This paper presents the design and development of low cost archetype dual rotor helicopter (LCADRH) for academic research in an educational institution. The LCADRH is installed with optical pitch encoder and yaw ...This paper presents the design and development of low cost archetype dual rotor helicopter (LCADRH) for academic research in an educational institution. The LCADRH is installed with optical pitch encoder and yaw encoder which measure elevation and side to side motion of helicopter. The objective of the project is to design and integrate the helicopter with data acquisition board and sensors to provide hardware features, software support capability for its rapid real time measurement and control. The low cost designed LCADRH facilitates the academic research for students in the institution and is able to provide hands on training to understand the concept of nonlinearity, system modelled and unmodelled dynamics and uncertainty, modelling, simulation and control by doing practical experiments. The mathematical model of the LCADRH is derived using grey box modelling method. The control of LCADRH is challenging due to its nonlinearity and effect of strong coupling between aerodynamic forces and torques generated by the both pitch and yaw actuators. In closed loop position control of LCADRH, pitch and yaw axis motion is regulated using linear quadratic controller (LQR). Encouraging results are obtained both in simulation and hardware.展开更多
High-frequency resistance(HFR)is a critical quantity strongly related to a fuel cell system’s performance.It is beneficial to estimate the fuel cell system’s HFR from the measurable operating conditions without reso...High-frequency resistance(HFR)is a critical quantity strongly related to a fuel cell system’s performance.It is beneficial to estimate the fuel cell system’s HFR from the measurable operating conditions without resorting to costly HFR measurement devices.In this study,we propose a data-driven approach for a real-time prediction of HFR.Specifically,we use a long short-term memory(LSTM)based machine learning model that takes into account both the current and past states of the fuel cell,as characterized through a set of sensors.These sensor signals form the input to the LSTM.The data is experimentally collected from a vehicle lab that operates a 100 kW automotive fuel cell stack running on an automotive-scale test station.Our current results indicate that our prediction model achieves high accuracy HFR predictions and outperforms other frequently used regression models.We also study the effect of the extracted features generated by our LSTM model.Our study finds that only very few dimensions of the extracted feature are influential in HFR prediction.The study highlights the potential to monitor HFR condition accurately and timely on a car.展开更多
文摘This paper presents the design and development of low cost archetype dual rotor helicopter (LCADRH) for academic research in an educational institution. The LCADRH is installed with optical pitch encoder and yaw encoder which measure elevation and side to side motion of helicopter. The objective of the project is to design and integrate the helicopter with data acquisition board and sensors to provide hardware features, software support capability for its rapid real time measurement and control. The low cost designed LCADRH facilitates the academic research for students in the institution and is able to provide hands on training to understand the concept of nonlinearity, system modelled and unmodelled dynamics and uncertainty, modelling, simulation and control by doing practical experiments. The mathematical model of the LCADRH is derived using grey box modelling method. The control of LCADRH is challenging due to its nonlinearity and effect of strong coupling between aerodynamic forces and torques generated by the both pitch and yaw actuators. In closed loop position control of LCADRH, pitch and yaw axis motion is regulated using linear quadratic controller (LQR). Encouraging results are obtained both in simulation and hardware.
文摘High-frequency resistance(HFR)is a critical quantity strongly related to a fuel cell system’s performance.It is beneficial to estimate the fuel cell system’s HFR from the measurable operating conditions without resorting to costly HFR measurement devices.In this study,we propose a data-driven approach for a real-time prediction of HFR.Specifically,we use a long short-term memory(LSTM)based machine learning model that takes into account both the current and past states of the fuel cell,as characterized through a set of sensors.These sensor signals form the input to the LSTM.The data is experimentally collected from a vehicle lab that operates a 100 kW automotive fuel cell stack running on an automotive-scale test station.Our current results indicate that our prediction model achieves high accuracy HFR predictions and outperforms other frequently used regression models.We also study the effect of the extracted features generated by our LSTM model.Our study finds that only very few dimensions of the extracted feature are influential in HFR prediction.The study highlights the potential to monitor HFR condition accurately and timely on a car.
