simulation results reveal a high model accuracy in battery state ...
This research work investigates the possibility to apply several neural network architectures for... more This research work investigates the possibility to apply several neural network architectures for simulation and prediction of the dynamic behavior of the complex economic processes. Therefore we will explore different neural networks architectures to build several neural models of the complex dynamic economy system. In future work we will use these architectures to be trained by well-known training algorithms, such as Levenberg-Marquardt back-propagation error and Radial Basic Function (RBF), to compare their results and to decide at the end, which one is the best among the different applications from the economy field. The results presented in this work are based on the experience accumulated by the authors in the field of identification, modeling and control of the industrial and economic processes, namely chemical, HVAC, automotive industry, and satellites constellation. The neural networks are strongly recommended for the highly nonlinear processes for which an analytic descrip...
Learning and Analytics in Intelligent Systems, 2020
This paper continues the presentation of new contributions to improve significantly the results d... more This paper continues the presentation of new contributions to improve significantly the results disseminated in the recent paper presented for FedCSIS’ 2018 International Conference on single-input single-output autoregressive moving average with exogenous input models in terms of accuracy, simplicity and real time fast implementation. The improvement is performed by developing accurate multi-inputs single-output adaptive neuro-fuzzy inference system models, suitable to be tailored also for modelling the nonlinear dynamics of any process or control systems. Compared to the conference paper the novelty is a further investigation on design and implementation of hybrid closed-loop control strategy structures consisting of the proposed improved models in combination with digital PI controllers that enhance significantly the tracking accuracy performance, overshoot and number of oscillations, transient convergence speed and robustness to consecutive step changes in the input setpoints. The effectiveness of this new control approach is demonstrated by extensive simulations conducted in MATLAB software environment followed by a rigorous performance analysis by comparison to MATLAB simulation results obtained for a same case study by a standard two input and a single output digital PI controller.
Electric Vehicles - Design, Modelling and Simulation [Working Title]
This research investigated different nonlinear models, state estimation techniques and control st... more This research investigated different nonlinear models, state estimation techniques and control strategies applied to rechargeable Li-ion batteries and electric motors powered and adapted to these batteries. The finality of these investigations was achieved by finding the most suitable design approach for the real-time implementation of the most advanced state estimators based on intelligent neural networks and neural control strategies. For performance comparison purposes, was chosen as case study an accurate and robust EKF state of charge (SOC) estimator built on a simple second-order RC equivalent circuit model (2RC ECM) accurate enough to accomplish the main goal. An intelligent nonlinear autoregressive with exogenous input (NARX) Shallow Neural Network (SSN) estimator was developed to estimate the battery SOC, predict the terminal voltage, and map the nonlinear open circuit voltage (OCV) battery characteristic curve as a function of SOC. Focusing on nonlinear modeling and linear...
The main objective of this research paper was to develop two intelligent state estimators using s... more The main objective of this research paper was to develop two intelligent state estimators using shallow neural network (SNN) and NARX architectures from a large class of deep learning models. This research developed a new modelling design approach, namely, an improved hybrid adaptive neural fuzzy inference system (ANFIS) battery model, which is simple, accurate, practical, and well suited for real-time implementations in HEV/EV applications, with this being one of the main contributions of this research. On the basis of this model, we built four state of charge (SOC) estimators of high accuracy, assessed by a percentage error of less than 0.5% in a steady state compared to the 2% reported in the literature in the field. Moreover, these estimators excelled by their robustness to changes in the model parameters values and the initial “guess value” of SOC from 80–90% to 30–40%, performing in the harsh and aggressive realistic conditions of the real world, simulated by three famous driv...
This research paper aims to design and implement an intelligent least short time memory (LSTM) de... more This research paper aims to design and implement an intelligent least short time memory (LSTM) deep learning classification technique to detect possible anomalies in measurements dataset within a particular Li-ion battery type. For the state of charge (SOC) and battery faults estimation, a Joint State and Parameter Extended Kalman Filter (JEKF) estimator is developed. The SOC accuracy performance is excellent, with less than 0.5% error during steady-state, compared to the 2% error reported in the literature. For the design and implementation of JEKF SOC and parameter estimation is chosen a preset Li-ion battery Simulink Simscape generic model. It is also helpful to generate the healthy and faulty measurement dataset to design and implement the proposed intelligent LSTM classifier deep learning technique. The generic Li-ion battery model is wisely selected for the “proof concept” purpose, model validation, and algorithms’ robustness, accuracy, and effectiveness. Compared to the tradi...
Smart Mobility - Recent Advances, New Perspectives and Applications [Working Title], 2022
This research paper will propose an incentive topic to investigate the accuracy of an adaptive ne... more This research paper will propose an incentive topic to investigate the accuracy of an adaptive neuro-fuzzy modeling approach of lithium-ion (Li-ion) batteries used in hybrid electric vehicles and electric vehicles. Based on this adaptive neuro-fuzzy inference system (ANFIS) modeling approach, we will show its effectiveness and suitability for modeling the nonlinear dynamics of any process or control system. This new ANFIS modeling approach improves the original nonlinear battery model and an alternative linear autoregressive exogenous input (ARX) polynomial model. The alternative ARX is generated using the least square errors estimation method and is preferred for its simplicity and faster implementation since it uses typical functions from the MATLAB system identification toolbox. The ARX and ANFIS models’ effectiveness is proved by many simulations conducted on attractive MATLAB R2021b and Simulink environments. The simulation results reveal a high model accuracy in battery state ...
This research work investigates the possibility to apply several neural network architectures for... more This research work investigates the possibility to apply several neural network architectures for simulation and prediction of the dynamic behavior of the complex economic processes. Therefore we will explore different neural networks architectures to build several neural models of the complex dynamic economy system. In future work we will use these architectures to be trained by well-known training algorithms, such as Levenberg-Marquardt back-propagation error and Radial Basic Function (RBF), to compare their results and to decide at the end, which one is the best among the different applications from the economy field. The results presented in this work are based on the experience accumulated by the authors in the field of identification, modeling and control of the industrial and economic processes, namely chemical, HVAC, automotive industry, and satellites constellation. The neural networks are strongly recommended for the highly nonlinear processes for which an analytic descrip...
Learning and Analytics in Intelligent Systems, 2020
This paper continues the presentation of new contributions to improve significantly the results d... more This paper continues the presentation of new contributions to improve significantly the results disseminated in the recent paper presented for FedCSIS’ 2018 International Conference on single-input single-output autoregressive moving average with exogenous input models in terms of accuracy, simplicity and real time fast implementation. The improvement is performed by developing accurate multi-inputs single-output adaptive neuro-fuzzy inference system models, suitable to be tailored also for modelling the nonlinear dynamics of any process or control systems. Compared to the conference paper the novelty is a further investigation on design and implementation of hybrid closed-loop control strategy structures consisting of the proposed improved models in combination with digital PI controllers that enhance significantly the tracking accuracy performance, overshoot and number of oscillations, transient convergence speed and robustness to consecutive step changes in the input setpoints. The effectiveness of this new control approach is demonstrated by extensive simulations conducted in MATLAB software environment followed by a rigorous performance analysis by comparison to MATLAB simulation results obtained for a same case study by a standard two input and a single output digital PI controller.
Uploads
Papers by Nicolae Tudoroiu